commit e8031b99216df18b4e139b5fff07cfad1e8a8c24 Author: ModelHub XC Date: Thu Jun 11 17:24:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: irriversible/Qwen3-1.7B-base-final Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..95e2589 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,65 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text + +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text + + +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +merges.txt filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/checkpoint-1644/rng_state.pth filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/checkpoint-1644/merges.txt filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/vocab.json filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/checkpoint-1644/scheduler.pt filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/checkpoint-1644/adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/checkpoint-1644/training_args.bin filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/checkpoint-1644/vocab.json filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/merges.txt filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/checkpoint-1644/tokenizer.json filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/tokenizer.json filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/training_args.bin filter=lfs diff=lfs merge=lfs -text +train_2026-01-03/checkpoint-1644/optimizer.pt filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/.mdl b/.mdl new file mode 100644 index 0000000..19ff6fb Binary files /dev/null and b/.mdl differ diff --git a/.msc b/.msc new file mode 100644 index 0000000..91bc1eb Binary files /dev/null and b/.msc differ diff --git a/.mv b/.mv new file mode 100644 index 0000000..61c803d --- /dev/null +++ b/.mv @@ -0,0 +1 @@ +Revision:master,CreatedAt:1753546359 \ No newline at end of file diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..6634c8c --- /dev/null +++ b/LICENSE @@ -0,0 +1,202 @@ + + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + + TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + + 1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + + 2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + + 3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + + 4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + + 5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + + 6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + + 7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + + 8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + + 9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + + END OF TERMS AND CONDITIONS + + APPENDIX: How to apply the Apache License to your work. + + To apply the Apache License to your work, attach the following + boilerplate notice, with the fields enclosed by brackets "[]" + replaced with your own identifying information. (Don't include + the brackets!) The text should be enclosed in the appropriate + comment syntax for the file format. We also recommend that a + file or class name and description of purpose be included on the + same "printed page" as the copyright notice for easier + identification within third-party archives. + + Copyright 2024 Alibaba Cloud + + Licensed under the Apache License, Version 2.0 (the "License"); + you may not use this file except in compliance with the License. + You may obtain a copy of the License at + + http://www.apache.org/licenses/LICENSE-2.0 + + Unless required by applicable law or agreed to in writing, software + distributed under the License is distributed on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + See the License for the specific language governing permissions and + limitations under the License. \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..4a6b3c1 --- /dev/null +++ b/README.md @@ -0,0 +1,57 @@ +--- +license: apache-2.0 +library_name: transformers +--- +# Qwen3-1.7B-Base + +## Qwen3 Highlights + +Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. +Building upon extensive advancements in training data, model architecture, and optimization techniques, Qwen3 delivers the following key improvements over the previously released Qwen2.5: + +- **Expanded Higher-Quality Pre-training Corpus:** Qwen3 is pre-trained on 36 trillion tokens across 119 languages — tripling the language coverage of Qwen2.5 — with a much richer mix of high-quality data, including coding, STEM, reasoning, book, multilingual, and synthetic data. +- **Training Techniques and Model Architecture:** Qwen3 incorporates a series of training techiques and architectural refinements, including global-batch load balancing loss for MoE models and qk layernorm for all models, leading to improved stability and overall performance. +- **Three-stage Pre-training:** Stage 1 focuses on broad language modeling and general knowledge acquisition, Stage 2 improves reasoning skills like STEM, coding, and logical reasoning, and Stage 3 enhances long-context comprehension by extending training sequence lengths up to 32k tokens. +- **Scaling Law Guided Hyperparameter Tuning:** Through comprehensive scaling law studies across the three-stage pre-training pipeline, Qwen3 systematically tunes critical hyperparameters — such as learning rate scheduler and batch size — separately for dense and MoE models, resulting in better training dynamics and final performance across different model scales. + +## Model Overview + +**Qwen3-1.7B-Base** has the following features: +- Type: Causal Language Models +- Training Stage: Pretraining +- Number of Parameters: 1.7B +- Number of Paramaters (Non-Embedding): 1.4B +- Number of Layers: 28 +- Number of Attention Heads (GQA): 16 for Q and 8 for KV +- Context Length: 32,768 + +For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/). + +## Requirements + +The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`. + +With `transformers<4.51.0`, you will encounter the following error: +``` +KeyError: 'qwen3' +``` + +## Evaluation & Performance + +Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen3/). + +### Citation + +If you find our work helpful, feel free to give us a cite. + +``` +@misc{qwen3technicalreport, + title={Qwen3 Technical Report}, + author={Qwen Team}, + year={2025}, + eprint={2505.09388}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2505.09388}, +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..78f3dea --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..cbbb313 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 151643, + "do_sample": false, + "eos_token_id": 151643, + "max_new_tokens": 2048, + "transformers_version": "4.37.0" +} \ No newline at end of file diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..59613a3 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df85b39330e5a425ee36253d0f894e4387e4f0a15b9c53cb467d668e6b3a841 +size 3441185608 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..bdbc67a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539 +size 7031645 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..6a3829e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,239 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('') and message.content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in message.content %}\n {%- set content = message.content.split('')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- endif %}\n{%- endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} \ No newline at end of file diff --git a/train_2026-01-03/README.md b/train_2026-01-03/README.md new file mode 100644 index 0000000..1348fff --- /dev/null +++ b/train_2026-01-03/README.md @@ -0,0 +1,58 @@ +--- +library_name: peft +license: other +base_model: /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base +tags: +- llama-factory +- lora +- generated_from_trainer +model-index: +- name: train_2026-01-03 + results: [] +--- + + + +# train_2026-01-03 + +This model is a fine-tuned version of [/root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base](https://huggingface.co//root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base) on the gpu_aiAgent_zh and the gpu_aiAgent_others datasets. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 5e-05 +- train_batch_size: 2 +- eval_batch_size: 8 +- seed: 42 +- gradient_accumulation_steps: 8 +- total_train_batch_size: 16 +- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- num_epochs: 3.0 + +### Training results + + + +### Framework versions + +- PEFT 0.15.2 +- Transformers 4.55.0 +- Pytorch 2.2.0 +- Datasets 3.6.0 +- Tokenizers 0.21.4 \ No newline at end of file diff --git a/train_2026-01-03/adapter_config.json b/train_2026-01-03/adapter_config.json new file mode 100644 index 0000000..020b75f --- /dev/null +++ b/train_2026-01-03/adapter_config.json @@ -0,0 +1,39 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base", + "bias": "none", + "corda_config": null, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "q_proj", + "v_proj", + "down_proj", + "o_proj", + "up_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/train_2026-01-03/adapter_model.safetensors b/train_2026-01-03/adapter_model.safetensors new file mode 100644 index 0000000..4642409 --- /dev/null +++ b/train_2026-01-03/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4397c270e546248f205eb7cb0915b4dce7a749cfed7e6f88a2170f9b8c87c7af +size 278973888 diff --git a/train_2026-01-03/added_tokens.json b/train_2026-01-03/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/train_2026-01-03/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/train_2026-01-03/all_results.json b/train_2026-01-03/all_results.json new file mode 100644 index 0000000..7c9317e --- /dev/null +++ b/train_2026-01-03/all_results.json @@ -0,0 +1,9 @@ +{ + "epoch": 3.0, + "num_input_tokens_seen": 9328224, + "total_flos": 8.278651518536909e+16, + "train_loss": 0.7471618294860904, + "train_runtime": 11618.0265, + "train_samples_per_second": 2.263, + "train_steps_per_second": 0.142 +} \ No newline at end of file diff --git a/train_2026-01-03/chat_template.jinja b/train_2026-01-03/chat_template.jinja new file mode 100644 index 0000000..d153f82 --- /dev/null +++ b/train_2026-01-03/chat_template.jinja @@ -0,0 +1,4 @@ +{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|endoftext|>' + ' +' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + ' +Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + ' +' }}{% endif %}{% endfor %} \ No newline at end of file diff --git a/train_2026-01-03/checkpoint-1644/README.md b/train_2026-01-03/checkpoint-1644/README.md new file mode 100644 index 0000000..e8368ba --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/README.md @@ -0,0 +1,202 @@ +--- +base_model: /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base +library_name: peft +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **Developed by:** [More Information Needed] +- **Funded by [optional]:** [More Information Needed] +- **Shared by [optional]:** [More Information Needed] +- **Model type:** [More Information Needed] +- **Language(s) (NLP):** [More Information Needed] +- **License:** [More Information Needed] +- **Finetuned from model [optional]:** [More Information Needed] + +### Model Sources [optional] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. + +## How to Get Started with the Model + +Use the code below to get started with the model. + +[More Information Needed] + +## Training Details + +### Training Data + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). + +- **Hardware Type:** [More Information Needed] +- **Hours used:** [More Information Needed] +- **Cloud Provider:** [More Information Needed] +- **Compute Region:** [More Information Needed] +- **Carbon Emitted:** [More Information Needed] + +## Technical Specifications [optional] + +### Model Architecture and Objective + +[More Information Needed] + +### Compute Infrastructure + +[More Information Needed] + +#### Hardware + +[More Information Needed] + +#### Software + +[More Information Needed] + +## Citation [optional] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[More Information Needed] + +## More Information [optional] + +[More Information Needed] + +## Model Card Authors [optional] + +[More Information Needed] + +## Model Card Contact + +[More Information Needed] +### Framework versions + +- PEFT 0.15.2 \ No newline at end of file diff --git a/train_2026-01-03/checkpoint-1644/adapter_config.json b/train_2026-01-03/checkpoint-1644/adapter_config.json new file mode 100644 index 0000000..020b75f --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/adapter_config.json @@ -0,0 +1,39 @@ +{ + "alpha_pattern": {}, + "auto_mapping": null, + "base_model_name_or_path": "/root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base", + "bias": "none", + "corda_config": null, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "k_proj", + "q_proj", + "v_proj", + "down_proj", + "o_proj", + "up_proj", + "gate_proj" + ], + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_dora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/train_2026-01-03/checkpoint-1644/adapter_model.safetensors b/train_2026-01-03/checkpoint-1644/adapter_model.safetensors new file mode 100644 index 0000000..4642409 --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4397c270e546248f205eb7cb0915b4dce7a749cfed7e6f88a2170f9b8c87c7af +size 278973888 diff --git a/train_2026-01-03/checkpoint-1644/added_tokens.json b/train_2026-01-03/checkpoint-1644/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/train_2026-01-03/checkpoint-1644/chat_template.jinja b/train_2026-01-03/checkpoint-1644/chat_template.jinja new file mode 100644 index 0000000..d153f82 --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/chat_template.jinja @@ -0,0 +1,4 @@ +{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ 'System: ' + system_message + '<|endoftext|>' + ' +' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '<|endoftext|>' + ' +Assistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + ' +' }}{% endif %}{% endfor %} \ No newline at end of file diff --git a/train_2026-01-03/checkpoint-1644/merges.txt b/train_2026-01-03/checkpoint-1644/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/train_2026-01-03/checkpoint-1644/optimizer.pt b/train_2026-01-03/checkpoint-1644/optimizer.pt new file mode 100644 index 0000000..042deca --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f7b86107a8252acc112e0e1bd3d1b918e71070bb1fc7045f4162f049a7aa6ff +size 558173226 diff --git a/train_2026-01-03/checkpoint-1644/rng_state.pth b/train_2026-01-03/checkpoint-1644/rng_state.pth new file mode 100644 index 0000000..cf44fee --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8347b1f64f7e683fb0aeb48f242d78bf3d6314b983cd2984c96d3095cba55d8 +size 14244 diff --git a/train_2026-01-03/checkpoint-1644/scheduler.pt b/train_2026-01-03/checkpoint-1644/scheduler.pt new file mode 100644 index 0000000..eeb175b --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43e55dd920266555d7c8bd9fec49183761a0750ffb123651906cda2b32fb3dbc +size 1064 diff --git a/train_2026-01-03/checkpoint-1644/special_tokens_map.json b/train_2026-01-03/checkpoint-1644/special_tokens_map.json new file mode 100644 index 0000000..17305b3 --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/train_2026-01-03/checkpoint-1644/tokenizer.json b/train_2026-01-03/checkpoint-1644/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/train_2026-01-03/checkpoint-1644/tokenizer_config.json b/train_2026-01-03/checkpoint-1644/tokenizer_config.json new file mode 100644 index 0000000..e6a51d3 --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_2026-01-03/checkpoint-1644/trainer_state.json b/train_2026-01-03/checkpoint-1644/trainer_state.json new file mode 100644 index 0000000..a2a9dff --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/trainer_state.json @@ -0,0 +1,3314 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 1644, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00913033553983109, + "grad_norm": 0.6315373182296753, + "learning_rate": 4.999926966182812e-05, + "loss": 1.469, + "num_input_tokens_seen": 31168, + "step": 5, + "train_runtime": 37.3694, + "train_tokens_per_second": 834.051 + }, + { + "epoch": 0.01826067107966218, + "grad_norm": 0.6748600006103516, + "learning_rate": 4.999630273613799e-05, + "loss": 1.5127, + "num_input_tokens_seen": 58992, + "step": 10, + "train_runtime": 70.3152, + "train_tokens_per_second": 838.965 + }, + { + "epoch": 0.027391006619493265, + "grad_norm": 0.8578517436981201, + "learning_rate": 4.999105384744215e-05, + "loss": 1.44, + "num_input_tokens_seen": 87296, + "step": 15, + "train_runtime": 103.3591, + "train_tokens_per_second": 844.59 + }, + { + "epoch": 0.03652134215932436, + "grad_norm": 0.6677753329277039, + "learning_rate": 4.998352347492226e-05, + "loss": 1.4987, + "num_input_tokens_seen": 114656, + "step": 20, + "train_runtime": 136.0501, + "train_tokens_per_second": 842.748 + }, + { + "epoch": 0.045651677699155443, + "grad_norm": 0.6610105037689209, + "learning_rate": 4.9973712306041256e-05, + "loss": 1.4058, + "num_input_tokens_seen": 143584, + "step": 25, + "train_runtime": 169.3921, + "train_tokens_per_second": 847.643 + }, + { + "epoch": 0.05478201323898653, + "grad_norm": 0.7272489666938782, + "learning_rate": 4.996162123648058e-05, + "loss": 1.4049, + "num_input_tokens_seen": 172224, + "step": 30, + "train_runtime": 202.5177, + "train_tokens_per_second": 850.415 + }, + { + "epoch": 0.06391234877881762, + "grad_norm": 0.6470730900764465, + "learning_rate": 4.99472513700584e-05, + "loss": 1.4239, + "num_input_tokens_seen": 200272, + "step": 35, + "train_runtime": 235.4246, + "train_tokens_per_second": 850.684 + }, + { + "epoch": 0.07304268431864872, + "grad_norm": 0.6487858295440674, + "learning_rate": 4.993060401862888e-05, + "loss": 1.389, + "num_input_tokens_seen": 227552, + "step": 40, + "train_runtime": 267.9205, + "train_tokens_per_second": 849.327 + }, + { + "epoch": 0.0821730198584798, + "grad_norm": 0.81675785779953, + "learning_rate": 4.9911680701962384e-05, + "loss": 1.3187, + "num_input_tokens_seen": 256320, + "step": 45, + "train_runtime": 301.0567, + "train_tokens_per_second": 851.401 + }, + { + "epoch": 0.09130335539831089, + "grad_norm": 0.590348482131958, + "learning_rate": 4.989048314760674e-05, + "loss": 1.31, + "num_input_tokens_seen": 287184, + "step": 50, + "train_runtime": 335.1262, + "train_tokens_per_second": 856.943 + }, + { + "epoch": 0.10043369093814197, + "grad_norm": 0.6573392748832703, + "learning_rate": 4.9867013290729535e-05, + "loss": 1.3295, + "num_input_tokens_seen": 314864, + "step": 55, + "train_runtime": 367.7602, + "train_tokens_per_second": 856.167 + }, + { + "epoch": 0.10956402647797306, + "grad_norm": 0.7032639980316162, + "learning_rate": 4.984127327394146e-05, + "loss": 1.2718, + "num_input_tokens_seen": 342912, + "step": 60, + "train_runtime": 400.5266, + "train_tokens_per_second": 856.153 + }, + { + "epoch": 0.11869436201780416, + "grad_norm": 0.789444088935852, + "learning_rate": 4.981326544710065e-05, + "loss": 1.2547, + "num_input_tokens_seen": 370064, + "step": 65, + "train_runtime": 432.9005, + "train_tokens_per_second": 854.848 + }, + { + "epoch": 0.12782469755763523, + "grad_norm": 0.7282975316047668, + "learning_rate": 4.978299236709826e-05, + "loss": 1.302, + "num_input_tokens_seen": 399584, + "step": 70, + "train_runtime": 466.4409, + "train_tokens_per_second": 856.666 + }, + { + "epoch": 0.13695503309746634, + "grad_norm": 0.7695715427398682, + "learning_rate": 4.975045679762496e-05, + "loss": 1.2328, + "num_input_tokens_seen": 430528, + "step": 75, + "train_runtime": 500.4187, + "train_tokens_per_second": 860.336 + }, + { + "epoch": 0.14608536863729743, + "grad_norm": 0.6912102699279785, + "learning_rate": 4.9715661708918624e-05, + "loss": 1.296, + "num_input_tokens_seen": 460080, + "step": 80, + "train_runtime": 533.9121, + "train_tokens_per_second": 861.715 + }, + { + "epoch": 0.15521570417712852, + "grad_norm": 0.7808125615119934, + "learning_rate": 4.9678610277493275e-05, + "loss": 1.3248, + "num_input_tokens_seen": 488176, + "step": 85, + "train_runtime": 566.9429, + "train_tokens_per_second": 861.067 + }, + { + "epoch": 0.1643460397169596, + "grad_norm": 0.8161223530769348, + "learning_rate": 4.9639305885848975e-05, + "loss": 1.207, + "num_input_tokens_seen": 516896, + "step": 90, + "train_runtime": 600.1453, + "train_tokens_per_second": 861.285 + }, + { + "epoch": 0.1734763752567907, + "grad_norm": 0.7836668491363525, + "learning_rate": 4.959775212216308e-05, + "loss": 1.2342, + "num_input_tokens_seen": 547440, + "step": 95, + "train_runtime": 634.2069, + "train_tokens_per_second": 863.188 + }, + { + "epoch": 0.18260671079662177, + "grad_norm": 0.7432403564453125, + "learning_rate": 4.955395277996268e-05, + "loss": 1.1931, + "num_input_tokens_seen": 577088, + "step": 100, + "train_runtime": 667.769, + "train_tokens_per_second": 864.203 + }, + { + "epoch": 0.19173704633645286, + "grad_norm": 0.7105097770690918, + "learning_rate": 4.9507911857778256e-05, + "loss": 1.2122, + "num_input_tokens_seen": 606976, + "step": 105, + "train_runtime": 702.605, + "train_tokens_per_second": 863.894 + }, + { + "epoch": 0.20086738187628395, + "grad_norm": 0.9018083810806274, + "learning_rate": 4.9459633558778684e-05, + "loss": 1.2973, + "num_input_tokens_seen": 634416, + "step": 110, + "train_runtime": 735.186, + "train_tokens_per_second": 862.933 + }, + { + "epoch": 0.20999771741611503, + "grad_norm": 0.878520131111145, + "learning_rate": 4.940912229038745e-05, + "loss": 1.2483, + "num_input_tokens_seen": 660192, + "step": 115, + "train_runtime": 767.1492, + "train_tokens_per_second": 860.578 + }, + { + "epoch": 0.21912805295594612, + "grad_norm": 0.7927104234695435, + "learning_rate": 4.9356382663880366e-05, + "loss": 1.1153, + "num_input_tokens_seen": 687936, + "step": 120, + "train_runtime": 799.9406, + "train_tokens_per_second": 859.984 + }, + { + "epoch": 0.22825838849577723, + "grad_norm": 0.9102480411529541, + "learning_rate": 4.930141949396454e-05, + "loss": 1.2269, + "num_input_tokens_seen": 716960, + "step": 125, + "train_runtime": 833.2659, + "train_tokens_per_second": 860.422 + }, + { + "epoch": 0.23738872403560832, + "grad_norm": 0.9657291173934937, + "learning_rate": 4.9244237798338866e-05, + "loss": 1.1324, + "num_input_tokens_seen": 744976, + "step": 130, + "train_runtime": 866.1684, + "train_tokens_per_second": 860.082 + }, + { + "epoch": 0.2465190595754394, + "grad_norm": 0.9540858268737793, + "learning_rate": 4.918484279723592e-05, + "loss": 1.1818, + "num_input_tokens_seen": 772176, + "step": 135, + "train_runtime": 898.6975, + "train_tokens_per_second": 859.217 + }, + { + "epoch": 0.25564939511527046, + "grad_norm": 0.9128895998001099, + "learning_rate": 4.9123239912945423e-05, + "loss": 1.1243, + "num_input_tokens_seen": 804528, + "step": 140, + "train_runtime": 933.4596, + "train_tokens_per_second": 861.878 + }, + { + "epoch": 0.2647797306551016, + "grad_norm": 0.896022379398346, + "learning_rate": 4.9059434769319205e-05, + "loss": 1.2134, + "num_input_tokens_seen": 831056, + "step": 145, + "train_runtime": 965.6266, + "train_tokens_per_second": 860.639 + }, + { + "epoch": 0.2739100661949327, + "grad_norm": 0.8580520153045654, + "learning_rate": 4.899343319125781e-05, + "loss": 1.0775, + "num_input_tokens_seen": 862416, + "step": 150, + "train_runtime": 999.9056, + "train_tokens_per_second": 862.497 + }, + { + "epoch": 0.28304040173476375, + "grad_norm": 0.9435716867446899, + "learning_rate": 4.892524120417872e-05, + "loss": 1.2069, + "num_input_tokens_seen": 889264, + "step": 155, + "train_runtime": 1032.1039, + "train_tokens_per_second": 861.603 + }, + { + "epoch": 0.29217073727459486, + "grad_norm": 0.9432860016822815, + "learning_rate": 4.8854865033466275e-05, + "loss": 1.1649, + "num_input_tokens_seen": 917104, + "step": 160, + "train_runtime": 1064.7569, + "train_tokens_per_second": 861.327 + }, + { + "epoch": 0.3013010728144259, + "grad_norm": 0.780659019947052, + "learning_rate": 4.878231110390337e-05, + "loss": 1.1495, + "num_input_tokens_seen": 947280, + "step": 165, + "train_runtime": 1098.5348, + "train_tokens_per_second": 862.312 + }, + { + "epoch": 0.31043140835425703, + "grad_norm": 1.0290687084197998, + "learning_rate": 4.870758603908489e-05, + "loss": 1.1231, + "num_input_tokens_seen": 978704, + "step": 170, + "train_runtime": 1132.7604, + "train_tokens_per_second": 863.999 + }, + { + "epoch": 0.3195617438940881, + "grad_norm": 0.8476850390434265, + "learning_rate": 4.863069666081307e-05, + "loss": 1.0885, + "num_input_tokens_seen": 1005904, + "step": 175, + "train_runtime": 1165.1167, + "train_tokens_per_second": 863.35 + }, + { + "epoch": 0.3286920794339192, + "grad_norm": 0.8470911383628845, + "learning_rate": 4.855164998847466e-05, + "loss": 1.1022, + "num_input_tokens_seen": 1034624, + "step": 180, + "train_runtime": 1198.278, + "train_tokens_per_second": 863.426 + }, + { + "epoch": 0.33782241497375026, + "grad_norm": 1.0513180494308472, + "learning_rate": 4.8470453238400195e-05, + "loss": 1.1223, + "num_input_tokens_seen": 1059280, + "step": 185, + "train_runtime": 1229.5356, + "train_tokens_per_second": 861.529 + }, + { + "epoch": 0.3469527505135814, + "grad_norm": 0.9217162132263184, + "learning_rate": 4.8387113823205096e-05, + "loss": 1.0287, + "num_input_tokens_seen": 1088960, + "step": 190, + "train_runtime": 1263.0899, + "train_tokens_per_second": 862.14 + }, + { + "epoch": 0.3560830860534125, + "grad_norm": 1.0153199434280396, + "learning_rate": 4.8301639351113065e-05, + "loss": 1.1138, + "num_input_tokens_seen": 1113712, + "step": 195, + "train_runtime": 1294.2756, + "train_tokens_per_second": 860.491 + }, + { + "epoch": 0.36521342159324355, + "grad_norm": 1.2406193017959595, + "learning_rate": 4.821403762526143e-05, + "loss": 1.1149, + "num_input_tokens_seen": 1141696, + "step": 200, + "train_runtime": 1326.999, + "train_tokens_per_second": 860.359 + }, + { + "epoch": 0.37434375713307466, + "grad_norm": 0.9366787075996399, + "learning_rate": 4.812431664298883e-05, + "loss": 1.1954, + "num_input_tokens_seen": 1172000, + "step": 205, + "train_runtime": 1362.1116, + "train_tokens_per_second": 860.429 + }, + { + "epoch": 0.3834740926729057, + "grad_norm": 0.8975793123245239, + "learning_rate": 4.803248459510511e-05, + "loss": 1.0426, + "num_input_tokens_seen": 1201136, + "step": 210, + "train_runtime": 1395.3356, + "train_tokens_per_second": 860.822 + }, + { + "epoch": 0.39260442821273683, + "grad_norm": 0.9986598491668701, + "learning_rate": 4.7938549865143544e-05, + "loss": 1.2254, + "num_input_tokens_seen": 1227792, + "step": 215, + "train_runtime": 1427.5362, + "train_tokens_per_second": 860.078 + }, + { + "epoch": 0.4017347637525679, + "grad_norm": 0.9591779112815857, + "learning_rate": 4.7842521028595526e-05, + "loss": 1.0323, + "num_input_tokens_seen": 1258240, + "step": 220, + "train_runtime": 1461.4996, + "train_tokens_per_second": 860.924 + }, + { + "epoch": 0.410865099292399, + "grad_norm": 1.1904876232147217, + "learning_rate": 4.7744406852127653e-05, + "loss": 0.9971, + "num_input_tokens_seen": 1289744, + "step": 225, + "train_runtime": 1495.7355, + "train_tokens_per_second": 862.281 + }, + { + "epoch": 0.41999543483223006, + "grad_norm": 1.1294660568237305, + "learning_rate": 4.764421629278144e-05, + "loss": 1.0328, + "num_input_tokens_seen": 1315040, + "step": 230, + "train_runtime": 1527.2934, + "train_tokens_per_second": 861.026 + }, + { + "epoch": 0.4291257703720612, + "grad_norm": 1.2325509786605835, + "learning_rate": 4.754195849715557e-05, + "loss": 1.0546, + "num_input_tokens_seen": 1344848, + "step": 235, + "train_runtime": 1560.7834, + "train_tokens_per_second": 861.649 + }, + { + "epoch": 0.43825610591189224, + "grad_norm": 0.991324245929718, + "learning_rate": 4.743764280057092e-05, + "loss": 1.1701, + "num_input_tokens_seen": 1371728, + "step": 240, + "train_runtime": 1593.0413, + "train_tokens_per_second": 861.075 + }, + { + "epoch": 0.44738644145172335, + "grad_norm": 1.1479493379592896, + "learning_rate": 4.73312787262183e-05, + "loss": 1.0949, + "num_input_tokens_seen": 1398896, + "step": 245, + "train_runtime": 1625.4235, + "train_tokens_per_second": 860.635 + }, + { + "epoch": 0.45651677699155446, + "grad_norm": 0.9881078600883484, + "learning_rate": 4.722287598428907e-05, + "loss": 1.1142, + "num_input_tokens_seen": 1425376, + "step": 250, + "train_runtime": 1657.4768, + "train_tokens_per_second": 859.967 + }, + { + "epoch": 0.4656471125313855, + "grad_norm": 1.3233039379119873, + "learning_rate": 4.711244447108866e-05, + "loss": 1.0364, + "num_input_tokens_seen": 1452416, + "step": 255, + "train_runtime": 1689.8742, + "train_tokens_per_second": 859.482 + }, + { + "epoch": 0.47477744807121663, + "grad_norm": 1.1027718782424927, + "learning_rate": 4.6999994268133166e-05, + "loss": 1.0669, + "num_input_tokens_seen": 1481440, + "step": 260, + "train_runtime": 1722.9242, + "train_tokens_per_second": 859.84 + }, + { + "epoch": 0.4839077836110477, + "grad_norm": 0.9862788915634155, + "learning_rate": 4.6885535641228904e-05, + "loss": 1.007, + "num_input_tokens_seen": 1510240, + "step": 265, + "train_runtime": 1756.1254, + "train_tokens_per_second": 859.984 + }, + { + "epoch": 0.4930381191508788, + "grad_norm": 0.8394035696983337, + "learning_rate": 4.676907903953531e-05, + "loss": 0.9444, + "num_input_tokens_seen": 1538208, + "step": 270, + "train_runtime": 1788.9168, + "train_tokens_per_second": 859.854 + }, + { + "epoch": 0.5021684546907099, + "grad_norm": 0.9921995401382446, + "learning_rate": 4.665063509461097e-05, + "loss": 1.0157, + "num_input_tokens_seen": 1566880, + "step": 275, + "train_runtime": 1821.9921, + "train_tokens_per_second": 859.982 + }, + { + "epoch": 0.5112987902305409, + "grad_norm": 1.0822592973709106, + "learning_rate": 4.6530214619443037e-05, + "loss": 1.0188, + "num_input_tokens_seen": 1593904, + "step": 280, + "train_runtime": 1854.3967, + "train_tokens_per_second": 859.527 + }, + { + "epoch": 0.520429125770372, + "grad_norm": 1.1514437198638916, + "learning_rate": 4.640782860746011e-05, + "loss": 0.9333, + "num_input_tokens_seen": 1621440, + "step": 285, + "train_runtime": 1887.0679, + "train_tokens_per_second": 859.238 + }, + { + "epoch": 0.5295594613102032, + "grad_norm": 1.1235507726669312, + "learning_rate": 4.628348823152863e-05, + "loss": 0.9435, + "num_input_tokens_seen": 1650064, + "step": 290, + "train_runtime": 1920.2198, + "train_tokens_per_second": 859.31 + }, + { + "epoch": 0.5386897968500343, + "grad_norm": 0.8459988832473755, + "learning_rate": 4.615720484293286e-05, + "loss": 0.9418, + "num_input_tokens_seen": 1677472, + "step": 295, + "train_runtime": 1952.7783, + "train_tokens_per_second": 859.018 + }, + { + "epoch": 0.5478201323898654, + "grad_norm": 1.2311139106750488, + "learning_rate": 4.602898997033861e-05, + "loss": 0.9934, + "num_input_tokens_seen": 1706672, + "step": 300, + "train_runtime": 1986.1813, + "train_tokens_per_second": 859.273 + }, + { + "epoch": 0.5569504679296964, + "grad_norm": 1.1580544710159302, + "learning_rate": 4.58988553187408e-05, + "loss": 1.0952, + "num_input_tokens_seen": 1734704, + "step": 305, + "train_runtime": 2020.184, + "train_tokens_per_second": 858.686 + }, + { + "epoch": 0.5660808034695275, + "grad_norm": 0.8693342804908752, + "learning_rate": 4.576681276839483e-05, + "loss": 0.9632, + "num_input_tokens_seen": 1763312, + "step": 310, + "train_runtime": 2053.3414, + "train_tokens_per_second": 858.752 + }, + { + "epoch": 0.5752111390093586, + "grad_norm": 0.9932484030723572, + "learning_rate": 4.5632874373732035e-05, + "loss": 0.931, + "num_input_tokens_seen": 1789616, + "step": 315, + "train_runtime": 2085.3946, + "train_tokens_per_second": 858.167 + }, + { + "epoch": 0.5843414745491897, + "grad_norm": 1.0481774806976318, + "learning_rate": 4.549705236225922e-05, + "loss": 1.0103, + "num_input_tokens_seen": 1817760, + "step": 320, + "train_runtime": 2118.2164, + "train_tokens_per_second": 858.156 + }, + { + "epoch": 0.5934718100890207, + "grad_norm": 0.9734839797019958, + "learning_rate": 4.5359359133442356e-05, + "loss": 0.9518, + "num_input_tokens_seen": 1845664, + "step": 325, + "train_runtime": 2150.9302, + "train_tokens_per_second": 858.077 + }, + { + "epoch": 0.6026021456288518, + "grad_norm": 0.935545802116394, + "learning_rate": 4.521980725757466e-05, + "loss": 0.8974, + "num_input_tokens_seen": 1875392, + "step": 330, + "train_runtime": 2184.587, + "train_tokens_per_second": 858.465 + }, + { + "epoch": 0.611732481168683, + "grad_norm": 1.1402722597122192, + "learning_rate": 4.5078409474628966e-05, + "loss": 0.9171, + "num_input_tokens_seen": 1902592, + "step": 335, + "train_runtime": 2217.1072, + "train_tokens_per_second": 858.142 + }, + { + "epoch": 0.6208628167085141, + "grad_norm": 1.1934939622879028, + "learning_rate": 4.4935178693094714e-05, + "loss": 0.899, + "num_input_tokens_seen": 1931328, + "step": 340, + "train_runtime": 2250.2974, + "train_tokens_per_second": 858.255 + }, + { + "epoch": 0.6299931522483452, + "grad_norm": 1.0187445878982544, + "learning_rate": 4.4790127988799494e-05, + "loss": 0.8964, + "num_input_tokens_seen": 1960528, + "step": 345, + "train_runtime": 2283.719, + "train_tokens_per_second": 858.48 + }, + { + "epoch": 0.6391234877881762, + "grad_norm": 1.0490012168884277, + "learning_rate": 4.464327060371529e-05, + "loss": 1.0919, + "num_input_tokens_seen": 1987168, + "step": 350, + "train_runtime": 2315.9585, + "train_tokens_per_second": 858.033 + }, + { + "epoch": 0.6482538233280073, + "grad_norm": 1.2056529521942139, + "learning_rate": 4.449461994474968e-05, + "loss": 1.0469, + "num_input_tokens_seen": 2014832, + "step": 355, + "train_runtime": 2348.6807, + "train_tokens_per_second": 857.857 + }, + { + "epoch": 0.6573841588678384, + "grad_norm": 0.9101769328117371, + "learning_rate": 4.434418958252179e-05, + "loss": 0.8841, + "num_input_tokens_seen": 2043840, + "step": 360, + "train_runtime": 2382.0483, + "train_tokens_per_second": 858.018 + }, + { + "epoch": 0.6665144944076695, + "grad_norm": 1.4810435771942139, + "learning_rate": 4.4191993250123483e-05, + "loss": 1.0016, + "num_input_tokens_seen": 2073120, + "step": 365, + "train_runtime": 2415.6373, + "train_tokens_per_second": 858.208 + }, + { + "epoch": 0.6756448299475005, + "grad_norm": 1.065366506576538, + "learning_rate": 4.4038044841865614e-05, + "loss": 0.9584, + "num_input_tokens_seen": 2098384, + "step": 370, + "train_runtime": 2447.2579, + "train_tokens_per_second": 857.443 + }, + { + "epoch": 0.6847751654873316, + "grad_norm": 1.2886056900024414, + "learning_rate": 4.388235841200956e-05, + "loss": 0.9964, + "num_input_tokens_seen": 2127008, + "step": 375, + "train_runtime": 2480.3435, + "train_tokens_per_second": 857.546 + }, + { + "epoch": 0.6939055010271628, + "grad_norm": 1.2109014987945557, + "learning_rate": 4.3724948173484216e-05, + "loss": 0.9808, + "num_input_tokens_seen": 2154624, + "step": 380, + "train_runtime": 2512.9908, + "train_tokens_per_second": 857.394 + }, + { + "epoch": 0.7030358365669939, + "grad_norm": 1.0763500928878784, + "learning_rate": 4.356582849658845e-05, + "loss": 0.9126, + "num_input_tokens_seen": 2184768, + "step": 385, + "train_runtime": 2546.895, + "train_tokens_per_second": 857.816 + }, + { + "epoch": 0.712166172106825, + "grad_norm": 1.1964282989501953, + "learning_rate": 4.340501390767924e-05, + "loss": 0.8749, + "num_input_tokens_seen": 2214336, + "step": 390, + "train_runtime": 2580.5251, + "train_tokens_per_second": 858.095 + }, + { + "epoch": 0.721296507646656, + "grad_norm": 1.2746434211730957, + "learning_rate": 4.324251908784546e-05, + "loss": 0.9203, + "num_input_tokens_seen": 2243296, + "step": 395, + "train_runtime": 2613.6736, + "train_tokens_per_second": 858.292 + }, + { + "epoch": 0.7304268431864871, + "grad_norm": 0.9673400521278381, + "learning_rate": 4.3078358871567706e-05, + "loss": 0.8857, + "num_input_tokens_seen": 2273424, + "step": 400, + "train_runtime": 2647.5272, + "train_tokens_per_second": 858.697 + }, + { + "epoch": 0.7395571787263182, + "grad_norm": 0.9456354975700378, + "learning_rate": 4.291254824536396e-05, + "loss": 0.9175, + "num_input_tokens_seen": 2303040, + "step": 405, + "train_runtime": 2682.2704, + "train_tokens_per_second": 858.616 + }, + { + "epoch": 0.7486875142661493, + "grad_norm": 1.1169666051864624, + "learning_rate": 4.274510234642148e-05, + "loss": 0.9572, + "num_input_tokens_seen": 2330352, + "step": 410, + "train_runtime": 2714.6955, + "train_tokens_per_second": 858.421 + }, + { + "epoch": 0.7578178498059803, + "grad_norm": 1.1452381610870361, + "learning_rate": 4.257603646121484e-05, + "loss": 1.0534, + "num_input_tokens_seen": 2357968, + "step": 415, + "train_runtime": 2747.2523, + "train_tokens_per_second": 858.3 + }, + { + "epoch": 0.7669481853458114, + "grad_norm": 1.2339755296707153, + "learning_rate": 4.240536602411048e-05, + "loss": 0.8583, + "num_input_tokens_seen": 2386800, + "step": 420, + "train_runtime": 2780.5385, + "train_tokens_per_second": 858.395 + }, + { + "epoch": 0.7760785208856426, + "grad_norm": 1.0699409246444702, + "learning_rate": 4.22331066159576e-05, + "loss": 0.8049, + "num_input_tokens_seen": 2416224, + "step": 425, + "train_runtime": 2813.8831, + "train_tokens_per_second": 858.68 + }, + { + "epoch": 0.7852088564254737, + "grad_norm": 1.0616157054901123, + "learning_rate": 4.205927396266577e-05, + "loss": 0.9599, + "num_input_tokens_seen": 2445120, + "step": 430, + "train_runtime": 2847.2801, + "train_tokens_per_second": 858.756 + }, + { + "epoch": 0.7943391919653047, + "grad_norm": 1.3448375463485718, + "learning_rate": 4.188388393376933e-05, + "loss": 0.8874, + "num_input_tokens_seen": 2473312, + "step": 435, + "train_runtime": 2880.2168, + "train_tokens_per_second": 858.724 + }, + { + "epoch": 0.8034695275051358, + "grad_norm": 1.3544775247573853, + "learning_rate": 4.1706952540978545e-05, + "loss": 0.8944, + "num_input_tokens_seen": 2500800, + "step": 440, + "train_runtime": 2912.8173, + "train_tokens_per_second": 858.55 + }, + { + "epoch": 0.8125998630449669, + "grad_norm": 1.1478849649429321, + "learning_rate": 4.152849593671793e-05, + "loss": 0.9774, + "num_input_tokens_seen": 2529392, + "step": 445, + "train_runtime": 2945.9115, + "train_tokens_per_second": 858.611 + }, + { + "epoch": 0.821730198584798, + "grad_norm": 1.1531591415405273, + "learning_rate": 4.134853041265162e-05, + "loss": 0.8543, + "num_input_tokens_seen": 2559536, + "step": 450, + "train_runtime": 2979.5242, + "train_tokens_per_second": 859.042 + }, + { + "epoch": 0.8308605341246291, + "grad_norm": 1.034783959388733, + "learning_rate": 4.11670723981961e-05, + "loss": 0.8293, + "num_input_tokens_seen": 2588144, + "step": 455, + "train_runtime": 3012.7186, + "train_tokens_per_second": 859.073 + }, + { + "epoch": 0.8399908696644601, + "grad_norm": 1.181213617324829, + "learning_rate": 4.098413845902033e-05, + "loss": 0.9264, + "num_input_tokens_seen": 2617968, + "step": 460, + "train_runtime": 3046.4091, + "train_tokens_per_second": 859.362 + }, + { + "epoch": 0.8491212052042912, + "grad_norm": 1.134751796722412, + "learning_rate": 4.079974529553341e-05, + "loss": 0.9641, + "num_input_tokens_seen": 2646896, + "step": 465, + "train_runtime": 3079.7911, + "train_tokens_per_second": 859.44 + }, + { + "epoch": 0.8582515407441224, + "grad_norm": 1.0939092636108398, + "learning_rate": 4.061390974135997e-05, + "loss": 0.805, + "num_input_tokens_seen": 2674288, + "step": 470, + "train_runtime": 3112.254, + "train_tokens_per_second": 859.277 + }, + { + "epoch": 0.8673818762839535, + "grad_norm": 1.4272619485855103, + "learning_rate": 4.042664876180341e-05, + "loss": 1.0411, + "num_input_tokens_seen": 2700464, + "step": 475, + "train_runtime": 3144.0731, + "train_tokens_per_second": 858.906 + }, + { + "epoch": 0.8765122118237845, + "grad_norm": 1.2609965801239014, + "learning_rate": 4.0237979452297094e-05, + "loss": 0.8638, + "num_input_tokens_seen": 2732112, + "step": 480, + "train_runtime": 3178.5283, + "train_tokens_per_second": 859.553 + }, + { + "epoch": 0.8856425473636156, + "grad_norm": 1.5450228452682495, + "learning_rate": 4.0047919036843675e-05, + "loss": 1.0152, + "num_input_tokens_seen": 2757872, + "step": 485, + "train_runtime": 3210.3201, + "train_tokens_per_second": 859.064 + }, + { + "epoch": 0.8947728829034467, + "grad_norm": 1.1069929599761963, + "learning_rate": 3.985648486644267e-05, + "loss": 0.9046, + "num_input_tokens_seen": 2786192, + "step": 490, + "train_runtime": 3243.3923, + "train_tokens_per_second": 859.036 + }, + { + "epoch": 0.9039032184432778, + "grad_norm": 1.0615628957748413, + "learning_rate": 3.966369441750648e-05, + "loss": 0.8428, + "num_input_tokens_seen": 2812368, + "step": 495, + "train_runtime": 3275.3944, + "train_tokens_per_second": 858.635 + }, + { + "epoch": 0.9130335539831089, + "grad_norm": 1.0123751163482666, + "learning_rate": 3.9469565290264906e-05, + "loss": 0.8138, + "num_input_tokens_seen": 2840912, + "step": 500, + "train_runtime": 3308.5472, + "train_tokens_per_second": 858.658 + }, + { + "epoch": 0.9221638895229399, + "grad_norm": 1.2222071886062622, + "learning_rate": 3.92741152071584e-05, + "loss": 0.8349, + "num_input_tokens_seen": 2870000, + "step": 505, + "train_runtime": 3343.2464, + "train_tokens_per_second": 858.447 + }, + { + "epoch": 0.931294225062771, + "grad_norm": 1.2460840940475464, + "learning_rate": 3.907736201122014e-05, + "loss": 0.883, + "num_input_tokens_seen": 2899328, + "step": 510, + "train_runtime": 3376.5896, + "train_tokens_per_second": 858.656 + }, + { + "epoch": 0.9404245606026022, + "grad_norm": 1.1203129291534424, + "learning_rate": 3.8879323664447096e-05, + "loss": 0.8141, + "num_input_tokens_seen": 2928832, + "step": 515, + "train_runtime": 3410.0362, + "train_tokens_per_second": 858.886 + }, + { + "epoch": 0.9495548961424333, + "grad_norm": 1.0772883892059326, + "learning_rate": 3.8680018246160295e-05, + "loss": 0.8964, + "num_input_tokens_seen": 2956352, + "step": 520, + "train_runtime": 3442.6688, + "train_tokens_per_second": 858.738 + }, + { + "epoch": 0.9586852316822643, + "grad_norm": 1.098358154296875, + "learning_rate": 3.8479463951354245e-05, + "loss": 0.7845, + "num_input_tokens_seen": 2985072, + "step": 525, + "train_runtime": 3475.9209, + "train_tokens_per_second": 858.786 + }, + { + "epoch": 0.9678155672220954, + "grad_norm": 1.61497163772583, + "learning_rate": 3.827767908903592e-05, + "loss": 0.9675, + "num_input_tokens_seen": 3013200, + "step": 530, + "train_runtime": 3508.7675, + "train_tokens_per_second": 858.763 + }, + { + "epoch": 0.9769459027619265, + "grad_norm": 1.2918585538864136, + "learning_rate": 3.8074682080553335e-05, + "loss": 0.9429, + "num_input_tokens_seen": 3044064, + "step": 535, + "train_runtime": 3542.8639, + "train_tokens_per_second": 859.21 + }, + { + "epoch": 0.9860762383017576, + "grad_norm": 1.1658656597137451, + "learning_rate": 3.7870491457913714e-05, + "loss": 0.9034, + "num_input_tokens_seen": 3071008, + "step": 540, + "train_runtime": 3575.2913, + "train_tokens_per_second": 858.953 + }, + { + "epoch": 0.9952065738415887, + "grad_norm": 1.8342398405075073, + "learning_rate": 3.7665125862091765e-05, + "loss": 0.8696, + "num_input_tokens_seen": 3100256, + "step": 545, + "train_runtime": 3608.7852, + "train_tokens_per_second": 859.086 + }, + { + "epoch": 1.0036521342159324, + "grad_norm": 1.1551634073257446, + "learning_rate": 3.7458604041327874e-05, + "loss": 0.9914, + "num_input_tokens_seen": 3125104, + "step": 550, + "train_runtime": 3638.8068, + "train_tokens_per_second": 858.827 + }, + { + "epoch": 1.0127824697557635, + "grad_norm": 1.2146859169006348, + "learning_rate": 3.725094484941654e-05, + "loss": 0.7924, + "num_input_tokens_seen": 3153200, + "step": 555, + "train_runtime": 3671.7067, + "train_tokens_per_second": 858.783 + }, + { + "epoch": 1.0219128052955946, + "grad_norm": 1.43285071849823, + "learning_rate": 3.704216724398515e-05, + "loss": 0.7542, + "num_input_tokens_seen": 3180768, + "step": 560, + "train_runtime": 3704.3172, + "train_tokens_per_second": 858.665 + }, + { + "epoch": 1.0310431408354257, + "grad_norm": 1.2489193677902222, + "learning_rate": 3.683229028476334e-05, + "loss": 0.7216, + "num_input_tokens_seen": 3208032, + "step": 565, + "train_runtime": 3736.7691, + "train_tokens_per_second": 858.504 + }, + { + "epoch": 1.0401734763752568, + "grad_norm": 1.520088791847229, + "learning_rate": 3.6621333131842994e-05, + "loss": 0.8276, + "num_input_tokens_seen": 3235216, + "step": 570, + "train_runtime": 3769.2767, + "train_tokens_per_second": 858.312 + }, + { + "epoch": 1.049303811915088, + "grad_norm": 1.1563032865524292, + "learning_rate": 3.640931504392902e-05, + "loss": 0.8081, + "num_input_tokens_seen": 3264128, + "step": 575, + "train_runtime": 3802.3942, + "train_tokens_per_second": 858.44 + }, + { + "epoch": 1.058434147454919, + "grad_norm": 1.2162935733795166, + "learning_rate": 3.6196255376581254e-05, + "loss": 0.7503, + "num_input_tokens_seen": 3291488, + "step": 580, + "train_runtime": 3834.8435, + "train_tokens_per_second": 858.311 + }, + { + "epoch": 1.0675644829947502, + "grad_norm": 1.1006977558135986, + "learning_rate": 3.598217358044743e-05, + "loss": 0.7449, + "num_input_tokens_seen": 3320544, + "step": 585, + "train_runtime": 3868.0173, + "train_tokens_per_second": 858.462 + }, + { + "epoch": 1.076694818534581, + "grad_norm": 1.2781275510787964, + "learning_rate": 3.576708919948747e-05, + "loss": 0.7779, + "num_input_tokens_seen": 3350544, + "step": 590, + "train_runtime": 3901.7778, + "train_tokens_per_second": 858.722 + }, + { + "epoch": 1.0858251540744122, + "grad_norm": 1.8124620914459229, + "learning_rate": 3.5551021869189286e-05, + "loss": 0.7257, + "num_input_tokens_seen": 3380800, + "step": 595, + "train_runtime": 3935.5685, + "train_tokens_per_second": 859.037 + }, + { + "epoch": 1.0949554896142433, + "grad_norm": 1.1860169172286987, + "learning_rate": 3.533399131477624e-05, + "loss": 0.7348, + "num_input_tokens_seen": 3408976, + "step": 600, + "train_runtime": 3968.4791, + "train_tokens_per_second": 859.013 + }, + { + "epoch": 1.1040858251540744, + "grad_norm": 1.4015891551971436, + "learning_rate": 3.511601734940636e-05, + "loss": 0.814, + "num_input_tokens_seen": 3437392, + "step": 605, + "train_runtime": 4002.5648, + "train_tokens_per_second": 858.797 + }, + { + "epoch": 1.1132161606939055, + "grad_norm": 1.445547342300415, + "learning_rate": 3.489711987236357e-05, + "loss": 0.6645, + "num_input_tokens_seen": 3465184, + "step": 610, + "train_runtime": 4035.2092, + "train_tokens_per_second": 858.737 + }, + { + "epoch": 1.1223464962337366, + "grad_norm": 1.2986106872558594, + "learning_rate": 3.467731886724104e-05, + "loss": 0.7804, + "num_input_tokens_seen": 3493520, + "step": 615, + "train_runtime": 4068.2429, + "train_tokens_per_second": 858.729 + }, + { + "epoch": 1.1314768317735677, + "grad_norm": 1.471055030822754, + "learning_rate": 3.445663440011685e-05, + "loss": 0.8645, + "num_input_tokens_seen": 3520400, + "step": 620, + "train_runtime": 4100.7487, + "train_tokens_per_second": 858.477 + }, + { + "epoch": 1.1406071673133988, + "grad_norm": 1.3849546909332275, + "learning_rate": 3.42350866177221e-05, + "loss": 0.7509, + "num_input_tokens_seen": 3550208, + "step": 625, + "train_runtime": 4134.4243, + "train_tokens_per_second": 858.695 + }, + { + "epoch": 1.1497375028532297, + "grad_norm": 1.3286018371582031, + "learning_rate": 3.4012695745601694e-05, + "loss": 0.738, + "num_input_tokens_seen": 3579424, + "step": 630, + "train_runtime": 4167.8838, + "train_tokens_per_second": 858.811 + }, + { + "epoch": 1.158867838393061, + "grad_norm": 1.5071204900741577, + "learning_rate": 3.378948208626792e-05, + "loss": 0.731, + "num_input_tokens_seen": 3608096, + "step": 635, + "train_runtime": 4201.1661, + "train_tokens_per_second": 858.832 + }, + { + "epoch": 1.167998173932892, + "grad_norm": 1.225210428237915, + "learning_rate": 3.356546601734692e-05, + "loss": 0.6878, + "num_input_tokens_seen": 3636352, + "step": 640, + "train_runtime": 4234.2595, + "train_tokens_per_second": 858.793 + }, + { + "epoch": 1.177128509472723, + "grad_norm": 1.3939982652664185, + "learning_rate": 3.3340667989718494e-05, + "loss": 0.6777, + "num_input_tokens_seen": 3665104, + "step": 645, + "train_runtime": 4267.4915, + "train_tokens_per_second": 858.843 + }, + { + "epoch": 1.1862588450125542, + "grad_norm": 1.551377773284912, + "learning_rate": 3.3115108525648995e-05, + "loss": 0.8185, + "num_input_tokens_seen": 3692784, + "step": 650, + "train_runtime": 4300.1569, + "train_tokens_per_second": 858.756 + }, + { + "epoch": 1.1953891805523853, + "grad_norm": 1.4566768407821655, + "learning_rate": 3.288880821691785e-05, + "loss": 0.7367, + "num_input_tokens_seen": 3720544, + "step": 655, + "train_runtime": 4332.9255, + "train_tokens_per_second": 858.668 + }, + { + "epoch": 1.2045195160922164, + "grad_norm": 1.6438571214675903, + "learning_rate": 3.2661787722937705e-05, + "loss": 0.7812, + "num_input_tokens_seen": 3748640, + "step": 660, + "train_runtime": 4365.8382, + "train_tokens_per_second": 858.63 + }, + { + "epoch": 1.2136498516320475, + "grad_norm": 1.207120418548584, + "learning_rate": 3.2434067768868365e-05, + "loss": 0.6602, + "num_input_tokens_seen": 3779312, + "step": 665, + "train_runtime": 4399.8682, + "train_tokens_per_second": 858.96 + }, + { + "epoch": 1.2227801871718786, + "grad_norm": 1.2142479419708252, + "learning_rate": 3.220566914372477e-05, + "loss": 0.7918, + "num_input_tokens_seen": 3807232, + "step": 670, + "train_runtime": 4432.6887, + "train_tokens_per_second": 858.899 + }, + { + "epoch": 1.2319105227117095, + "grad_norm": 1.5016285181045532, + "learning_rate": 3.1976612698479104e-05, + "loss": 0.6596, + "num_input_tokens_seen": 3835568, + "step": 675, + "train_runtime": 4465.6751, + "train_tokens_per_second": 858.9 + }, + { + "epoch": 1.2410408582515409, + "grad_norm": 1.6100620031356812, + "learning_rate": 3.174691934415727e-05, + "loss": 0.595, + "num_input_tokens_seen": 3866240, + "step": 680, + "train_runtime": 4499.6303, + "train_tokens_per_second": 859.235 + }, + { + "epoch": 1.2501711937913718, + "grad_norm": 1.548384666442871, + "learning_rate": 3.151661004992992e-05, + "loss": 0.7421, + "num_input_tokens_seen": 3894400, + "step": 685, + "train_runtime": 4532.4548, + "train_tokens_per_second": 859.225 + }, + { + "epoch": 1.2593015293312029, + "grad_norm": 1.2995214462280273, + "learning_rate": 3.128570584119806e-05, + "loss": 0.8241, + "num_input_tokens_seen": 3917984, + "step": 690, + "train_runtime": 4563.2092, + "train_tokens_per_second": 858.603 + }, + { + "epoch": 1.268431864871034, + "grad_norm": 2.447808027267456, + "learning_rate": 3.105422779767369e-05, + "loss": 0.7889, + "num_input_tokens_seen": 3943952, + "step": 695, + "train_runtime": 4595.1589, + "train_tokens_per_second": 858.284 + }, + { + "epoch": 1.277562200410865, + "grad_norm": 1.6894609928131104, + "learning_rate": 3.08221970514553e-05, + "loss": 0.8462, + "num_input_tokens_seen": 3970976, + "step": 700, + "train_runtime": 4627.5505, + "train_tokens_per_second": 858.116 + }, + { + "epoch": 1.2866925359506962, + "grad_norm": 1.449867844581604, + "learning_rate": 3.058963478509879e-05, + "loss": 0.8064, + "num_input_tokens_seen": 3998816, + "step": 705, + "train_runtime": 4661.3843, + "train_tokens_per_second": 857.86 + }, + { + "epoch": 1.2958228714905273, + "grad_norm": 1.7921152114868164, + "learning_rate": 3.0356562229683534e-05, + "loss": 0.7113, + "num_input_tokens_seen": 4026144, + "step": 710, + "train_runtime": 4693.863, + "train_tokens_per_second": 857.746 + }, + { + "epoch": 1.3049532070303584, + "grad_norm": 1.4323357343673706, + "learning_rate": 3.0123000662874272e-05, + "loss": 0.7086, + "num_input_tokens_seen": 4053232, + "step": 715, + "train_runtime": 4726.3529, + "train_tokens_per_second": 857.581 + }, + { + "epoch": 1.3140835425701893, + "grad_norm": 1.779567837715149, + "learning_rate": 2.9888971406978584e-05, + "loss": 0.6923, + "num_input_tokens_seen": 4080992, + "step": 720, + "train_runtime": 4759.0105, + "train_tokens_per_second": 857.53 + }, + { + "epoch": 1.3232138781100207, + "grad_norm": 1.556424617767334, + "learning_rate": 2.965449582700031e-05, + "loss": 0.7034, + "num_input_tokens_seen": 4108944, + "step": 725, + "train_runtime": 4792.0064, + "train_tokens_per_second": 857.458 + }, + { + "epoch": 1.3323442136498516, + "grad_norm": 1.2673003673553467, + "learning_rate": 2.9419595328689138e-05, + "loss": 0.7029, + "num_input_tokens_seen": 4137872, + "step": 730, + "train_runtime": 4825.2446, + "train_tokens_per_second": 857.547 + }, + { + "epoch": 1.3414745491896827, + "grad_norm": 1.414905309677124, + "learning_rate": 2.918429135658638e-05, + "loss": 0.7442, + "num_input_tokens_seen": 4167120, + "step": 735, + "train_runtime": 4858.5579, + "train_tokens_per_second": 857.687 + }, + { + "epoch": 1.3506048847295138, + "grad_norm": 2.0791618824005127, + "learning_rate": 2.8948605392067322e-05, + "loss": 0.6896, + "num_input_tokens_seen": 4197456, + "step": 740, + "train_runtime": 4892.5846, + "train_tokens_per_second": 857.922 + }, + { + "epoch": 1.359735220269345, + "grad_norm": 1.620800256729126, + "learning_rate": 2.8712558951380097e-05, + "loss": 0.7188, + "num_input_tokens_seen": 4226784, + "step": 745, + "train_runtime": 4926.0456, + "train_tokens_per_second": 858.048 + }, + { + "epoch": 1.368865555809176, + "grad_norm": 1.6217539310455322, + "learning_rate": 2.847617358368142e-05, + "loss": 0.7536, + "num_input_tokens_seen": 4257552, + "step": 750, + "train_runtime": 4960.2606, + "train_tokens_per_second": 858.332 + }, + { + "epoch": 1.3779958913490071, + "grad_norm": 1.5368753671646118, + "learning_rate": 2.8239470869069357e-05, + "loss": 0.6742, + "num_input_tokens_seen": 4285344, + "step": 755, + "train_runtime": 4993.0307, + "train_tokens_per_second": 858.265 + }, + { + "epoch": 1.3871262268888382, + "grad_norm": 1.3456413745880127, + "learning_rate": 2.800247241661321e-05, + "loss": 0.6787, + "num_input_tokens_seen": 4313920, + "step": 760, + "train_runtime": 5026.2219, + "train_tokens_per_second": 858.283 + }, + { + "epoch": 1.3962565624286691, + "grad_norm": 1.3520539999008179, + "learning_rate": 2.776519986238079e-05, + "loss": 0.8232, + "num_input_tokens_seen": 4341584, + "step": 765, + "train_runtime": 5058.8442, + "train_tokens_per_second": 858.217 + }, + { + "epoch": 1.4053868979685005, + "grad_norm": 1.5738906860351562, + "learning_rate": 2.75276748674632e-05, + "loss": 0.7529, + "num_input_tokens_seen": 4369072, + "step": 770, + "train_runtime": 5091.5528, + "train_tokens_per_second": 858.102 + }, + { + "epoch": 1.4145172335083314, + "grad_norm": 1.485304594039917, + "learning_rate": 2.7289919115997374e-05, + "loss": 0.7612, + "num_input_tokens_seen": 4397152, + "step": 775, + "train_runtime": 5124.3984, + "train_tokens_per_second": 858.082 + }, + { + "epoch": 1.4236475690481625, + "grad_norm": 1.7065860033035278, + "learning_rate": 2.7051954313186484e-05, + "loss": 0.777, + "num_input_tokens_seen": 4423120, + "step": 780, + "train_runtime": 5156.3448, + "train_tokens_per_second": 857.801 + }, + { + "epoch": 1.4327779045879936, + "grad_norm": 2.3600783348083496, + "learning_rate": 2.6813802183318404e-05, + "loss": 0.7732, + "num_input_tokens_seen": 4451328, + "step": 785, + "train_runtime": 5189.1907, + "train_tokens_per_second": 857.808 + }, + { + "epoch": 1.4419082401278247, + "grad_norm": 1.3053230047225952, + "learning_rate": 2.6575484467782486e-05, + "loss": 0.6874, + "num_input_tokens_seen": 4480256, + "step": 790, + "train_runtime": 5222.4951, + "train_tokens_per_second": 857.877 + }, + { + "epoch": 1.4510385756676558, + "grad_norm": 1.2987860441207886, + "learning_rate": 2.633702292308473e-05, + "loss": 0.6866, + "num_input_tokens_seen": 4509584, + "step": 795, + "train_runtime": 5255.8931, + "train_tokens_per_second": 858.005 + }, + { + "epoch": 1.460168911207487, + "grad_norm": 1.6623998880386353, + "learning_rate": 2.60984393188616e-05, + "loss": 0.6184, + "num_input_tokens_seen": 4537136, + "step": 800, + "train_runtime": 5288.583, + "train_tokens_per_second": 857.911 + }, + { + "epoch": 1.469299246747318, + "grad_norm": 1.233757734298706, + "learning_rate": 2.5859755435892597e-05, + "loss": 0.6364, + "num_input_tokens_seen": 4565424, + "step": 805, + "train_runtime": 5322.8159, + "train_tokens_per_second": 857.708 + }, + { + "epoch": 1.478429582287149, + "grad_norm": 1.917475700378418, + "learning_rate": 2.5620993064111902e-05, + "loss": 0.7312, + "num_input_tokens_seen": 4592976, + "step": 810, + "train_runtime": 5355.4266, + "train_tokens_per_second": 857.63 + }, + { + "epoch": 1.4875599178269803, + "grad_norm": 1.3960131406784058, + "learning_rate": 2.538217400061907e-05, + "loss": 0.6735, + "num_input_tokens_seen": 4622416, + "step": 815, + "train_runtime": 5388.765, + "train_tokens_per_second": 857.788 + }, + { + "epoch": 1.4966902533668112, + "grad_norm": 2.6439576148986816, + "learning_rate": 2.5143320047689173e-05, + "loss": 0.5681, + "num_input_tokens_seen": 4648848, + "step": 820, + "train_runtime": 5421.0274, + "train_tokens_per_second": 857.558 + }, + { + "epoch": 1.5058205889066423, + "grad_norm": 1.6874146461486816, + "learning_rate": 2.49044530107824e-05, + "loss": 0.7154, + "num_input_tokens_seen": 4674688, + "step": 825, + "train_runtime": 5453.0982, + "train_tokens_per_second": 857.254 + }, + { + "epoch": 1.5149509244464734, + "grad_norm": 2.135629892349243, + "learning_rate": 2.4665594696553428e-05, + "loss": 0.659, + "num_input_tokens_seen": 4700240, + "step": 830, + "train_runtime": 5484.8225, + "train_tokens_per_second": 856.954 + }, + { + "epoch": 1.5240812599863045, + "grad_norm": 1.135087490081787, + "learning_rate": 2.4426766910860585e-05, + "loss": 0.66, + "num_input_tokens_seen": 4729648, + "step": 835, + "train_runtime": 5518.3348, + "train_tokens_per_second": 857.079 + }, + { + "epoch": 1.5332115955261356, + "grad_norm": 1.5050617456436157, + "learning_rate": 2.4187991456775217e-05, + "loss": 0.8048, + "num_input_tokens_seen": 4758944, + "step": 840, + "train_runtime": 5551.5721, + "train_tokens_per_second": 857.225 + }, + { + "epoch": 1.5423419310659665, + "grad_norm": 2.2734262943267822, + "learning_rate": 2.3949290132591197e-05, + "loss": 0.6516, + "num_input_tokens_seen": 4787360, + "step": 845, + "train_runtime": 5584.6087, + "train_tokens_per_second": 857.242 + }, + { + "epoch": 1.5514722666057978, + "grad_norm": 1.2877403497695923, + "learning_rate": 2.3710684729834954e-05, + "loss": 0.6813, + "num_input_tokens_seen": 4815712, + "step": 850, + "train_runtime": 5617.6077, + "train_tokens_per_second": 857.253 + }, + { + "epoch": 1.5606026021456287, + "grad_norm": 1.3478307723999023, + "learning_rate": 2.3472197031276e-05, + "loss": 0.7308, + "num_input_tokens_seen": 4845280, + "step": 855, + "train_runtime": 5651.0463, + "train_tokens_per_second": 857.413 + }, + { + "epoch": 1.56973293768546, + "grad_norm": 1.378150463104248, + "learning_rate": 2.3233848808938453e-05, + "loss": 0.7728, + "num_input_tokens_seen": 4873936, + "step": 860, + "train_runtime": 5684.0879, + "train_tokens_per_second": 857.47 + }, + { + "epoch": 1.578863273225291, + "grad_norm": 1.5141141414642334, + "learning_rate": 2.299566182211333e-05, + "loss": 0.6673, + "num_input_tokens_seen": 4901104, + "step": 865, + "train_runtime": 5716.3954, + "train_tokens_per_second": 857.377 + }, + { + "epoch": 1.587993608765122, + "grad_norm": 1.601626992225647, + "learning_rate": 2.275765781537215e-05, + "loss": 0.7155, + "num_input_tokens_seen": 4929696, + "step": 870, + "train_runtime": 5749.5599, + "train_tokens_per_second": 857.404 + }, + { + "epoch": 1.5971239443049532, + "grad_norm": 1.5736284255981445, + "learning_rate": 2.251985851658181e-05, + "loss": 0.6372, + "num_input_tokens_seen": 4959408, + "step": 875, + "train_runtime": 5783.3079, + "train_tokens_per_second": 857.538 + }, + { + "epoch": 1.6062542798447843, + "grad_norm": 1.464152216911316, + "learning_rate": 2.228228563492098e-05, + "loss": 0.7021, + "num_input_tokens_seen": 4988800, + "step": 880, + "train_runtime": 5816.7568, + "train_tokens_per_second": 857.66 + }, + { + "epoch": 1.6153846153846154, + "grad_norm": 2.137424945831299, + "learning_rate": 2.2044960858898277e-05, + "loss": 0.6923, + "num_input_tokens_seen": 5018752, + "step": 885, + "train_runtime": 5850.4263, + "train_tokens_per_second": 857.844 + }, + { + "epoch": 1.6245149509244463, + "grad_norm": 1.4711562395095825, + "learning_rate": 2.1807905854372242e-05, + "loss": 0.6426, + "num_input_tokens_seen": 5047792, + "step": 890, + "train_runtime": 5883.6717, + "train_tokens_per_second": 857.932 + }, + { + "epoch": 1.6336452864642776, + "grad_norm": 1.6127244234085083, + "learning_rate": 2.1571142262573457e-05, + "loss": 0.5618, + "num_input_tokens_seen": 5076528, + "step": 895, + "train_runtime": 5916.924, + "train_tokens_per_second": 857.967 + }, + { + "epoch": 1.6427756220041085, + "grad_norm": 2.0708415508270264, + "learning_rate": 2.133469169812879e-05, + "loss": 0.616, + "num_input_tokens_seen": 5101504, + "step": 900, + "train_runtime": 5948.3179, + "train_tokens_per_second": 857.638 + }, + { + "epoch": 1.6519059575439399, + "grad_norm": 1.7397692203521729, + "learning_rate": 2.109857574708826e-05, + "loss": 0.6574, + "num_input_tokens_seen": 5129104, + "step": 905, + "train_runtime": 5982.137, + "train_tokens_per_second": 857.403 + }, + { + "epoch": 1.6610362930837708, + "grad_norm": 2.0171751976013184, + "learning_rate": 2.086281596495434e-05, + "loss": 0.6823, + "num_input_tokens_seen": 5156640, + "step": 910, + "train_runtime": 6014.8999, + "train_tokens_per_second": 857.311 + }, + { + "epoch": 1.6701666286236019, + "grad_norm": 1.524135708808899, + "learning_rate": 2.0627433874714115e-05, + "loss": 0.5728, + "num_input_tokens_seen": 5184848, + "step": 915, + "train_runtime": 6047.8057, + "train_tokens_per_second": 857.311 + }, + { + "epoch": 1.679296964163433, + "grad_norm": 1.4557563066482544, + "learning_rate": 2.0392450964874415e-05, + "loss": 0.7025, + "num_input_tokens_seen": 5212928, + "step": 920, + "train_runtime": 6080.8053, + "train_tokens_per_second": 857.276 + }, + { + "epoch": 1.688427299703264, + "grad_norm": 2.1225433349609375, + "learning_rate": 2.015788868750009e-05, + "loss": 0.5986, + "num_input_tokens_seen": 5243568, + "step": 925, + "train_runtime": 6114.7733, + "train_tokens_per_second": 857.525 + }, + { + "epoch": 1.6975576352430952, + "grad_norm": 1.5523720979690552, + "learning_rate": 1.9923768456255594e-05, + "loss": 0.6195, + "num_input_tokens_seen": 5269840, + "step": 930, + "train_runtime": 6146.8665, + "train_tokens_per_second": 857.321 + }, + { + "epoch": 1.7066879707829261, + "grad_norm": 1.5369882583618164, + "learning_rate": 1.969011164445011e-05, + "loss": 0.6283, + "num_input_tokens_seen": 5299120, + "step": 935, + "train_runtime": 6180.3855, + "train_tokens_per_second": 857.409 + }, + { + "epoch": 1.7158183063227574, + "grad_norm": 1.5137027502059937, + "learning_rate": 1.9456939583086303e-05, + "loss": 0.5767, + "num_input_tokens_seen": 5328464, + "step": 940, + "train_runtime": 6213.906, + "train_tokens_per_second": 857.506 + }, + { + "epoch": 1.7249486418625883, + "grad_norm": 1.5988773107528687, + "learning_rate": 1.9224273558913024e-05, + "loss": 0.5237, + "num_input_tokens_seen": 5354896, + "step": 945, + "train_runtime": 6245.9758, + "train_tokens_per_second": 857.335 + }, + { + "epoch": 1.7340789774024197, + "grad_norm": 1.878609538078308, + "learning_rate": 1.8992134812481915e-05, + "loss": 0.7184, + "num_input_tokens_seen": 5383856, + "step": 950, + "train_runtime": 6279.2585, + "train_tokens_per_second": 857.403 + }, + { + "epoch": 1.7432093129422506, + "grad_norm": 1.5450001955032349, + "learning_rate": 1.876054453620841e-05, + "loss": 0.6595, + "num_input_tokens_seen": 5412864, + "step": 955, + "train_runtime": 6312.6127, + "train_tokens_per_second": 857.468 + }, + { + "epoch": 1.7523396484820817, + "grad_norm": 1.623189091682434, + "learning_rate": 1.852952387243698e-05, + "loss": 0.6161, + "num_input_tokens_seen": 5441392, + "step": 960, + "train_runtime": 6345.6472, + "train_tokens_per_second": 857.5 + }, + { + "epoch": 1.7614699840219128, + "grad_norm": 1.7493008375167847, + "learning_rate": 1.829909391151103e-05, + "loss": 0.6076, + "num_input_tokens_seen": 5470928, + "step": 965, + "train_runtime": 6379.1343, + "train_tokens_per_second": 857.629 + }, + { + "epoch": 1.770600319561744, + "grad_norm": 1.557199478149414, + "learning_rate": 1.8069275689847466e-05, + "loss": 0.5543, + "num_input_tokens_seen": 5500576, + "step": 970, + "train_runtime": 6412.7424, + "train_tokens_per_second": 857.757 + }, + { + "epoch": 1.779730655101575, + "grad_norm": 1.6990467309951782, + "learning_rate": 1.784009018801634e-05, + "loss": 0.6496, + "num_input_tokens_seen": 5528288, + "step": 975, + "train_runtime": 6445.5057, + "train_tokens_per_second": 857.697 + }, + { + "epoch": 1.788860990641406, + "grad_norm": 1.5374281406402588, + "learning_rate": 1.7611558328825384e-05, + "loss": 0.6315, + "num_input_tokens_seen": 5557472, + "step": 980, + "train_runtime": 6478.8281, + "train_tokens_per_second": 857.79 + }, + { + "epoch": 1.7979913261812372, + "grad_norm": 1.4920860528945923, + "learning_rate": 1.738370097541e-05, + "loss": 0.5654, + "num_input_tokens_seen": 5585120, + "step": 985, + "train_runtime": 6511.6592, + "train_tokens_per_second": 857.711 + }, + { + "epoch": 1.8071216617210681, + "grad_norm": 1.4632899761199951, + "learning_rate": 1.7156538929328593e-05, + "loss": 0.5803, + "num_input_tokens_seen": 5613760, + "step": 990, + "train_runtime": 6544.853, + "train_tokens_per_second": 857.737 + }, + { + "epoch": 1.8162519972608995, + "grad_norm": 1.9237911701202393, + "learning_rate": 1.6930092928663532e-05, + "loss": 0.5516, + "num_input_tokens_seen": 5643504, + "step": 995, + "train_runtime": 6578.4548, + "train_tokens_per_second": 857.877 + }, + { + "epoch": 1.8253823328007304, + "grad_norm": 2.859373092651367, + "learning_rate": 1.6704383646127973e-05, + "loss": 0.653, + "num_input_tokens_seen": 5671936, + "step": 1000, + "train_runtime": 6611.438, + "train_tokens_per_second": 857.897 + }, + { + "epoch": 1.8345126683405615, + "grad_norm": 1.613446593284607, + "learning_rate": 1.6479431687178584e-05, + "loss": 0.6456, + "num_input_tokens_seen": 5701200, + "step": 1005, + "train_runtime": 6646.1194, + "train_tokens_per_second": 857.824 + }, + { + "epoch": 1.8436430038803926, + "grad_norm": 2.326117753982544, + "learning_rate": 1.6255257588134426e-05, + "loss": 0.6778, + "num_input_tokens_seen": 5728032, + "step": 1010, + "train_runtime": 6678.532, + "train_tokens_per_second": 857.678 + }, + { + "epoch": 1.8527733394202237, + "grad_norm": 1.6666271686553955, + "learning_rate": 1.603188181430216e-05, + "loss": 0.6779, + "num_input_tokens_seen": 5756080, + "step": 1015, + "train_runtime": 6711.4743, + "train_tokens_per_second": 857.648 + }, + { + "epoch": 1.8619036749600548, + "grad_norm": 1.2438191175460815, + "learning_rate": 1.580932475810772e-05, + "loss": 0.5039, + "num_input_tokens_seen": 5785760, + "step": 1020, + "train_runtime": 6745.102, + "train_tokens_per_second": 857.772 + }, + { + "epoch": 1.8710340104998857, + "grad_norm": 1.6979848146438599, + "learning_rate": 1.5587606737234654e-05, + "loss": 0.6694, + "num_input_tokens_seen": 5813936, + "step": 1025, + "train_runtime": 6777.9312, + "train_tokens_per_second": 857.774 + }, + { + "epoch": 1.880164346039717, + "grad_norm": 1.7147233486175537, + "learning_rate": 1.5366747992769287e-05, + "loss": 0.5749, + "num_input_tokens_seen": 5844128, + "step": 1030, + "train_runtime": 6811.7365, + "train_tokens_per_second": 857.95 + }, + { + "epoch": 1.889294681579548, + "grad_norm": 1.3455411195755005, + "learning_rate": 1.5146768687352864e-05, + "loss": 0.5602, + "num_input_tokens_seen": 5872512, + "step": 1035, + "train_runtime": 6844.8473, + "train_tokens_per_second": 857.946 + }, + { + "epoch": 1.8984250171193793, + "grad_norm": 1.3454474210739136, + "learning_rate": 1.4927688903340836e-05, + "loss": 0.645, + "num_input_tokens_seen": 5898992, + "step": 1040, + "train_runtime": 6877.0142, + "train_tokens_per_second": 857.784 + }, + { + "epoch": 1.9075553526592102, + "grad_norm": 1.5111793279647827, + "learning_rate": 1.4709528640969552e-05, + "loss": 0.6209, + "num_input_tokens_seen": 5929632, + "step": 1045, + "train_runtime": 6910.9697, + "train_tokens_per_second": 858.003 + }, + { + "epoch": 1.9166856881990413, + "grad_norm": 1.53132164478302, + "learning_rate": 1.4492307816530375e-05, + "loss": 0.5908, + "num_input_tokens_seen": 5956832, + "step": 1050, + "train_runtime": 6943.4823, + "train_tokens_per_second": 857.903 + }, + { + "epoch": 1.9258160237388724, + "grad_norm": 1.7620954513549805, + "learning_rate": 1.4276046260551462e-05, + "loss": 0.5957, + "num_input_tokens_seen": 5985104, + "step": 1055, + "train_runtime": 6976.3497, + "train_tokens_per_second": 857.913 + }, + { + "epoch": 1.9349463592787035, + "grad_norm": 1.6221617460250854, + "learning_rate": 1.4060763715987418e-05, + "loss": 0.6543, + "num_input_tokens_seen": 6010992, + "step": 1060, + "train_runtime": 7008.2681, + "train_tokens_per_second": 857.7 + }, + { + "epoch": 1.9440766948185346, + "grad_norm": 1.9814153909683228, + "learning_rate": 1.3846479836416929e-05, + "loss": 0.5055, + "num_input_tokens_seen": 6041008, + "step": 1065, + "train_runtime": 7042.0949, + "train_tokens_per_second": 857.842 + }, + { + "epoch": 1.9532070303583655, + "grad_norm": 1.3477661609649658, + "learning_rate": 1.3633214184248521e-05, + "loss": 0.5246, + "num_input_tokens_seen": 6070832, + "step": 1070, + "train_runtime": 7075.8177, + "train_tokens_per_second": 857.969 + }, + { + "epoch": 1.9623373658981969, + "grad_norm": 2.347092390060425, + "learning_rate": 1.342098622893469e-05, + "loss": 0.5412, + "num_input_tokens_seen": 6100064, + "step": 1075, + "train_runtime": 7109.1762, + "train_tokens_per_second": 858.055 + }, + { + "epoch": 1.9714677014380277, + "grad_norm": 1.9612821340560913, + "learning_rate": 1.3209815345194496e-05, + "loss": 0.624, + "num_input_tokens_seen": 6127088, + "step": 1080, + "train_runtime": 7141.5945, + "train_tokens_per_second": 857.944 + }, + { + "epoch": 1.980598036977859, + "grad_norm": 1.7594658136367798, + "learning_rate": 1.2999720811244767e-05, + "loss": 0.5854, + "num_input_tokens_seen": 6154768, + "step": 1085, + "train_runtime": 7174.3094, + "train_tokens_per_second": 857.89 + }, + { + "epoch": 1.98972837251769, + "grad_norm": 1.341110110282898, + "learning_rate": 1.2790721807040216e-05, + "loss": 0.5972, + "num_input_tokens_seen": 6181824, + "step": 1090, + "train_runtime": 7206.6527, + "train_tokens_per_second": 857.794 + }, + { + "epoch": 1.998858708057521, + "grad_norm": 1.0875003337860107, + "learning_rate": 1.2582837412522418e-05, + "loss": 0.5627, + "num_input_tokens_seen": 6211904, + "step": 1095, + "train_runtime": 7240.3539, + "train_tokens_per_second": 857.956 + }, + { + "epoch": 2.0073042684318647, + "grad_norm": 1.4245753288269043, + "learning_rate": 1.2376086605877976e-05, + "loss": 0.544, + "num_input_tokens_seen": 6238272, + "step": 1100, + "train_runtime": 7270.9785, + "train_tokens_per_second": 857.969 + }, + { + "epoch": 2.016434603971696, + "grad_norm": 1.5748745203018188, + "learning_rate": 1.2170488261805978e-05, + "loss": 0.4701, + "num_input_tokens_seen": 6268288, + "step": 1105, + "train_runtime": 7305.8219, + "train_tokens_per_second": 857.985 + }, + { + "epoch": 2.025564939511527, + "grad_norm": 1.5691639184951782, + "learning_rate": 1.1966061149794846e-05, + "loss": 0.4359, + "num_input_tokens_seen": 6299168, + "step": 1110, + "train_runtime": 7339.8668, + "train_tokens_per_second": 858.213 + }, + { + "epoch": 2.0346952750513583, + "grad_norm": 1.7195948362350464, + "learning_rate": 1.176282393240888e-05, + "loss": 0.4436, + "num_input_tokens_seen": 6329296, + "step": 1115, + "train_runtime": 7373.7902, + "train_tokens_per_second": 858.35 + }, + { + "epoch": 2.043825610591189, + "grad_norm": 1.504329800605774, + "learning_rate": 1.1560795163584492e-05, + "loss": 0.5898, + "num_input_tokens_seen": 6356992, + "step": 1120, + "train_runtime": 7406.474, + "train_tokens_per_second": 858.302 + }, + { + "epoch": 2.0529559461310205, + "grad_norm": 1.5670088529586792, + "learning_rate": 1.1359993286936382e-05, + "loss": 0.5882, + "num_input_tokens_seen": 6382256, + "step": 1125, + "train_runtime": 7438.1266, + "train_tokens_per_second": 858.046 + }, + { + "epoch": 2.0620862816708514, + "grad_norm": 1.3568974733352661, + "learning_rate": 1.1160436634073786e-05, + "loss": 0.4388, + "num_input_tokens_seen": 6410016, + "step": 1130, + "train_runtime": 7470.9275, + "train_tokens_per_second": 857.995 + }, + { + "epoch": 2.0712166172106823, + "grad_norm": 1.301599144935608, + "learning_rate": 1.0962143422926929e-05, + "loss": 0.5827, + "num_input_tokens_seen": 6438768, + "step": 1135, + "train_runtime": 7504.1642, + "train_tokens_per_second": 858.026 + }, + { + "epoch": 2.0803469527505136, + "grad_norm": 1.7366254329681396, + "learning_rate": 1.0765131756083899e-05, + "loss": 0.5261, + "num_input_tokens_seen": 6466400, + "step": 1140, + "train_runtime": 7536.8587, + "train_tokens_per_second": 857.97 + }, + { + "epoch": 2.0894772882903445, + "grad_norm": 1.5877344608306885, + "learning_rate": 1.0569419619138012e-05, + "loss": 0.5661, + "num_input_tokens_seen": 6493488, + "step": 1145, + "train_runtime": 7569.2668, + "train_tokens_per_second": 857.875 + }, + { + "epoch": 2.098607623830176, + "grad_norm": 1.3803666830062866, + "learning_rate": 1.0375024879045889e-05, + "loss": 0.538, + "num_input_tokens_seen": 6521104, + "step": 1150, + "train_runtime": 7601.999, + "train_tokens_per_second": 857.814 + }, + { + "epoch": 2.1077379593700067, + "grad_norm": 1.4870142936706543, + "learning_rate": 1.0181965282496289e-05, + "loss": 0.7164, + "num_input_tokens_seen": 6548832, + "step": 1155, + "train_runtime": 7634.8619, + "train_tokens_per_second": 857.754 + }, + { + "epoch": 2.116868294909838, + "grad_norm": 2.605409860610962, + "learning_rate": 9.990258454290055e-06, + "loss": 0.5611, + "num_input_tokens_seen": 6577648, + "step": 1160, + "train_runtime": 7668.0751, + "train_tokens_per_second": 857.796 + }, + { + "epoch": 2.125998630449669, + "grad_norm": 1.7612236738204956, + "learning_rate": 9.799921895731062e-06, + "loss": 0.5341, + "num_input_tokens_seen": 6604720, + "step": 1165, + "train_runtime": 7700.4964, + "train_tokens_per_second": 857.701 + }, + { + "epoch": 2.1351289659895003, + "grad_norm": 1.2417925596237183, + "learning_rate": 9.610972983028493e-06, + "loss": 0.4899, + "num_input_tokens_seen": 6631696, + "step": 1170, + "train_runtime": 7732.822, + "train_tokens_per_second": 857.604 + }, + { + "epoch": 2.144259301529331, + "grad_norm": 1.9707194566726685, + "learning_rate": 9.423428965710554e-06, + "loss": 0.6115, + "num_input_tokens_seen": 6659728, + "step": 1175, + "train_runtime": 7765.6556, + "train_tokens_per_second": 857.587 + }, + { + "epoch": 2.153389637069162, + "grad_norm": 1.5473870038986206, + "learning_rate": 9.237306965049677e-06, + "loss": 0.5713, + "num_input_tokens_seen": 6688928, + "step": 1180, + "train_runtime": 7799.0145, + "train_tokens_per_second": 857.663 + }, + { + "epoch": 2.1625199726089934, + "grad_norm": 1.9179930686950684, + "learning_rate": 9.05262397249955e-06, + "loss": 0.5144, + "num_input_tokens_seen": 6717488, + "step": 1185, + "train_runtime": 7832.0227, + "train_tokens_per_second": 857.695 + }, + { + "epoch": 2.1716503081488243, + "grad_norm": 2.1739985942840576, + "learning_rate": 8.869396848143893e-06, + "loss": 0.5139, + "num_input_tokens_seen": 6746864, + "step": 1190, + "train_runtime": 7865.4644, + "train_tokens_per_second": 857.783 + }, + { + "epoch": 2.1807806436886557, + "grad_norm": 1.552583932876587, + "learning_rate": 8.687642319157279e-06, + "loss": 0.5763, + "num_input_tokens_seen": 6775216, + "step": 1195, + "train_runtime": 7898.5982, + "train_tokens_per_second": 857.774 + }, + { + "epoch": 2.1899109792284865, + "grad_norm": 1.612890362739563, + "learning_rate": 8.507376978278053e-06, + "loss": 0.5669, + "num_input_tokens_seen": 6806496, + "step": 1200, + "train_runtime": 7932.917, + "train_tokens_per_second": 858.007 + }, + { + "epoch": 2.199041314768318, + "grad_norm": 1.8803805112838745, + "learning_rate": 8.328617282293591e-06, + "loss": 0.5508, + "num_input_tokens_seen": 6835744, + "step": 1205, + "train_runtime": 7967.5177, + "train_tokens_per_second": 857.952 + }, + { + "epoch": 2.2081716503081488, + "grad_norm": 1.420291781425476, + "learning_rate": 8.151379550537894e-06, + "loss": 0.5538, + "num_input_tokens_seen": 6864560, + "step": 1210, + "train_runtime": 8000.595, + "train_tokens_per_second": 858.006 + }, + { + "epoch": 2.21730198584798, + "grad_norm": 1.4852449893951416, + "learning_rate": 7.975679963401772e-06, + "loss": 0.4806, + "num_input_tokens_seen": 6893360, + "step": 1215, + "train_runtime": 8033.8187, + "train_tokens_per_second": 858.043 + }, + { + "epoch": 2.226432321387811, + "grad_norm": 1.8254742622375488, + "learning_rate": 7.801534560855703e-06, + "loss": 0.4594, + "num_input_tokens_seen": 6922336, + "step": 1220, + "train_runtime": 8067.0217, + "train_tokens_per_second": 858.103 + }, + { + "epoch": 2.235562656927642, + "grad_norm": 1.6726877689361572, + "learning_rate": 7.628959240985514e-06, + "loss": 0.4625, + "num_input_tokens_seen": 6952464, + "step": 1225, + "train_runtime": 8100.7878, + "train_tokens_per_second": 858.245 + }, + { + "epoch": 2.2446929924674732, + "grad_norm": 1.6740381717681885, + "learning_rate": 7.457969758541009e-06, + "loss": 0.5248, + "num_input_tokens_seen": 6978480, + "step": 1230, + "train_runtime": 8132.8942, + "train_tokens_per_second": 858.056 + }, + { + "epoch": 2.253823328007304, + "grad_norm": 1.6061497926712036, + "learning_rate": 7.288581723497689e-06, + "loss": 0.5796, + "num_input_tokens_seen": 7006576, + "step": 1235, + "train_runtime": 8165.7446, + "train_tokens_per_second": 858.045 + }, + { + "epoch": 2.2629536635471355, + "grad_norm": 1.6302696466445923, + "learning_rate": 7.12081059963168e-06, + "loss": 0.4509, + "num_input_tokens_seen": 7034848, + "step": 1240, + "train_runtime": 8198.7143, + "train_tokens_per_second": 858.043 + }, + { + "epoch": 2.2720839990869663, + "grad_norm": 2.3190863132476807, + "learning_rate": 6.954671703108034e-06, + "loss": 0.4935, + "num_input_tokens_seen": 7064656, + "step": 1245, + "train_runtime": 8232.3363, + "train_tokens_per_second": 858.159 + }, + { + "epoch": 2.2812143346267977, + "grad_norm": 1.5536160469055176, + "learning_rate": 6.790180201082439e-06, + "loss": 0.5073, + "num_input_tokens_seen": 7093536, + "step": 1250, + "train_runtime": 8265.6241, + "train_tokens_per_second": 858.197 + }, + { + "epoch": 2.2903446701666286, + "grad_norm": 1.4936327934265137, + "learning_rate": 6.627351110316635e-06, + "loss": 0.4892, + "num_input_tokens_seen": 7122352, + "step": 1255, + "train_runtime": 8299.0146, + "train_tokens_per_second": 858.217 + }, + { + "epoch": 2.2994750057064595, + "grad_norm": 1.524456262588501, + "learning_rate": 6.466199295807471e-06, + "loss": 0.5268, + "num_input_tokens_seen": 7149840, + "step": 1260, + "train_runtime": 8331.6714, + "train_tokens_per_second": 858.152 + }, + { + "epoch": 2.308605341246291, + "grad_norm": 1.4873135089874268, + "learning_rate": 6.306739469429859e-06, + "loss": 0.5226, + "num_input_tokens_seen": 7175312, + "step": 1265, + "train_runtime": 8363.3798, + "train_tokens_per_second": 857.944 + }, + { + "epoch": 2.317735676786122, + "grad_norm": 1.4220759868621826, + "learning_rate": 6.1489861885936805e-06, + "loss": 0.4098, + "num_input_tokens_seen": 7205408, + "step": 1270, + "train_runtime": 8397.1884, + "train_tokens_per_second": 858.074 + }, + { + "epoch": 2.326866012325953, + "grad_norm": 1.7989997863769531, + "learning_rate": 5.992953854914838e-06, + "loss": 0.5064, + "num_input_tokens_seen": 7230896, + "step": 1275, + "train_runtime": 8428.9734, + "train_tokens_per_second": 857.862 + }, + { + "epoch": 2.335996347865784, + "grad_norm": 1.6997673511505127, + "learning_rate": 5.838656712900487e-06, + "loss": 0.486, + "num_input_tokens_seen": 7258640, + "step": 1280, + "train_runtime": 8461.701, + "train_tokens_per_second": 857.823 + }, + { + "epoch": 2.3451266834056153, + "grad_norm": 1.655226469039917, + "learning_rate": 5.686108848648624e-06, + "loss": 0.5659, + "num_input_tokens_seen": 7287552, + "step": 1285, + "train_runtime": 8494.9769, + "train_tokens_per_second": 857.866 + }, + { + "epoch": 2.354257018945446, + "grad_norm": 1.5733911991119385, + "learning_rate": 5.535324188562157e-06, + "loss": 0.5572, + "num_input_tokens_seen": 7315152, + "step": 1290, + "train_runtime": 8527.6021, + "train_tokens_per_second": 857.821 + }, + { + "epoch": 2.3633873544852775, + "grad_norm": 1.6711825132369995, + "learning_rate": 5.386316498077492e-06, + "loss": 0.5891, + "num_input_tokens_seen": 7341792, + "step": 1295, + "train_runtime": 8559.7095, + "train_tokens_per_second": 857.715 + }, + { + "epoch": 2.3725176900251084, + "grad_norm": 1.575325846672058, + "learning_rate": 5.239099380407916e-06, + "loss": 0.5121, + "num_input_tokens_seen": 7369360, + "step": 1300, + "train_runtime": 8592.4006, + "train_tokens_per_second": 857.66 + }, + { + "epoch": 2.3816480255649397, + "grad_norm": 1.923042893409729, + "learning_rate": 5.09368627530169e-06, + "loss": 0.4585, + "num_input_tokens_seen": 7399936, + "step": 1305, + "train_runtime": 8627.583, + "train_tokens_per_second": 857.707 + }, + { + "epoch": 2.3907783611047706, + "grad_norm": 1.294421911239624, + "learning_rate": 4.950090457815129e-06, + "loss": 0.5115, + "num_input_tokens_seen": 7426080, + "step": 1310, + "train_runtime": 8659.572, + "train_tokens_per_second": 857.557 + }, + { + "epoch": 2.3999086966446015, + "grad_norm": 1.5188215970993042, + "learning_rate": 4.808325037100691e-06, + "loss": 0.3663, + "num_input_tokens_seen": 7454432, + "step": 1315, + "train_runtime": 8701.6759, + "train_tokens_per_second": 856.666 + }, + { + "epoch": 2.409039032184433, + "grad_norm": 1.4130005836486816, + "learning_rate": 4.6684029552101886e-06, + "loss": 0.4918, + "num_input_tokens_seen": 7484848, + "step": 1320, + "train_runtime": 8735.6362, + "train_tokens_per_second": 856.818 + }, + { + "epoch": 2.4181693677242637, + "grad_norm": 1.4493566751480103, + "learning_rate": 4.530336985913333e-06, + "loss": 0.4168, + "num_input_tokens_seen": 7514592, + "step": 1325, + "train_runtime": 8769.282, + "train_tokens_per_second": 856.922 + }, + { + "epoch": 2.427299703264095, + "grad_norm": 1.8940752744674683, + "learning_rate": 4.394139733531555e-06, + "loss": 0.4658, + "num_input_tokens_seen": 7545680, + "step": 1330, + "train_runtime": 8803.6245, + "train_tokens_per_second": 857.111 + }, + { + "epoch": 2.436430038803926, + "grad_norm": 1.8865268230438232, + "learning_rate": 4.259823631787346e-06, + "loss": 0.4081, + "num_input_tokens_seen": 7575472, + "step": 1335, + "train_runtime": 8837.4345, + "train_tokens_per_second": 857.203 + }, + { + "epoch": 2.4455603743437573, + "grad_norm": 1.537660002708435, + "learning_rate": 4.127400942669141e-06, + "loss": 0.4739, + "num_input_tokens_seen": 7604016, + "step": 1340, + "train_runtime": 8870.4991, + "train_tokens_per_second": 857.225 + }, + { + "epoch": 2.454690709883588, + "grad_norm": 1.0611555576324463, + "learning_rate": 3.996883755311917e-06, + "loss": 0.3149, + "num_input_tokens_seen": 7636112, + "step": 1345, + "train_runtime": 8905.1047, + "train_tokens_per_second": 857.498 + }, + { + "epoch": 2.463821045423419, + "grad_norm": 2.0281214714050293, + "learning_rate": 3.868283984893542e-06, + "loss": 0.565, + "num_input_tokens_seen": 7665152, + "step": 1350, + "train_runtime": 8938.4023, + "train_tokens_per_second": 857.553 + }, + { + "epoch": 2.4729513809632504, + "grad_norm": 1.5192010402679443, + "learning_rate": 3.741613371547023e-06, + "loss": 0.4656, + "num_input_tokens_seen": 7692112, + "step": 1355, + "train_runtime": 8970.7428, + "train_tokens_per_second": 857.467 + }, + { + "epoch": 2.4820817165030817, + "grad_norm": 1.6683508157730103, + "learning_rate": 3.6168834792887103e-06, + "loss": 0.4552, + "num_input_tokens_seen": 7720064, + "step": 1360, + "train_runtime": 9003.5935, + "train_tokens_per_second": 857.443 + }, + { + "epoch": 2.4912120520429126, + "grad_norm": 1.5640547275543213, + "learning_rate": 3.494105694962596e-06, + "loss": 0.4571, + "num_input_tokens_seen": 7751040, + "step": 1365, + "train_runtime": 9037.7684, + "train_tokens_per_second": 857.628 + }, + { + "epoch": 2.5003423875827435, + "grad_norm": 2.0412251949310303, + "learning_rate": 3.373291227200806e-06, + "loss": 0.5344, + "num_input_tokens_seen": 7776944, + "step": 1370, + "train_runtime": 9069.7333, + "train_tokens_per_second": 857.461 + }, + { + "epoch": 2.509472723122575, + "grad_norm": 1.6897809505462646, + "learning_rate": 3.2544511054003246e-06, + "loss": 0.501, + "num_input_tokens_seen": 7804880, + "step": 1375, + "train_runtime": 9102.5099, + "train_tokens_per_second": 857.443 + }, + { + "epoch": 2.5186030586624057, + "grad_norm": 1.7537122964859009, + "learning_rate": 3.1375961787160983e-06, + "loss": 0.5723, + "num_input_tokens_seen": 7834144, + "step": 1380, + "train_runtime": 9135.9522, + "train_tokens_per_second": 857.507 + }, + { + "epoch": 2.527733394202237, + "grad_norm": 1.6396698951721191, + "learning_rate": 3.0227371150706035e-06, + "loss": 0.5347, + "num_input_tokens_seen": 7862112, + "step": 1385, + "train_runtime": 9168.7182, + "train_tokens_per_second": 857.493 + }, + { + "epoch": 2.536863729742068, + "grad_norm": 1.4223724603652954, + "learning_rate": 2.9098844001799407e-06, + "loss": 0.4727, + "num_input_tokens_seen": 7889648, + "step": 1390, + "train_runtime": 9201.3802, + "train_tokens_per_second": 857.442 + }, + { + "epoch": 2.5459940652818993, + "grad_norm": 2.2084455490112305, + "learning_rate": 2.7990483365965825e-06, + "loss": 0.6187, + "num_input_tokens_seen": 7917840, + "step": 1395, + "train_runtime": 9234.3184, + "train_tokens_per_second": 857.436 + }, + { + "epoch": 2.55512440082173, + "grad_norm": 1.9658094644546509, + "learning_rate": 2.6902390427688273e-06, + "loss": 0.5945, + "num_input_tokens_seen": 7945968, + "step": 1400, + "train_runtime": 9267.0379, + "train_tokens_per_second": 857.444 + }, + { + "epoch": 2.564254736361561, + "grad_norm": 1.4048709869384766, + "learning_rate": 2.5834664521170504e-06, + "loss": 0.5123, + "num_input_tokens_seen": 7976608, + "step": 1405, + "train_runtime": 9302.2298, + "train_tokens_per_second": 857.494 + }, + { + "epoch": 2.5733850719013924, + "grad_norm": 1.8931680917739868, + "learning_rate": 2.4787403121268955e-06, + "loss": 0.4564, + "num_input_tokens_seen": 8005312, + "step": 1410, + "train_runtime": 9335.3807, + "train_tokens_per_second": 857.524 + }, + { + "epoch": 2.5825154074412233, + "grad_norm": 1.8574892282485962, + "learning_rate": 2.3760701834593806e-06, + "loss": 0.5329, + "num_input_tokens_seen": 8032320, + "step": 1415, + "train_runtime": 9367.8306, + "train_tokens_per_second": 857.437 + }, + { + "epoch": 2.5916457429810547, + "grad_norm": 1.5250113010406494, + "learning_rate": 2.2754654390780924e-06, + "loss": 0.5803, + "num_input_tokens_seen": 8059600, + "step": 1420, + "train_runtime": 9400.4807, + "train_tokens_per_second": 857.36 + }, + { + "epoch": 2.6007760785208855, + "grad_norm": 1.251405954360962, + "learning_rate": 2.1769352633935175e-06, + "loss": 0.4759, + "num_input_tokens_seen": 8090544, + "step": 1425, + "train_runtime": 9434.7027, + "train_tokens_per_second": 857.53 + }, + { + "epoch": 2.609906414060717, + "grad_norm": 2.3054699897766113, + "learning_rate": 2.0804886514245726e-06, + "loss": 0.4964, + "num_input_tokens_seen": 8117472, + "step": 1430, + "train_runtime": 9467.0753, + "train_tokens_per_second": 857.442 + }, + { + "epoch": 2.6190367496005478, + "grad_norm": 1.6009160280227661, + "learning_rate": 1.986134407977416e-06, + "loss": 0.4652, + "num_input_tokens_seen": 8145360, + "step": 1435, + "train_runtime": 9499.7537, + "train_tokens_per_second": 857.429 + }, + { + "epoch": 2.6281670851403787, + "grad_norm": 1.5399287939071655, + "learning_rate": 1.8938811468416695e-06, + "loss": 0.5859, + "num_input_tokens_seen": 8171552, + "step": 1440, + "train_runtime": 9531.6877, + "train_tokens_per_second": 857.304 + }, + { + "epoch": 2.63729742068021, + "grad_norm": 1.5960819721221924, + "learning_rate": 1.8037372900040289e-06, + "loss": 0.6222, + "num_input_tokens_seen": 8199280, + "step": 1445, + "train_runtime": 9564.4618, + "train_tokens_per_second": 857.265 + }, + { + "epoch": 2.6464277562200413, + "grad_norm": 1.9178729057312012, + "learning_rate": 1.7157110668794108e-06, + "loss": 0.3722, + "num_input_tokens_seen": 8226656, + "step": 1450, + "train_runtime": 9596.9118, + "train_tokens_per_second": 857.219 + }, + { + "epoch": 2.6555580917598722, + "grad_norm": 1.9778716564178467, + "learning_rate": 1.6298105135596569e-06, + "loss": 0.5299, + "num_input_tokens_seen": 8255232, + "step": 1455, + "train_runtime": 9630.1532, + "train_tokens_per_second": 857.227 + }, + { + "epoch": 2.664688427299703, + "grad_norm": 1.8453866243362427, + "learning_rate": 1.5460434720799278e-06, + "loss": 0.447, + "num_input_tokens_seen": 8281744, + "step": 1460, + "train_runtime": 9662.2517, + "train_tokens_per_second": 857.124 + }, + { + "epoch": 2.6738187628395345, + "grad_norm": 1.5484800338745117, + "learning_rate": 1.464417589702774e-06, + "loss": 0.3965, + "num_input_tokens_seen": 8310384, + "step": 1465, + "train_runtime": 9695.4301, + "train_tokens_per_second": 857.144 + }, + { + "epoch": 2.6829490983793653, + "grad_norm": 1.297414779663086, + "learning_rate": 1.3849403182199988e-06, + "loss": 0.4579, + "num_input_tokens_seen": 8340384, + "step": 1470, + "train_runtime": 9729.2243, + "train_tokens_per_second": 857.251 + }, + { + "epoch": 2.6920794339191967, + "grad_norm": 1.7842596769332886, + "learning_rate": 1.3076189132723764e-06, + "loss": 0.5361, + "num_input_tokens_seen": 8368224, + "step": 1475, + "train_runtime": 9761.9824, + "train_tokens_per_second": 857.226 + }, + { + "epoch": 2.7012097694590276, + "grad_norm": 1.3124113082885742, + "learning_rate": 1.2324604336872658e-06, + "loss": 0.4439, + "num_input_tokens_seen": 8398976, + "step": 1480, + "train_runtime": 9796.1279, + "train_tokens_per_second": 857.377 + }, + { + "epoch": 2.710340104998859, + "grad_norm": 1.8986421823501587, + "learning_rate": 1.159471740834195e-06, + "loss": 0.3843, + "num_input_tokens_seen": 8426000, + "step": 1485, + "train_runtime": 9828.5258, + "train_tokens_per_second": 857.3 + }, + { + "epoch": 2.71947044053869, + "grad_norm": 1.2986937761306763, + "learning_rate": 1.0886594979984816e-06, + "loss": 0.4191, + "num_input_tokens_seen": 8452800, + "step": 1490, + "train_runtime": 9860.8783, + "train_tokens_per_second": 857.206 + }, + { + "epoch": 2.7286007760785207, + "grad_norm": 1.4023627042770386, + "learning_rate": 1.0200301697729204e-06, + "loss": 0.4898, + "num_input_tokens_seen": 8478592, + "step": 1495, + "train_runtime": 9892.7604, + "train_tokens_per_second": 857.05 + }, + { + "epoch": 2.737731111618352, + "grad_norm": 1.7444908618927002, + "learning_rate": 9.535900214676097e-07, + "loss": 0.4288, + "num_input_tokens_seen": 8506240, + "step": 1500, + "train_runtime": 9925.5818, + "train_tokens_per_second": 857.002 + }, + { + "epoch": 2.746861447158183, + "grad_norm": 1.5377986431121826, + "learning_rate": 8.893451185379958e-07, + "loss": 0.4114, + "num_input_tokens_seen": 8533840, + "step": 1505, + "train_runtime": 9959.5353, + "train_tokens_per_second": 856.851 + }, + { + "epoch": 2.7559917826980143, + "grad_norm": 1.6170401573181152, + "learning_rate": 8.273013260311379e-07, + "loss": 0.4987, + "num_input_tokens_seen": 8559296, + "step": 1510, + "train_runtime": 9991.2783, + "train_tokens_per_second": 856.677 + }, + { + "epoch": 2.765122118237845, + "grad_norm": 2.0063154697418213, + "learning_rate": 7.674643080502724e-07, + "loss": 0.4648, + "num_input_tokens_seen": 8587664, + "step": 1515, + "train_runtime": 10761.2574, + "train_tokens_per_second": 798.017 + }, + { + "epoch": 2.7742524537776765, + "grad_norm": 1.877916693687439, + "learning_rate": 7.098395272377295e-07, + "loss": 0.5213, + "num_input_tokens_seen": 8614480, + "step": 1520, + "train_runtime": 10793.6481, + "train_tokens_per_second": 798.106 + }, + { + "epoch": 2.7833827893175074, + "grad_norm": 1.7010425329208374, + "learning_rate": 6.544322442762318e-07, + "loss": 0.499, + "num_input_tokens_seen": 8642960, + "step": 1525, + "train_runtime": 10826.7994, + "train_tokens_per_second": 798.293 + }, + { + "epoch": 2.7925131248573383, + "grad_norm": 1.5449343919754028, + "learning_rate": 6.012475174086485e-07, + "loss": 0.4285, + "num_input_tokens_seen": 8671248, + "step": 1530, + "train_runtime": 10859.8866, + "train_tokens_per_second": 798.466 + }, + { + "epoch": 2.8016434603971696, + "grad_norm": 1.7787251472473145, + "learning_rate": 5.502902019762002e-07, + "loss": 0.4615, + "num_input_tokens_seen": 8698912, + "step": 1535, + "train_runtime": 10892.5607, + "train_tokens_per_second": 798.61 + }, + { + "epoch": 2.810773795937001, + "grad_norm": 1.502289891242981, + "learning_rate": 5.015649499752279e-07, + "loss": 0.4648, + "num_input_tokens_seen": 8726896, + "step": 1540, + "train_runtime": 10925.4558, + "train_tokens_per_second": 798.767 + }, + { + "epoch": 2.819904131476832, + "grad_norm": 1.522641658782959, + "learning_rate": 4.5507620963247954e-07, + "loss": 0.4858, + "num_input_tokens_seen": 8751920, + "step": 1545, + "train_runtime": 10956.9252, + "train_tokens_per_second": 798.757 + }, + { + "epoch": 2.8290344670166627, + "grad_norm": 2.1871094703674316, + "learning_rate": 4.1082822499903253e-07, + "loss": 0.4944, + "num_input_tokens_seen": 8780080, + "step": 1550, + "train_runtime": 10989.8787, + "train_tokens_per_second": 798.924 + }, + { + "epoch": 2.838164802556494, + "grad_norm": 1.5429576635360718, + "learning_rate": 3.6882503556285307e-07, + "loss": 0.4598, + "num_input_tokens_seen": 8804880, + "step": 1555, + "train_runtime": 11021.2763, + "train_tokens_per_second": 798.898 + }, + { + "epoch": 2.847295138096325, + "grad_norm": 1.883806586265564, + "learning_rate": 3.290704758800139e-07, + "loss": 0.4981, + "num_input_tokens_seen": 8834736, + "step": 1560, + "train_runtime": 11055.0559, + "train_tokens_per_second": 799.158 + }, + { + "epoch": 2.8564254736361563, + "grad_norm": 1.7535673379898071, + "learning_rate": 2.915681752246241e-07, + "loss": 0.5183, + "num_input_tokens_seen": 8862544, + "step": 1565, + "train_runtime": 11087.6895, + "train_tokens_per_second": 799.314 + }, + { + "epoch": 2.865555809175987, + "grad_norm": 2.0906741619110107, + "learning_rate": 2.563215572575273e-07, + "loss": 0.4789, + "num_input_tokens_seen": 8892720, + "step": 1570, + "train_runtime": 11121.4717, + "train_tokens_per_second": 799.599 + }, + { + "epoch": 2.8746861447158185, + "grad_norm": 1.9282186031341553, + "learning_rate": 2.2333383971372413e-07, + "loss": 0.4666, + "num_input_tokens_seen": 8918880, + "step": 1575, + "train_runtime": 11153.5256, + "train_tokens_per_second": 799.647 + }, + { + "epoch": 2.8838164802556494, + "grad_norm": 1.4631140232086182, + "learning_rate": 1.9260803410863226e-07, + "loss": 0.4199, + "num_input_tokens_seen": 8952352, + "step": 1580, + "train_runtime": 11188.7542, + "train_tokens_per_second": 800.121 + }, + { + "epoch": 2.8929468157954803, + "grad_norm": 1.2672832012176514, + "learning_rate": 1.641469454631561e-07, + "loss": 0.4318, + "num_input_tokens_seen": 8981984, + "step": 1585, + "train_runtime": 11222.3784, + "train_tokens_per_second": 800.364 + }, + { + "epoch": 2.9020771513353116, + "grad_norm": 1.3364146947860718, + "learning_rate": 1.3795317204761128e-07, + "loss": 0.36, + "num_input_tokens_seen": 9012864, + "step": 1590, + "train_runtime": 11256.7019, + "train_tokens_per_second": 800.666 + }, + { + "epoch": 2.9112074868751425, + "grad_norm": 1.5411438941955566, + "learning_rate": 1.140291051445197e-07, + "loss": 0.4392, + "num_input_tokens_seen": 9040848, + "step": 1595, + "train_runtime": 11289.6253, + "train_tokens_per_second": 800.81 + }, + { + "epoch": 2.920337822414974, + "grad_norm": 1.6634502410888672, + "learning_rate": 9.237692883031502e-08, + "loss": 0.4489, + "num_input_tokens_seen": 9071104, + "step": 1600, + "train_runtime": 11323.3685, + "train_tokens_per_second": 801.096 + }, + { + "epoch": 2.9294681579548048, + "grad_norm": 1.9743751287460327, + "learning_rate": 7.29986197759408e-08, + "loss": 0.5492, + "num_input_tokens_seen": 9101904, + "step": 1605, + "train_runtime": 11358.5692, + "train_tokens_per_second": 801.325 + }, + { + "epoch": 2.938598493494636, + "grad_norm": 1.0921943187713623, + "learning_rate": 5.589594706640055e-08, + "loss": 0.503, + "num_input_tokens_seen": 9131728, + "step": 1610, + "train_runtime": 11392.3267, + "train_tokens_per_second": 801.568 + }, + { + "epoch": 2.947728829034467, + "grad_norm": 1.501896858215332, + "learning_rate": 4.1070472039259065e-08, + "loss": 0.4689, + "num_input_tokens_seen": 9162144, + "step": 1615, + "train_runtime": 11426.2624, + "train_tokens_per_second": 801.85 + }, + { + "epoch": 2.956859164574298, + "grad_norm": 1.5929884910583496, + "learning_rate": 2.8523548142103673e-08, + "loss": 0.542, + "num_input_tokens_seen": 9189808, + "step": 1620, + "train_runtime": 11458.9394, + "train_tokens_per_second": 801.977 + }, + { + "epoch": 2.965989500114129, + "grad_norm": 1.3482941389083862, + "learning_rate": 1.825632080897366e-08, + "loss": 0.3969, + "num_input_tokens_seen": 9220032, + "step": 1625, + "train_runtime": 11492.8101, + "train_tokens_per_second": 802.243 + }, + { + "epoch": 2.9751198356539605, + "grad_norm": 1.901435136795044, + "learning_rate": 1.026972735581333e-08, + "loss": 0.496, + "num_input_tokens_seen": 9248592, + "step": 1630, + "train_runtime": 11525.8653, + "train_tokens_per_second": 802.421 + }, + { + "epoch": 2.9842501711937914, + "grad_norm": 1.747241735458374, + "learning_rate": 4.564496894882142e-09, + "loss": 0.5585, + "num_input_tokens_seen": 9276416, + "step": 1635, + "train_runtime": 11558.7218, + "train_tokens_per_second": 802.547 + }, + { + "epoch": 2.9933805067336223, + "grad_norm": 1.4872362613677979, + "learning_rate": 1.1411502681996088e-09, + "loss": 0.4553, + "num_input_tokens_seen": 9306352, + "step": 1640, + "train_runtime": 11592.3707, + "train_tokens_per_second": 802.8 + } + ], + "logging_steps": 5, + "max_steps": 1644, + "num_input_tokens_seen": 9328224, + "num_train_epochs": 3, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 8.278651518536909e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/train_2026-01-03/checkpoint-1644/training_args.bin b/train_2026-01-03/checkpoint-1644/training_args.bin new file mode 100644 index 0000000..f255cae --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c49abbca48ff5cef0283d6103fb9370193dff725b5232b4da7a83cdcabbca6 +size 5752 diff --git a/train_2026-01-03/checkpoint-1644/vocab.json b/train_2026-01-03/checkpoint-1644/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/train_2026-01-03/checkpoint-1644/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833 diff --git a/train_2026-01-03/llamaboard_config.yaml b/train_2026-01-03/llamaboard_config.yaml new file mode 100644 index 0000000..939bce8 --- /dev/null +++ b/train_2026-01-03/llamaboard_config.yaml @@ -0,0 +1,86 @@ +top.booster: auto +top.checkpoint_path: [] +top.finetuning_type: lora +top.model_name: Qwen3-1.7B-Base +top.quantization_bit: none +top.quantization_method: bnb +top.rope_scaling: none +top.template: default +train.additional_target: '' +train.apollo_rank: 16 +train.apollo_scale: 32 +train.apollo_target: all +train.apollo_update_interval: 200 +train.badam_mode: layer +train.badam_switch_interval: 50 +train.badam_switch_mode: ascending +train.badam_update_ratio: 0.05 +train.batch_size: 2 +train.compute_type: bf16 +train.create_new_adapter: false +train.cutoff_len: 2048 +train.dataset: +- gpu_aiAgent_zh +- gpu_aiAgent_others +train.dataset_dir: data +train.ds_offload: false +train.ds_stage: none +train.enable_thinking: true +train.extra_args: '{"optim": "adamw_torch"}' +train.freeze_extra_modules: '' +train.freeze_language_model: false +train.freeze_multi_modal_projector: true +train.freeze_trainable_layers: 2 +train.freeze_trainable_modules: all +train.freeze_vision_tower: true +train.galore_rank: 16 +train.galore_scale: 2 +train.galore_target: all +train.galore_update_interval: 200 +train.gradient_accumulation_steps: 8 +train.image_max_pixels: 768*768 +train.image_min_pixels: 32*32 +train.learning_rate: 5e-5 +train.logging_steps: 5 +train.lora_alpha: 128 +train.lora_dropout: 0 +train.lora_rank: 64 +train.lora_target: '' +train.loraplus_lr_ratio: 0 +train.lr_scheduler_type: cosine +train.mask_history: false +train.max_grad_norm: '1.0' +train.max_samples: '100000' +train.neat_packing: false +train.neftune_alpha: 0 +train.num_train_epochs: '3.0' +train.packing: false +train.ppo_score_norm: false +train.ppo_whiten_rewards: false +train.pref_beta: 0.1 +train.pref_ftx: 0 +train.pref_loss: sigmoid +train.report_to: none +train.resize_vocab: false +train.reward_model: [] +train.save_steps: 100 +train.swanlab_api_key: '' +train.swanlab_link: '' +train.swanlab_mode: cloud +train.swanlab_project: llamafactory +train.swanlab_run_name: '' +train.swanlab_workspace: '' +train.train_on_prompt: false +train.training_stage: Supervised Fine-Tuning +train.use_apollo: false +train.use_badam: false +train.use_dora: false +train.use_galore: false +train.use_llama_pro: false +train.use_pissa: false +train.use_rslora: false +train.use_swanlab: false +train.val_size: 0 +train.video_max_pixels: 256*256 +train.video_min_pixels: 16*16 +train.warmup_steps: 0 diff --git a/train_2026-01-03/merges.txt b/train_2026-01-03/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/train_2026-01-03/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/train_2026-01-03/running_log.txt b/train_2026-01-03/running_log.txt new file mode 100644 index 0000000..2e6c6cf --- /dev/null +++ b/train_2026-01-03/running_log.txt @@ -0,0 +1,1702 @@ +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file vocab.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file merges.txt +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file tokenizer.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file added_tokens.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file special_tokens_map.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file tokenizer_config.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file chat_template.jinja +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2336 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. +[INFO|2026-01-03 17:49:53] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 17:49:53] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file vocab.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file merges.txt +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file tokenizer.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file added_tokens.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file special_tokens_map.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file tokenizer_config.json +[INFO|2026-01-03 17:49:53] tokenization_utils_base.py:2065 >> loading file chat_template.jinja +[INFO|2026-01-03 17:49:54] tokenization_utils_base.py:2336 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. +[INFO|2026-01-03 17:49:54] logging.py:143 >> Loading dataset gpu_aiAgent_zh.jsonl... +[INFO|2026-01-03 17:49:55] logging.py:143 >> Loading dataset processed_dataset1.jsonl... +[INFO|2026-01-03 17:49:59] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 17:49:59] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 17:49:59] logging.py:143 >> KV cache is disabled during training. +[INFO|2026-01-03 17:49:59] modeling_utils.py:1305 >> loading weights file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/model.safetensors +[INFO|2026-01-03 17:49:59] modeling_utils.py:2411 >> Instantiating Qwen3ForCausalLM model under default dtype torch.bfloat16. +[INFO|2026-01-03 17:49:59] configuration_utils.py:1098 >> Generate config GenerationConfig { + "bos_token_id": 151643, + "eos_token_id": 151643, + "use_cache": false +} + +[INFO|2026-01-03 17:50:00] modeling_utils.py:5606 >> All model checkpoint weights were used when initializing Qwen3ForCausalLM. + +[INFO|2026-01-03 17:50:00] modeling_utils.py:5614 >> All the weights of Qwen3ForCausalLM were initialized from the model checkpoint at /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base. +If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen3ForCausalLM for predictions without further training. +[INFO|2026-01-03 17:50:00] configuration_utils.py:1051 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/generation_config.json +[INFO|2026-01-03 17:50:00] configuration_utils.py:1098 >> Generate config GenerationConfig { + "bos_token_id": 151643, + "eos_token_id": 151643, + "max_new_tokens": 2048 +} + +[INFO|2026-01-03 17:50:00] logging.py:143 >> Gradient checkpointing enabled. +[INFO|2026-01-03 17:50:00] logging.py:143 >> Using torch SDPA for faster training and inference. +[INFO|2026-01-03 17:50:00] logging.py:143 >> Upcasting trainable params to float32. +[INFO|2026-01-03 17:50:00] logging.py:143 >> Fine-tuning method: LoRA +[INFO|2026-01-03 17:50:00] logging.py:143 >> Found linear modules: k_proj,q_proj,v_proj,down_proj,o_proj,up_proj,gate_proj +[INFO|2026-01-03 17:50:03] logging.py:143 >> trainable params: 69,730,304 || all params: 1,790,305,280 || trainable%: 3.8949 +[INFO|2026-01-03 17:50:03] trainer.py:757 >> Using auto half precision backend +[INFO|2026-01-03 17:50:04] trainer.py:2433 >> ***** Running training ***** +[INFO|2026-01-03 17:50:04] trainer.py:2434 >> Num examples = 8,762 +[INFO|2026-01-03 17:50:04] trainer.py:2435 >> Num Epochs = 3 +[INFO|2026-01-03 17:50:04] trainer.py:2436 >> Instantaneous batch size per device = 2 +[INFO|2026-01-03 17:50:04] trainer.py:2439 >> Total train batch size (w. parallel, distributed & accumulation) = 16 +[INFO|2026-01-03 17:50:04] trainer.py:2440 >> Gradient Accumulation steps = 8 +[INFO|2026-01-03 17:50:04] trainer.py:2441 >> Total optimization steps = 1,644 +[INFO|2026-01-03 17:50:04] trainer.py:2442 >> Number of trainable parameters = 69,730,304 +[INFO|2026-01-03 17:50:41] logging.py:143 >> {'loss': 1.4690, 'learning_rate': 4.9999e-05, 'epoch': 0.01, 'throughput': 834.18} +[INFO|2026-01-03 17:51:14] logging.py:143 >> {'loss': 1.5127, 'learning_rate': 4.9996e-05, 'epoch': 0.02, 'throughput': 839.03} +[INFO|2026-01-03 17:51:47] logging.py:143 >> {'loss': 1.4400, 'learning_rate': 4.9991e-05, 'epoch': 0.03, 'throughput': 844.64} +[INFO|2026-01-03 17:52:20] logging.py:143 >> {'loss': 1.4987, 'learning_rate': 4.9984e-05, 'epoch': 0.04, 'throughput': 842.78} +[INFO|2026-01-03 17:52:53] logging.py:143 >> {'loss': 1.4058, 'learning_rate': 4.9974e-05, 'epoch': 0.05, 'throughput': 847.67} +[INFO|2026-01-03 17:53:26] logging.py:143 >> {'loss': 1.4049, 'learning_rate': 4.9962e-05, 'epoch': 0.05, 'throughput': 850.44} +[INFO|2026-01-03 17:53:59] logging.py:143 >> {'loss': 1.4239, 'learning_rate': 4.9947e-05, 'epoch': 0.06, 'throughput': 850.70} +[INFO|2026-01-03 17:54:32] logging.py:143 >> {'loss': 1.3890, 'learning_rate': 4.9931e-05, 'epoch': 0.07, 'throughput': 849.34} +[INFO|2026-01-03 17:55:05] logging.py:143 >> {'loss': 1.3187, 'learning_rate': 4.9912e-05, 'epoch': 0.08, 'throughput': 851.42} +[INFO|2026-01-03 17:55:39] logging.py:143 >> {'loss': 1.3100, 'learning_rate': 4.9890e-05, 'epoch': 0.09, 'throughput': 856.96} +[INFO|2026-01-03 17:56:11] logging.py:143 >> {'loss': 1.3295, 'learning_rate': 4.9867e-05, 'epoch': 0.10, 'throughput': 856.18} +[INFO|2026-01-03 17:56:44] logging.py:143 >> {'loss': 1.2718, 'learning_rate': 4.9841e-05, 'epoch': 0.11, 'throughput': 856.16} +[INFO|2026-01-03 17:57:17] logging.py:143 >> {'loss': 1.2547, 'learning_rate': 4.9813e-05, 'epoch': 0.12, 'throughput': 854.86} +[INFO|2026-01-03 17:57:50] logging.py:143 >> {'loss': 1.3020, 'learning_rate': 4.9783e-05, 'epoch': 0.13, 'throughput': 856.68} +[INFO|2026-01-03 17:58:24] logging.py:143 >> {'loss': 1.2328, 'learning_rate': 4.9750e-05, 'epoch': 0.14, 'throughput': 860.35} +[INFO|2026-01-03 17:58:58] logging.py:143 >> {'loss': 1.2960, 'learning_rate': 4.9716e-05, 'epoch': 0.15, 'throughput': 861.72} +[INFO|2026-01-03 17:59:31] logging.py:143 >> {'loss': 1.3248, 'learning_rate': 4.9679e-05, 'epoch': 0.16, 'throughput': 861.08} +[INFO|2026-01-03 18:00:04] logging.py:143 >> {'loss': 1.2070, 'learning_rate': 4.9639e-05, 'epoch': 0.16, 'throughput': 861.29} +[INFO|2026-01-03 18:00:38] logging.py:143 >> {'loss': 1.2342, 'learning_rate': 4.9598e-05, 'epoch': 0.17, 'throughput': 863.20} +[INFO|2026-01-03 18:01:11] logging.py:143 >> {'loss': 1.1931, 'learning_rate': 4.9554e-05, 'epoch': 0.18, 'throughput': 864.21} +[INFO|2026-01-03 18:01:11] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-100 +[INFO|2026-01-03 18:01:11] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 18:01:11] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 18:01:12] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-100/chat_template.jinja +[INFO|2026-01-03 18:01:12] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-100/tokenizer_config.json +[INFO|2026-01-03 18:01:12] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-100/special_tokens_map.json +[INFO|2026-01-03 18:01:46] logging.py:143 >> {'loss': 1.2122, 'learning_rate': 4.9508e-05, 'epoch': 0.19, 'throughput': 863.90} +[INFO|2026-01-03 18:02:19] logging.py:143 >> {'loss': 1.2973, 'learning_rate': 4.9460e-05, 'epoch': 0.20, 'throughput': 862.94} +[INFO|2026-01-03 18:02:51] logging.py:143 >> {'loss': 1.2483, 'learning_rate': 4.9409e-05, 'epoch': 0.21, 'throughput': 860.58} +[INFO|2026-01-03 18:03:24] logging.py:143 >> {'loss': 1.1153, 'learning_rate': 4.9356e-05, 'epoch': 0.22, 'throughput': 859.99} +[INFO|2026-01-03 18:03:57] logging.py:143 >> {'loss': 1.2269, 'learning_rate': 4.9301e-05, 'epoch': 0.23, 'throughput': 860.43} +[INFO|2026-01-03 18:04:30] logging.py:143 >> {'loss': 1.1324, 'learning_rate': 4.9244e-05, 'epoch': 0.24, 'throughput': 860.09} +[INFO|2026-01-03 18:05:02] logging.py:143 >> {'loss': 1.1818, 'learning_rate': 4.9185e-05, 'epoch': 0.25, 'throughput': 859.22} +[INFO|2026-01-03 18:05:37] logging.py:143 >> {'loss': 1.1243, 'learning_rate': 4.9123e-05, 'epoch': 0.26, 'throughput': 861.88} +[INFO|2026-01-03 18:06:09] logging.py:143 >> {'loss': 1.2134, 'learning_rate': 4.9059e-05, 'epoch': 0.26, 'throughput': 860.64} +[INFO|2026-01-03 18:06:44] logging.py:143 >> {'loss': 1.0775, 'learning_rate': 4.8993e-05, 'epoch': 0.27, 'throughput': 862.50} +[INFO|2026-01-03 18:07:16] logging.py:143 >> {'loss': 1.2069, 'learning_rate': 4.8925e-05, 'epoch': 0.28, 'throughput': 861.61} +[INFO|2026-01-03 18:07:48] logging.py:143 >> {'loss': 1.1649, 'learning_rate': 4.8855e-05, 'epoch': 0.29, 'throughput': 861.33} +[INFO|2026-01-03 18:08:22] logging.py:143 >> {'loss': 1.1495, 'learning_rate': 4.8782e-05, 'epoch': 0.30, 'throughput': 862.32} +[INFO|2026-01-03 18:08:56] logging.py:143 >> {'loss': 1.1231, 'learning_rate': 4.8708e-05, 'epoch': 0.31, 'throughput': 864.00} +[INFO|2026-01-03 18:09:29] logging.py:143 >> {'loss': 1.0885, 'learning_rate': 4.8631e-05, 'epoch': 0.32, 'throughput': 863.35} +[INFO|2026-01-03 18:10:02] logging.py:143 >> {'loss': 1.1022, 'learning_rate': 4.8552e-05, 'epoch': 0.33, 'throughput': 863.43} +[INFO|2026-01-03 18:10:33] logging.py:143 >> {'loss': 1.1223, 'learning_rate': 4.8470e-05, 'epoch': 0.34, 'throughput': 861.53} +[INFO|2026-01-03 18:11:07] logging.py:143 >> {'loss': 1.0287, 'learning_rate': 4.8387e-05, 'epoch': 0.35, 'throughput': 862.14} +[INFO|2026-01-03 18:11:38] logging.py:143 >> {'loss': 1.1138, 'learning_rate': 4.8302e-05, 'epoch': 0.36, 'throughput': 860.49} +[INFO|2026-01-03 18:12:11] logging.py:143 >> {'loss': 1.1149, 'learning_rate': 4.8214e-05, 'epoch': 0.37, 'throughput': 860.36} +[INFO|2026-01-03 18:12:11] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-200 +[INFO|2026-01-03 18:12:11] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 18:12:11] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 18:12:11] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-200/chat_template.jinja +[INFO|2026-01-03 18:12:11] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-200/tokenizer_config.json +[INFO|2026-01-03 18:12:11] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-200/special_tokens_map.json +[INFO|2026-01-03 18:12:46] logging.py:143 >> {'loss': 1.1954, 'learning_rate': 4.8124e-05, 'epoch': 0.37, 'throughput': 860.43} +[INFO|2026-01-03 18:13:19] logging.py:143 >> {'loss': 1.0426, 'learning_rate': 4.8032e-05, 'epoch': 0.38, 'throughput': 860.83} +[INFO|2026-01-03 18:13:51] logging.py:143 >> {'loss': 1.2254, 'learning_rate': 4.7939e-05, 'epoch': 0.39, 'throughput': 860.08} +[INFO|2026-01-03 18:14:25] logging.py:143 >> {'loss': 1.0323, 'learning_rate': 4.7843e-05, 'epoch': 0.40, 'throughput': 860.93} +[INFO|2026-01-03 18:14:59] logging.py:143 >> {'loss': 0.9971, 'learning_rate': 4.7744e-05, 'epoch': 0.41, 'throughput': 862.28} +[INFO|2026-01-03 18:15:31] logging.py:143 >> {'loss': 1.0328, 'learning_rate': 4.7644e-05, 'epoch': 0.42, 'throughput': 861.03} +[INFO|2026-01-03 18:16:04] logging.py:143 >> {'loss': 1.0546, 'learning_rate': 4.7542e-05, 'epoch': 0.43, 'throughput': 861.65} +[INFO|2026-01-03 18:16:37] logging.py:143 >> {'loss': 1.1701, 'learning_rate': 4.7438e-05, 'epoch': 0.44, 'throughput': 861.08} +[INFO|2026-01-03 18:17:09] logging.py:143 >> {'loss': 1.0949, 'learning_rate': 4.7331e-05, 'epoch': 0.45, 'throughput': 860.64} +[INFO|2026-01-03 18:17:41] logging.py:143 >> {'loss': 1.1142, 'learning_rate': 4.7223e-05, 'epoch': 0.46, 'throughput': 859.97} +[INFO|2026-01-03 18:18:14] logging.py:143 >> {'loss': 1.0364, 'learning_rate': 4.7112e-05, 'epoch': 0.47, 'throughput': 859.48} +[INFO|2026-01-03 18:18:47] logging.py:143 >> {'loss': 1.0669, 'learning_rate': 4.7000e-05, 'epoch': 0.47, 'throughput': 859.84} +[INFO|2026-01-03 18:19:20] logging.py:143 >> {'loss': 1.0070, 'learning_rate': 4.6886e-05, 'epoch': 0.48, 'throughput': 859.99} +[INFO|2026-01-03 18:19:53] logging.py:143 >> {'loss': 0.9444, 'learning_rate': 4.6769e-05, 'epoch': 0.49, 'throughput': 859.86} +[INFO|2026-01-03 18:20:26] logging.py:143 >> {'loss': 1.0157, 'learning_rate': 4.6651e-05, 'epoch': 0.50, 'throughput': 859.98} +[INFO|2026-01-03 18:20:58] logging.py:143 >> {'loss': 1.0188, 'learning_rate': 4.6530e-05, 'epoch': 0.51, 'throughput': 859.53} +[INFO|2026-01-03 18:21:31] logging.py:143 >> {'loss': 0.9333, 'learning_rate': 4.6408e-05, 'epoch': 0.52, 'throughput': 859.24} +[INFO|2026-01-03 18:22:04] logging.py:143 >> {'loss': 0.9435, 'learning_rate': 4.6283e-05, 'epoch': 0.53, 'throughput': 859.31} +[INFO|2026-01-03 18:22:36] logging.py:143 >> {'loss': 0.9418, 'learning_rate': 4.6157e-05, 'epoch': 0.54, 'throughput': 859.02} +[INFO|2026-01-03 18:23:10] logging.py:143 >> {'loss': 0.9934, 'learning_rate': 4.6029e-05, 'epoch': 0.55, 'throughput': 859.28} +[INFO|2026-01-03 18:23:10] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-300 +[INFO|2026-01-03 18:23:10] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 18:23:10] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 18:23:10] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-300/chat_template.jinja +[INFO|2026-01-03 18:23:10] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-300/tokenizer_config.json +[INFO|2026-01-03 18:23:10] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-300/special_tokens_map.json +[INFO|2026-01-03 18:23:44] logging.py:143 >> {'loss': 1.0952, 'learning_rate': 4.5899e-05, 'epoch': 0.56, 'throughput': 858.69} +[INFO|2026-01-03 18:24:17] logging.py:143 >> {'loss': 0.9632, 'learning_rate': 4.5767e-05, 'epoch': 0.57, 'throughput': 858.75} +[INFO|2026-01-03 18:24:49] logging.py:143 >> {'loss': 0.9310, 'learning_rate': 4.5633e-05, 'epoch': 0.58, 'throughput': 858.17} +[INFO|2026-01-03 18:25:22] logging.py:143 >> {'loss': 1.0103, 'learning_rate': 4.5497e-05, 'epoch': 0.58, 'throughput': 858.16} +[INFO|2026-01-03 18:25:55] logging.py:143 >> {'loss': 0.9518, 'learning_rate': 4.5359e-05, 'epoch': 0.59, 'throughput': 858.08} +[INFO|2026-01-03 18:26:28] logging.py:143 >> {'loss': 0.8974, 'learning_rate': 4.5220e-05, 'epoch': 0.60, 'throughput': 858.47} +[INFO|2026-01-03 18:27:01] logging.py:143 >> {'loss': 0.9171, 'learning_rate': 4.5078e-05, 'epoch': 0.61, 'throughput': 858.14} +[INFO|2026-01-03 18:27:34] logging.py:143 >> {'loss': 0.8990, 'learning_rate': 4.4935e-05, 'epoch': 0.62, 'throughput': 858.26} +[INFO|2026-01-03 18:28:07] logging.py:143 >> {'loss': 0.8964, 'learning_rate': 4.4790e-05, 'epoch': 0.63, 'throughput': 858.48} +[INFO|2026-01-03 18:28:40] logging.py:143 >> {'loss': 1.0919, 'learning_rate': 4.4643e-05, 'epoch': 0.64, 'throughput': 858.03} +[INFO|2026-01-03 18:29:12] logging.py:143 >> {'loss': 1.0469, 'learning_rate': 4.4495e-05, 'epoch': 0.65, 'throughput': 857.86} +[INFO|2026-01-03 18:29:46] logging.py:143 >> {'loss': 0.8841, 'learning_rate': 4.4344e-05, 'epoch': 0.66, 'throughput': 858.02} +[INFO|2026-01-03 18:30:19] logging.py:143 >> {'loss': 1.0016, 'learning_rate': 4.4192e-05, 'epoch': 0.67, 'throughput': 858.21} +[INFO|2026-01-03 18:30:51] logging.py:143 >> {'loss': 0.9584, 'learning_rate': 4.4038e-05, 'epoch': 0.68, 'throughput': 857.44} +[INFO|2026-01-03 18:31:24] logging.py:143 >> {'loss': 0.9964, 'learning_rate': 4.3882e-05, 'epoch': 0.68, 'throughput': 857.55} +[INFO|2026-01-03 18:31:57] logging.py:143 >> {'loss': 0.9808, 'learning_rate': 4.3725e-05, 'epoch': 0.69, 'throughput': 857.40} +[INFO|2026-01-03 18:32:31] logging.py:143 >> {'loss': 0.9126, 'learning_rate': 4.3566e-05, 'epoch': 0.70, 'throughput': 857.82} +[INFO|2026-01-03 18:33:04] logging.py:143 >> {'loss': 0.8749, 'learning_rate': 4.3405e-05, 'epoch': 0.71, 'throughput': 858.10} +[INFO|2026-01-03 18:33:37] logging.py:143 >> {'loss': 0.9203, 'learning_rate': 4.3243e-05, 'epoch': 0.72, 'throughput': 858.29} +[INFO|2026-01-03 18:34:11] logging.py:143 >> {'loss': 0.8857, 'learning_rate': 4.3078e-05, 'epoch': 0.73, 'throughput': 858.70} +[INFO|2026-01-03 18:34:11] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-400 +[INFO|2026-01-03 18:34:11] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 18:34:11] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 18:34:11] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-400/chat_template.jinja +[INFO|2026-01-03 18:34:11] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-400/tokenizer_config.json +[INFO|2026-01-03 18:34:11] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-400/special_tokens_map.json +[INFO|2026-01-03 18:34:46] logging.py:143 >> {'loss': 0.9175, 'learning_rate': 4.2913e-05, 'epoch': 0.74, 'throughput': 858.62} +[INFO|2026-01-03 18:35:18] logging.py:143 >> {'loss': 0.9572, 'learning_rate': 4.2745e-05, 'epoch': 0.75, 'throughput': 858.42} +[INFO|2026-01-03 18:35:51] logging.py:143 >> {'loss': 1.0534, 'learning_rate': 4.2576e-05, 'epoch': 0.76, 'throughput': 858.30} +[INFO|2026-01-03 18:36:24] logging.py:143 >> {'loss': 0.8583, 'learning_rate': 4.2405e-05, 'epoch': 0.77, 'throughput': 858.40} +[INFO|2026-01-03 18:36:58] logging.py:143 >> {'loss': 0.8049, 'learning_rate': 4.2233e-05, 'epoch': 0.78, 'throughput': 858.68} +[INFO|2026-01-03 18:37:31] logging.py:143 >> {'loss': 0.9599, 'learning_rate': 4.2059e-05, 'epoch': 0.79, 'throughput': 858.76} +[INFO|2026-01-03 18:38:04] logging.py:143 >> {'loss': 0.8874, 'learning_rate': 4.1884e-05, 'epoch': 0.79, 'throughput': 858.73} +[INFO|2026-01-03 18:38:36] logging.py:143 >> {'loss': 0.8944, 'learning_rate': 4.1707e-05, 'epoch': 0.80, 'throughput': 858.55} +[INFO|2026-01-03 18:39:10] logging.py:143 >> {'loss': 0.9774, 'learning_rate': 4.1528e-05, 'epoch': 0.81, 'throughput': 858.61} +[INFO|2026-01-03 18:39:43] logging.py:143 >> {'loss': 0.8543, 'learning_rate': 4.1349e-05, 'epoch': 0.82, 'throughput': 859.04} +[INFO|2026-01-03 18:40:16] logging.py:143 >> {'loss': 0.8293, 'learning_rate': 4.1167e-05, 'epoch': 0.83, 'throughput': 859.07} +[INFO|2026-01-03 18:40:50] logging.py:143 >> {'loss': 0.9264, 'learning_rate': 4.0984e-05, 'epoch': 0.84, 'throughput': 859.36} +[INFO|2026-01-03 18:41:23] logging.py:143 >> {'loss': 0.9641, 'learning_rate': 4.0800e-05, 'epoch': 0.85, 'throughput': 859.44} +[INFO|2026-01-03 18:41:56] logging.py:143 >> {'loss': 0.8050, 'learning_rate': 4.0614e-05, 'epoch': 0.86, 'throughput': 859.28} +[INFO|2026-01-03 18:42:28] logging.py:143 >> {'loss': 1.0411, 'learning_rate': 4.0427e-05, 'epoch': 0.87, 'throughput': 858.91} +[INFO|2026-01-03 18:43:02] logging.py:143 >> {'loss': 0.8638, 'learning_rate': 4.0238e-05, 'epoch': 0.88, 'throughput': 859.55} +[INFO|2026-01-03 18:43:34] logging.py:143 >> {'loss': 1.0152, 'learning_rate': 4.0048e-05, 'epoch': 0.89, 'throughput': 859.07} +[INFO|2026-01-03 18:44:07] logging.py:143 >> {'loss': 0.9046, 'learning_rate': 3.9856e-05, 'epoch': 0.89, 'throughput': 859.04} +[INFO|2026-01-03 18:44:39] logging.py:143 >> {'loss': 0.8428, 'learning_rate': 3.9664e-05, 'epoch': 0.90, 'throughput': 858.64} +[INFO|2026-01-03 18:45:12] logging.py:143 >> {'loss': 0.8138, 'learning_rate': 3.9470e-05, 'epoch': 0.91, 'throughput': 858.66} +[INFO|2026-01-03 18:45:12] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-500 +[INFO|2026-01-03 18:45:12] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 18:45:12] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 18:45:13] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-500/chat_template.jinja +[INFO|2026-01-03 18:45:13] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-500/tokenizer_config.json +[INFO|2026-01-03 18:45:13] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-500/special_tokens_map.json +[INFO|2026-01-03 18:45:47] logging.py:143 >> {'loss': 0.8349, 'learning_rate': 3.9274e-05, 'epoch': 0.92, 'throughput': 858.45} +[INFO|2026-01-03 18:46:20] logging.py:143 >> {'loss': 0.8830, 'learning_rate': 3.9077e-05, 'epoch': 0.93, 'throughput': 858.66} +[INFO|2026-01-03 18:46:54] logging.py:143 >> {'loss': 0.8141, 'learning_rate': 3.8879e-05, 'epoch': 0.94, 'throughput': 858.89} +[INFO|2026-01-03 18:47:26] logging.py:143 >> {'loss': 0.8964, 'learning_rate': 3.8680e-05, 'epoch': 0.95, 'throughput': 858.74} +[INFO|2026-01-03 18:48:00] logging.py:143 >> {'loss': 0.7845, 'learning_rate': 3.8479e-05, 'epoch': 0.96, 'throughput': 858.79} +[INFO|2026-01-03 18:48:32] logging.py:143 >> {'loss': 0.9675, 'learning_rate': 3.8278e-05, 'epoch': 0.97, 'throughput': 858.76} +[INFO|2026-01-03 18:49:06] logging.py:143 >> {'loss': 0.9429, 'learning_rate': 3.8075e-05, 'epoch': 0.98, 'throughput': 859.21} +[INFO|2026-01-03 18:49:39] logging.py:143 >> {'loss': 0.9034, 'learning_rate': 3.7870e-05, 'epoch': 0.99, 'throughput': 858.95} +[INFO|2026-01-03 18:50:12] logging.py:143 >> {'loss': 0.8696, 'learning_rate': 3.7665e-05, 'epoch': 1.00, 'throughput': 859.09} +[INFO|2026-01-03 18:50:42] logging.py:143 >> {'loss': 0.9914, 'learning_rate': 3.7459e-05, 'epoch': 1.00, 'throughput': 858.83} +[INFO|2026-01-03 18:51:15] logging.py:143 >> {'loss': 0.7924, 'learning_rate': 3.7251e-05, 'epoch': 1.01, 'throughput': 858.78} +[INFO|2026-01-03 18:51:48] logging.py:143 >> {'loss': 0.7542, 'learning_rate': 3.7042e-05, 'epoch': 1.02, 'throughput': 858.67} +[INFO|2026-01-03 18:52:20] logging.py:143 >> {'loss': 0.7216, 'learning_rate': 3.6832e-05, 'epoch': 1.03, 'throughput': 858.51} +[INFO|2026-01-03 18:52:53] logging.py:143 >> {'loss': 0.8276, 'learning_rate': 3.6621e-05, 'epoch': 1.04, 'throughput': 858.31} +[INFO|2026-01-03 18:53:26] logging.py:143 >> {'loss': 0.8081, 'learning_rate': 3.6409e-05, 'epoch': 1.05, 'throughput': 858.44} +[INFO|2026-01-03 18:53:58] logging.py:143 >> {'loss': 0.7503, 'learning_rate': 3.6196e-05, 'epoch': 1.06, 'throughput': 858.31} +[INFO|2026-01-03 18:54:32] logging.py:143 >> {'loss': 0.7449, 'learning_rate': 3.5982e-05, 'epoch': 1.07, 'throughput': 858.46} +[INFO|2026-01-03 18:55:05] logging.py:143 >> {'loss': 0.7779, 'learning_rate': 3.5767e-05, 'epoch': 1.08, 'throughput': 858.72} +[INFO|2026-01-03 18:55:39] logging.py:143 >> {'loss': 0.7257, 'learning_rate': 3.5551e-05, 'epoch': 1.09, 'throughput': 859.04} +[INFO|2026-01-03 18:56:12] logging.py:143 >> {'loss': 0.7348, 'learning_rate': 3.5334e-05, 'epoch': 1.09, 'throughput': 859.01} +[INFO|2026-01-03 18:56:12] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-600 +[INFO|2026-01-03 18:56:12] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 18:56:12] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 18:56:12] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-600/chat_template.jinja +[INFO|2026-01-03 18:56:12] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-600/tokenizer_config.json +[INFO|2026-01-03 18:56:12] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-600/special_tokens_map.json +[INFO|2026-01-03 18:56:46] logging.py:143 >> {'loss': 0.8140, 'learning_rate': 3.5116e-05, 'epoch': 1.10, 'throughput': 858.80} +[INFO|2026-01-03 18:57:19] logging.py:143 >> {'loss': 0.6645, 'learning_rate': 3.4897e-05, 'epoch': 1.11, 'throughput': 858.74} +[INFO|2026-01-03 18:57:52] logging.py:143 >> {'loss': 0.7804, 'learning_rate': 3.4677e-05, 'epoch': 1.12, 'throughput': 858.73} +[INFO|2026-01-03 18:58:24] logging.py:143 >> {'loss': 0.8645, 'learning_rate': 3.4457e-05, 'epoch': 1.13, 'throughput': 858.48} +[INFO|2026-01-03 18:58:58] logging.py:143 >> {'loss': 0.7509, 'learning_rate': 3.4235e-05, 'epoch': 1.14, 'throughput': 858.70} +[INFO|2026-01-03 18:59:32] logging.py:143 >> {'loss': 0.7380, 'learning_rate': 3.4013e-05, 'epoch': 1.15, 'throughput': 858.81} +[INFO|2026-01-03 19:00:05] logging.py:143 >> {'loss': 0.7310, 'learning_rate': 3.3789e-05, 'epoch': 1.16, 'throughput': 858.83} +[INFO|2026-01-03 19:00:38] logging.py:143 >> {'loss': 0.6878, 'learning_rate': 3.3565e-05, 'epoch': 1.17, 'throughput': 858.79} +[INFO|2026-01-03 19:01:11] logging.py:143 >> {'loss': 0.6777, 'learning_rate': 3.3341e-05, 'epoch': 1.18, 'throughput': 858.84} +[INFO|2026-01-03 19:01:44] logging.py:143 >> {'loss': 0.8185, 'learning_rate': 3.3115e-05, 'epoch': 1.19, 'throughput': 858.76} +[INFO|2026-01-03 19:02:17] logging.py:143 >> {'loss': 0.7367, 'learning_rate': 3.2889e-05, 'epoch': 1.20, 'throughput': 858.67} +[INFO|2026-01-03 19:02:49] logging.py:143 >> {'loss': 0.7812, 'learning_rate': 3.2662e-05, 'epoch': 1.20, 'throughput': 858.63} +[INFO|2026-01-03 19:03:23] logging.py:143 >> {'loss': 0.6602, 'learning_rate': 3.2434e-05, 'epoch': 1.21, 'throughput': 858.96} +[INFO|2026-01-03 19:03:56] logging.py:143 >> {'loss': 0.7918, 'learning_rate': 3.2206e-05, 'epoch': 1.22, 'throughput': 858.90} +[INFO|2026-01-03 19:04:29] logging.py:143 >> {'loss': 0.6596, 'learning_rate': 3.1977e-05, 'epoch': 1.23, 'throughput': 858.90} +[INFO|2026-01-03 19:05:03] logging.py:143 >> {'loss': 0.5950, 'learning_rate': 3.1747e-05, 'epoch': 1.24, 'throughput': 859.24} +[INFO|2026-01-03 19:05:36] logging.py:143 >> {'loss': 0.7421, 'learning_rate': 3.1517e-05, 'epoch': 1.25, 'throughput': 859.23} +[INFO|2026-01-03 19:06:07] logging.py:143 >> {'loss': 0.8241, 'learning_rate': 3.1286e-05, 'epoch': 1.26, 'throughput': 858.60} +[INFO|2026-01-03 19:06:39] logging.py:143 >> {'loss': 0.7889, 'learning_rate': 3.1054e-05, 'epoch': 1.27, 'throughput': 858.29} +[INFO|2026-01-03 19:07:11] logging.py:143 >> {'loss': 0.8462, 'learning_rate': 3.0822e-05, 'epoch': 1.28, 'throughput': 858.12} +[INFO|2026-01-03 19:07:11] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-700 +[INFO|2026-01-03 19:07:11] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 19:07:11] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 19:07:12] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-700/chat_template.jinja +[INFO|2026-01-03 19:07:12] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-700/tokenizer_config.json +[INFO|2026-01-03 19:07:12] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-700/special_tokens_map.json +[INFO|2026-01-03 19:07:45] logging.py:143 >> {'loss': 0.8064, 'learning_rate': 3.0590e-05, 'epoch': 1.29, 'throughput': 857.86} +[INFO|2026-01-03 19:08:17] logging.py:143 >> {'loss': 0.7113, 'learning_rate': 3.0357e-05, 'epoch': 1.30, 'throughput': 857.75} +[INFO|2026-01-03 19:08:50] logging.py:143 >> {'loss': 0.7086, 'learning_rate': 3.0123e-05, 'epoch': 1.30, 'throughput': 857.58} +[INFO|2026-01-03 19:09:23] logging.py:143 >> {'loss': 0.6923, 'learning_rate': 2.9889e-05, 'epoch': 1.31, 'throughput': 857.53} +[INFO|2026-01-03 19:09:56] logging.py:143 >> {'loss': 0.7034, 'learning_rate': 2.9654e-05, 'epoch': 1.32, 'throughput': 857.46} +[INFO|2026-01-03 19:10:29] logging.py:143 >> {'loss': 0.7029, 'learning_rate': 2.9420e-05, 'epoch': 1.33, 'throughput': 857.55} +[INFO|2026-01-03 19:11:02] logging.py:143 >> {'loss': 0.7442, 'learning_rate': 2.9184e-05, 'epoch': 1.34, 'throughput': 857.69} +[INFO|2026-01-03 19:11:36] logging.py:143 >> {'loss': 0.6896, 'learning_rate': 2.8949e-05, 'epoch': 1.35, 'throughput': 857.92} +[INFO|2026-01-03 19:12:10] logging.py:143 >> {'loss': 0.7188, 'learning_rate': 2.8713e-05, 'epoch': 1.36, 'throughput': 858.05} +[INFO|2026-01-03 19:12:44] logging.py:143 >> {'loss': 0.7536, 'learning_rate': 2.8476e-05, 'epoch': 1.37, 'throughput': 858.33} +[INFO|2026-01-03 19:13:17] logging.py:143 >> {'loss': 0.6742, 'learning_rate': 2.8239e-05, 'epoch': 1.38, 'throughput': 858.27} +[INFO|2026-01-03 19:13:50] logging.py:143 >> {'loss': 0.6787, 'learning_rate': 2.8002e-05, 'epoch': 1.39, 'throughput': 858.28} +[INFO|2026-01-03 19:14:22] logging.py:143 >> {'loss': 0.8232, 'learning_rate': 2.7765e-05, 'epoch': 1.40, 'throughput': 858.22} +[INFO|2026-01-03 19:14:55] logging.py:143 >> {'loss': 0.7529, 'learning_rate': 2.7528e-05, 'epoch': 1.41, 'throughput': 858.10} +[INFO|2026-01-03 19:15:28] logging.py:143 >> {'loss': 0.7612, 'learning_rate': 2.7290e-05, 'epoch': 1.41, 'throughput': 858.08} +[INFO|2026-01-03 19:16:00] logging.py:143 >> {'loss': 0.7770, 'learning_rate': 2.7052e-05, 'epoch': 1.42, 'throughput': 857.80} +[INFO|2026-01-03 19:16:33] logging.py:143 >> {'loss': 0.7732, 'learning_rate': 2.6814e-05, 'epoch': 1.43, 'throughput': 857.81} +[INFO|2026-01-03 19:17:06] logging.py:143 >> {'loss': 0.6874, 'learning_rate': 2.6575e-05, 'epoch': 1.44, 'throughput': 857.88} +[INFO|2026-01-03 19:17:40] logging.py:143 >> {'loss': 0.6866, 'learning_rate': 2.6337e-05, 'epoch': 1.45, 'throughput': 858.01} +[INFO|2026-01-03 19:18:12] logging.py:143 >> {'loss': 0.6184, 'learning_rate': 2.6098e-05, 'epoch': 1.46, 'throughput': 857.91} +[INFO|2026-01-03 19:18:12] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-800 +[INFO|2026-01-03 19:18:12] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 19:18:12] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 19:18:13] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-800/chat_template.jinja +[INFO|2026-01-03 19:18:13] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-800/tokenizer_config.json +[INFO|2026-01-03 19:18:13] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-800/special_tokens_map.json +[INFO|2026-01-03 19:18:46] logging.py:143 >> {'loss': 0.6364, 'learning_rate': 2.5860e-05, 'epoch': 1.47, 'throughput': 857.71} +[INFO|2026-01-03 19:19:19] logging.py:143 >> {'loss': 0.7312, 'learning_rate': 2.5621e-05, 'epoch': 1.48, 'throughput': 857.63} +[INFO|2026-01-03 19:19:52] logging.py:143 >> {'loss': 0.6735, 'learning_rate': 2.5382e-05, 'epoch': 1.49, 'throughput': 857.79} +[INFO|2026-01-03 19:20:25] logging.py:143 >> {'loss': 0.5681, 'learning_rate': 2.5143e-05, 'epoch': 1.50, 'throughput': 857.56} +[INFO|2026-01-03 19:20:57] logging.py:143 >> {'loss': 0.7154, 'learning_rate': 2.4904e-05, 'epoch': 1.51, 'throughput': 857.25} +[INFO|2026-01-03 19:21:28] logging.py:143 >> {'loss': 0.6590, 'learning_rate': 2.4666e-05, 'epoch': 1.51, 'throughput': 856.95} +[INFO|2026-01-03 19:22:02] logging.py:143 >> {'loss': 0.6600, 'learning_rate': 2.4427e-05, 'epoch': 1.52, 'throughput': 857.08} +[INFO|2026-01-03 19:22:35] logging.py:143 >> {'loss': 0.8048, 'learning_rate': 2.4188e-05, 'epoch': 1.53, 'throughput': 857.23} +[INFO|2026-01-03 19:23:08] logging.py:143 >> {'loss': 0.6516, 'learning_rate': 2.3949e-05, 'epoch': 1.54, 'throughput': 857.24} +[INFO|2026-01-03 19:23:41] logging.py:143 >> {'loss': 0.6813, 'learning_rate': 2.3711e-05, 'epoch': 1.55, 'throughput': 857.25} +[INFO|2026-01-03 19:24:15] logging.py:143 >> {'loss': 0.7308, 'learning_rate': 2.3472e-05, 'epoch': 1.56, 'throughput': 857.41} +[INFO|2026-01-03 19:24:48] logging.py:143 >> {'loss': 0.7728, 'learning_rate': 2.3234e-05, 'epoch': 1.57, 'throughput': 857.47} +[INFO|2026-01-03 19:25:20] logging.py:143 >> {'loss': 0.6673, 'learning_rate': 2.2996e-05, 'epoch': 1.58, 'throughput': 857.38} +[INFO|2026-01-03 19:25:53] logging.py:143 >> {'loss': 0.7155, 'learning_rate': 2.2758e-05, 'epoch': 1.59, 'throughput': 857.40} +[INFO|2026-01-03 19:26:27] logging.py:143 >> {'loss': 0.6372, 'learning_rate': 2.2520e-05, 'epoch': 1.60, 'throughput': 857.54} +[INFO|2026-01-03 19:27:00] logging.py:143 >> {'loss': 0.7021, 'learning_rate': 2.2282e-05, 'epoch': 1.61, 'throughput': 857.66} +[INFO|2026-01-03 19:27:34] logging.py:143 >> {'loss': 0.6923, 'learning_rate': 2.2045e-05, 'epoch': 1.62, 'throughput': 857.84} +[INFO|2026-01-03 19:28:07] logging.py:143 >> {'loss': 0.6426, 'learning_rate': 2.1808e-05, 'epoch': 1.62, 'throughput': 857.93} +[INFO|2026-01-03 19:28:41] logging.py:143 >> {'loss': 0.5618, 'learning_rate': 2.1571e-05, 'epoch': 1.63, 'throughput': 857.97} +[INFO|2026-01-03 19:29:12] logging.py:143 >> {'loss': 0.6160, 'learning_rate': 2.1335e-05, 'epoch': 1.64, 'throughput': 857.64} +[INFO|2026-01-03 19:29:12] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-900 +[INFO|2026-01-03 19:29:12] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 19:29:12] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 19:29:12] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-900/chat_template.jinja +[INFO|2026-01-03 19:29:12] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-900/tokenizer_config.json +[INFO|2026-01-03 19:29:12] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-900/special_tokens_map.json +[INFO|2026-01-03 19:29:46] logging.py:143 >> {'loss': 0.6574, 'learning_rate': 2.1099e-05, 'epoch': 1.65, 'throughput': 857.40} +[INFO|2026-01-03 19:30:19] logging.py:143 >> {'loss': 0.6823, 'learning_rate': 2.0863e-05, 'epoch': 1.66, 'throughput': 857.31} +[INFO|2026-01-03 19:30:51] logging.py:143 >> {'loss': 0.5728, 'learning_rate': 2.0627e-05, 'epoch': 1.67, 'throughput': 857.31} +[INFO|2026-01-03 19:31:24] logging.py:143 >> {'loss': 0.7025, 'learning_rate': 2.0392e-05, 'epoch': 1.68, 'throughput': 857.28} +[INFO|2026-01-03 19:31:58] logging.py:143 >> {'loss': 0.5986, 'learning_rate': 2.0158e-05, 'epoch': 1.69, 'throughput': 857.53} +[INFO|2026-01-03 19:32:30] logging.py:143 >> {'loss': 0.6195, 'learning_rate': 1.9924e-05, 'epoch': 1.70, 'throughput': 857.32} +[INFO|2026-01-03 19:33:04] logging.py:143 >> {'loss': 0.6283, 'learning_rate': 1.9690e-05, 'epoch': 1.71, 'throughput': 857.41} +[INFO|2026-01-03 19:33:38] logging.py:143 >> {'loss': 0.5767, 'learning_rate': 1.9457e-05, 'epoch': 1.72, 'throughput': 857.51} +[INFO|2026-01-03 19:34:10] logging.py:143 >> {'loss': 0.5237, 'learning_rate': 1.9224e-05, 'epoch': 1.72, 'throughput': 857.34} +[INFO|2026-01-03 19:34:43] logging.py:143 >> {'loss': 0.7184, 'learning_rate': 1.8992e-05, 'epoch': 1.73, 'throughput': 857.40} +[INFO|2026-01-03 19:35:16] logging.py:143 >> {'loss': 0.6595, 'learning_rate': 1.8761e-05, 'epoch': 1.74, 'throughput': 857.47} +[INFO|2026-01-03 19:35:49] logging.py:143 >> {'loss': 0.6161, 'learning_rate': 1.8530e-05, 'epoch': 1.75, 'throughput': 857.50} +[INFO|2026-01-03 19:36:23] logging.py:143 >> {'loss': 0.6076, 'learning_rate': 1.8299e-05, 'epoch': 1.76, 'throughput': 857.63} +[INFO|2026-01-03 19:36:56] logging.py:143 >> {'loss': 0.5543, 'learning_rate': 1.8069e-05, 'epoch': 1.77, 'throughput': 857.76} +[INFO|2026-01-03 19:37:29] logging.py:143 >> {'loss': 0.6496, 'learning_rate': 1.7840e-05, 'epoch': 1.78, 'throughput': 857.70} +[INFO|2026-01-03 19:38:02] logging.py:143 >> {'loss': 0.6315, 'learning_rate': 1.7612e-05, 'epoch': 1.79, 'throughput': 857.79} +[INFO|2026-01-03 19:38:35] logging.py:143 >> {'loss': 0.5654, 'learning_rate': 1.7384e-05, 'epoch': 1.80, 'throughput': 857.71} +[INFO|2026-01-03 19:39:08] logging.py:143 >> {'loss': 0.5803, 'learning_rate': 1.7157e-05, 'epoch': 1.81, 'throughput': 857.74} +[INFO|2026-01-03 19:39:42] logging.py:143 >> {'loss': 0.5516, 'learning_rate': 1.6930e-05, 'epoch': 1.82, 'throughput': 857.88} +[INFO|2026-01-03 19:40:15] logging.py:143 >> {'loss': 0.6530, 'learning_rate': 1.6704e-05, 'epoch': 1.83, 'throughput': 857.90} +[INFO|2026-01-03 19:40:15] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1000 +[INFO|2026-01-03 19:40:15] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 19:40:15] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 19:40:15] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1000/chat_template.jinja +[INFO|2026-01-03 19:40:15] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1000/tokenizer_config.json +[INFO|2026-01-03 19:40:15] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1000/special_tokens_map.json +[INFO|2026-01-03 19:40:50] logging.py:143 >> {'loss': 0.6456, 'learning_rate': 1.6479e-05, 'epoch': 1.83, 'throughput': 857.82} +[INFO|2026-01-03 19:41:22] logging.py:143 >> {'loss': 0.6778, 'learning_rate': 1.6255e-05, 'epoch': 1.84, 'throughput': 857.68} +[INFO|2026-01-03 19:41:55] logging.py:143 >> {'loss': 0.6779, 'learning_rate': 1.6032e-05, 'epoch': 1.85, 'throughput': 857.65} +[INFO|2026-01-03 19:42:29] logging.py:143 >> {'loss': 0.5039, 'learning_rate': 1.5809e-05, 'epoch': 1.86, 'throughput': 857.77} +[INFO|2026-01-03 19:43:02] logging.py:143 >> {'loss': 0.6694, 'learning_rate': 1.5588e-05, 'epoch': 1.87, 'throughput': 857.78} +[INFO|2026-01-03 19:43:35] logging.py:143 >> {'loss': 0.5749, 'learning_rate': 1.5367e-05, 'epoch': 1.88, 'throughput': 857.95} +[INFO|2026-01-03 19:44:08] logging.py:143 >> {'loss': 0.5602, 'learning_rate': 1.5147e-05, 'epoch': 1.89, 'throughput': 857.95} +[INFO|2026-01-03 19:44:41] logging.py:143 >> {'loss': 0.6450, 'learning_rate': 1.4928e-05, 'epoch': 1.90, 'throughput': 857.78} +[INFO|2026-01-03 19:45:15] logging.py:143 >> {'loss': 0.6209, 'learning_rate': 1.4710e-05, 'epoch': 1.91, 'throughput': 858.00} +[INFO|2026-01-03 19:45:47] logging.py:143 >> {'loss': 0.5908, 'learning_rate': 1.4492e-05, 'epoch': 1.92, 'throughput': 857.90} +[INFO|2026-01-03 19:46:20] logging.py:143 >> {'loss': 0.5957, 'learning_rate': 1.4276e-05, 'epoch': 1.93, 'throughput': 857.91} +[INFO|2026-01-03 19:46:52] logging.py:143 >> {'loss': 0.6543, 'learning_rate': 1.4061e-05, 'epoch': 1.93, 'throughput': 857.70} +[INFO|2026-01-03 19:47:26] logging.py:143 >> {'loss': 0.5055, 'learning_rate': 1.3846e-05, 'epoch': 1.94, 'throughput': 857.84} +[INFO|2026-01-03 19:47:59] logging.py:143 >> {'loss': 0.5246, 'learning_rate': 1.3633e-05, 'epoch': 1.95, 'throughput': 857.97} +[INFO|2026-01-03 19:48:33] logging.py:143 >> {'loss': 0.5412, 'learning_rate': 1.3421e-05, 'epoch': 1.96, 'throughput': 858.06} +[INFO|2026-01-03 19:49:05] logging.py:143 >> {'loss': 0.6240, 'learning_rate': 1.3210e-05, 'epoch': 1.97, 'throughput': 857.94} +[INFO|2026-01-03 19:49:38] logging.py:143 >> {'loss': 0.5854, 'learning_rate': 1.3000e-05, 'epoch': 1.98, 'throughput': 857.89} +[INFO|2026-01-03 19:50:10] logging.py:143 >> {'loss': 0.5972, 'learning_rate': 1.2791e-05, 'epoch': 1.99, 'throughput': 857.79} +[INFO|2026-01-03 19:50:44] logging.py:143 >> {'loss': 0.5627, 'learning_rate': 1.2583e-05, 'epoch': 2.00, 'throughput': 857.96} +[INFO|2026-01-03 19:51:15] logging.py:143 >> {'loss': 0.5440, 'learning_rate': 1.2376e-05, 'epoch': 2.01, 'throughput': 857.97} +[INFO|2026-01-03 19:51:15] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1100 +[INFO|2026-01-03 19:51:15] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 19:51:15] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 19:51:15] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1100/chat_template.jinja +[INFO|2026-01-03 19:51:15] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1100/tokenizer_config.json +[INFO|2026-01-03 19:51:15] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1100/special_tokens_map.json +[INFO|2026-01-03 19:51:49] logging.py:143 >> {'loss': 0.4701, 'learning_rate': 1.2170e-05, 'epoch': 2.02, 'throughput': 857.99} +[INFO|2026-01-03 19:52:23] logging.py:143 >> {'loss': 0.4359, 'learning_rate': 1.1966e-05, 'epoch': 2.03, 'throughput': 858.21} +[INFO|2026-01-03 19:52:57] logging.py:143 >> {'loss': 0.4436, 'learning_rate': 1.1763e-05, 'epoch': 2.03, 'throughput': 858.35} +[INFO|2026-01-03 19:53:30] logging.py:143 >> {'loss': 0.5898, 'learning_rate': 1.1561e-05, 'epoch': 2.04, 'throughput': 858.30} +[INFO|2026-01-03 19:54:02] logging.py:143 >> {'loss': 0.5882, 'learning_rate': 1.1360e-05, 'epoch': 2.05, 'throughput': 858.05} +[INFO|2026-01-03 19:54:35] logging.py:143 >> {'loss': 0.4388, 'learning_rate': 1.1160e-05, 'epoch': 2.06, 'throughput': 858.00} +[INFO|2026-01-03 19:55:08] logging.py:143 >> {'loss': 0.5827, 'learning_rate': 1.0962e-05, 'epoch': 2.07, 'throughput': 858.03} +[INFO|2026-01-03 19:55:40] logging.py:143 >> {'loss': 0.5261, 'learning_rate': 1.0765e-05, 'epoch': 2.08, 'throughput': 857.97} +[INFO|2026-01-03 19:56:13] logging.py:143 >> {'loss': 0.5661, 'learning_rate': 1.0569e-05, 'epoch': 2.09, 'throughput': 857.88} +[INFO|2026-01-03 19:56:46] logging.py:143 >> {'loss': 0.5380, 'learning_rate': 1.0375e-05, 'epoch': 2.10, 'throughput': 857.82} +[INFO|2026-01-03 19:57:18] logging.py:143 >> {'loss': 0.7164, 'learning_rate': 1.0182e-05, 'epoch': 2.11, 'throughput': 857.75} +[INFO|2026-01-03 19:57:52] logging.py:143 >> {'loss': 0.5611, 'learning_rate': 9.9903e-06, 'epoch': 2.12, 'throughput': 857.80} +[INFO|2026-01-03 19:58:24] logging.py:143 >> {'loss': 0.5341, 'learning_rate': 9.7999e-06, 'epoch': 2.13, 'throughput': 857.70} +[INFO|2026-01-03 19:58:56] logging.py:143 >> {'loss': 0.4899, 'learning_rate': 9.6110e-06, 'epoch': 2.14, 'throughput': 857.60} +[INFO|2026-01-03 19:59:29] logging.py:143 >> {'loss': 0.6115, 'learning_rate': 9.4234e-06, 'epoch': 2.14, 'throughput': 857.59} +[INFO|2026-01-03 20:00:03] logging.py:143 >> {'loss': 0.5713, 'learning_rate': 9.2373e-06, 'epoch': 2.15, 'throughput': 857.66} +[INFO|2026-01-03 20:00:36] logging.py:143 >> {'loss': 0.5144, 'learning_rate': 9.0526e-06, 'epoch': 2.16, 'throughput': 857.70} +[INFO|2026-01-03 20:01:09] logging.py:143 >> {'loss': 0.5139, 'learning_rate': 8.8694e-06, 'epoch': 2.17, 'throughput': 857.78} +[INFO|2026-01-03 20:01:42] logging.py:143 >> {'loss': 0.5763, 'learning_rate': 8.6876e-06, 'epoch': 2.18, 'throughput': 857.78} +[INFO|2026-01-03 20:02:17] logging.py:143 >> {'loss': 0.5669, 'learning_rate': 8.5074e-06, 'epoch': 2.19, 'throughput': 858.01} +[INFO|2026-01-03 20:02:17] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1200 +[INFO|2026-01-03 20:02:17] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 20:02:17] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 20:02:17] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1200/chat_template.jinja +[INFO|2026-01-03 20:02:17] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1200/tokenizer_config.json +[INFO|2026-01-03 20:02:17] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1200/special_tokens_map.json +[INFO|2026-01-03 20:02:51] logging.py:143 >> {'loss': 0.5508, 'learning_rate': 8.3286e-06, 'epoch': 2.20, 'throughput': 857.95} +[INFO|2026-01-03 20:03:24] logging.py:143 >> {'loss': 0.5538, 'learning_rate': 8.1514e-06, 'epoch': 2.21, 'throughput': 858.01} +[INFO|2026-01-03 20:03:57] logging.py:143 >> {'loss': 0.4806, 'learning_rate': 7.9757e-06, 'epoch': 2.22, 'throughput': 858.04} +[INFO|2026-01-03 20:04:31] logging.py:143 >> {'loss': 0.4594, 'learning_rate': 7.8015e-06, 'epoch': 2.23, 'throughput': 858.10} +[INFO|2026-01-03 20:05:04] logging.py:143 >> {'loss': 0.4625, 'learning_rate': 7.6290e-06, 'epoch': 2.24, 'throughput': 858.25} +[INFO|2026-01-03 20:05:37] logging.py:143 >> {'loss': 0.5248, 'learning_rate': 7.4580e-06, 'epoch': 2.24, 'throughput': 858.06} +[INFO|2026-01-03 20:06:09] logging.py:143 >> {'loss': 0.5796, 'learning_rate': 7.2886e-06, 'epoch': 2.25, 'throughput': 858.05} +[INFO|2026-01-03 20:06:42] logging.py:143 >> {'loss': 0.4509, 'learning_rate': 7.1208e-06, 'epoch': 2.26, 'throughput': 858.04} +[INFO|2026-01-03 20:07:16] logging.py:143 >> {'loss': 0.4935, 'learning_rate': 6.9547e-06, 'epoch': 2.27, 'throughput': 858.16} +[INFO|2026-01-03 20:07:49] logging.py:143 >> {'loss': 0.5073, 'learning_rate': 6.7902e-06, 'epoch': 2.28, 'throughput': 858.20} +[INFO|2026-01-03 20:08:23] logging.py:143 >> {'loss': 0.4892, 'learning_rate': 6.6274e-06, 'epoch': 2.29, 'throughput': 858.22} +[INFO|2026-01-03 20:08:55] logging.py:143 >> {'loss': 0.5268, 'learning_rate': 6.4662e-06, 'epoch': 2.30, 'throughput': 858.15} +[INFO|2026-01-03 20:09:27] logging.py:143 >> {'loss': 0.5226, 'learning_rate': 6.3067e-06, 'epoch': 2.31, 'throughput': 857.94} +[INFO|2026-01-03 20:10:01] logging.py:143 >> {'loss': 0.4098, 'learning_rate': 6.1490e-06, 'epoch': 2.32, 'throughput': 858.07} +[INFO|2026-01-03 20:10:33] logging.py:143 >> {'loss': 0.5064, 'learning_rate': 5.9930e-06, 'epoch': 2.33, 'throughput': 857.86} +[INFO|2026-01-03 20:11:05] logging.py:143 >> {'loss': 0.4860, 'learning_rate': 5.8387e-06, 'epoch': 2.34, 'throughput': 857.82} +[INFO|2026-01-03 20:11:39] logging.py:143 >> {'loss': 0.5659, 'learning_rate': 5.6861e-06, 'epoch': 2.35, 'throughput': 857.87} +[INFO|2026-01-03 20:12:11] logging.py:143 >> {'loss': 0.5572, 'learning_rate': 5.5353e-06, 'epoch': 2.35, 'throughput': 857.82} +[INFO|2026-01-03 20:12:43] logging.py:143 >> {'loss': 0.5891, 'learning_rate': 5.3863e-06, 'epoch': 2.36, 'throughput': 857.72} +[INFO|2026-01-03 20:13:16] logging.py:143 >> {'loss': 0.5121, 'learning_rate': 5.2391e-06, 'epoch': 2.37, 'throughput': 857.66} +[INFO|2026-01-03 20:13:16] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1300 +[INFO|2026-01-03 20:13:16] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 20:13:16] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 20:13:16] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1300/chat_template.jinja +[INFO|2026-01-03 20:13:16] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1300/tokenizer_config.json +[INFO|2026-01-03 20:13:16] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1300/special_tokens_map.json +[INFO|2026-01-03 20:13:51] logging.py:143 >> {'loss': 0.4585, 'learning_rate': 5.0937e-06, 'epoch': 2.38, 'throughput': 857.71} +[INFO|2026-01-03 20:14:23] logging.py:143 >> {'loss': 0.5115, 'learning_rate': 4.9501e-06, 'epoch': 2.39, 'throughput': 857.56} +[INFO|2026-01-03 20:15:05] logging.py:143 >> {'loss': 0.3663, 'learning_rate': 4.8083e-06, 'epoch': 2.40, 'throughput': 856.67} +[INFO|2026-01-03 20:15:39] logging.py:143 >> {'loss': 0.4918, 'learning_rate': 4.6684e-06, 'epoch': 2.41, 'throughput': 856.82} +[INFO|2026-01-03 20:16:13] logging.py:143 >> {'loss': 0.4168, 'learning_rate': 4.5303e-06, 'epoch': 2.42, 'throughput': 856.92} +[INFO|2026-01-03 20:16:47] logging.py:143 >> {'loss': 0.4658, 'learning_rate': 4.3941e-06, 'epoch': 2.43, 'throughput': 857.11} +[INFO|2026-01-03 20:17:21] logging.py:143 >> {'loss': 0.4081, 'learning_rate': 4.2598e-06, 'epoch': 2.44, 'throughput': 857.20} +[INFO|2026-01-03 20:17:54] logging.py:143 >> {'loss': 0.4739, 'learning_rate': 4.1274e-06, 'epoch': 2.45, 'throughput': 857.23} +[INFO|2026-01-03 20:18:29] logging.py:143 >> {'loss': 0.3149, 'learning_rate': 3.9969e-06, 'epoch': 2.45, 'throughput': 857.50} +[INFO|2026-01-03 20:19:02] logging.py:143 >> {'loss': 0.5650, 'learning_rate': 3.8683e-06, 'epoch': 2.46, 'throughput': 857.55} +[INFO|2026-01-03 20:19:34] logging.py:143 >> {'loss': 0.4656, 'learning_rate': 3.7416e-06, 'epoch': 2.47, 'throughput': 857.47} +[INFO|2026-01-03 20:20:07] logging.py:143 >> {'loss': 0.4552, 'learning_rate': 3.6169e-06, 'epoch': 2.48, 'throughput': 857.44} +[INFO|2026-01-03 20:20:41] logging.py:143 >> {'loss': 0.4571, 'learning_rate': 3.4941e-06, 'epoch': 2.49, 'throughput': 857.63} +[INFO|2026-01-03 20:21:13] logging.py:143 >> {'loss': 0.5344, 'learning_rate': 3.3733e-06, 'epoch': 2.50, 'throughput': 857.46} +[INFO|2026-01-03 20:21:46] logging.py:143 >> {'loss': 0.5010, 'learning_rate': 3.2545e-06, 'epoch': 2.51, 'throughput': 857.44} +[INFO|2026-01-03 20:22:20] logging.py:143 >> {'loss': 0.5723, 'learning_rate': 3.1376e-06, 'epoch': 2.52, 'throughput': 857.51} +[INFO|2026-01-03 20:22:52] logging.py:143 >> {'loss': 0.5347, 'learning_rate': 3.0227e-06, 'epoch': 2.53, 'throughput': 857.49} +[INFO|2026-01-03 20:23:25] logging.py:143 >> {'loss': 0.4727, 'learning_rate': 2.9099e-06, 'epoch': 2.54, 'throughput': 857.44} +[INFO|2026-01-03 20:23:58] logging.py:143 >> {'loss': 0.6187, 'learning_rate': 2.7990e-06, 'epoch': 2.55, 'throughput': 857.44} +[INFO|2026-01-03 20:24:31] logging.py:143 >> {'loss': 0.5945, 'learning_rate': 2.6902e-06, 'epoch': 2.56, 'throughput': 857.44} +[INFO|2026-01-03 20:24:31] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1400 +[INFO|2026-01-03 20:24:31] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 20:24:31] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 20:24:31] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1400/chat_template.jinja +[INFO|2026-01-03 20:24:31] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1400/tokenizer_config.json +[INFO|2026-01-03 20:24:31] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1400/special_tokens_map.json +[INFO|2026-01-03 20:25:06] logging.py:143 >> {'loss': 0.5123, 'learning_rate': 2.5835e-06, 'epoch': 2.56, 'throughput': 857.49} +[INFO|2026-01-03 20:25:39] logging.py:143 >> {'loss': 0.4564, 'learning_rate': 2.4787e-06, 'epoch': 2.57, 'throughput': 857.52} +[INFO|2026-01-03 20:26:11] logging.py:143 >> {'loss': 0.5329, 'learning_rate': 2.3761e-06, 'epoch': 2.58, 'throughput': 857.44} +[INFO|2026-01-03 20:26:44] logging.py:143 >> {'loss': 0.5803, 'learning_rate': 2.2755e-06, 'epoch': 2.59, 'throughput': 857.36} +[INFO|2026-01-03 20:27:18] logging.py:143 >> {'loss': 0.4759, 'learning_rate': 2.1769e-06, 'epoch': 2.60, 'throughput': 857.53} +[INFO|2026-01-03 20:27:51] logging.py:143 >> {'loss': 0.4964, 'learning_rate': 2.0805e-06, 'epoch': 2.61, 'throughput': 857.44} +[INFO|2026-01-03 20:28:23] logging.py:143 >> {'loss': 0.4652, 'learning_rate': 1.9861e-06, 'epoch': 2.62, 'throughput': 857.43} +[INFO|2026-01-03 20:28:55] logging.py:143 >> {'loss': 0.5859, 'learning_rate': 1.8939e-06, 'epoch': 2.63, 'throughput': 857.30} +[INFO|2026-01-03 20:29:28] logging.py:143 >> {'loss': 0.6222, 'learning_rate': 1.8037e-06, 'epoch': 2.64, 'throughput': 857.27} +[INFO|2026-01-03 20:30:01] logging.py:143 >> {'loss': 0.3722, 'learning_rate': 1.7157e-06, 'epoch': 2.65, 'throughput': 857.22} +[INFO|2026-01-03 20:30:34] logging.py:143 >> {'loss': 0.5299, 'learning_rate': 1.6298e-06, 'epoch': 2.66, 'throughput': 857.23} +[INFO|2026-01-03 20:31:06] logging.py:143 >> {'loss': 0.4470, 'learning_rate': 1.5460e-06, 'epoch': 2.66, 'throughput': 857.12} +[INFO|2026-01-03 20:31:39] logging.py:143 >> {'loss': 0.3965, 'learning_rate': 1.4644e-06, 'epoch': 2.67, 'throughput': 857.14} +[INFO|2026-01-03 20:32:13] logging.py:143 >> {'loss': 0.4579, 'learning_rate': 1.3849e-06, 'epoch': 2.68, 'throughput': 857.25} +[INFO|2026-01-03 20:32:46] logging.py:143 >> {'loss': 0.5361, 'learning_rate': 1.3076e-06, 'epoch': 2.69, 'throughput': 857.23} +[INFO|2026-01-03 20:33:20] logging.py:143 >> {'loss': 0.4439, 'learning_rate': 1.2325e-06, 'epoch': 2.70, 'throughput': 857.38} +[INFO|2026-01-03 20:33:52] logging.py:143 >> {'loss': 0.3843, 'learning_rate': 1.1595e-06, 'epoch': 2.71, 'throughput': 857.30} +[INFO|2026-01-03 20:34:25] logging.py:143 >> {'loss': 0.4191, 'learning_rate': 1.0887e-06, 'epoch': 2.72, 'throughput': 857.21} +[INFO|2026-01-03 20:34:56] logging.py:143 >> {'loss': 0.4898, 'learning_rate': 1.0200e-06, 'epoch': 2.73, 'throughput': 857.05} +[INFO|2026-01-03 20:35:29] logging.py:143 >> {'loss': 0.4288, 'learning_rate': 9.5359e-07, 'epoch': 2.74, 'throughput': 857.00} +[INFO|2026-01-03 20:35:29] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1500 +[INFO|2026-01-03 20:35:29] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 20:35:29] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 20:35:30] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1500/chat_template.jinja +[INFO|2026-01-03 20:35:30] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1500/tokenizer_config.json +[INFO|2026-01-03 20:35:30] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1500/special_tokens_map.json +[INFO|2026-01-03 20:36:03] logging.py:143 >> {'loss': 0.4114, 'learning_rate': 8.8935e-07, 'epoch': 2.75, 'throughput': 856.85} +[INFO|2026-01-03 20:36:35] logging.py:143 >> {'loss': 0.4987, 'learning_rate': 8.2730e-07, 'epoch': 2.76, 'throughput': 856.68} +[INFO|2026-01-03 20:49:25] logging.py:143 >> {'loss': 0.4648, 'learning_rate': 7.6746e-07, 'epoch': 2.77, 'throughput': 798.02} +[INFO|2026-01-03 20:49:57] logging.py:143 >> {'loss': 0.5213, 'learning_rate': 7.0984e-07, 'epoch': 2.77, 'throughput': 798.11} +[INFO|2026-01-03 20:50:30] logging.py:143 >> {'loss': 0.4990, 'learning_rate': 6.5443e-07, 'epoch': 2.78, 'throughput': 798.29} +[INFO|2026-01-03 20:51:04] logging.py:143 >> {'loss': 0.4285, 'learning_rate': 6.0125e-07, 'epoch': 2.79, 'throughput': 798.47} +[INFO|2026-01-03 20:51:36] logging.py:143 >> {'loss': 0.4615, 'learning_rate': 5.5029e-07, 'epoch': 2.80, 'throughput': 798.61} +[INFO|2026-01-03 20:52:09] logging.py:143 >> {'loss': 0.4648, 'learning_rate': 5.0156e-07, 'epoch': 2.81, 'throughput': 798.77} +[INFO|2026-01-03 20:52:41] logging.py:143 >> {'loss': 0.4858, 'learning_rate': 4.5508e-07, 'epoch': 2.82, 'throughput': 798.76} +[INFO|2026-01-03 20:53:14] logging.py:143 >> {'loss': 0.4944, 'learning_rate': 4.1083e-07, 'epoch': 2.83, 'throughput': 798.92} +[INFO|2026-01-03 20:53:45] logging.py:143 >> {'loss': 0.4598, 'learning_rate': 3.6883e-07, 'epoch': 2.84, 'throughput': 798.90} +[INFO|2026-01-03 20:54:19] logging.py:143 >> {'loss': 0.4981, 'learning_rate': 3.2907e-07, 'epoch': 2.85, 'throughput': 799.16} +[INFO|2026-01-03 20:54:51] logging.py:143 >> {'loss': 0.5183, 'learning_rate': 2.9157e-07, 'epoch': 2.86, 'throughput': 799.31} +[INFO|2026-01-03 20:55:25] logging.py:143 >> {'loss': 0.4789, 'learning_rate': 2.5632e-07, 'epoch': 2.87, 'throughput': 799.60} +[INFO|2026-01-03 20:55:57] logging.py:143 >> {'loss': 0.4666, 'learning_rate': 2.2333e-07, 'epoch': 2.87, 'throughput': 799.65} +[INFO|2026-01-03 20:56:32] logging.py:143 >> {'loss': 0.4199, 'learning_rate': 1.9261e-07, 'epoch': 2.88, 'throughput': 800.12} +[INFO|2026-01-03 20:57:06] logging.py:143 >> {'loss': 0.4318, 'learning_rate': 1.6415e-07, 'epoch': 2.89, 'throughput': 800.36} +[INFO|2026-01-03 20:57:40] logging.py:143 >> {'loss': 0.3600, 'learning_rate': 1.3795e-07, 'epoch': 2.90, 'throughput': 800.67} +[INFO|2026-01-03 20:58:13] logging.py:143 >> {'loss': 0.4392, 'learning_rate': 1.1403e-07, 'epoch': 2.91, 'throughput': 800.81} +[INFO|2026-01-03 20:58:47] logging.py:143 >> {'loss': 0.4489, 'learning_rate': 9.2377e-08, 'epoch': 2.92, 'throughput': 801.10} +[INFO|2026-01-03 20:58:47] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1600 +[INFO|2026-01-03 20:58:47] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 20:58:47] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 20:58:47] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1600/chat_template.jinja +[INFO|2026-01-03 20:58:47] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1600/tokenizer_config.json +[INFO|2026-01-03 20:58:47] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1600/special_tokens_map.json +[INFO|2026-01-03 20:59:22] logging.py:143 >> {'loss': 0.5492, 'learning_rate': 7.2999e-08, 'epoch': 2.93, 'throughput': 801.33} +[INFO|2026-01-03 20:59:56] logging.py:143 >> {'loss': 0.5030, 'learning_rate': 5.5896e-08, 'epoch': 2.94, 'throughput': 801.57} +[INFO|2026-01-03 21:00:30] logging.py:143 >> {'loss': 0.4689, 'learning_rate': 4.1070e-08, 'epoch': 2.95, 'throughput': 801.85} +[INFO|2026-01-03 21:01:03] logging.py:143 >> {'loss': 0.5420, 'learning_rate': 2.8524e-08, 'epoch': 2.96, 'throughput': 801.98} +[INFO|2026-01-03 21:01:36] logging.py:143 >> {'loss': 0.3969, 'learning_rate': 1.8256e-08, 'epoch': 2.97, 'throughput': 802.24} +[INFO|2026-01-03 21:02:09] logging.py:143 >> {'loss': 0.4960, 'learning_rate': 1.0270e-08, 'epoch': 2.98, 'throughput': 802.42} +[INFO|2026-01-03 21:02:42] logging.py:143 >> {'loss': 0.5585, 'learning_rate': 4.5645e-09, 'epoch': 2.98, 'throughput': 802.55} +[INFO|2026-01-03 21:03:16] logging.py:143 >> {'loss': 0.4553, 'learning_rate': 1.1412e-09, 'epoch': 2.99, 'throughput': 802.80} +[INFO|2026-01-03 21:03:40] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1644 +[INFO|2026-01-03 21:03:40] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 21:03:40] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 21:03:41] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1644/chat_template.jinja +[INFO|2026-01-03 21:03:41] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1644/tokenizer_config.json +[INFO|2026-01-03 21:03:41] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/checkpoint-1644/special_tokens_map.json +[INFO|2026-01-03 21:03:42] trainer.py:2718 >> + +Training completed. Do not forget to share your model on huggingface.co/models =) + + +[INFO|2026-01-03 21:03:42] trainer.py:4074 >> Saving model checkpoint to saves/Qwen3-1.7B-Base/lora/train_2026-01-03 +[INFO|2026-01-03 21:03:42] configuration_utils.py:750 >> loading configuration file /root/autodl-tmp/models/modelscope_cache/models/Qwen/Qwen3-1___7B-Base/config.json +[INFO|2026-01-03 21:03:42] configuration_utils.py:817 >> Model config Qwen3Config { + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.55.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} + +[INFO|2026-01-03 21:03:42] tokenization_utils_base.py:2393 >> chat template saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/chat_template.jinja +[INFO|2026-01-03 21:03:42] tokenization_utils_base.py:2562 >> tokenizer config file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/tokenizer_config.json +[INFO|2026-01-03 21:03:42] tokenization_utils_base.py:2571 >> Special tokens file saved in saves/Qwen3-1.7B-Base/lora/train_2026-01-03/special_tokens_map.json +[WARNING|2026-01-03 21:03:42] logging.py:148 >> No metric eval_loss to plot. +[WARNING|2026-01-03 21:03:42] logging.py:148 >> No metric eval_accuracy to plot. +[INFO|2026-01-03 21:03:42] modelcard.py:456 >> Dropping the following result as it does not have all the necessary fields: +{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}} diff --git a/train_2026-01-03/special_tokens_map.json b/train_2026-01-03/special_tokens_map.json new file mode 100644 index 0000000..17305b3 --- /dev/null +++ b/train_2026-01-03/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/train_2026-01-03/tokenizer.json b/train_2026-01-03/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/train_2026-01-03/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/train_2026-01-03/tokenizer_config.json b/train_2026-01-03/tokenizer_config.json new file mode 100644 index 0000000..e6a51d3 --- /dev/null +++ b/train_2026-01-03/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_2026-01-03/train_results.json b/train_2026-01-03/train_results.json new file mode 100644 index 0000000..7c9317e --- /dev/null +++ b/train_2026-01-03/train_results.json @@ -0,0 +1,9 @@ +{ + "epoch": 3.0, + "num_input_tokens_seen": 9328224, + "total_flos": 8.278651518536909e+16, + "train_loss": 0.7471618294860904, + "train_runtime": 11618.0265, + "train_samples_per_second": 2.263, + "train_steps_per_second": 0.142 +} \ No newline at end of file diff --git a/train_2026-01-03/trainer_log.jsonl b/train_2026-01-03/trainer_log.jsonl new file mode 100644 index 0000000..94cacfa --- /dev/null +++ b/train_2026-01-03/trainer_log.jsonl @@ -0,0 +1,329 @@ +{"current_steps": 5, "total_steps": 1644, "loss": 1.469, "lr": 4.999926966182812e-05, "epoch": 0.00913033553983109, "percentage": 0.3, "elapsed_time": "0:00:37", "remaining_time": "3:24:07", "throughput": 834.18, "total_tokens": 31168} +{"current_steps": 10, "total_steps": 1644, "loss": 1.5127, "lr": 4.999630273613799e-05, "epoch": 0.01826067107966218, "percentage": 0.61, "elapsed_time": "0:01:10", "remaining_time": "3:11:28", "throughput": 839.03, "total_tokens": 58992} +{"current_steps": 15, "total_steps": 1644, "loss": 1.44, "lr": 4.999105384744215e-05, "epoch": 0.027391006619493265, "percentage": 0.91, "elapsed_time": "0:01:43", "remaining_time": "3:07:04", "throughput": 844.64, "total_tokens": 87296} +{"current_steps": 20, "total_steps": 1644, "loss": 1.4987, "lr": 4.998352347492226e-05, "epoch": 0.03652134215932436, "percentage": 1.22, "elapsed_time": "0:02:16", "remaining_time": "3:04:06", "throughput": 842.78, "total_tokens": 114656} +{"current_steps": 25, "total_steps": 1644, "loss": 1.4058, "lr": 4.9973712306041256e-05, "epoch": 0.045651677699155443, "percentage": 1.52, "elapsed_time": "0:02:49", "remaining_time": "3:02:49", "throughput": 847.67, "total_tokens": 143584} +{"current_steps": 30, "total_steps": 1644, "loss": 1.4049, "lr": 4.996162123648058e-05, "epoch": 0.05478201323898653, "percentage": 1.82, "elapsed_time": "0:03:22", "remaining_time": "3:01:35", "throughput": 850.44, "total_tokens": 172224} +{"current_steps": 35, "total_steps": 1644, "loss": 1.4239, "lr": 4.99472513700584e-05, "epoch": 0.06391234877881762, "percentage": 2.13, "elapsed_time": "0:03:55", "remaining_time": "3:00:22", "throughput": 850.7, "total_tokens": 200272} +{"current_steps": 40, "total_steps": 1644, "loss": 1.389, "lr": 4.993060401862888e-05, "epoch": 0.07304268431864872, "percentage": 2.43, "elapsed_time": "0:04:27", "remaining_time": "2:59:03", "throughput": 849.34, "total_tokens": 227552} +{"current_steps": 45, "total_steps": 1644, "loss": 1.3187, "lr": 4.9911680701962384e-05, "epoch": 0.0821730198584798, "percentage": 2.74, "elapsed_time": "0:05:01", "remaining_time": "2:58:17", "throughput": 851.42, "total_tokens": 256320} +{"current_steps": 50, "total_steps": 1644, "loss": 1.31, "lr": 4.989048314760674e-05, "epoch": 0.09130335539831089, "percentage": 3.04, "elapsed_time": "0:05:35", "remaining_time": "2:58:03", "throughput": 856.96, "total_tokens": 287184} +{"current_steps": 55, "total_steps": 1644, "loss": 1.3295, "lr": 4.9867013290729535e-05, "epoch": 0.10043369093814197, "percentage": 3.35, "elapsed_time": "0:06:07", "remaining_time": "2:57:04", "throughput": 856.18, "total_tokens": 314864} +{"current_steps": 60, "total_steps": 1644, "loss": 1.2718, "lr": 4.984127327394146e-05, "epoch": 0.10956402647797306, "percentage": 3.65, "elapsed_time": "0:06:40", "remaining_time": "2:56:13", "throughput": 856.16, "total_tokens": 342912} +{"current_steps": 65, "total_steps": 1644, "loss": 1.2547, "lr": 4.981326544710065e-05, "epoch": 0.11869436201780416, "percentage": 3.95, "elapsed_time": "0:07:12", "remaining_time": "2:55:16", "throughput": 854.86, "total_tokens": 370064} +{"current_steps": 70, "total_steps": 1644, "loss": 1.302, "lr": 4.978299236709826e-05, "epoch": 0.12782469755763523, "percentage": 4.26, "elapsed_time": "0:07:46", "remaining_time": "2:54:48", "throughput": 856.68, "total_tokens": 399584} +{"current_steps": 75, "total_steps": 1644, "loss": 1.2328, "lr": 4.975045679762496e-05, "epoch": 0.13695503309746634, "percentage": 4.56, "elapsed_time": "0:08:20", "remaining_time": "2:54:28", "throughput": 860.35, "total_tokens": 430528} +{"current_steps": 80, "total_steps": 1644, "loss": 1.296, "lr": 4.9715661708918624e-05, "epoch": 0.14608536863729743, "percentage": 4.87, "elapsed_time": "0:08:53", "remaining_time": "2:53:57", "throughput": 861.72, "total_tokens": 460080} +{"current_steps": 85, "total_steps": 1644, "loss": 1.3248, "lr": 4.9678610277493275e-05, "epoch": 0.15521570417712852, "percentage": 5.17, "elapsed_time": "0:09:26", "remaining_time": "2:53:18", "throughput": 861.08, "total_tokens": 488176} +{"current_steps": 90, "total_steps": 1644, "loss": 1.207, "lr": 4.9639305885848975e-05, "epoch": 0.1643460397169596, "percentage": 5.47, "elapsed_time": "0:10:00", "remaining_time": "2:52:42", "throughput": 861.29, "total_tokens": 516896} +{"current_steps": 95, "total_steps": 1644, "loss": 1.2342, "lr": 4.959775212216308e-05, "epoch": 0.1734763752567907, "percentage": 5.78, "elapsed_time": "0:10:34", "remaining_time": "2:52:20", "throughput": 863.2, "total_tokens": 547440} +{"current_steps": 100, "total_steps": 1644, "loss": 1.1931, "lr": 4.955395277996268e-05, "epoch": 0.18260671079662177, "percentage": 6.08, "elapsed_time": "0:11:07", "remaining_time": "2:51:50", "throughput": 864.21, "total_tokens": 577088} +{"current_steps": 105, "total_steps": 1644, "loss": 1.2122, "lr": 4.9507911857778256e-05, "epoch": 0.19173704633645286, "percentage": 6.39, "elapsed_time": "0:11:42", "remaining_time": "2:51:38", "throughput": 863.9, "total_tokens": 606976} +{"current_steps": 110, "total_steps": 1644, "loss": 1.2973, "lr": 4.9459633558778684e-05, "epoch": 0.20086738187628395, "percentage": 6.69, "elapsed_time": "0:12:15", "remaining_time": "2:50:52", "throughput": 862.94, "total_tokens": 634416} +{"current_steps": 115, "total_steps": 1644, "loss": 1.2483, "lr": 4.940912229038745e-05, "epoch": 0.20999771741611503, "percentage": 7.0, "elapsed_time": "0:12:47", "remaining_time": "2:49:59", "throughput": 860.58, "total_tokens": 660192} +{"current_steps": 120, "total_steps": 1644, "loss": 1.1153, "lr": 4.9356382663880366e-05, "epoch": 0.21912805295594612, "percentage": 7.3, "elapsed_time": "0:13:19", "remaining_time": "2:49:19", "throughput": 859.99, "total_tokens": 687936} +{"current_steps": 125, "total_steps": 1644, "loss": 1.2269, "lr": 4.930141949396454e-05, "epoch": 0.22825838849577723, "percentage": 7.6, "elapsed_time": "0:13:53", "remaining_time": "2:48:45", "throughput": 860.43, "total_tokens": 716960} +{"current_steps": 130, "total_steps": 1644, "loss": 1.1324, "lr": 4.9244237798338866e-05, "epoch": 0.23738872403560832, "percentage": 7.91, "elapsed_time": "0:14:26", "remaining_time": "2:48:07", "throughput": 860.09, "total_tokens": 744976} +{"current_steps": 135, "total_steps": 1644, "loss": 1.1818, "lr": 4.918484279723592e-05, "epoch": 0.2465190595754394, "percentage": 8.21, "elapsed_time": "0:14:58", "remaining_time": "2:47:25", "throughput": 859.22, "total_tokens": 772176} +{"current_steps": 140, "total_steps": 1644, "loss": 1.1243, "lr": 4.9123239912945423e-05, "epoch": 0.25564939511527046, "percentage": 8.52, "elapsed_time": "0:15:33", "remaining_time": "2:47:07", "throughput": 861.88, "total_tokens": 804528} +{"current_steps": 145, "total_steps": 1644, "loss": 1.2134, "lr": 4.9059434769319205e-05, "epoch": 0.2647797306551016, "percentage": 8.82, "elapsed_time": "0:16:05", "remaining_time": "2:46:22", "throughput": 860.64, "total_tokens": 831056} +{"current_steps": 150, "total_steps": 1644, "loss": 1.0775, "lr": 4.899343319125781e-05, "epoch": 0.2739100661949327, "percentage": 9.12, "elapsed_time": "0:16:39", "remaining_time": "2:45:59", "throughput": 862.5, "total_tokens": 862416} +{"current_steps": 155, "total_steps": 1644, "loss": 1.2069, "lr": 4.892524120417872e-05, "epoch": 0.28304040173476375, "percentage": 9.43, "elapsed_time": "0:17:12", "remaining_time": "2:45:14", "throughput": 861.61, "total_tokens": 889264} +{"current_steps": 160, "total_steps": 1644, "loss": 1.1649, "lr": 4.8854865033466275e-05, "epoch": 0.29217073727459486, "percentage": 9.73, "elapsed_time": "0:17:44", "remaining_time": "2:44:35", "throughput": 861.33, "total_tokens": 917104} +{"current_steps": 165, "total_steps": 1644, "loss": 1.1495, "lr": 4.878231110390337e-05, "epoch": 0.3013010728144259, "percentage": 10.04, "elapsed_time": "0:18:18", "remaining_time": "2:44:06", "throughput": 862.32, "total_tokens": 947280} +{"current_steps": 170, "total_steps": 1644, "loss": 1.1231, "lr": 4.870758603908489e-05, "epoch": 0.31043140835425703, "percentage": 10.34, "elapsed_time": "0:18:52", "remaining_time": "2:43:41", "throughput": 864.0, "total_tokens": 978704} +{"current_steps": 175, "total_steps": 1644, "loss": 1.0885, "lr": 4.863069666081307e-05, "epoch": 0.3195617438940881, "percentage": 10.64, "elapsed_time": "0:19:25", "remaining_time": "2:43:00", "throughput": 863.35, "total_tokens": 1005904} +{"current_steps": 180, "total_steps": 1644, "loss": 1.1022, "lr": 4.855164998847466e-05, "epoch": 0.3286920794339192, "percentage": 10.95, "elapsed_time": "0:19:58", "remaining_time": "2:42:25", "throughput": 863.43, "total_tokens": 1034624} +{"current_steps": 185, "total_steps": 1644, "loss": 1.1223, "lr": 4.8470453238400195e-05, "epoch": 0.33782241497375026, "percentage": 11.25, "elapsed_time": "0:20:29", "remaining_time": "2:41:36", "throughput": 861.53, "total_tokens": 1059280} +{"current_steps": 190, "total_steps": 1644, "loss": 1.0287, "lr": 4.8387113823205096e-05, "epoch": 0.3469527505135814, "percentage": 11.56, "elapsed_time": "0:21:03", "remaining_time": "2:41:05", "throughput": 862.14, "total_tokens": 1088960} +{"current_steps": 195, "total_steps": 1644, "loss": 1.1138, "lr": 4.8301639351113065e-05, "epoch": 0.3560830860534125, "percentage": 11.86, "elapsed_time": "0:21:34", "remaining_time": "2:40:17", "throughput": 860.49, "total_tokens": 1113712} +{"current_steps": 200, "total_steps": 1644, "loss": 1.1149, "lr": 4.821403762526143e-05, "epoch": 0.36521342159324355, "percentage": 12.17, "elapsed_time": "0:22:06", "remaining_time": "2:39:40", "throughput": 860.36, "total_tokens": 1141696} +{"current_steps": 205, "total_steps": 1644, "loss": 1.1954, "lr": 4.812431664298883e-05, "epoch": 0.37434375713307466, "percentage": 12.47, "elapsed_time": "0:22:42", "remaining_time": "2:39:21", "throughput": 860.43, "total_tokens": 1172000} +{"current_steps": 210, "total_steps": 1644, "loss": 1.0426, "lr": 4.803248459510511e-05, "epoch": 0.3834740926729057, "percentage": 12.77, "elapsed_time": "0:23:15", "remaining_time": "2:38:48", "throughput": 860.83, "total_tokens": 1201136} +{"current_steps": 215, "total_steps": 1644, "loss": 1.2254, "lr": 4.7938549865143544e-05, "epoch": 0.39260442821273683, "percentage": 13.08, "elapsed_time": "0:23:47", "remaining_time": "2:38:08", "throughput": 860.08, "total_tokens": 1227792} +{"current_steps": 220, "total_steps": 1644, "loss": 1.0323, "lr": 4.7842521028595526e-05, "epoch": 0.4017347637525679, "percentage": 13.38, "elapsed_time": "0:24:21", "remaining_time": "2:37:39", "throughput": 860.93, "total_tokens": 1258240} +{"current_steps": 225, "total_steps": 1644, "loss": 0.9971, "lr": 4.7744406852127653e-05, "epoch": 0.410865099292399, "percentage": 13.69, "elapsed_time": "0:24:55", "remaining_time": "2:37:13", "throughput": 862.28, "total_tokens": 1289744} +{"current_steps": 230, "total_steps": 1644, "loss": 1.0328, "lr": 4.764421629278144e-05, "epoch": 0.41999543483223006, "percentage": 13.99, "elapsed_time": "0:25:27", "remaining_time": "2:36:29", "throughput": 861.03, "total_tokens": 1315040} +{"current_steps": 235, "total_steps": 1644, "loss": 1.0546, "lr": 4.754195849715557e-05, "epoch": 0.4291257703720612, "percentage": 14.29, "elapsed_time": "0:26:00", "remaining_time": "2:35:58", "throughput": 861.65, "total_tokens": 1344848} +{"current_steps": 240, "total_steps": 1644, "loss": 1.1701, "lr": 4.743764280057092e-05, "epoch": 0.43825610591189224, "percentage": 14.6, "elapsed_time": "0:26:33", "remaining_time": "2:35:19", "throughput": 861.08, "total_tokens": 1371728} +{"current_steps": 245, "total_steps": 1644, "loss": 1.0949, "lr": 4.73312787262183e-05, "epoch": 0.44738644145172335, "percentage": 14.9, "elapsed_time": "0:27:05", "remaining_time": "2:34:41", "throughput": 860.64, "total_tokens": 1398896} +{"current_steps": 250, "total_steps": 1644, "loss": 1.1142, "lr": 4.722287598428907e-05, "epoch": 0.45651677699155446, "percentage": 15.21, "elapsed_time": "0:27:37", "remaining_time": "2:34:02", "throughput": 859.97, "total_tokens": 1425376} +{"current_steps": 255, "total_steps": 1644, "loss": 1.0364, "lr": 4.711244447108866e-05, "epoch": 0.4656471125313855, "percentage": 15.51, "elapsed_time": "0:28:09", "remaining_time": "2:33:24", "throughput": 859.48, "total_tokens": 1452416} +{"current_steps": 260, "total_steps": 1644, "loss": 1.0669, "lr": 4.6999994268133166e-05, "epoch": 0.47477744807121663, "percentage": 15.82, "elapsed_time": "0:28:42", "remaining_time": "2:32:51", "throughput": 859.84, "total_tokens": 1481440} +{"current_steps": 265, "total_steps": 1644, "loss": 1.007, "lr": 4.6885535641228904e-05, "epoch": 0.4839077836110477, "percentage": 16.12, "elapsed_time": "0:29:16", "remaining_time": "2:32:18", "throughput": 859.99, "total_tokens": 1510240} +{"current_steps": 270, "total_steps": 1644, "loss": 0.9444, "lr": 4.676907903953531e-05, "epoch": 0.4930381191508788, "percentage": 16.42, "elapsed_time": "0:29:48", "remaining_time": "2:31:43", "throughput": 859.86, "total_tokens": 1538208} +{"current_steps": 275, "total_steps": 1644, "loss": 1.0157, "lr": 4.665063509461097e-05, "epoch": 0.5021684546907099, "percentage": 16.73, "elapsed_time": "0:30:21", "remaining_time": "2:31:10", "throughput": 859.98, "total_tokens": 1566880} +{"current_steps": 280, "total_steps": 1644, "loss": 1.0188, "lr": 4.6530214619443037e-05, "epoch": 0.5112987902305409, "percentage": 17.03, "elapsed_time": "0:30:54", "remaining_time": "2:30:33", "throughput": 859.53, "total_tokens": 1593904} +{"current_steps": 285, "total_steps": 1644, "loss": 0.9333, "lr": 4.640782860746011e-05, "epoch": 0.520429125770372, "percentage": 17.34, "elapsed_time": "0:31:27", "remaining_time": "2:29:58", "throughput": 859.24, "total_tokens": 1621440} +{"current_steps": 290, "total_steps": 1644, "loss": 0.9435, "lr": 4.628348823152863e-05, "epoch": 0.5295594613102032, "percentage": 17.64, "elapsed_time": "0:32:00", "remaining_time": "2:29:25", "throughput": 859.31, "total_tokens": 1650064} +{"current_steps": 295, "total_steps": 1644, "loss": 0.9418, "lr": 4.615720484293286e-05, "epoch": 0.5386897968500343, "percentage": 17.94, "elapsed_time": "0:32:32", "remaining_time": "2:28:49", "throughput": 859.02, "total_tokens": 1677472} +{"current_steps": 300, "total_steps": 1644, "loss": 0.9934, "lr": 4.602898997033861e-05, "epoch": 0.5478201323898654, "percentage": 18.25, "elapsed_time": "0:33:06", "remaining_time": "2:28:18", "throughput": 859.28, "total_tokens": 1706672} +{"current_steps": 305, "total_steps": 1644, "loss": 1.0952, "lr": 4.58988553187408e-05, "epoch": 0.5569504679296964, "percentage": 18.55, "elapsed_time": "0:33:40", "remaining_time": "2:27:48", "throughput": 858.69, "total_tokens": 1734704} +{"current_steps": 310, "total_steps": 1644, "loss": 0.9632, "lr": 4.576681276839483e-05, "epoch": 0.5660808034695275, "percentage": 18.86, "elapsed_time": "0:34:13", "remaining_time": "2:27:15", "throughput": 858.75, "total_tokens": 1763312} +{"current_steps": 315, "total_steps": 1644, "loss": 0.931, "lr": 4.5632874373732035e-05, "epoch": 0.5752111390093586, "percentage": 19.16, "elapsed_time": "0:34:45", "remaining_time": "2:26:38", "throughput": 858.17, "total_tokens": 1789616} +{"current_steps": 320, "total_steps": 1644, "loss": 1.0103, "lr": 4.549705236225922e-05, "epoch": 0.5843414745491897, "percentage": 19.46, "elapsed_time": "0:35:18", "remaining_time": "2:26:04", "throughput": 858.16, "total_tokens": 1817760} +{"current_steps": 325, "total_steps": 1644, "loss": 0.9518, "lr": 4.5359359133442356e-05, "epoch": 0.5934718100890207, "percentage": 19.77, "elapsed_time": "0:35:50", "remaining_time": "2:25:29", "throughput": 858.08, "total_tokens": 1845664} +{"current_steps": 330, "total_steps": 1644, "loss": 0.8974, "lr": 4.521980725757466e-05, "epoch": 0.6026021456288518, "percentage": 20.07, "elapsed_time": "0:36:24", "remaining_time": "2:24:58", "throughput": 858.47, "total_tokens": 1875392} +{"current_steps": 335, "total_steps": 1644, "loss": 0.9171, "lr": 4.5078409474628966e-05, "epoch": 0.611732481168683, "percentage": 20.38, "elapsed_time": "0:36:57", "remaining_time": "2:24:23", "throughput": 858.14, "total_tokens": 1902592} +{"current_steps": 340, "total_steps": 1644, "loss": 0.899, "lr": 4.4935178693094714e-05, "epoch": 0.6208628167085141, "percentage": 20.68, "elapsed_time": "0:37:30", "remaining_time": "2:23:50", "throughput": 858.26, "total_tokens": 1931328} +{"current_steps": 345, "total_steps": 1644, "loss": 0.8964, "lr": 4.4790127988799494e-05, "epoch": 0.6299931522483452, "percentage": 20.99, "elapsed_time": "0:38:03", "remaining_time": "2:23:18", "throughput": 858.48, "total_tokens": 1960528} +{"current_steps": 350, "total_steps": 1644, "loss": 1.0919, "lr": 4.464327060371529e-05, "epoch": 0.6391234877881762, "percentage": 21.29, "elapsed_time": "0:38:35", "remaining_time": "2:22:42", "throughput": 858.03, "total_tokens": 1987168} +{"current_steps": 355, "total_steps": 1644, "loss": 1.0469, "lr": 4.449461994474968e-05, "epoch": 0.6482538233280073, "percentage": 21.59, "elapsed_time": "0:39:08", "remaining_time": "2:22:08", "throughput": 857.86, "total_tokens": 2014832} +{"current_steps": 360, "total_steps": 1644, "loss": 0.8841, "lr": 4.434418958252179e-05, "epoch": 0.6573841588678384, "percentage": 21.9, "elapsed_time": "0:39:42", "remaining_time": "2:21:35", "throughput": 858.02, "total_tokens": 2043840} +{"current_steps": 365, "total_steps": 1644, "loss": 1.0016, "lr": 4.4191993250123483e-05, "epoch": 0.6665144944076695, "percentage": 22.2, "elapsed_time": "0:40:15", "remaining_time": "2:21:04", "throughput": 858.21, "total_tokens": 2073120} +{"current_steps": 370, "total_steps": 1644, "loss": 0.9584, "lr": 4.4038044841865614e-05, "epoch": 0.6756448299475005, "percentage": 22.51, "elapsed_time": "0:40:47", "remaining_time": "2:20:26", "throughput": 857.44, "total_tokens": 2098384} +{"current_steps": 375, "total_steps": 1644, "loss": 0.9964, "lr": 4.388235841200956e-05, "epoch": 0.6847751654873316, "percentage": 22.81, "elapsed_time": "0:41:20", "remaining_time": "2:19:53", "throughput": 857.55, "total_tokens": 2127008} +{"current_steps": 380, "total_steps": 1644, "loss": 0.9808, "lr": 4.3724948173484216e-05, "epoch": 0.6939055010271628, "percentage": 23.11, "elapsed_time": "0:41:52", "remaining_time": "2:19:18", "throughput": 857.4, "total_tokens": 2154624} +{"current_steps": 385, "total_steps": 1644, "loss": 0.9126, "lr": 4.356582849658845e-05, "epoch": 0.7030358365669939, "percentage": 23.42, "elapsed_time": "0:42:26", "remaining_time": "2:18:48", "throughput": 857.82, "total_tokens": 2184768} +{"current_steps": 390, "total_steps": 1644, "loss": 0.8749, "lr": 4.340501390767924e-05, "epoch": 0.712166172106825, "percentage": 23.72, "elapsed_time": "0:43:00", "remaining_time": "2:18:17", "throughput": 858.1, "total_tokens": 2214336} +{"current_steps": 395, "total_steps": 1644, "loss": 0.9203, "lr": 4.324251908784546e-05, "epoch": 0.721296507646656, "percentage": 24.03, "elapsed_time": "0:43:33", "remaining_time": "2:17:44", "throughput": 858.29, "total_tokens": 2243296} +{"current_steps": 400, "total_steps": 1644, "loss": 0.8857, "lr": 4.3078358871567706e-05, "epoch": 0.7304268431864871, "percentage": 24.33, "elapsed_time": "0:44:07", "remaining_time": "2:17:13", "throughput": 858.7, "total_tokens": 2273424} +{"current_steps": 405, "total_steps": 1644, "loss": 0.9175, "lr": 4.291254824536396e-05, "epoch": 0.7395571787263182, "percentage": 24.64, "elapsed_time": "0:44:42", "remaining_time": "2:16:45", "throughput": 858.62, "total_tokens": 2303040} +{"current_steps": 410, "total_steps": 1644, "loss": 0.9572, "lr": 4.274510234642148e-05, "epoch": 0.7486875142661493, "percentage": 24.94, "elapsed_time": "0:45:14", "remaining_time": "2:16:10", "throughput": 858.42, "total_tokens": 2330352} +{"current_steps": 415, "total_steps": 1644, "loss": 1.0534, "lr": 4.257603646121484e-05, "epoch": 0.7578178498059803, "percentage": 25.24, "elapsed_time": "0:45:47", "remaining_time": "2:15:35", "throughput": 858.3, "total_tokens": 2357968} +{"current_steps": 420, "total_steps": 1644, "loss": 0.8583, "lr": 4.240536602411048e-05, "epoch": 0.7669481853458114, "percentage": 25.55, "elapsed_time": "0:46:20", "remaining_time": "2:15:03", "throughput": 858.4, "total_tokens": 2386800} +{"current_steps": 425, "total_steps": 1644, "loss": 0.8049, "lr": 4.22331066159576e-05, "epoch": 0.7760785208856426, "percentage": 25.85, "elapsed_time": "0:46:53", "remaining_time": "2:14:30", "throughput": 858.68, "total_tokens": 2416224} +{"current_steps": 430, "total_steps": 1644, "loss": 0.9599, "lr": 4.205927396266577e-05, "epoch": 0.7852088564254737, "percentage": 26.16, "elapsed_time": "0:47:27", "remaining_time": "2:13:58", "throughput": 858.76, "total_tokens": 2445120} +{"current_steps": 435, "total_steps": 1644, "loss": 0.8874, "lr": 4.188388393376933e-05, "epoch": 0.7943391919653047, "percentage": 26.46, "elapsed_time": "0:48:00", "remaining_time": "2:13:25", "throughput": 858.73, "total_tokens": 2473312} +{"current_steps": 440, "total_steps": 1644, "loss": 0.8944, "lr": 4.1706952540978545e-05, "epoch": 0.8034695275051358, "percentage": 26.76, "elapsed_time": "0:48:32", "remaining_time": "2:12:50", "throughput": 858.55, "total_tokens": 2500800} +{"current_steps": 445, "total_steps": 1644, "loss": 0.9774, "lr": 4.152849593671793e-05, "epoch": 0.8125998630449669, "percentage": 27.07, "elapsed_time": "0:49:05", "remaining_time": "2:12:17", "throughput": 858.61, "total_tokens": 2529392} +{"current_steps": 450, "total_steps": 1644, "loss": 0.8543, "lr": 4.134853041265162e-05, "epoch": 0.821730198584798, "percentage": 27.37, "elapsed_time": "0:49:39", "remaining_time": "2:11:45", "throughput": 859.04, "total_tokens": 2559536} +{"current_steps": 455, "total_steps": 1644, "loss": 0.8293, "lr": 4.11670723981961e-05, "epoch": 0.8308605341246291, "percentage": 27.68, "elapsed_time": "0:50:12", "remaining_time": "2:11:12", "throughput": 859.07, "total_tokens": 2588144} +{"current_steps": 460, "total_steps": 1644, "loss": 0.9264, "lr": 4.098413845902033e-05, "epoch": 0.8399908696644601, "percentage": 27.98, "elapsed_time": "0:50:46", "remaining_time": "2:10:41", "throughput": 859.36, "total_tokens": 2617968} +{"current_steps": 465, "total_steps": 1644, "loss": 0.9641, "lr": 4.079974529553341e-05, "epoch": 0.8491212052042912, "percentage": 28.28, "elapsed_time": "0:51:19", "remaining_time": "2:10:08", "throughput": 859.44, "total_tokens": 2646896} +{"current_steps": 470, "total_steps": 1644, "loss": 0.805, "lr": 4.061390974135997e-05, "epoch": 0.8582515407441224, "percentage": 28.59, "elapsed_time": "0:51:52", "remaining_time": "2:09:33", "throughput": 859.28, "total_tokens": 2674288} +{"current_steps": 475, "total_steps": 1644, "loss": 1.0411, "lr": 4.042664876180341e-05, "epoch": 0.8673818762839535, "percentage": 28.89, "elapsed_time": "0:52:24", "remaining_time": "2:08:57", "throughput": 858.91, "total_tokens": 2700464} +{"current_steps": 480, "total_steps": 1644, "loss": 0.8638, "lr": 4.0237979452297094e-05, "epoch": 0.8765122118237845, "percentage": 29.2, "elapsed_time": "0:52:58", "remaining_time": "2:08:27", "throughput": 859.55, "total_tokens": 2732112} +{"current_steps": 485, "total_steps": 1644, "loss": 1.0152, "lr": 4.0047919036843675e-05, "epoch": 0.8856425473636156, "percentage": 29.5, "elapsed_time": "0:53:30", "remaining_time": "2:07:51", "throughput": 859.07, "total_tokens": 2757872} +{"current_steps": 490, "total_steps": 1644, "loss": 0.9046, "lr": 3.985648486644267e-05, "epoch": 0.8947728829034467, "percentage": 29.81, "elapsed_time": "0:54:03", "remaining_time": "2:07:18", "throughput": 859.04, "total_tokens": 2786192} +{"current_steps": 495, "total_steps": 1644, "loss": 0.8428, "lr": 3.966369441750648e-05, "epoch": 0.9039032184432778, "percentage": 30.11, "elapsed_time": "0:54:35", "remaining_time": "2:06:42", "throughput": 858.64, "total_tokens": 2812368} +{"current_steps": 500, "total_steps": 1644, "loss": 0.8138, "lr": 3.9469565290264906e-05, "epoch": 0.9130335539831089, "percentage": 30.41, "elapsed_time": "0:55:08", "remaining_time": "2:06:09", "throughput": 858.66, "total_tokens": 2840912} +{"current_steps": 505, "total_steps": 1644, "loss": 0.8349, "lr": 3.92741152071584e-05, "epoch": 0.9221638895229399, "percentage": 30.72, "elapsed_time": "0:55:43", "remaining_time": "2:05:40", "throughput": 858.45, "total_tokens": 2870000} +{"current_steps": 510, "total_steps": 1644, "loss": 0.883, "lr": 3.907736201122014e-05, "epoch": 0.931294225062771, "percentage": 31.02, "elapsed_time": "0:56:16", "remaining_time": "2:05:07", "throughput": 858.66, "total_tokens": 2899328} +{"current_steps": 515, "total_steps": 1644, "loss": 0.8141, "lr": 3.8879323664447096e-05, "epoch": 0.9404245606026022, "percentage": 31.33, "elapsed_time": "0:56:50", "remaining_time": "2:04:35", "throughput": 858.89, "total_tokens": 2928832} +{"current_steps": 520, "total_steps": 1644, "loss": 0.8964, "lr": 3.8680018246160295e-05, "epoch": 0.9495548961424333, "percentage": 31.63, "elapsed_time": "0:57:22", "remaining_time": "2:04:01", "throughput": 858.74, "total_tokens": 2956352} +{"current_steps": 525, "total_steps": 1644, "loss": 0.7845, "lr": 3.8479463951354245e-05, "epoch": 0.9586852316822643, "percentage": 31.93, "elapsed_time": "0:57:55", "remaining_time": "2:03:28", "throughput": 858.79, "total_tokens": 2985072} +{"current_steps": 530, "total_steps": 1644, "loss": 0.9675, "lr": 3.827767908903592e-05, "epoch": 0.9678155672220954, "percentage": 32.24, "elapsed_time": "0:58:28", "remaining_time": "2:02:55", "throughput": 858.76, "total_tokens": 3013200} +{"current_steps": 535, "total_steps": 1644, "loss": 0.9429, "lr": 3.8074682080553335e-05, "epoch": 0.9769459027619265, "percentage": 32.54, "elapsed_time": "0:59:02", "remaining_time": "2:02:23", "throughput": 859.21, "total_tokens": 3044064} +{"current_steps": 540, "total_steps": 1644, "loss": 0.9034, "lr": 3.7870491457913714e-05, "epoch": 0.9860762383017576, "percentage": 32.85, "elapsed_time": "0:59:35", "remaining_time": "2:01:49", "throughput": 858.95, "total_tokens": 3071008} +{"current_steps": 545, "total_steps": 1644, "loss": 0.8696, "lr": 3.7665125862091765e-05, "epoch": 0.9952065738415887, "percentage": 33.15, "elapsed_time": "1:00:08", "remaining_time": "2:01:17", "throughput": 859.09, "total_tokens": 3100256} +{"current_steps": 550, "total_steps": 1644, "loss": 0.9914, "lr": 3.7458604041327874e-05, "epoch": 1.0036521342159324, "percentage": 33.45, "elapsed_time": "1:00:38", "remaining_time": "2:00:37", "throughput": 858.83, "total_tokens": 3125104} +{"current_steps": 555, "total_steps": 1644, "loss": 0.7924, "lr": 3.725094484941654e-05, "epoch": 1.0127824697557635, "percentage": 33.76, "elapsed_time": "1:01:11", "remaining_time": "2:00:04", "throughput": 858.78, "total_tokens": 3153200} +{"current_steps": 560, "total_steps": 1644, "loss": 0.7542, "lr": 3.704216724398515e-05, "epoch": 1.0219128052955946, "percentage": 34.06, "elapsed_time": "1:01:44", "remaining_time": "1:59:30", "throughput": 858.67, "total_tokens": 3180768} +{"current_steps": 565, "total_steps": 1644, "loss": 0.7216, "lr": 3.683229028476334e-05, "epoch": 1.0310431408354257, "percentage": 34.37, "elapsed_time": "1:02:16", "remaining_time": "1:58:56", "throughput": 858.51, "total_tokens": 3208032} +{"current_steps": 570, "total_steps": 1644, "loss": 0.8276, "lr": 3.6621333131842994e-05, "epoch": 1.0401734763752568, "percentage": 34.67, "elapsed_time": "1:02:49", "remaining_time": "1:58:22", "throughput": 858.31, "total_tokens": 3235216} +{"current_steps": 575, "total_steps": 1644, "loss": 0.8081, "lr": 3.640931504392902e-05, "epoch": 1.049303811915088, "percentage": 34.98, "elapsed_time": "1:03:22", "remaining_time": "1:57:49", "throughput": 858.44, "total_tokens": 3264128} +{"current_steps": 580, "total_steps": 1644, "loss": 0.7503, "lr": 3.6196255376581254e-05, "epoch": 1.058434147454919, "percentage": 35.28, "elapsed_time": "1:03:54", "remaining_time": "1:57:14", "throughput": 858.31, "total_tokens": 3291488} +{"current_steps": 585, "total_steps": 1644, "loss": 0.7449, "lr": 3.598217358044743e-05, "epoch": 1.0675644829947502, "percentage": 35.58, "elapsed_time": "1:04:28", "remaining_time": "1:56:42", "throughput": 858.46, "total_tokens": 3320544} +{"current_steps": 590, "total_steps": 1644, "loss": 0.7779, "lr": 3.576708919948747e-05, "epoch": 1.076694818534581, "percentage": 35.89, "elapsed_time": "1:05:01", "remaining_time": "1:56:10", "throughput": 858.72, "total_tokens": 3350544} +{"current_steps": 595, "total_steps": 1644, "loss": 0.7257, "lr": 3.5551021869189286e-05, "epoch": 1.0858251540744122, "percentage": 36.19, "elapsed_time": "1:05:35", "remaining_time": "1:55:38", "throughput": 859.04, "total_tokens": 3380800} +{"current_steps": 600, "total_steps": 1644, "loss": 0.7348, "lr": 3.533399131477624e-05, "epoch": 1.0949554896142433, "percentage": 36.5, "elapsed_time": "1:06:08", "remaining_time": "1:55:05", "throughput": 859.01, "total_tokens": 3408976} +{"current_steps": 605, "total_steps": 1644, "loss": 0.814, "lr": 3.511601734940636e-05, "epoch": 1.1040858251540744, "percentage": 36.8, "elapsed_time": "1:06:42", "remaining_time": "1:54:33", "throughput": 858.8, "total_tokens": 3437392} +{"current_steps": 610, "total_steps": 1644, "loss": 0.6645, "lr": 3.489711987236357e-05, "epoch": 1.1132161606939055, "percentage": 37.1, "elapsed_time": "1:07:15", "remaining_time": "1:54:00", "throughput": 858.74, "total_tokens": 3465184} +{"current_steps": 615, "total_steps": 1644, "loss": 0.7804, "lr": 3.467731886724104e-05, "epoch": 1.1223464962337366, "percentage": 37.41, "elapsed_time": "1:07:48", "remaining_time": "1:53:26", "throughput": 858.73, "total_tokens": 3493520} +{"current_steps": 620, "total_steps": 1644, "loss": 0.8645, "lr": 3.445663440011685e-05, "epoch": 1.1314768317735677, "percentage": 37.71, "elapsed_time": "1:08:20", "remaining_time": "1:52:52", "throughput": 858.48, "total_tokens": 3520400} +{"current_steps": 625, "total_steps": 1644, "loss": 0.7509, "lr": 3.42350866177221e-05, "epoch": 1.1406071673133988, "percentage": 38.02, "elapsed_time": "1:08:54", "remaining_time": "1:52:20", "throughput": 858.7, "total_tokens": 3550208} +{"current_steps": 630, "total_steps": 1644, "loss": 0.738, "lr": 3.4012695745601694e-05, "epoch": 1.1497375028532297, "percentage": 38.32, "elapsed_time": "1:09:27", "remaining_time": "1:51:48", "throughput": 858.81, "total_tokens": 3579424} +{"current_steps": 635, "total_steps": 1644, "loss": 0.731, "lr": 3.378948208626792e-05, "epoch": 1.158867838393061, "percentage": 38.63, "elapsed_time": "1:10:01", "remaining_time": "1:51:15", "throughput": 858.83, "total_tokens": 3608096} +{"current_steps": 640, "total_steps": 1644, "loss": 0.6878, "lr": 3.356546601734692e-05, "epoch": 1.167998173932892, "percentage": 38.93, "elapsed_time": "1:10:34", "remaining_time": "1:50:42", "throughput": 858.79, "total_tokens": 3636352} +{"current_steps": 645, "total_steps": 1644, "loss": 0.6777, "lr": 3.3340667989718494e-05, "epoch": 1.177128509472723, "percentage": 39.23, "elapsed_time": "1:11:07", "remaining_time": "1:50:09", "throughput": 858.84, "total_tokens": 3665104} +{"current_steps": 650, "total_steps": 1644, "loss": 0.8185, "lr": 3.3115108525648995e-05, "epoch": 1.1862588450125542, "percentage": 39.54, "elapsed_time": "1:11:40", "remaining_time": "1:49:35", "throughput": 858.76, "total_tokens": 3692784} +{"current_steps": 655, "total_steps": 1644, "loss": 0.7367, "lr": 3.288880821691785e-05, "epoch": 1.1953891805523853, "percentage": 39.84, "elapsed_time": "1:12:12", "remaining_time": "1:49:02", "throughput": 858.67, "total_tokens": 3720544} +{"current_steps": 660, "total_steps": 1644, "loss": 0.7812, "lr": 3.2661787722937705e-05, "epoch": 1.2045195160922164, "percentage": 40.15, "elapsed_time": "1:12:45", "remaining_time": "1:48:29", "throughput": 858.63, "total_tokens": 3748640} +{"current_steps": 665, "total_steps": 1644, "loss": 0.6602, "lr": 3.2434067768868365e-05, "epoch": 1.2136498516320475, "percentage": 40.45, "elapsed_time": "1:13:19", "remaining_time": "1:47:57", "throughput": 858.96, "total_tokens": 3779312} +{"current_steps": 670, "total_steps": 1644, "loss": 0.7918, "lr": 3.220566914372477e-05, "epoch": 1.2227801871718786, "percentage": 40.75, "elapsed_time": "1:13:52", "remaining_time": "1:47:23", "throughput": 858.9, "total_tokens": 3807232} +{"current_steps": 675, "total_steps": 1644, "loss": 0.6596, "lr": 3.1976612698479104e-05, "epoch": 1.2319105227117095, "percentage": 41.06, "elapsed_time": "1:14:25", "remaining_time": "1:46:50", "throughput": 858.9, "total_tokens": 3835568} +{"current_steps": 680, "total_steps": 1644, "loss": 0.595, "lr": 3.174691934415727e-05, "epoch": 1.2410408582515409, "percentage": 41.36, "elapsed_time": "1:14:59", "remaining_time": "1:46:18", "throughput": 859.24, "total_tokens": 3866240} +{"current_steps": 685, "total_steps": 1644, "loss": 0.7421, "lr": 3.151661004992992e-05, "epoch": 1.2501711937913718, "percentage": 41.67, "elapsed_time": "1:15:32", "remaining_time": "1:45:45", "throughput": 859.23, "total_tokens": 3894400} +{"current_steps": 690, "total_steps": 1644, "loss": 0.8241, "lr": 3.128570584119806e-05, "epoch": 1.2593015293312029, "percentage": 41.97, "elapsed_time": "1:16:03", "remaining_time": "1:45:09", "throughput": 858.6, "total_tokens": 3917984} +{"current_steps": 695, "total_steps": 1644, "loss": 0.7889, "lr": 3.105422779767369e-05, "epoch": 1.268431864871034, "percentage": 42.27, "elapsed_time": "1:16:35", "remaining_time": "1:44:34", "throughput": 858.29, "total_tokens": 3943952} +{"current_steps": 700, "total_steps": 1644, "loss": 0.8462, "lr": 3.08221970514553e-05, "epoch": 1.277562200410865, "percentage": 42.58, "elapsed_time": "1:17:07", "remaining_time": "1:44:00", "throughput": 858.12, "total_tokens": 3970976} +{"current_steps": 705, "total_steps": 1644, "loss": 0.8064, "lr": 3.058963478509879e-05, "epoch": 1.2866925359506962, "percentage": 42.88, "elapsed_time": "1:17:41", "remaining_time": "1:43:28", "throughput": 857.86, "total_tokens": 3998816} +{"current_steps": 710, "total_steps": 1644, "loss": 0.7113, "lr": 3.0356562229683534e-05, "epoch": 1.2958228714905273, "percentage": 43.19, "elapsed_time": "1:18:13", "remaining_time": "1:42:54", "throughput": 857.75, "total_tokens": 4026144} +{"current_steps": 715, "total_steps": 1644, "loss": 0.7086, "lr": 3.0123000662874272e-05, "epoch": 1.3049532070303584, "percentage": 43.49, "elapsed_time": "1:18:46", "remaining_time": "1:42:20", "throughput": 857.58, "total_tokens": 4053232} +{"current_steps": 720, "total_steps": 1644, "loss": 0.6923, "lr": 2.9888971406978584e-05, "epoch": 1.3140835425701893, "percentage": 43.8, "elapsed_time": "1:19:19", "remaining_time": "1:41:47", "throughput": 857.53, "total_tokens": 4080992} +{"current_steps": 725, "total_steps": 1644, "loss": 0.7034, "lr": 2.965449582700031e-05, "epoch": 1.3232138781100207, "percentage": 44.1, "elapsed_time": "1:19:52", "remaining_time": "1:41:14", "throughput": 857.46, "total_tokens": 4108944} +{"current_steps": 730, "total_steps": 1644, "loss": 0.7029, "lr": 2.9419595328689138e-05, "epoch": 1.3323442136498516, "percentage": 44.4, "elapsed_time": "1:20:25", "remaining_time": "1:40:41", "throughput": 857.55, "total_tokens": 4137872} +{"current_steps": 735, "total_steps": 1644, "loss": 0.7442, "lr": 2.918429135658638e-05, "epoch": 1.3414745491896827, "percentage": 44.71, "elapsed_time": "1:20:58", "remaining_time": "1:40:08", "throughput": 857.69, "total_tokens": 4167120} +{"current_steps": 740, "total_steps": 1644, "loss": 0.6896, "lr": 2.8948605392067322e-05, "epoch": 1.3506048847295138, "percentage": 45.01, "elapsed_time": "1:21:32", "remaining_time": "1:39:36", "throughput": 857.92, "total_tokens": 4197456} +{"current_steps": 745, "total_steps": 1644, "loss": 0.7188, "lr": 2.8712558951380097e-05, "epoch": 1.359735220269345, "percentage": 45.32, "elapsed_time": "1:22:06", "remaining_time": "1:39:04", "throughput": 858.05, "total_tokens": 4226784} +{"current_steps": 750, "total_steps": 1644, "loss": 0.7536, "lr": 2.847617358368142e-05, "epoch": 1.368865555809176, "percentage": 45.62, "elapsed_time": "1:22:40", "remaining_time": "1:38:32", "throughput": 858.33, "total_tokens": 4257552} +{"current_steps": 755, "total_steps": 1644, "loss": 0.6742, "lr": 2.8239470869069357e-05, "epoch": 1.3779958913490071, "percentage": 45.92, "elapsed_time": "1:23:13", "remaining_time": "1:37:59", "throughput": 858.27, "total_tokens": 4285344} +{"current_steps": 760, "total_steps": 1644, "loss": 0.6787, "lr": 2.800247241661321e-05, "epoch": 1.3871262268888382, "percentage": 46.23, "elapsed_time": "1:23:46", "remaining_time": "1:37:26", "throughput": 858.28, "total_tokens": 4313920} +{"current_steps": 765, "total_steps": 1644, "loss": 0.8232, "lr": 2.776519986238079e-05, "epoch": 1.3962565624286691, "percentage": 46.53, "elapsed_time": "1:24:18", "remaining_time": "1:36:52", "throughput": 858.22, "total_tokens": 4341584} +{"current_steps": 770, "total_steps": 1644, "loss": 0.7529, "lr": 2.75276748674632e-05, "epoch": 1.4053868979685005, "percentage": 46.84, "elapsed_time": "1:24:51", "remaining_time": "1:36:19", "throughput": 858.1, "total_tokens": 4369072} +{"current_steps": 775, "total_steps": 1644, "loss": 0.7612, "lr": 2.7289919115997374e-05, "epoch": 1.4145172335083314, "percentage": 47.14, "elapsed_time": "1:25:24", "remaining_time": "1:35:45", "throughput": 858.08, "total_tokens": 4397152} +{"current_steps": 780, "total_steps": 1644, "loss": 0.777, "lr": 2.7051954313186484e-05, "epoch": 1.4236475690481625, "percentage": 47.45, "elapsed_time": "1:25:56", "remaining_time": "1:35:11", "throughput": 857.8, "total_tokens": 4423120} +{"current_steps": 785, "total_steps": 1644, "loss": 0.7732, "lr": 2.6813802183318404e-05, "epoch": 1.4327779045879936, "percentage": 47.75, "elapsed_time": "1:26:29", "remaining_time": "1:34:38", "throughput": 857.81, "total_tokens": 4451328} +{"current_steps": 790, "total_steps": 1644, "loss": 0.6874, "lr": 2.6575484467782486e-05, "epoch": 1.4419082401278247, "percentage": 48.05, "elapsed_time": "1:27:02", "remaining_time": "1:34:05", "throughput": 857.88, "total_tokens": 4480256} +{"current_steps": 795, "total_steps": 1644, "loss": 0.6866, "lr": 2.633702292308473e-05, "epoch": 1.4510385756676558, "percentage": 48.36, "elapsed_time": "1:27:35", "remaining_time": "1:33:32", "throughput": 858.01, "total_tokens": 4509584} +{"current_steps": 800, "total_steps": 1644, "loss": 0.6184, "lr": 2.60984393188616e-05, "epoch": 1.460168911207487, "percentage": 48.66, "elapsed_time": "1:28:08", "remaining_time": "1:32:59", "throughput": 857.91, "total_tokens": 4537136} +{"current_steps": 805, "total_steps": 1644, "loss": 0.6364, "lr": 2.5859755435892597e-05, "epoch": 1.469299246747318, "percentage": 48.97, "elapsed_time": "1:28:42", "remaining_time": "1:32:27", "throughput": 857.71, "total_tokens": 4565424} +{"current_steps": 810, "total_steps": 1644, "loss": 0.7312, "lr": 2.5620993064111902e-05, "epoch": 1.478429582287149, "percentage": 49.27, "elapsed_time": "1:29:15", "remaining_time": "1:31:54", "throughput": 857.63, "total_tokens": 4592976} +{"current_steps": 815, "total_steps": 1644, "loss": 0.6735, "lr": 2.538217400061907e-05, "epoch": 1.4875599178269803, "percentage": 49.57, "elapsed_time": "1:29:48", "remaining_time": "1:31:21", "throughput": 857.79, "total_tokens": 4622416} +{"current_steps": 820, "total_steps": 1644, "loss": 0.5681, "lr": 2.5143320047689173e-05, "epoch": 1.4966902533668112, "percentage": 49.88, "elapsed_time": "1:30:21", "remaining_time": "1:30:47", "throughput": 857.56, "total_tokens": 4648848} +{"current_steps": 825, "total_steps": 1644, "loss": 0.7154, "lr": 2.49044530107824e-05, "epoch": 1.5058205889066423, "percentage": 50.18, "elapsed_time": "1:30:53", "remaining_time": "1:30:13", "throughput": 857.25, "total_tokens": 4674688} +{"current_steps": 830, "total_steps": 1644, "loss": 0.659, "lr": 2.4665594696553428e-05, "epoch": 1.5149509244464734, "percentage": 50.49, "elapsed_time": "1:31:24", "remaining_time": "1:29:39", "throughput": 856.95, "total_tokens": 4700240} +{"current_steps": 835, "total_steps": 1644, "loss": 0.66, "lr": 2.4426766910860585e-05, "epoch": 1.5240812599863045, "percentage": 50.79, "elapsed_time": "1:31:58", "remaining_time": "1:29:06", "throughput": 857.08, "total_tokens": 4729648} +{"current_steps": 840, "total_steps": 1644, "loss": 0.8048, "lr": 2.4187991456775217e-05, "epoch": 1.5332115955261356, "percentage": 51.09, "elapsed_time": "1:32:31", "remaining_time": "1:28:33", "throughput": 857.23, "total_tokens": 4758944} +{"current_steps": 845, "total_steps": 1644, "loss": 0.6516, "lr": 2.3949290132591197e-05, "epoch": 1.5423419310659665, "percentage": 51.4, "elapsed_time": "1:33:04", "remaining_time": "1:28:00", "throughput": 857.24, "total_tokens": 4787360} +{"current_steps": 850, "total_steps": 1644, "loss": 0.6813, "lr": 2.3710684729834954e-05, "epoch": 1.5514722666057978, "percentage": 51.7, "elapsed_time": "1:33:37", "remaining_time": "1:27:27", "throughput": 857.25, "total_tokens": 4815712} +{"current_steps": 855, "total_steps": 1644, "loss": 0.7308, "lr": 2.3472197031276e-05, "epoch": 1.5606026021456287, "percentage": 52.01, "elapsed_time": "1:34:11", "remaining_time": "1:26:54", "throughput": 857.41, "total_tokens": 4845280} +{"current_steps": 860, "total_steps": 1644, "loss": 0.7728, "lr": 2.3233848808938453e-05, "epoch": 1.56973293768546, "percentage": 52.31, "elapsed_time": "1:34:44", "remaining_time": "1:26:21", "throughput": 857.47, "total_tokens": 4873936} +{"current_steps": 865, "total_steps": 1644, "loss": 0.6673, "lr": 2.299566182211333e-05, "epoch": 1.578863273225291, "percentage": 52.62, "elapsed_time": "1:35:16", "remaining_time": "1:25:48", "throughput": 857.38, "total_tokens": 4901104} +{"current_steps": 870, "total_steps": 1644, "loss": 0.7155, "lr": 2.275765781537215e-05, "epoch": 1.587993608765122, "percentage": 52.92, "elapsed_time": "1:35:49", "remaining_time": "1:25:15", "throughput": 857.4, "total_tokens": 4929696} +{"current_steps": 875, "total_steps": 1644, "loss": 0.6372, "lr": 2.251985851658181e-05, "epoch": 1.5971239443049532, "percentage": 53.22, "elapsed_time": "1:36:23", "remaining_time": "1:24:42", "throughput": 857.54, "total_tokens": 4959408} +{"current_steps": 880, "total_steps": 1644, "loss": 0.7021, "lr": 2.228228563492098e-05, "epoch": 1.6062542798447843, "percentage": 53.53, "elapsed_time": "1:36:56", "remaining_time": "1:24:09", "throughput": 857.66, "total_tokens": 4988800} +{"current_steps": 885, "total_steps": 1644, "loss": 0.6923, "lr": 2.2044960858898277e-05, "epoch": 1.6153846153846154, "percentage": 53.83, "elapsed_time": "1:37:30", "remaining_time": "1:23:37", "throughput": 857.84, "total_tokens": 5018752} +{"current_steps": 890, "total_steps": 1644, "loss": 0.6426, "lr": 2.1807905854372242e-05, "epoch": 1.6245149509244463, "percentage": 54.14, "elapsed_time": "1:38:03", "remaining_time": "1:23:04", "throughput": 857.93, "total_tokens": 5047792} +{"current_steps": 895, "total_steps": 1644, "loss": 0.5618, "lr": 2.1571142262573457e-05, "epoch": 1.6336452864642776, "percentage": 54.44, "elapsed_time": "1:38:36", "remaining_time": "1:22:31", "throughput": 857.97, "total_tokens": 5076528} +{"current_steps": 900, "total_steps": 1644, "loss": 0.616, "lr": 2.133469169812879e-05, "epoch": 1.6427756220041085, "percentage": 54.74, "elapsed_time": "1:39:08", "remaining_time": "1:21:57", "throughput": 857.64, "total_tokens": 5101504} +{"current_steps": 905, "total_steps": 1644, "loss": 0.6574, "lr": 2.109857574708826e-05, "epoch": 1.6519059575439399, "percentage": 55.05, "elapsed_time": "1:39:42", "remaining_time": "1:21:24", "throughput": 857.4, "total_tokens": 5129104} +{"current_steps": 910, "total_steps": 1644, "loss": 0.6823, "lr": 2.086281596495434e-05, "epoch": 1.6610362930837708, "percentage": 55.35, "elapsed_time": "1:40:14", "remaining_time": "1:20:51", "throughput": 857.31, "total_tokens": 5156640} +{"current_steps": 915, "total_steps": 1644, "loss": 0.5728, "lr": 2.0627433874714115e-05, "epoch": 1.6701666286236019, "percentage": 55.66, "elapsed_time": "1:40:47", "remaining_time": "1:20:18", "throughput": 857.31, "total_tokens": 5184848} +{"current_steps": 920, "total_steps": 1644, "loss": 0.7025, "lr": 2.0392450964874415e-05, "epoch": 1.679296964163433, "percentage": 55.96, "elapsed_time": "1:41:20", "remaining_time": "1:19:45", "throughput": 857.28, "total_tokens": 5212928} +{"current_steps": 925, "total_steps": 1644, "loss": 0.5986, "lr": 2.015788868750009e-05, "epoch": 1.688427299703264, "percentage": 56.27, "elapsed_time": "1:41:54", "remaining_time": "1:19:12", "throughput": 857.53, "total_tokens": 5243568} +{"current_steps": 930, "total_steps": 1644, "loss": 0.6195, "lr": 1.9923768456255594e-05, "epoch": 1.6975576352430952, "percentage": 56.57, "elapsed_time": "1:42:26", "remaining_time": "1:18:39", "throughput": 857.32, "total_tokens": 5269840} +{"current_steps": 935, "total_steps": 1644, "loss": 0.6283, "lr": 1.969011164445011e-05, "epoch": 1.7066879707829261, "percentage": 56.87, "elapsed_time": "1:43:00", "remaining_time": "1:18:06", "throughput": 857.41, "total_tokens": 5299120} +{"current_steps": 940, "total_steps": 1644, "loss": 0.5767, "lr": 1.9456939583086303e-05, "epoch": 1.7158183063227574, "percentage": 57.18, "elapsed_time": "1:43:33", "remaining_time": "1:17:33", "throughput": 857.51, "total_tokens": 5328464} +{"current_steps": 945, "total_steps": 1644, "loss": 0.5237, "lr": 1.9224273558913024e-05, "epoch": 1.7249486418625883, "percentage": 57.48, "elapsed_time": "1:44:05", "remaining_time": "1:17:00", "throughput": 857.34, "total_tokens": 5354896} +{"current_steps": 950, "total_steps": 1644, "loss": 0.7184, "lr": 1.8992134812481915e-05, "epoch": 1.7340789774024197, "percentage": 57.79, "elapsed_time": "1:44:39", "remaining_time": "1:16:27", "throughput": 857.4, "total_tokens": 5383856} +{"current_steps": 955, "total_steps": 1644, "loss": 0.6595, "lr": 1.876054453620841e-05, "epoch": 1.7432093129422506, "percentage": 58.09, "elapsed_time": "1:45:12", "remaining_time": "1:15:54", "throughput": 857.47, "total_tokens": 5412864} +{"current_steps": 960, "total_steps": 1644, "loss": 0.6161, "lr": 1.852952387243698e-05, "epoch": 1.7523396484820817, "percentage": 58.39, "elapsed_time": "1:45:45", "remaining_time": "1:15:21", "throughput": 857.5, "total_tokens": 5441392} +{"current_steps": 965, "total_steps": 1644, "loss": 0.6076, "lr": 1.829909391151103e-05, "epoch": 1.7614699840219128, "percentage": 58.7, "elapsed_time": "1:46:19", "remaining_time": "1:14:48", "throughput": 857.63, "total_tokens": 5470928} +{"current_steps": 970, "total_steps": 1644, "loss": 0.5543, "lr": 1.8069275689847466e-05, "epoch": 1.770600319561744, "percentage": 59.0, "elapsed_time": "1:46:52", "remaining_time": "1:14:15", "throughput": 857.76, "total_tokens": 5500576} +{"current_steps": 975, "total_steps": 1644, "loss": 0.6496, "lr": 1.784009018801634e-05, "epoch": 1.779730655101575, "percentage": 59.31, "elapsed_time": "1:47:25", "remaining_time": "1:13:42", "throughput": 857.7, "total_tokens": 5528288} +{"current_steps": 980, "total_steps": 1644, "loss": 0.6315, "lr": 1.7611558328825384e-05, "epoch": 1.788860990641406, "percentage": 59.61, "elapsed_time": "1:47:58", "remaining_time": "1:13:09", "throughput": 857.79, "total_tokens": 5557472} +{"current_steps": 985, "total_steps": 1644, "loss": 0.5654, "lr": 1.738370097541e-05, "epoch": 1.7979913261812372, "percentage": 59.91, "elapsed_time": "1:48:31", "remaining_time": "1:12:36", "throughput": 857.71, "total_tokens": 5585120} +{"current_steps": 990, "total_steps": 1644, "loss": 0.5803, "lr": 1.7156538929328593e-05, "epoch": 1.8071216617210681, "percentage": 60.22, "elapsed_time": "1:49:04", "remaining_time": "1:12:03", "throughput": 857.74, "total_tokens": 5613760} +{"current_steps": 995, "total_steps": 1644, "loss": 0.5516, "lr": 1.6930092928663532e-05, "epoch": 1.8162519972608995, "percentage": 60.52, "elapsed_time": "1:49:38", "remaining_time": "1:11:30", "throughput": 857.88, "total_tokens": 5643504} +{"current_steps": 1000, "total_steps": 1644, "loss": 0.653, "lr": 1.6704383646127973e-05, "epoch": 1.8253823328007304, "percentage": 60.83, "elapsed_time": "1:50:11", "remaining_time": "1:10:57", "throughput": 857.9, "total_tokens": 5671936} +{"current_steps": 1005, "total_steps": 1644, "loss": 0.6456, "lr": 1.6479431687178584e-05, "epoch": 1.8345126683405615, "percentage": 61.13, "elapsed_time": "1:50:46", "remaining_time": "1:10:25", "throughput": 857.82, "total_tokens": 5701200} +{"current_steps": 1010, "total_steps": 1644, "loss": 0.6778, "lr": 1.6255257588134426e-05, "epoch": 1.8436430038803926, "percentage": 61.44, "elapsed_time": "1:51:18", "remaining_time": "1:09:52", "throughput": 857.68, "total_tokens": 5728032} +{"current_steps": 1015, "total_steps": 1644, "loss": 0.6779, "lr": 1.603188181430216e-05, "epoch": 1.8527733394202237, "percentage": 61.74, "elapsed_time": "1:51:51", "remaining_time": "1:09:19", "throughput": 857.65, "total_tokens": 5756080} +{"current_steps": 1020, "total_steps": 1644, "loss": 0.5039, "lr": 1.580932475810772e-05, "epoch": 1.8619036749600548, "percentage": 62.04, "elapsed_time": "1:52:25", "remaining_time": "1:08:46", "throughput": 857.77, "total_tokens": 5785760} +{"current_steps": 1025, "total_steps": 1644, "loss": 0.6694, "lr": 1.5587606737234654e-05, "epoch": 1.8710340104998857, "percentage": 62.35, "elapsed_time": "1:52:57", "remaining_time": "1:08:13", "throughput": 857.78, "total_tokens": 5813936} +{"current_steps": 1030, "total_steps": 1644, "loss": 0.5749, "lr": 1.5366747992769287e-05, "epoch": 1.880164346039717, "percentage": 62.65, "elapsed_time": "1:53:31", "remaining_time": "1:07:40", "throughput": 857.95, "total_tokens": 5844128} +{"current_steps": 1035, "total_steps": 1644, "loss": 0.5602, "lr": 1.5146768687352864e-05, "epoch": 1.889294681579548, "percentage": 62.96, "elapsed_time": "1:54:04", "remaining_time": "1:07:07", "throughput": 857.95, "total_tokens": 5872512} +{"current_steps": 1040, "total_steps": 1644, "loss": 0.645, "lr": 1.4927688903340836e-05, "epoch": 1.8984250171193793, "percentage": 63.26, "elapsed_time": "1:54:37", "remaining_time": "1:06:33", "throughput": 857.78, "total_tokens": 5898992} +{"current_steps": 1045, "total_steps": 1644, "loss": 0.6209, "lr": 1.4709528640969552e-05, "epoch": 1.9075553526592102, "percentage": 63.56, "elapsed_time": "1:55:10", "remaining_time": "1:06:01", "throughput": 858.0, "total_tokens": 5929632} +{"current_steps": 1050, "total_steps": 1644, "loss": 0.5908, "lr": 1.4492307816530375e-05, "epoch": 1.9166856881990413, "percentage": 63.87, "elapsed_time": "1:55:43", "remaining_time": "1:05:28", "throughput": 857.9, "total_tokens": 5956832} +{"current_steps": 1055, "total_steps": 1644, "loss": 0.5957, "lr": 1.4276046260551462e-05, "epoch": 1.9258160237388724, "percentage": 64.17, "elapsed_time": "1:56:16", "remaining_time": "1:04:54", "throughput": 857.91, "total_tokens": 5985104} +{"current_steps": 1060, "total_steps": 1644, "loss": 0.6543, "lr": 1.4060763715987418e-05, "epoch": 1.9349463592787035, "percentage": 64.48, "elapsed_time": "1:56:48", "remaining_time": "1:04:21", "throughput": 857.7, "total_tokens": 6010992} +{"current_steps": 1065, "total_steps": 1644, "loss": 0.5055, "lr": 1.3846479836416929e-05, "epoch": 1.9440766948185346, "percentage": 64.78, "elapsed_time": "1:57:22", "remaining_time": "1:03:48", "throughput": 857.84, "total_tokens": 6041008} +{"current_steps": 1070, "total_steps": 1644, "loss": 0.5246, "lr": 1.3633214184248521e-05, "epoch": 1.9532070303583655, "percentage": 65.09, "elapsed_time": "1:57:55", "remaining_time": "1:03:15", "throughput": 857.97, "total_tokens": 6070832} +{"current_steps": 1075, "total_steps": 1644, "loss": 0.5412, "lr": 1.342098622893469e-05, "epoch": 1.9623373658981969, "percentage": 65.39, "elapsed_time": "1:58:29", "remaining_time": "1:02:42", "throughput": 858.06, "total_tokens": 6100064} +{"current_steps": 1080, "total_steps": 1644, "loss": 0.624, "lr": 1.3209815345194496e-05, "epoch": 1.9714677014380277, "percentage": 65.69, "elapsed_time": "1:59:01", "remaining_time": "1:02:09", "throughput": 857.94, "total_tokens": 6127088} +{"current_steps": 1085, "total_steps": 1644, "loss": 0.5854, "lr": 1.2999720811244767e-05, "epoch": 1.980598036977859, "percentage": 66.0, "elapsed_time": "1:59:34", "remaining_time": "1:01:36", "throughput": 857.89, "total_tokens": 6154768} +{"current_steps": 1090, "total_steps": 1644, "loss": 0.5972, "lr": 1.2790721807040216e-05, "epoch": 1.98972837251769, "percentage": 66.3, "elapsed_time": "2:00:06", "remaining_time": "1:01:02", "throughput": 857.79, "total_tokens": 6181824} +{"current_steps": 1095, "total_steps": 1644, "loss": 0.5627, "lr": 1.2582837412522418e-05, "epoch": 1.998858708057521, "percentage": 66.61, "elapsed_time": "2:00:40", "remaining_time": "1:00:30", "throughput": 857.96, "total_tokens": 6211904} +{"current_steps": 1100, "total_steps": 1644, "loss": 0.544, "lr": 1.2376086605877976e-05, "epoch": 2.0073042684318647, "percentage": 66.91, "elapsed_time": "2:01:10", "remaining_time": "0:59:55", "throughput": 857.97, "total_tokens": 6238272} +{"current_steps": 1105, "total_steps": 1644, "loss": 0.4701, "lr": 1.2170488261805978e-05, "epoch": 2.016434603971696, "percentage": 67.21, "elapsed_time": "2:01:45", "remaining_time": "0:59:23", "throughput": 857.99, "total_tokens": 6268288} +{"current_steps": 1110, "total_steps": 1644, "loss": 0.4359, "lr": 1.1966061149794846e-05, "epoch": 2.025564939511527, "percentage": 67.52, "elapsed_time": "2:02:19", "remaining_time": "0:58:51", "throughput": 858.21, "total_tokens": 6299168} +{"current_steps": 1115, "total_steps": 1644, "loss": 0.4436, "lr": 1.176282393240888e-05, "epoch": 2.0346952750513583, "percentage": 67.82, "elapsed_time": "2:02:53", "remaining_time": "0:58:18", "throughput": 858.35, "total_tokens": 6329296} +{"current_steps": 1120, "total_steps": 1644, "loss": 0.5898, "lr": 1.1560795163584492e-05, "epoch": 2.043825610591189, "percentage": 68.13, "elapsed_time": "2:03:26", "remaining_time": "0:57:45", "throughput": 858.3, "total_tokens": 6356992} +{"current_steps": 1125, "total_steps": 1644, "loss": 0.5882, "lr": 1.1359993286936382e-05, "epoch": 2.0529559461310205, "percentage": 68.43, "elapsed_time": "2:03:58", "remaining_time": "0:57:11", "throughput": 858.05, "total_tokens": 6382256} +{"current_steps": 1130, "total_steps": 1644, "loss": 0.4388, "lr": 1.1160436634073786e-05, "epoch": 2.0620862816708514, "percentage": 68.73, "elapsed_time": "2:04:30", "remaining_time": "0:56:38", "throughput": 858.0, "total_tokens": 6410016} +{"current_steps": 1135, "total_steps": 1644, "loss": 0.5827, "lr": 1.0962143422926929e-05, "epoch": 2.0712166172106823, "percentage": 69.04, "elapsed_time": "2:05:04", "remaining_time": "0:56:05", "throughput": 858.03, "total_tokens": 6438768} +{"current_steps": 1140, "total_steps": 1644, "loss": 0.5261, "lr": 1.0765131756083899e-05, "epoch": 2.0803469527505136, "percentage": 69.34, "elapsed_time": "2:05:36", "remaining_time": "0:55:32", "throughput": 857.97, "total_tokens": 6466400} +{"current_steps": 1145, "total_steps": 1644, "loss": 0.5661, "lr": 1.0569419619138012e-05, "epoch": 2.0894772882903445, "percentage": 69.65, "elapsed_time": "2:06:09", "remaining_time": "0:54:58", "throughput": 857.88, "total_tokens": 6493488} +{"current_steps": 1150, "total_steps": 1644, "loss": 0.538, "lr": 1.0375024879045889e-05, "epoch": 2.098607623830176, "percentage": 69.95, "elapsed_time": "2:06:41", "remaining_time": "0:54:25", "throughput": 857.82, "total_tokens": 6521104} +{"current_steps": 1155, "total_steps": 1644, "loss": 0.7164, "lr": 1.0181965282496289e-05, "epoch": 2.1077379593700067, "percentage": 70.26, "elapsed_time": "2:07:14", "remaining_time": "0:53:52", "throughput": 857.75, "total_tokens": 6548832} +{"current_steps": 1160, "total_steps": 1644, "loss": 0.5611, "lr": 9.990258454290055e-06, "epoch": 2.116868294909838, "percentage": 70.56, "elapsed_time": "2:07:48", "remaining_time": "0:53:19", "throughput": 857.8, "total_tokens": 6577648} +{"current_steps": 1165, "total_steps": 1644, "loss": 0.5341, "lr": 9.799921895731062e-06, "epoch": 2.125998630449669, "percentage": 70.86, "elapsed_time": "2:08:20", "remaining_time": "0:52:46", "throughput": 857.7, "total_tokens": 6604720} +{"current_steps": 1170, "total_steps": 1644, "loss": 0.4899, "lr": 9.610972983028493e-06, "epoch": 2.1351289659895003, "percentage": 71.17, "elapsed_time": "2:08:52", "remaining_time": "0:52:12", "throughput": 857.6, "total_tokens": 6631696} +{"current_steps": 1175, "total_steps": 1644, "loss": 0.6115, "lr": 9.423428965710554e-06, "epoch": 2.144259301529331, "percentage": 71.47, "elapsed_time": "2:09:25", "remaining_time": "0:51:39", "throughput": 857.59, "total_tokens": 6659728} +{"current_steps": 1180, "total_steps": 1644, "loss": 0.5713, "lr": 9.237306965049677e-06, "epoch": 2.153389637069162, "percentage": 71.78, "elapsed_time": "2:09:59", "remaining_time": "0:51:06", "throughput": 857.66, "total_tokens": 6688928} +{"current_steps": 1185, "total_steps": 1644, "loss": 0.5144, "lr": 9.05262397249955e-06, "epoch": 2.1625199726089934, "percentage": 72.08, "elapsed_time": "2:10:32", "remaining_time": "0:50:33", "throughput": 857.7, "total_tokens": 6717488} +{"current_steps": 1190, "total_steps": 1644, "loss": 0.5139, "lr": 8.869396848143893e-06, "epoch": 2.1716503081488243, "percentage": 72.38, "elapsed_time": "2:11:05", "remaining_time": "0:50:00", "throughput": 857.78, "total_tokens": 6746864} +{"current_steps": 1195, "total_steps": 1644, "loss": 0.5763, "lr": 8.687642319157279e-06, "epoch": 2.1807806436886557, "percentage": 72.69, "elapsed_time": "2:11:38", "remaining_time": "0:49:27", "throughput": 857.78, "total_tokens": 6775216} +{"current_steps": 1200, "total_steps": 1644, "loss": 0.5669, "lr": 8.507376978278053e-06, "epoch": 2.1899109792284865, "percentage": 72.99, "elapsed_time": "2:12:12", "remaining_time": "0:48:55", "throughput": 858.01, "total_tokens": 6806496} +{"current_steps": 1205, "total_steps": 1644, "loss": 0.5508, "lr": 8.328617282293591e-06, "epoch": 2.199041314768318, "percentage": 73.3, "elapsed_time": "2:12:47", "remaining_time": "0:48:22", "throughput": 857.95, "total_tokens": 6835744} +{"current_steps": 1210, "total_steps": 1644, "loss": 0.5538, "lr": 8.151379550537894e-06, "epoch": 2.2081716503081488, "percentage": 73.6, "elapsed_time": "2:13:20", "remaining_time": "0:47:49", "throughput": 858.01, "total_tokens": 6864560} +{"current_steps": 1215, "total_steps": 1644, "loss": 0.4806, "lr": 7.975679963401772e-06, "epoch": 2.21730198584798, "percentage": 73.91, "elapsed_time": "2:13:53", "remaining_time": "0:47:16", "throughput": 858.04, "total_tokens": 6893360} +{"current_steps": 1220, "total_steps": 1644, "loss": 0.4594, "lr": 7.801534560855703e-06, "epoch": 2.226432321387811, "percentage": 74.21, "elapsed_time": "2:14:27", "remaining_time": "0:46:43", "throughput": 858.1, "total_tokens": 6922336} +{"current_steps": 1225, "total_steps": 1644, "loss": 0.4625, "lr": 7.628959240985514e-06, "epoch": 2.235562656927642, "percentage": 74.51, "elapsed_time": "2:15:00", "remaining_time": "0:46:10", "throughput": 858.25, "total_tokens": 6952464} +{"current_steps": 1230, "total_steps": 1644, "loss": 0.5248, "lr": 7.457969758541009e-06, "epoch": 2.2446929924674732, "percentage": 74.82, "elapsed_time": "2:15:32", "remaining_time": "0:45:37", "throughput": 858.06, "total_tokens": 6978480} +{"current_steps": 1235, "total_steps": 1644, "loss": 0.5796, "lr": 7.288581723497689e-06, "epoch": 2.253823328007304, "percentage": 75.12, "elapsed_time": "2:16:05", "remaining_time": "0:45:04", "throughput": 858.05, "total_tokens": 7006576} +{"current_steps": 1240, "total_steps": 1644, "loss": 0.4509, "lr": 7.12081059963168e-06, "epoch": 2.2629536635471355, "percentage": 75.43, "elapsed_time": "2:16:38", "remaining_time": "0:44:31", "throughput": 858.04, "total_tokens": 7034848} +{"current_steps": 1245, "total_steps": 1644, "loss": 0.4935, "lr": 6.954671703108034e-06, "epoch": 2.2720839990869663, "percentage": 75.73, "elapsed_time": "2:17:12", "remaining_time": "0:43:58", "throughput": 858.16, "total_tokens": 7064656} +{"current_steps": 1250, "total_steps": 1644, "loss": 0.5073, "lr": 6.790180201082439e-06, "epoch": 2.2812143346267977, "percentage": 76.03, "elapsed_time": "2:17:45", "remaining_time": "0:43:25", "throughput": 858.2, "total_tokens": 7093536} +{"current_steps": 1255, "total_steps": 1644, "loss": 0.4892, "lr": 6.627351110316635e-06, "epoch": 2.2903446701666286, "percentage": 76.34, "elapsed_time": "2:18:19", "remaining_time": "0:42:52", "throughput": 858.22, "total_tokens": 7122352} +{"current_steps": 1260, "total_steps": 1644, "loss": 0.5268, "lr": 6.466199295807471e-06, "epoch": 2.2994750057064595, "percentage": 76.64, "elapsed_time": "2:18:51", "remaining_time": "0:42:19", "throughput": 858.15, "total_tokens": 7149840} +{"current_steps": 1265, "total_steps": 1644, "loss": 0.5226, "lr": 6.306739469429859e-06, "epoch": 2.308605341246291, "percentage": 76.95, "elapsed_time": "2:19:23", "remaining_time": "0:41:45", "throughput": 857.94, "total_tokens": 7175312} +{"current_steps": 1270, "total_steps": 1644, "loss": 0.4098, "lr": 6.1489861885936805e-06, "epoch": 2.317735676786122, "percentage": 77.25, "elapsed_time": "2:19:57", "remaining_time": "0:41:12", "throughput": 858.07, "total_tokens": 7205408} +{"current_steps": 1275, "total_steps": 1644, "loss": 0.5064, "lr": 5.992953854914838e-06, "epoch": 2.326866012325953, "percentage": 77.55, "elapsed_time": "2:20:28", "remaining_time": "0:40:39", "throughput": 857.86, "total_tokens": 7230896} +{"current_steps": 1280, "total_steps": 1644, "loss": 0.486, "lr": 5.838656712900487e-06, "epoch": 2.335996347865784, "percentage": 77.86, "elapsed_time": "2:21:01", "remaining_time": "0:40:06", "throughput": 857.82, "total_tokens": 7258640} +{"current_steps": 1285, "total_steps": 1644, "loss": 0.5659, "lr": 5.686108848648624e-06, "epoch": 2.3451266834056153, "percentage": 78.16, "elapsed_time": "2:21:34", "remaining_time": "0:39:33", "throughput": 857.87, "total_tokens": 7287552} +{"current_steps": 1290, "total_steps": 1644, "loss": 0.5572, "lr": 5.535324188562157e-06, "epoch": 2.354257018945446, "percentage": 78.47, "elapsed_time": "2:22:07", "remaining_time": "0:39:00", "throughput": 857.82, "total_tokens": 7315152} +{"current_steps": 1295, "total_steps": 1644, "loss": 0.5891, "lr": 5.386316498077492e-06, "epoch": 2.3633873544852775, "percentage": 78.77, "elapsed_time": "2:22:39", "remaining_time": "0:38:26", "throughput": 857.72, "total_tokens": 7341792} +{"current_steps": 1300, "total_steps": 1644, "loss": 0.5121, "lr": 5.239099380407916e-06, "epoch": 2.3725176900251084, "percentage": 79.08, "elapsed_time": "2:23:12", "remaining_time": "0:37:53", "throughput": 857.66, "total_tokens": 7369360} +{"current_steps": 1305, "total_steps": 1644, "loss": 0.4585, "lr": 5.09368627530169e-06, "epoch": 2.3816480255649397, "percentage": 79.38, "elapsed_time": "2:23:47", "remaining_time": "0:37:21", "throughput": 857.71, "total_tokens": 7399936} +{"current_steps": 1310, "total_steps": 1644, "loss": 0.5115, "lr": 4.950090457815129e-06, "epoch": 2.3907783611047706, "percentage": 79.68, "elapsed_time": "2:24:19", "remaining_time": "0:36:47", "throughput": 857.56, "total_tokens": 7426080} +{"current_steps": 1315, "total_steps": 1644, "loss": 0.3663, "lr": 4.808325037100691e-06, "epoch": 2.3999086966446015, "percentage": 79.99, "elapsed_time": "2:25:01", "remaining_time": "0:36:17", "throughput": 856.67, "total_tokens": 7454432} +{"current_steps": 1320, "total_steps": 1644, "loss": 0.4918, "lr": 4.6684029552101886e-06, "epoch": 2.409039032184433, "percentage": 80.29, "elapsed_time": "2:25:35", "remaining_time": "0:35:44", "throughput": 856.82, "total_tokens": 7484848} +{"current_steps": 1325, "total_steps": 1644, "loss": 0.4168, "lr": 4.530336985913333e-06, "epoch": 2.4181693677242637, "percentage": 80.6, "elapsed_time": "2:26:09", "remaining_time": "0:35:11", "throughput": 856.92, "total_tokens": 7514592} +{"current_steps": 1330, "total_steps": 1644, "loss": 0.4658, "lr": 4.394139733531555e-06, "epoch": 2.427299703264095, "percentage": 80.9, "elapsed_time": "2:26:43", "remaining_time": "0:34:38", "throughput": 857.11, "total_tokens": 7545680} +{"current_steps": 1335, "total_steps": 1644, "loss": 0.4081, "lr": 4.259823631787346e-06, "epoch": 2.436430038803926, "percentage": 81.2, "elapsed_time": "2:27:17", "remaining_time": "0:34:05", "throughput": 857.2, "total_tokens": 7575472} +{"current_steps": 1340, "total_steps": 1644, "loss": 0.4739, "lr": 4.127400942669141e-06, "epoch": 2.4455603743437573, "percentage": 81.51, "elapsed_time": "2:27:50", "remaining_time": "0:33:32", "throughput": 857.23, "total_tokens": 7604016} +{"current_steps": 1345, "total_steps": 1644, "loss": 0.3149, "lr": 3.996883755311917e-06, "epoch": 2.454690709883588, "percentage": 81.81, "elapsed_time": "2:28:25", "remaining_time": "0:32:59", "throughput": 857.5, "total_tokens": 7636112} +{"current_steps": 1350, "total_steps": 1644, "loss": 0.565, "lr": 3.868283984893542e-06, "epoch": 2.463821045423419, "percentage": 82.12, "elapsed_time": "2:28:58", "remaining_time": "0:32:26", "throughput": 857.55, "total_tokens": 7665152} +{"current_steps": 1355, "total_steps": 1644, "loss": 0.4656, "lr": 3.741613371547023e-06, "epoch": 2.4729513809632504, "percentage": 82.42, "elapsed_time": "2:29:30", "remaining_time": "0:31:53", "throughput": 857.47, "total_tokens": 7692112} +{"current_steps": 1360, "total_steps": 1644, "loss": 0.4552, "lr": 3.6168834792887103e-06, "epoch": 2.4820817165030817, "percentage": 82.73, "elapsed_time": "2:30:03", "remaining_time": "0:31:20", "throughput": 857.44, "total_tokens": 7720064} +{"current_steps": 1365, "total_steps": 1644, "loss": 0.4571, "lr": 3.494105694962596e-06, "epoch": 2.4912120520429126, "percentage": 83.03, "elapsed_time": "2:30:37", "remaining_time": "0:30:47", "throughput": 857.63, "total_tokens": 7751040} +{"current_steps": 1370, "total_steps": 1644, "loss": 0.5344, "lr": 3.373291227200806e-06, "epoch": 2.5003423875827435, "percentage": 83.33, "elapsed_time": "2:31:09", "remaining_time": "0:30:13", "throughput": 857.46, "total_tokens": 7776944} +{"current_steps": 1375, "total_steps": 1644, "loss": 0.501, "lr": 3.2544511054003246e-06, "epoch": 2.509472723122575, "percentage": 83.64, "elapsed_time": "2:31:42", "remaining_time": "0:29:40", "throughput": 857.44, "total_tokens": 7804880} +{"current_steps": 1380, "total_steps": 1644, "loss": 0.5723, "lr": 3.1375961787160983e-06, "epoch": 2.5186030586624057, "percentage": 83.94, "elapsed_time": "2:32:15", "remaining_time": "0:29:07", "throughput": 857.51, "total_tokens": 7834144} +{"current_steps": 1385, "total_steps": 1644, "loss": 0.5347, "lr": 3.0227371150706035e-06, "epoch": 2.527733394202237, "percentage": 84.25, "elapsed_time": "2:32:48", "remaining_time": "0:28:34", "throughput": 857.49, "total_tokens": 7862112} +{"current_steps": 1390, "total_steps": 1644, "loss": 0.4727, "lr": 2.9098844001799407e-06, "epoch": 2.536863729742068, "percentage": 84.55, "elapsed_time": "2:33:21", "remaining_time": "0:28:01", "throughput": 857.44, "total_tokens": 7889648} +{"current_steps": 1395, "total_steps": 1644, "loss": 0.6187, "lr": 2.7990483365965825e-06, "epoch": 2.5459940652818993, "percentage": 84.85, "elapsed_time": "2:33:54", "remaining_time": "0:27:28", "throughput": 857.44, "total_tokens": 7917840} +{"current_steps": 1400, "total_steps": 1644, "loss": 0.5945, "lr": 2.6902390427688273e-06, "epoch": 2.55512440082173, "percentage": 85.16, "elapsed_time": "2:34:27", "remaining_time": "0:26:55", "throughput": 857.44, "total_tokens": 7945968} +{"current_steps": 1405, "total_steps": 1644, "loss": 0.5123, "lr": 2.5834664521170504e-06, "epoch": 2.564254736361561, "percentage": 85.46, "elapsed_time": "2:35:02", "remaining_time": "0:26:22", "throughput": 857.49, "total_tokens": 7976608} +{"current_steps": 1410, "total_steps": 1644, "loss": 0.4564, "lr": 2.4787403121268955e-06, "epoch": 2.5733850719013924, "percentage": 85.77, "elapsed_time": "2:35:35", "remaining_time": "0:25:49", "throughput": 857.52, "total_tokens": 8005312} +{"current_steps": 1415, "total_steps": 1644, "loss": 0.5329, "lr": 2.3760701834593806e-06, "epoch": 2.5825154074412233, "percentage": 86.07, "elapsed_time": "2:36:07", "remaining_time": "0:25:16", "throughput": 857.44, "total_tokens": 8032320} +{"current_steps": 1420, "total_steps": 1644, "loss": 0.5803, "lr": 2.2754654390780924e-06, "epoch": 2.5916457429810547, "percentage": 86.37, "elapsed_time": "2:36:40", "remaining_time": "0:24:42", "throughput": 857.36, "total_tokens": 8059600} +{"current_steps": 1425, "total_steps": 1644, "loss": 0.4759, "lr": 2.1769352633935175e-06, "epoch": 2.6007760785208855, "percentage": 86.68, "elapsed_time": "2:37:14", "remaining_time": "0:24:09", "throughput": 857.53, "total_tokens": 8090544} +{"current_steps": 1430, "total_steps": 1644, "loss": 0.4964, "lr": 2.0804886514245726e-06, "epoch": 2.609906414060717, "percentage": 86.98, "elapsed_time": "2:37:47", "remaining_time": "0:23:36", "throughput": 857.44, "total_tokens": 8117472} +{"current_steps": 1435, "total_steps": 1644, "loss": 0.4652, "lr": 1.986134407977416e-06, "epoch": 2.6190367496005478, "percentage": 87.29, "elapsed_time": "2:38:19", "remaining_time": "0:23:03", "throughput": 857.43, "total_tokens": 8145360} +{"current_steps": 1440, "total_steps": 1644, "loss": 0.5859, "lr": 1.8938811468416695e-06, "epoch": 2.6281670851403787, "percentage": 87.59, "elapsed_time": "2:38:51", "remaining_time": "0:22:30", "throughput": 857.3, "total_tokens": 8171552} +{"current_steps": 1445, "total_steps": 1644, "loss": 0.6222, "lr": 1.8037372900040289e-06, "epoch": 2.63729742068021, "percentage": 87.9, "elapsed_time": "2:39:24", "remaining_time": "0:21:57", "throughput": 857.27, "total_tokens": 8199280} +{"current_steps": 1450, "total_steps": 1644, "loss": 0.3722, "lr": 1.7157110668794108e-06, "epoch": 2.6464277562200413, "percentage": 88.2, "elapsed_time": "2:39:56", "remaining_time": "0:21:23", "throughput": 857.22, "total_tokens": 8226656} +{"current_steps": 1455, "total_steps": 1644, "loss": 0.5299, "lr": 1.6298105135596569e-06, "epoch": 2.6555580917598722, "percentage": 88.5, "elapsed_time": "2:40:30", "remaining_time": "0:20:50", "throughput": 857.23, "total_tokens": 8255232} +{"current_steps": 1460, "total_steps": 1644, "loss": 0.447, "lr": 1.5460434720799278e-06, "epoch": 2.664688427299703, "percentage": 88.81, "elapsed_time": "2:41:02", "remaining_time": "0:20:17", "throughput": 857.12, "total_tokens": 8281744} +{"current_steps": 1465, "total_steps": 1644, "loss": 0.3965, "lr": 1.464417589702774e-06, "epoch": 2.6738187628395345, "percentage": 89.11, "elapsed_time": "2:41:35", "remaining_time": "0:19:44", "throughput": 857.14, "total_tokens": 8310384} +{"current_steps": 1470, "total_steps": 1644, "loss": 0.4579, "lr": 1.3849403182199988e-06, "epoch": 2.6829490983793653, "percentage": 89.42, "elapsed_time": "2:42:09", "remaining_time": "0:19:11", "throughput": 857.25, "total_tokens": 8340384} +{"current_steps": 1475, "total_steps": 1644, "loss": 0.5361, "lr": 1.3076189132723764e-06, "epoch": 2.6920794339191967, "percentage": 89.72, "elapsed_time": "2:42:41", "remaining_time": "0:18:38", "throughput": 857.23, "total_tokens": 8368224} +{"current_steps": 1480, "total_steps": 1644, "loss": 0.4439, "lr": 1.2324604336872658e-06, "epoch": 2.7012097694590276, "percentage": 90.02, "elapsed_time": "2:43:16", "remaining_time": "0:18:05", "throughput": 857.38, "total_tokens": 8398976} +{"current_steps": 1485, "total_steps": 1644, "loss": 0.3843, "lr": 1.159471740834195e-06, "epoch": 2.710340104998859, "percentage": 90.33, "elapsed_time": "2:43:48", "remaining_time": "0:17:32", "throughput": 857.3, "total_tokens": 8426000} +{"current_steps": 1490, "total_steps": 1644, "loss": 0.4191, "lr": 1.0886594979984816e-06, "epoch": 2.71947044053869, "percentage": 90.63, "elapsed_time": "2:44:20", "remaining_time": "0:16:59", "throughput": 857.21, "total_tokens": 8452800} +{"current_steps": 1495, "total_steps": 1644, "loss": 0.4898, "lr": 1.0200301697729204e-06, "epoch": 2.7286007760785207, "percentage": 90.94, "elapsed_time": "2:44:52", "remaining_time": "0:16:25", "throughput": 857.05, "total_tokens": 8478592} +{"current_steps": 1500, "total_steps": 1644, "loss": 0.4288, "lr": 9.535900214676097e-07, "epoch": 2.737731111618352, "percentage": 91.24, "elapsed_time": "2:45:25", "remaining_time": "0:15:52", "throughput": 857.0, "total_tokens": 8506240} +{"current_steps": 1505, "total_steps": 1644, "loss": 0.4114, "lr": 8.893451185379958e-07, "epoch": 2.746861447158183, "percentage": 91.55, "elapsed_time": "2:45:59", "remaining_time": "0:15:19", "throughput": 856.85, "total_tokens": 8533840} +{"current_steps": 1510, "total_steps": 1644, "loss": 0.4987, "lr": 8.273013260311379e-07, "epoch": 2.7559917826980143, "percentage": 91.85, "elapsed_time": "2:46:31", "remaining_time": "0:14:46", "throughput": 856.68, "total_tokens": 8559296} +{"current_steps": 1515, "total_steps": 1644, "loss": 0.4648, "lr": 7.674643080502724e-07, "epoch": 2.765122118237845, "percentage": 92.15, "elapsed_time": "2:59:21", "remaining_time": "0:15:16", "throughput": 798.02, "total_tokens": 8587664} +{"current_steps": 1520, "total_steps": 1644, "loss": 0.5213, "lr": 7.098395272377295e-07, "epoch": 2.7742524537776765, "percentage": 92.46, "elapsed_time": "2:59:53", "remaining_time": "0:14:40", "throughput": 798.11, "total_tokens": 8614480} +{"current_steps": 1525, "total_steps": 1644, "loss": 0.499, "lr": 6.544322442762318e-07, "epoch": 2.7833827893175074, "percentage": 92.76, "elapsed_time": "3:00:26", "remaining_time": "0:14:04", "throughput": 798.29, "total_tokens": 8642960} +{"current_steps": 1530, "total_steps": 1644, "loss": 0.4285, "lr": 6.012475174086485e-07, "epoch": 2.7925131248573383, "percentage": 93.07, "elapsed_time": "3:00:59", "remaining_time": "0:13:29", "throughput": 798.47, "total_tokens": 8671248} +{"current_steps": 1535, "total_steps": 1644, "loss": 0.4615, "lr": 5.502902019762002e-07, "epoch": 2.8016434603971696, "percentage": 93.37, "elapsed_time": "3:01:32", "remaining_time": "0:12:53", "throughput": 798.61, "total_tokens": 8698912} +{"current_steps": 1540, "total_steps": 1644, "loss": 0.4648, "lr": 5.015649499752279e-07, "epoch": 2.810773795937001, "percentage": 93.67, "elapsed_time": "3:02:05", "remaining_time": "0:12:17", "throughput": 798.77, "total_tokens": 8726896} +{"current_steps": 1545, "total_steps": 1644, "loss": 0.4858, "lr": 4.5507620963247954e-07, "epoch": 2.819904131476832, "percentage": 93.98, "elapsed_time": "3:02:36", "remaining_time": "0:11:42", "throughput": 798.76, "total_tokens": 8751920} +{"current_steps": 1550, "total_steps": 1644, "loss": 0.4944, "lr": 4.1082822499903253e-07, "epoch": 2.8290344670166627, "percentage": 94.28, "elapsed_time": "3:03:09", "remaining_time": "0:11:06", "throughput": 798.92, "total_tokens": 8780080} +{"current_steps": 1555, "total_steps": 1644, "loss": 0.4598, "lr": 3.6882503556285307e-07, "epoch": 2.838164802556494, "percentage": 94.59, "elapsed_time": "3:03:41", "remaining_time": "0:10:30", "throughput": 798.9, "total_tokens": 8804880} +{"current_steps": 1560, "total_steps": 1644, "loss": 0.4981, "lr": 3.290704758800139e-07, "epoch": 2.847295138096325, "percentage": 94.89, "elapsed_time": "3:04:15", "remaining_time": "0:09:55", "throughput": 799.16, "total_tokens": 8834736} +{"current_steps": 1565, "total_steps": 1644, "loss": 0.5183, "lr": 2.915681752246241e-07, "epoch": 2.8564254736361563, "percentage": 95.19, "elapsed_time": "3:04:47", "remaining_time": "0:09:19", "throughput": 799.31, "total_tokens": 8862544} +{"current_steps": 1570, "total_steps": 1644, "loss": 0.4789, "lr": 2.563215572575273e-07, "epoch": 2.865555809175987, "percentage": 95.5, "elapsed_time": "3:05:21", "remaining_time": "0:08:44", "throughput": 799.6, "total_tokens": 8892720} +{"current_steps": 1575, "total_steps": 1644, "loss": 0.4666, "lr": 2.2333383971372413e-07, "epoch": 2.8746861447158185, "percentage": 95.8, "elapsed_time": "3:05:53", "remaining_time": "0:08:08", "throughput": 799.65, "total_tokens": 8918880} +{"current_steps": 1580, "total_steps": 1644, "loss": 0.4199, "lr": 1.9260803410863226e-07, "epoch": 2.8838164802556494, "percentage": 96.11, "elapsed_time": "3:06:28", "remaining_time": "0:07:33", "throughput": 800.12, "total_tokens": 8952352} +{"current_steps": 1585, "total_steps": 1644, "loss": 0.4318, "lr": 1.641469454631561e-07, "epoch": 2.8929468157954803, "percentage": 96.41, "elapsed_time": "3:07:02", "remaining_time": "0:06:57", "throughput": 800.36, "total_tokens": 8981984} +{"current_steps": 1590, "total_steps": 1644, "loss": 0.36, "lr": 1.3795317204761128e-07, "epoch": 2.9020771513353116, "percentage": 96.72, "elapsed_time": "3:07:36", "remaining_time": "0:06:22", "throughput": 800.67, "total_tokens": 9012864} +{"current_steps": 1595, "total_steps": 1644, "loss": 0.4392, "lr": 1.140291051445197e-07, "epoch": 2.9112074868751425, "percentage": 97.02, "elapsed_time": "3:08:09", "remaining_time": "0:05:46", "throughput": 800.81, "total_tokens": 9040848} +{"current_steps": 1600, "total_steps": 1644, "loss": 0.4489, "lr": 9.237692883031502e-08, "epoch": 2.920337822414974, "percentage": 97.32, "elapsed_time": "3:08:43", "remaining_time": "0:05:11", "throughput": 801.1, "total_tokens": 9071104} +{"current_steps": 1605, "total_steps": 1644, "loss": 0.5492, "lr": 7.29986197759408e-08, "epoch": 2.9294681579548048, "percentage": 97.63, "elapsed_time": "3:09:18", "remaining_time": "0:04:36", "throughput": 801.33, "total_tokens": 9101904} +{"current_steps": 1610, "total_steps": 1644, "loss": 0.503, "lr": 5.589594706640055e-08, "epoch": 2.938598493494636, "percentage": 97.93, "elapsed_time": "3:09:52", "remaining_time": "0:04:00", "throughput": 801.57, "total_tokens": 9131728} +{"current_steps": 1615, "total_steps": 1644, "loss": 0.4689, "lr": 4.1070472039259065e-08, "epoch": 2.947728829034467, "percentage": 98.24, "elapsed_time": "3:10:26", "remaining_time": "0:03:25", "throughput": 801.85, "total_tokens": 9162144} +{"current_steps": 1620, "total_steps": 1644, "loss": 0.542, "lr": 2.8523548142103673e-08, "epoch": 2.956859164574298, "percentage": 98.54, "elapsed_time": "3:10:58", "remaining_time": "0:02:49", "throughput": 801.98, "total_tokens": 9189808} +{"current_steps": 1625, "total_steps": 1644, "loss": 0.3969, "lr": 1.825632080897366e-08, "epoch": 2.965989500114129, "percentage": 98.84, "elapsed_time": "3:11:32", "remaining_time": "0:02:14", "throughput": 802.24, "total_tokens": 9220032} +{"current_steps": 1630, "total_steps": 1644, "loss": 0.496, "lr": 1.026972735581333e-08, "epoch": 2.9751198356539605, "percentage": 99.15, "elapsed_time": "3:12:05", "remaining_time": "0:01:38", "throughput": 802.42, "total_tokens": 9248592} +{"current_steps": 1635, "total_steps": 1644, "loss": 0.5585, "lr": 4.564496894882142e-09, "epoch": 2.9842501711937914, "percentage": 99.45, "elapsed_time": "3:12:38", "remaining_time": "0:01:03", "throughput": 802.55, "total_tokens": 9276416} +{"current_steps": 1640, "total_steps": 1644, "loss": 0.4553, "lr": 1.1411502681996088e-09, "epoch": 2.9933805067336223, "percentage": 99.76, "elapsed_time": "3:13:12", "remaining_time": "0:00:28", "throughput": 802.8, "total_tokens": 9306352} +{"current_steps": 1644, "total_steps": 1644, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:13:38", "remaining_time": "0:00:00", "throughput": 802.91, "total_tokens": 9328224} diff --git a/train_2026-01-03/trainer_state.json b/train_2026-01-03/trainer_state.json new file mode 100644 index 0000000..b355bbe --- /dev/null +++ b/train_2026-01-03/trainer_state.json @@ -0,0 +1,3324 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "eval_steps": 500, + "global_step": 1644, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00913033553983109, + "grad_norm": 0.6315373182296753, + "learning_rate": 4.999926966182812e-05, + "loss": 1.469, + "num_input_tokens_seen": 31168, + "step": 5, + "train_runtime": 37.3694, + "train_tokens_per_second": 834.051 + }, + { + "epoch": 0.01826067107966218, + "grad_norm": 0.6748600006103516, + "learning_rate": 4.999630273613799e-05, + "loss": 1.5127, + "num_input_tokens_seen": 58992, + "step": 10, + "train_runtime": 70.3152, + "train_tokens_per_second": 838.965 + }, + { + "epoch": 0.027391006619493265, + "grad_norm": 0.8578517436981201, + "learning_rate": 4.999105384744215e-05, + "loss": 1.44, + "num_input_tokens_seen": 87296, + "step": 15, + "train_runtime": 103.3591, + "train_tokens_per_second": 844.59 + }, + { + "epoch": 0.03652134215932436, + "grad_norm": 0.6677753329277039, + "learning_rate": 4.998352347492226e-05, + "loss": 1.4987, + "num_input_tokens_seen": 114656, + "step": 20, + "train_runtime": 136.0501, + "train_tokens_per_second": 842.748 + }, + { + "epoch": 0.045651677699155443, + "grad_norm": 0.6610105037689209, + "learning_rate": 4.9973712306041256e-05, + "loss": 1.4058, + "num_input_tokens_seen": 143584, + "step": 25, + "train_runtime": 169.3921, + "train_tokens_per_second": 847.643 + }, + { + "epoch": 0.05478201323898653, + "grad_norm": 0.7272489666938782, + "learning_rate": 4.996162123648058e-05, + "loss": 1.4049, + "num_input_tokens_seen": 172224, + "step": 30, + "train_runtime": 202.5177, + "train_tokens_per_second": 850.415 + }, + { + "epoch": 0.06391234877881762, + "grad_norm": 0.6470730900764465, + "learning_rate": 4.99472513700584e-05, + "loss": 1.4239, + "num_input_tokens_seen": 200272, + "step": 35, + "train_runtime": 235.4246, + "train_tokens_per_second": 850.684 + }, + { + "epoch": 0.07304268431864872, + "grad_norm": 0.6487858295440674, + "learning_rate": 4.993060401862888e-05, + "loss": 1.389, + "num_input_tokens_seen": 227552, + "step": 40, + "train_runtime": 267.9205, + "train_tokens_per_second": 849.327 + }, + { + "epoch": 0.0821730198584798, + "grad_norm": 0.81675785779953, + "learning_rate": 4.9911680701962384e-05, + "loss": 1.3187, + "num_input_tokens_seen": 256320, + "step": 45, + "train_runtime": 301.0567, + "train_tokens_per_second": 851.401 + }, + { + "epoch": 0.09130335539831089, + "grad_norm": 0.590348482131958, + "learning_rate": 4.989048314760674e-05, + "loss": 1.31, + "num_input_tokens_seen": 287184, + "step": 50, + "train_runtime": 335.1262, + "train_tokens_per_second": 856.943 + }, + { + "epoch": 0.10043369093814197, + "grad_norm": 0.6573392748832703, + "learning_rate": 4.9867013290729535e-05, + "loss": 1.3295, + "num_input_tokens_seen": 314864, + "step": 55, + "train_runtime": 367.7602, + "train_tokens_per_second": 856.167 + }, + { + "epoch": 0.10956402647797306, + "grad_norm": 0.7032639980316162, + "learning_rate": 4.984127327394146e-05, + "loss": 1.2718, + "num_input_tokens_seen": 342912, + "step": 60, + "train_runtime": 400.5266, + "train_tokens_per_second": 856.153 + }, + { + "epoch": 0.11869436201780416, + "grad_norm": 0.789444088935852, + "learning_rate": 4.981326544710065e-05, + "loss": 1.2547, + "num_input_tokens_seen": 370064, + "step": 65, + "train_runtime": 432.9005, + "train_tokens_per_second": 854.848 + }, + { + "epoch": 0.12782469755763523, + "grad_norm": 0.7282975316047668, + "learning_rate": 4.978299236709826e-05, + "loss": 1.302, + "num_input_tokens_seen": 399584, + "step": 70, + "train_runtime": 466.4409, + "train_tokens_per_second": 856.666 + }, + { + "epoch": 0.13695503309746634, + "grad_norm": 0.7695715427398682, + "learning_rate": 4.975045679762496e-05, + "loss": 1.2328, + "num_input_tokens_seen": 430528, + "step": 75, + "train_runtime": 500.4187, + "train_tokens_per_second": 860.336 + }, + { + "epoch": 0.14608536863729743, + "grad_norm": 0.6912102699279785, + "learning_rate": 4.9715661708918624e-05, + "loss": 1.296, + "num_input_tokens_seen": 460080, + "step": 80, + "train_runtime": 533.9121, + "train_tokens_per_second": 861.715 + }, + { + "epoch": 0.15521570417712852, + "grad_norm": 0.7808125615119934, + "learning_rate": 4.9678610277493275e-05, + "loss": 1.3248, + "num_input_tokens_seen": 488176, + "step": 85, + "train_runtime": 566.9429, + "train_tokens_per_second": 861.067 + }, + { + "epoch": 0.1643460397169596, + "grad_norm": 0.8161223530769348, + "learning_rate": 4.9639305885848975e-05, + "loss": 1.207, + "num_input_tokens_seen": 516896, + "step": 90, + "train_runtime": 600.1453, + "train_tokens_per_second": 861.285 + }, + { + "epoch": 0.1734763752567907, + "grad_norm": 0.7836668491363525, + "learning_rate": 4.959775212216308e-05, + "loss": 1.2342, + "num_input_tokens_seen": 547440, + "step": 95, + "train_runtime": 634.2069, + "train_tokens_per_second": 863.188 + }, + { + "epoch": 0.18260671079662177, + "grad_norm": 0.7432403564453125, + "learning_rate": 4.955395277996268e-05, + "loss": 1.1931, + "num_input_tokens_seen": 577088, + "step": 100, + "train_runtime": 667.769, + "train_tokens_per_second": 864.203 + }, + { + "epoch": 0.19173704633645286, + "grad_norm": 0.7105097770690918, + "learning_rate": 4.9507911857778256e-05, + "loss": 1.2122, + "num_input_tokens_seen": 606976, + "step": 105, + "train_runtime": 702.605, + "train_tokens_per_second": 863.894 + }, + { + "epoch": 0.20086738187628395, + "grad_norm": 0.9018083810806274, + "learning_rate": 4.9459633558778684e-05, + "loss": 1.2973, + "num_input_tokens_seen": 634416, + "step": 110, + "train_runtime": 735.186, + "train_tokens_per_second": 862.933 + }, + { + "epoch": 0.20999771741611503, + "grad_norm": 0.878520131111145, + "learning_rate": 4.940912229038745e-05, + "loss": 1.2483, + "num_input_tokens_seen": 660192, + "step": 115, + "train_runtime": 767.1492, + "train_tokens_per_second": 860.578 + }, + { + "epoch": 0.21912805295594612, + "grad_norm": 0.7927104234695435, + "learning_rate": 4.9356382663880366e-05, + "loss": 1.1153, + "num_input_tokens_seen": 687936, + "step": 120, + "train_runtime": 799.9406, + "train_tokens_per_second": 859.984 + }, + { + "epoch": 0.22825838849577723, + "grad_norm": 0.9102480411529541, + "learning_rate": 4.930141949396454e-05, + "loss": 1.2269, + "num_input_tokens_seen": 716960, + "step": 125, + "train_runtime": 833.2659, + "train_tokens_per_second": 860.422 + }, + { + "epoch": 0.23738872403560832, + "grad_norm": 0.9657291173934937, + "learning_rate": 4.9244237798338866e-05, + "loss": 1.1324, + "num_input_tokens_seen": 744976, + "step": 130, + "train_runtime": 866.1684, + "train_tokens_per_second": 860.082 + }, + { + "epoch": 0.2465190595754394, + "grad_norm": 0.9540858268737793, + "learning_rate": 4.918484279723592e-05, + "loss": 1.1818, + "num_input_tokens_seen": 772176, + "step": 135, + "train_runtime": 898.6975, + "train_tokens_per_second": 859.217 + }, + { + "epoch": 0.25564939511527046, + "grad_norm": 0.9128895998001099, + "learning_rate": 4.9123239912945423e-05, + "loss": 1.1243, + "num_input_tokens_seen": 804528, + "step": 140, + "train_runtime": 933.4596, + "train_tokens_per_second": 861.878 + }, + { + "epoch": 0.2647797306551016, + "grad_norm": 0.896022379398346, + "learning_rate": 4.9059434769319205e-05, + "loss": 1.2134, + "num_input_tokens_seen": 831056, + "step": 145, + "train_runtime": 965.6266, + "train_tokens_per_second": 860.639 + }, + { + "epoch": 0.2739100661949327, + "grad_norm": 0.8580520153045654, + "learning_rate": 4.899343319125781e-05, + "loss": 1.0775, + "num_input_tokens_seen": 862416, + "step": 150, + "train_runtime": 999.9056, + "train_tokens_per_second": 862.497 + }, + { + "epoch": 0.28304040173476375, + "grad_norm": 0.9435716867446899, + "learning_rate": 4.892524120417872e-05, + "loss": 1.2069, + "num_input_tokens_seen": 889264, + "step": 155, + "train_runtime": 1032.1039, + "train_tokens_per_second": 861.603 + }, + { + "epoch": 0.29217073727459486, + "grad_norm": 0.9432860016822815, + "learning_rate": 4.8854865033466275e-05, + "loss": 1.1649, + "num_input_tokens_seen": 917104, + "step": 160, + "train_runtime": 1064.7569, + "train_tokens_per_second": 861.327 + }, + { + "epoch": 0.3013010728144259, + "grad_norm": 0.780659019947052, + "learning_rate": 4.878231110390337e-05, + "loss": 1.1495, + "num_input_tokens_seen": 947280, + "step": 165, + "train_runtime": 1098.5348, + "train_tokens_per_second": 862.312 + }, + { + "epoch": 0.31043140835425703, + "grad_norm": 1.0290687084197998, + "learning_rate": 4.870758603908489e-05, + "loss": 1.1231, + "num_input_tokens_seen": 978704, + "step": 170, + "train_runtime": 1132.7604, + "train_tokens_per_second": 863.999 + }, + { + "epoch": 0.3195617438940881, + "grad_norm": 0.8476850390434265, + "learning_rate": 4.863069666081307e-05, + "loss": 1.0885, + "num_input_tokens_seen": 1005904, + "step": 175, + "train_runtime": 1165.1167, + "train_tokens_per_second": 863.35 + }, + { + "epoch": 0.3286920794339192, + "grad_norm": 0.8470911383628845, + "learning_rate": 4.855164998847466e-05, + "loss": 1.1022, + "num_input_tokens_seen": 1034624, + "step": 180, + "train_runtime": 1198.278, + "train_tokens_per_second": 863.426 + }, + { + "epoch": 0.33782241497375026, + "grad_norm": 1.0513180494308472, + "learning_rate": 4.8470453238400195e-05, + "loss": 1.1223, + "num_input_tokens_seen": 1059280, + "step": 185, + "train_runtime": 1229.5356, + "train_tokens_per_second": 861.529 + }, + { + "epoch": 0.3469527505135814, + "grad_norm": 0.9217162132263184, + "learning_rate": 4.8387113823205096e-05, + "loss": 1.0287, + "num_input_tokens_seen": 1088960, + "step": 190, + "train_runtime": 1263.0899, + "train_tokens_per_second": 862.14 + }, + { + "epoch": 0.3560830860534125, + "grad_norm": 1.0153199434280396, + "learning_rate": 4.8301639351113065e-05, + "loss": 1.1138, + "num_input_tokens_seen": 1113712, + "step": 195, + "train_runtime": 1294.2756, + "train_tokens_per_second": 860.491 + }, + { + "epoch": 0.36521342159324355, + "grad_norm": 1.2406193017959595, + "learning_rate": 4.821403762526143e-05, + "loss": 1.1149, + "num_input_tokens_seen": 1141696, + "step": 200, + "train_runtime": 1326.999, + "train_tokens_per_second": 860.359 + }, + { + "epoch": 0.37434375713307466, + "grad_norm": 0.9366787075996399, + "learning_rate": 4.812431664298883e-05, + "loss": 1.1954, + "num_input_tokens_seen": 1172000, + "step": 205, + "train_runtime": 1362.1116, + "train_tokens_per_second": 860.429 + }, + { + "epoch": 0.3834740926729057, + "grad_norm": 0.8975793123245239, + "learning_rate": 4.803248459510511e-05, + "loss": 1.0426, + "num_input_tokens_seen": 1201136, + "step": 210, + "train_runtime": 1395.3356, + "train_tokens_per_second": 860.822 + }, + { + "epoch": 0.39260442821273683, + "grad_norm": 0.9986598491668701, + "learning_rate": 4.7938549865143544e-05, + "loss": 1.2254, + "num_input_tokens_seen": 1227792, + "step": 215, + "train_runtime": 1427.5362, + "train_tokens_per_second": 860.078 + }, + { + "epoch": 0.4017347637525679, + "grad_norm": 0.9591779112815857, + "learning_rate": 4.7842521028595526e-05, + "loss": 1.0323, + "num_input_tokens_seen": 1258240, + "step": 220, + "train_runtime": 1461.4996, + "train_tokens_per_second": 860.924 + }, + { + "epoch": 0.410865099292399, + "grad_norm": 1.1904876232147217, + "learning_rate": 4.7744406852127653e-05, + "loss": 0.9971, + "num_input_tokens_seen": 1289744, + "step": 225, + "train_runtime": 1495.7355, + "train_tokens_per_second": 862.281 + }, + { + "epoch": 0.41999543483223006, + "grad_norm": 1.1294660568237305, + "learning_rate": 4.764421629278144e-05, + "loss": 1.0328, + "num_input_tokens_seen": 1315040, + "step": 230, + "train_runtime": 1527.2934, + "train_tokens_per_second": 861.026 + }, + { + "epoch": 0.4291257703720612, + "grad_norm": 1.2325509786605835, + "learning_rate": 4.754195849715557e-05, + "loss": 1.0546, + "num_input_tokens_seen": 1344848, + "step": 235, + "train_runtime": 1560.7834, + "train_tokens_per_second": 861.649 + }, + { + "epoch": 0.43825610591189224, + "grad_norm": 0.991324245929718, + "learning_rate": 4.743764280057092e-05, + "loss": 1.1701, + "num_input_tokens_seen": 1371728, + "step": 240, + "train_runtime": 1593.0413, + "train_tokens_per_second": 861.075 + }, + { + "epoch": 0.44738644145172335, + "grad_norm": 1.1479493379592896, + "learning_rate": 4.73312787262183e-05, + "loss": 1.0949, + "num_input_tokens_seen": 1398896, + "step": 245, + "train_runtime": 1625.4235, + "train_tokens_per_second": 860.635 + }, + { + "epoch": 0.45651677699155446, + "grad_norm": 0.9881078600883484, + "learning_rate": 4.722287598428907e-05, + "loss": 1.1142, + "num_input_tokens_seen": 1425376, + "step": 250, + "train_runtime": 1657.4768, + "train_tokens_per_second": 859.967 + }, + { + "epoch": 0.4656471125313855, + "grad_norm": 1.3233039379119873, + "learning_rate": 4.711244447108866e-05, + "loss": 1.0364, + "num_input_tokens_seen": 1452416, + "step": 255, + "train_runtime": 1689.8742, + "train_tokens_per_second": 859.482 + }, + { + "epoch": 0.47477744807121663, + "grad_norm": 1.1027718782424927, + "learning_rate": 4.6999994268133166e-05, + "loss": 1.0669, + "num_input_tokens_seen": 1481440, + "step": 260, + "train_runtime": 1722.9242, + "train_tokens_per_second": 859.84 + }, + { + "epoch": 0.4839077836110477, + "grad_norm": 0.9862788915634155, + "learning_rate": 4.6885535641228904e-05, + "loss": 1.007, + "num_input_tokens_seen": 1510240, + "step": 265, + "train_runtime": 1756.1254, + "train_tokens_per_second": 859.984 + }, + { + "epoch": 0.4930381191508788, + "grad_norm": 0.8394035696983337, + "learning_rate": 4.676907903953531e-05, + "loss": 0.9444, + "num_input_tokens_seen": 1538208, + "step": 270, + "train_runtime": 1788.9168, + "train_tokens_per_second": 859.854 + }, + { + "epoch": 0.5021684546907099, + "grad_norm": 0.9921995401382446, + "learning_rate": 4.665063509461097e-05, + "loss": 1.0157, + "num_input_tokens_seen": 1566880, + "step": 275, + "train_runtime": 1821.9921, + "train_tokens_per_second": 859.982 + }, + { + "epoch": 0.5112987902305409, + "grad_norm": 1.0822592973709106, + "learning_rate": 4.6530214619443037e-05, + "loss": 1.0188, + "num_input_tokens_seen": 1593904, + "step": 280, + "train_runtime": 1854.3967, + "train_tokens_per_second": 859.527 + }, + { + "epoch": 0.520429125770372, + "grad_norm": 1.1514437198638916, + "learning_rate": 4.640782860746011e-05, + "loss": 0.9333, + "num_input_tokens_seen": 1621440, + "step": 285, + "train_runtime": 1887.0679, + "train_tokens_per_second": 859.238 + }, + { + "epoch": 0.5295594613102032, + "grad_norm": 1.1235507726669312, + "learning_rate": 4.628348823152863e-05, + "loss": 0.9435, + "num_input_tokens_seen": 1650064, + "step": 290, + "train_runtime": 1920.2198, + "train_tokens_per_second": 859.31 + }, + { + "epoch": 0.5386897968500343, + "grad_norm": 0.8459988832473755, + "learning_rate": 4.615720484293286e-05, + "loss": 0.9418, + "num_input_tokens_seen": 1677472, + "step": 295, + "train_runtime": 1952.7783, + "train_tokens_per_second": 859.018 + }, + { + "epoch": 0.5478201323898654, + "grad_norm": 1.2311139106750488, + "learning_rate": 4.602898997033861e-05, + "loss": 0.9934, + "num_input_tokens_seen": 1706672, + "step": 300, + "train_runtime": 1986.1813, + "train_tokens_per_second": 859.273 + }, + { + "epoch": 0.5569504679296964, + "grad_norm": 1.1580544710159302, + "learning_rate": 4.58988553187408e-05, + "loss": 1.0952, + "num_input_tokens_seen": 1734704, + "step": 305, + "train_runtime": 2020.184, + "train_tokens_per_second": 858.686 + }, + { + "epoch": 0.5660808034695275, + "grad_norm": 0.8693342804908752, + "learning_rate": 4.576681276839483e-05, + "loss": 0.9632, + "num_input_tokens_seen": 1763312, + "step": 310, + "train_runtime": 2053.3414, + "train_tokens_per_second": 858.752 + }, + { + "epoch": 0.5752111390093586, + "grad_norm": 0.9932484030723572, + "learning_rate": 4.5632874373732035e-05, + "loss": 0.931, + "num_input_tokens_seen": 1789616, + "step": 315, + "train_runtime": 2085.3946, + "train_tokens_per_second": 858.167 + }, + { + "epoch": 0.5843414745491897, + "grad_norm": 1.0481774806976318, + "learning_rate": 4.549705236225922e-05, + "loss": 1.0103, + "num_input_tokens_seen": 1817760, + "step": 320, + "train_runtime": 2118.2164, + "train_tokens_per_second": 858.156 + }, + { + "epoch": 0.5934718100890207, + "grad_norm": 0.9734839797019958, + "learning_rate": 4.5359359133442356e-05, + "loss": 0.9518, + "num_input_tokens_seen": 1845664, + "step": 325, + "train_runtime": 2150.9302, + "train_tokens_per_second": 858.077 + }, + { + "epoch": 0.6026021456288518, + "grad_norm": 0.935545802116394, + "learning_rate": 4.521980725757466e-05, + "loss": 0.8974, + "num_input_tokens_seen": 1875392, + "step": 330, + "train_runtime": 2184.587, + "train_tokens_per_second": 858.465 + }, + { + "epoch": 0.611732481168683, + "grad_norm": 1.1402722597122192, + "learning_rate": 4.5078409474628966e-05, + "loss": 0.9171, + "num_input_tokens_seen": 1902592, + "step": 335, + "train_runtime": 2217.1072, + "train_tokens_per_second": 858.142 + }, + { + "epoch": 0.6208628167085141, + "grad_norm": 1.1934939622879028, + "learning_rate": 4.4935178693094714e-05, + "loss": 0.899, + "num_input_tokens_seen": 1931328, + "step": 340, + "train_runtime": 2250.2974, + "train_tokens_per_second": 858.255 + }, + { + "epoch": 0.6299931522483452, + "grad_norm": 1.0187445878982544, + "learning_rate": 4.4790127988799494e-05, + "loss": 0.8964, + "num_input_tokens_seen": 1960528, + "step": 345, + "train_runtime": 2283.719, + "train_tokens_per_second": 858.48 + }, + { + "epoch": 0.6391234877881762, + "grad_norm": 1.0490012168884277, + "learning_rate": 4.464327060371529e-05, + "loss": 1.0919, + "num_input_tokens_seen": 1987168, + "step": 350, + "train_runtime": 2315.9585, + "train_tokens_per_second": 858.033 + }, + { + "epoch": 0.6482538233280073, + "grad_norm": 1.2056529521942139, + "learning_rate": 4.449461994474968e-05, + "loss": 1.0469, + "num_input_tokens_seen": 2014832, + "step": 355, + "train_runtime": 2348.6807, + "train_tokens_per_second": 857.857 + }, + { + "epoch": 0.6573841588678384, + "grad_norm": 0.9101769328117371, + "learning_rate": 4.434418958252179e-05, + "loss": 0.8841, + "num_input_tokens_seen": 2043840, + "step": 360, + "train_runtime": 2382.0483, + "train_tokens_per_second": 858.018 + }, + { + "epoch": 0.6665144944076695, + "grad_norm": 1.4810435771942139, + "learning_rate": 4.4191993250123483e-05, + "loss": 1.0016, + "num_input_tokens_seen": 2073120, + "step": 365, + "train_runtime": 2415.6373, + "train_tokens_per_second": 858.208 + }, + { + "epoch": 0.6756448299475005, + "grad_norm": 1.065366506576538, + "learning_rate": 4.4038044841865614e-05, + "loss": 0.9584, + "num_input_tokens_seen": 2098384, + "step": 370, + "train_runtime": 2447.2579, + "train_tokens_per_second": 857.443 + }, + { + "epoch": 0.6847751654873316, + "grad_norm": 1.2886056900024414, + "learning_rate": 4.388235841200956e-05, + "loss": 0.9964, + "num_input_tokens_seen": 2127008, + "step": 375, + "train_runtime": 2480.3435, + "train_tokens_per_second": 857.546 + }, + { + "epoch": 0.6939055010271628, + "grad_norm": 1.2109014987945557, + "learning_rate": 4.3724948173484216e-05, + "loss": 0.9808, + "num_input_tokens_seen": 2154624, + "step": 380, + "train_runtime": 2512.9908, + "train_tokens_per_second": 857.394 + }, + { + "epoch": 0.7030358365669939, + "grad_norm": 1.0763500928878784, + "learning_rate": 4.356582849658845e-05, + "loss": 0.9126, + "num_input_tokens_seen": 2184768, + "step": 385, + "train_runtime": 2546.895, + "train_tokens_per_second": 857.816 + }, + { + "epoch": 0.712166172106825, + "grad_norm": 1.1964282989501953, + "learning_rate": 4.340501390767924e-05, + "loss": 0.8749, + "num_input_tokens_seen": 2214336, + "step": 390, + "train_runtime": 2580.5251, + "train_tokens_per_second": 858.095 + }, + { + "epoch": 0.721296507646656, + "grad_norm": 1.2746434211730957, + "learning_rate": 4.324251908784546e-05, + "loss": 0.9203, + "num_input_tokens_seen": 2243296, + "step": 395, + "train_runtime": 2613.6736, + "train_tokens_per_second": 858.292 + }, + { + "epoch": 0.7304268431864871, + "grad_norm": 0.9673400521278381, + "learning_rate": 4.3078358871567706e-05, + "loss": 0.8857, + "num_input_tokens_seen": 2273424, + "step": 400, + "train_runtime": 2647.5272, + "train_tokens_per_second": 858.697 + }, + { + "epoch": 0.7395571787263182, + "grad_norm": 0.9456354975700378, + "learning_rate": 4.291254824536396e-05, + "loss": 0.9175, + "num_input_tokens_seen": 2303040, + "step": 405, + "train_runtime": 2682.2704, + "train_tokens_per_second": 858.616 + }, + { + "epoch": 0.7486875142661493, + "grad_norm": 1.1169666051864624, + "learning_rate": 4.274510234642148e-05, + "loss": 0.9572, + "num_input_tokens_seen": 2330352, + "step": 410, + "train_runtime": 2714.6955, + "train_tokens_per_second": 858.421 + }, + { + "epoch": 0.7578178498059803, + "grad_norm": 1.1452381610870361, + "learning_rate": 4.257603646121484e-05, + "loss": 1.0534, + "num_input_tokens_seen": 2357968, + "step": 415, + "train_runtime": 2747.2523, + "train_tokens_per_second": 858.3 + }, + { + "epoch": 0.7669481853458114, + "grad_norm": 1.2339755296707153, + "learning_rate": 4.240536602411048e-05, + "loss": 0.8583, + "num_input_tokens_seen": 2386800, + "step": 420, + "train_runtime": 2780.5385, + "train_tokens_per_second": 858.395 + }, + { + "epoch": 0.7760785208856426, + "grad_norm": 1.0699409246444702, + "learning_rate": 4.22331066159576e-05, + "loss": 0.8049, + "num_input_tokens_seen": 2416224, + "step": 425, + "train_runtime": 2813.8831, + "train_tokens_per_second": 858.68 + }, + { + "epoch": 0.7852088564254737, + "grad_norm": 1.0616157054901123, + "learning_rate": 4.205927396266577e-05, + "loss": 0.9599, + "num_input_tokens_seen": 2445120, + "step": 430, + "train_runtime": 2847.2801, + "train_tokens_per_second": 858.756 + }, + { + "epoch": 0.7943391919653047, + "grad_norm": 1.3448375463485718, + "learning_rate": 4.188388393376933e-05, + "loss": 0.8874, + "num_input_tokens_seen": 2473312, + "step": 435, + "train_runtime": 2880.2168, + "train_tokens_per_second": 858.724 + }, + { + "epoch": 0.8034695275051358, + "grad_norm": 1.3544775247573853, + "learning_rate": 4.1706952540978545e-05, + "loss": 0.8944, + "num_input_tokens_seen": 2500800, + "step": 440, + "train_runtime": 2912.8173, + "train_tokens_per_second": 858.55 + }, + { + "epoch": 0.8125998630449669, + "grad_norm": 1.1478849649429321, + "learning_rate": 4.152849593671793e-05, + "loss": 0.9774, + "num_input_tokens_seen": 2529392, + "step": 445, + "train_runtime": 2945.9115, + "train_tokens_per_second": 858.611 + }, + { + "epoch": 0.821730198584798, + "grad_norm": 1.1531591415405273, + "learning_rate": 4.134853041265162e-05, + "loss": 0.8543, + "num_input_tokens_seen": 2559536, + "step": 450, + "train_runtime": 2979.5242, + "train_tokens_per_second": 859.042 + }, + { + "epoch": 0.8308605341246291, + "grad_norm": 1.034783959388733, + "learning_rate": 4.11670723981961e-05, + "loss": 0.8293, + "num_input_tokens_seen": 2588144, + "step": 455, + "train_runtime": 3012.7186, + "train_tokens_per_second": 859.073 + }, + { + "epoch": 0.8399908696644601, + "grad_norm": 1.181213617324829, + "learning_rate": 4.098413845902033e-05, + "loss": 0.9264, + "num_input_tokens_seen": 2617968, + "step": 460, + "train_runtime": 3046.4091, + "train_tokens_per_second": 859.362 + }, + { + "epoch": 0.8491212052042912, + "grad_norm": 1.134751796722412, + "learning_rate": 4.079974529553341e-05, + "loss": 0.9641, + "num_input_tokens_seen": 2646896, + "step": 465, + "train_runtime": 3079.7911, + "train_tokens_per_second": 859.44 + }, + { + "epoch": 0.8582515407441224, + "grad_norm": 1.0939092636108398, + "learning_rate": 4.061390974135997e-05, + "loss": 0.805, + "num_input_tokens_seen": 2674288, + "step": 470, + "train_runtime": 3112.254, + "train_tokens_per_second": 859.277 + }, + { + "epoch": 0.8673818762839535, + "grad_norm": 1.4272619485855103, + "learning_rate": 4.042664876180341e-05, + "loss": 1.0411, + "num_input_tokens_seen": 2700464, + "step": 475, + "train_runtime": 3144.0731, + "train_tokens_per_second": 858.906 + }, + { + "epoch": 0.8765122118237845, + "grad_norm": 1.2609965801239014, + "learning_rate": 4.0237979452297094e-05, + "loss": 0.8638, + "num_input_tokens_seen": 2732112, + "step": 480, + "train_runtime": 3178.5283, + "train_tokens_per_second": 859.553 + }, + { + "epoch": 0.8856425473636156, + "grad_norm": 1.5450228452682495, + "learning_rate": 4.0047919036843675e-05, + "loss": 1.0152, + "num_input_tokens_seen": 2757872, + "step": 485, + "train_runtime": 3210.3201, + "train_tokens_per_second": 859.064 + }, + { + "epoch": 0.8947728829034467, + "grad_norm": 1.1069929599761963, + "learning_rate": 3.985648486644267e-05, + "loss": 0.9046, + "num_input_tokens_seen": 2786192, + "step": 490, + "train_runtime": 3243.3923, + "train_tokens_per_second": 859.036 + }, + { + "epoch": 0.9039032184432778, + "grad_norm": 1.0615628957748413, + "learning_rate": 3.966369441750648e-05, + "loss": 0.8428, + "num_input_tokens_seen": 2812368, + "step": 495, + "train_runtime": 3275.3944, + "train_tokens_per_second": 858.635 + }, + { + "epoch": 0.9130335539831089, + "grad_norm": 1.0123751163482666, + "learning_rate": 3.9469565290264906e-05, + "loss": 0.8138, + "num_input_tokens_seen": 2840912, + "step": 500, + "train_runtime": 3308.5472, + "train_tokens_per_second": 858.658 + }, + { + "epoch": 0.9221638895229399, + "grad_norm": 1.2222071886062622, + "learning_rate": 3.92741152071584e-05, + "loss": 0.8349, + "num_input_tokens_seen": 2870000, + "step": 505, + "train_runtime": 3343.2464, + "train_tokens_per_second": 858.447 + }, + { + "epoch": 0.931294225062771, + "grad_norm": 1.2460840940475464, + "learning_rate": 3.907736201122014e-05, + "loss": 0.883, + "num_input_tokens_seen": 2899328, + "step": 510, + "train_runtime": 3376.5896, + "train_tokens_per_second": 858.656 + }, + { + "epoch": 0.9404245606026022, + "grad_norm": 1.1203129291534424, + "learning_rate": 3.8879323664447096e-05, + "loss": 0.8141, + "num_input_tokens_seen": 2928832, + "step": 515, + "train_runtime": 3410.0362, + "train_tokens_per_second": 858.886 + }, + { + "epoch": 0.9495548961424333, + "grad_norm": 1.0772883892059326, + "learning_rate": 3.8680018246160295e-05, + "loss": 0.8964, + "num_input_tokens_seen": 2956352, + "step": 520, + "train_runtime": 3442.6688, + "train_tokens_per_second": 858.738 + }, + { + "epoch": 0.9586852316822643, + "grad_norm": 1.098358154296875, + "learning_rate": 3.8479463951354245e-05, + "loss": 0.7845, + "num_input_tokens_seen": 2985072, + "step": 525, + "train_runtime": 3475.9209, + "train_tokens_per_second": 858.786 + }, + { + "epoch": 0.9678155672220954, + "grad_norm": 1.61497163772583, + "learning_rate": 3.827767908903592e-05, + "loss": 0.9675, + "num_input_tokens_seen": 3013200, + "step": 530, + "train_runtime": 3508.7675, + "train_tokens_per_second": 858.763 + }, + { + "epoch": 0.9769459027619265, + "grad_norm": 1.2918585538864136, + "learning_rate": 3.8074682080553335e-05, + "loss": 0.9429, + "num_input_tokens_seen": 3044064, + "step": 535, + "train_runtime": 3542.8639, + "train_tokens_per_second": 859.21 + }, + { + "epoch": 0.9860762383017576, + "grad_norm": 1.1658656597137451, + "learning_rate": 3.7870491457913714e-05, + "loss": 0.9034, + "num_input_tokens_seen": 3071008, + "step": 540, + "train_runtime": 3575.2913, + "train_tokens_per_second": 858.953 + }, + { + "epoch": 0.9952065738415887, + "grad_norm": 1.8342398405075073, + "learning_rate": 3.7665125862091765e-05, + "loss": 0.8696, + "num_input_tokens_seen": 3100256, + "step": 545, + "train_runtime": 3608.7852, + "train_tokens_per_second": 859.086 + }, + { + "epoch": 1.0036521342159324, + "grad_norm": 1.1551634073257446, + "learning_rate": 3.7458604041327874e-05, + "loss": 0.9914, + "num_input_tokens_seen": 3125104, + "step": 550, + "train_runtime": 3638.8068, + "train_tokens_per_second": 858.827 + }, + { + "epoch": 1.0127824697557635, + "grad_norm": 1.2146859169006348, + "learning_rate": 3.725094484941654e-05, + "loss": 0.7924, + "num_input_tokens_seen": 3153200, + "step": 555, + "train_runtime": 3671.7067, + "train_tokens_per_second": 858.783 + }, + { + "epoch": 1.0219128052955946, + "grad_norm": 1.43285071849823, + "learning_rate": 3.704216724398515e-05, + "loss": 0.7542, + "num_input_tokens_seen": 3180768, + "step": 560, + "train_runtime": 3704.3172, + "train_tokens_per_second": 858.665 + }, + { + "epoch": 1.0310431408354257, + "grad_norm": 1.2489193677902222, + "learning_rate": 3.683229028476334e-05, + "loss": 0.7216, + "num_input_tokens_seen": 3208032, + "step": 565, + "train_runtime": 3736.7691, + "train_tokens_per_second": 858.504 + }, + { + "epoch": 1.0401734763752568, + "grad_norm": 1.520088791847229, + "learning_rate": 3.6621333131842994e-05, + "loss": 0.8276, + "num_input_tokens_seen": 3235216, + "step": 570, + "train_runtime": 3769.2767, + "train_tokens_per_second": 858.312 + }, + { + "epoch": 1.049303811915088, + "grad_norm": 1.1563032865524292, + "learning_rate": 3.640931504392902e-05, + "loss": 0.8081, + "num_input_tokens_seen": 3264128, + "step": 575, + "train_runtime": 3802.3942, + "train_tokens_per_second": 858.44 + }, + { + "epoch": 1.058434147454919, + "grad_norm": 1.2162935733795166, + "learning_rate": 3.6196255376581254e-05, + "loss": 0.7503, + "num_input_tokens_seen": 3291488, + "step": 580, + "train_runtime": 3834.8435, + "train_tokens_per_second": 858.311 + }, + { + "epoch": 1.0675644829947502, + "grad_norm": 1.1006977558135986, + "learning_rate": 3.598217358044743e-05, + "loss": 0.7449, + "num_input_tokens_seen": 3320544, + "step": 585, + "train_runtime": 3868.0173, + "train_tokens_per_second": 858.462 + }, + { + "epoch": 1.076694818534581, + "grad_norm": 1.2781275510787964, + "learning_rate": 3.576708919948747e-05, + "loss": 0.7779, + "num_input_tokens_seen": 3350544, + "step": 590, + "train_runtime": 3901.7778, + "train_tokens_per_second": 858.722 + }, + { + "epoch": 1.0858251540744122, + "grad_norm": 1.8124620914459229, + "learning_rate": 3.5551021869189286e-05, + "loss": 0.7257, + "num_input_tokens_seen": 3380800, + "step": 595, + "train_runtime": 3935.5685, + "train_tokens_per_second": 859.037 + }, + { + "epoch": 1.0949554896142433, + "grad_norm": 1.1860169172286987, + "learning_rate": 3.533399131477624e-05, + "loss": 0.7348, + "num_input_tokens_seen": 3408976, + "step": 600, + "train_runtime": 3968.4791, + "train_tokens_per_second": 859.013 + }, + { + "epoch": 1.1040858251540744, + "grad_norm": 1.4015891551971436, + "learning_rate": 3.511601734940636e-05, + "loss": 0.814, + "num_input_tokens_seen": 3437392, + "step": 605, + "train_runtime": 4002.5648, + "train_tokens_per_second": 858.797 + }, + { + "epoch": 1.1132161606939055, + "grad_norm": 1.445547342300415, + "learning_rate": 3.489711987236357e-05, + "loss": 0.6645, + "num_input_tokens_seen": 3465184, + "step": 610, + "train_runtime": 4035.2092, + "train_tokens_per_second": 858.737 + }, + { + "epoch": 1.1223464962337366, + "grad_norm": 1.2986106872558594, + "learning_rate": 3.467731886724104e-05, + "loss": 0.7804, + "num_input_tokens_seen": 3493520, + "step": 615, + "train_runtime": 4068.2429, + "train_tokens_per_second": 858.729 + }, + { + "epoch": 1.1314768317735677, + "grad_norm": 1.471055030822754, + "learning_rate": 3.445663440011685e-05, + "loss": 0.8645, + "num_input_tokens_seen": 3520400, + "step": 620, + "train_runtime": 4100.7487, + "train_tokens_per_second": 858.477 + }, + { + "epoch": 1.1406071673133988, + "grad_norm": 1.3849546909332275, + "learning_rate": 3.42350866177221e-05, + "loss": 0.7509, + "num_input_tokens_seen": 3550208, + "step": 625, + "train_runtime": 4134.4243, + "train_tokens_per_second": 858.695 + }, + { + "epoch": 1.1497375028532297, + "grad_norm": 1.3286018371582031, + "learning_rate": 3.4012695745601694e-05, + "loss": 0.738, + "num_input_tokens_seen": 3579424, + "step": 630, + "train_runtime": 4167.8838, + "train_tokens_per_second": 858.811 + }, + { + "epoch": 1.158867838393061, + "grad_norm": 1.5071204900741577, + "learning_rate": 3.378948208626792e-05, + "loss": 0.731, + "num_input_tokens_seen": 3608096, + "step": 635, + "train_runtime": 4201.1661, + "train_tokens_per_second": 858.832 + }, + { + "epoch": 1.167998173932892, + "grad_norm": 1.225210428237915, + "learning_rate": 3.356546601734692e-05, + "loss": 0.6878, + "num_input_tokens_seen": 3636352, + "step": 640, + "train_runtime": 4234.2595, + "train_tokens_per_second": 858.793 + }, + { + "epoch": 1.177128509472723, + "grad_norm": 1.3939982652664185, + "learning_rate": 3.3340667989718494e-05, + "loss": 0.6777, + "num_input_tokens_seen": 3665104, + "step": 645, + "train_runtime": 4267.4915, + "train_tokens_per_second": 858.843 + }, + { + "epoch": 1.1862588450125542, + "grad_norm": 1.551377773284912, + "learning_rate": 3.3115108525648995e-05, + "loss": 0.8185, + "num_input_tokens_seen": 3692784, + "step": 650, + "train_runtime": 4300.1569, + "train_tokens_per_second": 858.756 + }, + { + "epoch": 1.1953891805523853, + "grad_norm": 1.4566768407821655, + "learning_rate": 3.288880821691785e-05, + "loss": 0.7367, + "num_input_tokens_seen": 3720544, + "step": 655, + "train_runtime": 4332.9255, + "train_tokens_per_second": 858.668 + }, + { + "epoch": 1.2045195160922164, + "grad_norm": 1.6438571214675903, + "learning_rate": 3.2661787722937705e-05, + "loss": 0.7812, + "num_input_tokens_seen": 3748640, + "step": 660, + "train_runtime": 4365.8382, + "train_tokens_per_second": 858.63 + }, + { + "epoch": 1.2136498516320475, + "grad_norm": 1.207120418548584, + "learning_rate": 3.2434067768868365e-05, + "loss": 0.6602, + "num_input_tokens_seen": 3779312, + "step": 665, + "train_runtime": 4399.8682, + "train_tokens_per_second": 858.96 + }, + { + "epoch": 1.2227801871718786, + "grad_norm": 1.2142479419708252, + "learning_rate": 3.220566914372477e-05, + "loss": 0.7918, + "num_input_tokens_seen": 3807232, + "step": 670, + "train_runtime": 4432.6887, + "train_tokens_per_second": 858.899 + }, + { + "epoch": 1.2319105227117095, + "grad_norm": 1.5016285181045532, + "learning_rate": 3.1976612698479104e-05, + "loss": 0.6596, + "num_input_tokens_seen": 3835568, + "step": 675, + "train_runtime": 4465.6751, + "train_tokens_per_second": 858.9 + }, + { + "epoch": 1.2410408582515409, + "grad_norm": 1.6100620031356812, + "learning_rate": 3.174691934415727e-05, + "loss": 0.595, + "num_input_tokens_seen": 3866240, + "step": 680, + "train_runtime": 4499.6303, + "train_tokens_per_second": 859.235 + }, + { + "epoch": 1.2501711937913718, + "grad_norm": 1.548384666442871, + "learning_rate": 3.151661004992992e-05, + "loss": 0.7421, + "num_input_tokens_seen": 3894400, + "step": 685, + "train_runtime": 4532.4548, + "train_tokens_per_second": 859.225 + }, + { + "epoch": 1.2593015293312029, + "grad_norm": 1.2995214462280273, + "learning_rate": 3.128570584119806e-05, + "loss": 0.8241, + "num_input_tokens_seen": 3917984, + "step": 690, + "train_runtime": 4563.2092, + "train_tokens_per_second": 858.603 + }, + { + "epoch": 1.268431864871034, + "grad_norm": 2.447808027267456, + "learning_rate": 3.105422779767369e-05, + "loss": 0.7889, + "num_input_tokens_seen": 3943952, + "step": 695, + "train_runtime": 4595.1589, + "train_tokens_per_second": 858.284 + }, + { + "epoch": 1.277562200410865, + "grad_norm": 1.6894609928131104, + "learning_rate": 3.08221970514553e-05, + "loss": 0.8462, + "num_input_tokens_seen": 3970976, + "step": 700, + "train_runtime": 4627.5505, + "train_tokens_per_second": 858.116 + }, + { + "epoch": 1.2866925359506962, + "grad_norm": 1.449867844581604, + "learning_rate": 3.058963478509879e-05, + "loss": 0.8064, + "num_input_tokens_seen": 3998816, + "step": 705, + "train_runtime": 4661.3843, + "train_tokens_per_second": 857.86 + }, + { + "epoch": 1.2958228714905273, + "grad_norm": 1.7921152114868164, + "learning_rate": 3.0356562229683534e-05, + "loss": 0.7113, + "num_input_tokens_seen": 4026144, + "step": 710, + "train_runtime": 4693.863, + "train_tokens_per_second": 857.746 + }, + { + "epoch": 1.3049532070303584, + "grad_norm": 1.4323357343673706, + "learning_rate": 3.0123000662874272e-05, + "loss": 0.7086, + "num_input_tokens_seen": 4053232, + "step": 715, + "train_runtime": 4726.3529, + "train_tokens_per_second": 857.581 + }, + { + "epoch": 1.3140835425701893, + "grad_norm": 1.779567837715149, + "learning_rate": 2.9888971406978584e-05, + "loss": 0.6923, + "num_input_tokens_seen": 4080992, + "step": 720, + "train_runtime": 4759.0105, + "train_tokens_per_second": 857.53 + }, + { + "epoch": 1.3232138781100207, + "grad_norm": 1.556424617767334, + "learning_rate": 2.965449582700031e-05, + "loss": 0.7034, + "num_input_tokens_seen": 4108944, + "step": 725, + "train_runtime": 4792.0064, + "train_tokens_per_second": 857.458 + }, + { + "epoch": 1.3323442136498516, + "grad_norm": 1.2673003673553467, + "learning_rate": 2.9419595328689138e-05, + "loss": 0.7029, + "num_input_tokens_seen": 4137872, + "step": 730, + "train_runtime": 4825.2446, + "train_tokens_per_second": 857.547 + }, + { + "epoch": 1.3414745491896827, + "grad_norm": 1.414905309677124, + "learning_rate": 2.918429135658638e-05, + "loss": 0.7442, + "num_input_tokens_seen": 4167120, + "step": 735, + "train_runtime": 4858.5579, + "train_tokens_per_second": 857.687 + }, + { + "epoch": 1.3506048847295138, + "grad_norm": 2.0791618824005127, + "learning_rate": 2.8948605392067322e-05, + "loss": 0.6896, + "num_input_tokens_seen": 4197456, + "step": 740, + "train_runtime": 4892.5846, + "train_tokens_per_second": 857.922 + }, + { + "epoch": 1.359735220269345, + "grad_norm": 1.620800256729126, + "learning_rate": 2.8712558951380097e-05, + "loss": 0.7188, + "num_input_tokens_seen": 4226784, + "step": 745, + "train_runtime": 4926.0456, + "train_tokens_per_second": 858.048 + }, + { + "epoch": 1.368865555809176, + "grad_norm": 1.6217539310455322, + "learning_rate": 2.847617358368142e-05, + "loss": 0.7536, + "num_input_tokens_seen": 4257552, + "step": 750, + "train_runtime": 4960.2606, + "train_tokens_per_second": 858.332 + }, + { + "epoch": 1.3779958913490071, + "grad_norm": 1.5368753671646118, + "learning_rate": 2.8239470869069357e-05, + "loss": 0.6742, + "num_input_tokens_seen": 4285344, + "step": 755, + "train_runtime": 4993.0307, + "train_tokens_per_second": 858.265 + }, + { + "epoch": 1.3871262268888382, + "grad_norm": 1.3456413745880127, + "learning_rate": 2.800247241661321e-05, + "loss": 0.6787, + "num_input_tokens_seen": 4313920, + "step": 760, + "train_runtime": 5026.2219, + "train_tokens_per_second": 858.283 + }, + { + "epoch": 1.3962565624286691, + "grad_norm": 1.3520539999008179, + "learning_rate": 2.776519986238079e-05, + "loss": 0.8232, + "num_input_tokens_seen": 4341584, + "step": 765, + "train_runtime": 5058.8442, + "train_tokens_per_second": 858.217 + }, + { + "epoch": 1.4053868979685005, + "grad_norm": 1.5738906860351562, + "learning_rate": 2.75276748674632e-05, + "loss": 0.7529, + "num_input_tokens_seen": 4369072, + "step": 770, + "train_runtime": 5091.5528, + "train_tokens_per_second": 858.102 + }, + { + "epoch": 1.4145172335083314, + "grad_norm": 1.485304594039917, + "learning_rate": 2.7289919115997374e-05, + "loss": 0.7612, + "num_input_tokens_seen": 4397152, + "step": 775, + "train_runtime": 5124.3984, + "train_tokens_per_second": 858.082 + }, + { + "epoch": 1.4236475690481625, + "grad_norm": 1.7065860033035278, + "learning_rate": 2.7051954313186484e-05, + "loss": 0.777, + "num_input_tokens_seen": 4423120, + "step": 780, + "train_runtime": 5156.3448, + "train_tokens_per_second": 857.801 + }, + { + "epoch": 1.4327779045879936, + "grad_norm": 2.3600783348083496, + "learning_rate": 2.6813802183318404e-05, + "loss": 0.7732, + "num_input_tokens_seen": 4451328, + "step": 785, + "train_runtime": 5189.1907, + "train_tokens_per_second": 857.808 + }, + { + "epoch": 1.4419082401278247, + "grad_norm": 1.3053230047225952, + "learning_rate": 2.6575484467782486e-05, + "loss": 0.6874, + "num_input_tokens_seen": 4480256, + "step": 790, + "train_runtime": 5222.4951, + "train_tokens_per_second": 857.877 + }, + { + "epoch": 1.4510385756676558, + "grad_norm": 1.2987860441207886, + "learning_rate": 2.633702292308473e-05, + "loss": 0.6866, + "num_input_tokens_seen": 4509584, + "step": 795, + "train_runtime": 5255.8931, + "train_tokens_per_second": 858.005 + }, + { + "epoch": 1.460168911207487, + "grad_norm": 1.6623998880386353, + "learning_rate": 2.60984393188616e-05, + "loss": 0.6184, + "num_input_tokens_seen": 4537136, + "step": 800, + "train_runtime": 5288.583, + "train_tokens_per_second": 857.911 + }, + { + "epoch": 1.469299246747318, + "grad_norm": 1.233757734298706, + "learning_rate": 2.5859755435892597e-05, + "loss": 0.6364, + "num_input_tokens_seen": 4565424, + "step": 805, + "train_runtime": 5322.8159, + "train_tokens_per_second": 857.708 + }, + { + "epoch": 1.478429582287149, + "grad_norm": 1.917475700378418, + "learning_rate": 2.5620993064111902e-05, + "loss": 0.7312, + "num_input_tokens_seen": 4592976, + "step": 810, + "train_runtime": 5355.4266, + "train_tokens_per_second": 857.63 + }, + { + "epoch": 1.4875599178269803, + "grad_norm": 1.3960131406784058, + "learning_rate": 2.538217400061907e-05, + "loss": 0.6735, + "num_input_tokens_seen": 4622416, + "step": 815, + "train_runtime": 5388.765, + "train_tokens_per_second": 857.788 + }, + { + "epoch": 1.4966902533668112, + "grad_norm": 2.6439576148986816, + "learning_rate": 2.5143320047689173e-05, + "loss": 0.5681, + "num_input_tokens_seen": 4648848, + "step": 820, + "train_runtime": 5421.0274, + "train_tokens_per_second": 857.558 + }, + { + "epoch": 1.5058205889066423, + "grad_norm": 1.6874146461486816, + "learning_rate": 2.49044530107824e-05, + "loss": 0.7154, + "num_input_tokens_seen": 4674688, + "step": 825, + "train_runtime": 5453.0982, + "train_tokens_per_second": 857.254 + }, + { + "epoch": 1.5149509244464734, + "grad_norm": 2.135629892349243, + "learning_rate": 2.4665594696553428e-05, + "loss": 0.659, + "num_input_tokens_seen": 4700240, + "step": 830, + "train_runtime": 5484.8225, + "train_tokens_per_second": 856.954 + }, + { + "epoch": 1.5240812599863045, + "grad_norm": 1.135087490081787, + "learning_rate": 2.4426766910860585e-05, + "loss": 0.66, + "num_input_tokens_seen": 4729648, + "step": 835, + "train_runtime": 5518.3348, + "train_tokens_per_second": 857.079 + }, + { + "epoch": 1.5332115955261356, + "grad_norm": 1.5050617456436157, + "learning_rate": 2.4187991456775217e-05, + "loss": 0.8048, + "num_input_tokens_seen": 4758944, + "step": 840, + "train_runtime": 5551.5721, + "train_tokens_per_second": 857.225 + }, + { + "epoch": 1.5423419310659665, + "grad_norm": 2.2734262943267822, + "learning_rate": 2.3949290132591197e-05, + "loss": 0.6516, + "num_input_tokens_seen": 4787360, + "step": 845, + "train_runtime": 5584.6087, + "train_tokens_per_second": 857.242 + }, + { + "epoch": 1.5514722666057978, + "grad_norm": 1.2877403497695923, + "learning_rate": 2.3710684729834954e-05, + "loss": 0.6813, + "num_input_tokens_seen": 4815712, + "step": 850, + "train_runtime": 5617.6077, + "train_tokens_per_second": 857.253 + }, + { + "epoch": 1.5606026021456287, + "grad_norm": 1.3478307723999023, + "learning_rate": 2.3472197031276e-05, + "loss": 0.7308, + "num_input_tokens_seen": 4845280, + "step": 855, + "train_runtime": 5651.0463, + "train_tokens_per_second": 857.413 + }, + { + "epoch": 1.56973293768546, + "grad_norm": 1.378150463104248, + "learning_rate": 2.3233848808938453e-05, + "loss": 0.7728, + "num_input_tokens_seen": 4873936, + "step": 860, + "train_runtime": 5684.0879, + "train_tokens_per_second": 857.47 + }, + { + "epoch": 1.578863273225291, + "grad_norm": 1.5141141414642334, + "learning_rate": 2.299566182211333e-05, + "loss": 0.6673, + "num_input_tokens_seen": 4901104, + "step": 865, + "train_runtime": 5716.3954, + "train_tokens_per_second": 857.377 + }, + { + "epoch": 1.587993608765122, + "grad_norm": 1.601626992225647, + "learning_rate": 2.275765781537215e-05, + "loss": 0.7155, + "num_input_tokens_seen": 4929696, + "step": 870, + "train_runtime": 5749.5599, + "train_tokens_per_second": 857.404 + }, + { + "epoch": 1.5971239443049532, + "grad_norm": 1.5736284255981445, + "learning_rate": 2.251985851658181e-05, + "loss": 0.6372, + "num_input_tokens_seen": 4959408, + "step": 875, + "train_runtime": 5783.3079, + "train_tokens_per_second": 857.538 + }, + { + "epoch": 1.6062542798447843, + "grad_norm": 1.464152216911316, + "learning_rate": 2.228228563492098e-05, + "loss": 0.7021, + "num_input_tokens_seen": 4988800, + "step": 880, + "train_runtime": 5816.7568, + "train_tokens_per_second": 857.66 + }, + { + "epoch": 1.6153846153846154, + "grad_norm": 2.137424945831299, + "learning_rate": 2.2044960858898277e-05, + "loss": 0.6923, + "num_input_tokens_seen": 5018752, + "step": 885, + "train_runtime": 5850.4263, + "train_tokens_per_second": 857.844 + }, + { + "epoch": 1.6245149509244463, + "grad_norm": 1.4711562395095825, + "learning_rate": 2.1807905854372242e-05, + "loss": 0.6426, + "num_input_tokens_seen": 5047792, + "step": 890, + "train_runtime": 5883.6717, + "train_tokens_per_second": 857.932 + }, + { + "epoch": 1.6336452864642776, + "grad_norm": 1.6127244234085083, + "learning_rate": 2.1571142262573457e-05, + "loss": 0.5618, + "num_input_tokens_seen": 5076528, + "step": 895, + "train_runtime": 5916.924, + "train_tokens_per_second": 857.967 + }, + { + "epoch": 1.6427756220041085, + "grad_norm": 2.0708415508270264, + "learning_rate": 2.133469169812879e-05, + "loss": 0.616, + "num_input_tokens_seen": 5101504, + "step": 900, + "train_runtime": 5948.3179, + "train_tokens_per_second": 857.638 + }, + { + "epoch": 1.6519059575439399, + "grad_norm": 1.7397692203521729, + "learning_rate": 2.109857574708826e-05, + "loss": 0.6574, + "num_input_tokens_seen": 5129104, + "step": 905, + "train_runtime": 5982.137, + "train_tokens_per_second": 857.403 + }, + { + "epoch": 1.6610362930837708, + "grad_norm": 2.0171751976013184, + "learning_rate": 2.086281596495434e-05, + "loss": 0.6823, + "num_input_tokens_seen": 5156640, + "step": 910, + "train_runtime": 6014.8999, + "train_tokens_per_second": 857.311 + }, + { + "epoch": 1.6701666286236019, + "grad_norm": 1.524135708808899, + "learning_rate": 2.0627433874714115e-05, + "loss": 0.5728, + "num_input_tokens_seen": 5184848, + "step": 915, + "train_runtime": 6047.8057, + "train_tokens_per_second": 857.311 + }, + { + "epoch": 1.679296964163433, + "grad_norm": 1.4557563066482544, + "learning_rate": 2.0392450964874415e-05, + "loss": 0.7025, + "num_input_tokens_seen": 5212928, + "step": 920, + "train_runtime": 6080.8053, + "train_tokens_per_second": 857.276 + }, + { + "epoch": 1.688427299703264, + "grad_norm": 2.1225433349609375, + "learning_rate": 2.015788868750009e-05, + "loss": 0.5986, + "num_input_tokens_seen": 5243568, + "step": 925, + "train_runtime": 6114.7733, + "train_tokens_per_second": 857.525 + }, + { + "epoch": 1.6975576352430952, + "grad_norm": 1.5523720979690552, + "learning_rate": 1.9923768456255594e-05, + "loss": 0.6195, + "num_input_tokens_seen": 5269840, + "step": 930, + "train_runtime": 6146.8665, + "train_tokens_per_second": 857.321 + }, + { + "epoch": 1.7066879707829261, + "grad_norm": 1.5369882583618164, + "learning_rate": 1.969011164445011e-05, + "loss": 0.6283, + "num_input_tokens_seen": 5299120, + "step": 935, + "train_runtime": 6180.3855, + "train_tokens_per_second": 857.409 + }, + { + "epoch": 1.7158183063227574, + "grad_norm": 1.5137027502059937, + "learning_rate": 1.9456939583086303e-05, + "loss": 0.5767, + "num_input_tokens_seen": 5328464, + "step": 940, + "train_runtime": 6213.906, + "train_tokens_per_second": 857.506 + }, + { + "epoch": 1.7249486418625883, + "grad_norm": 1.5988773107528687, + "learning_rate": 1.9224273558913024e-05, + "loss": 0.5237, + "num_input_tokens_seen": 5354896, + "step": 945, + "train_runtime": 6245.9758, + "train_tokens_per_second": 857.335 + }, + { + "epoch": 1.7340789774024197, + "grad_norm": 1.878609538078308, + "learning_rate": 1.8992134812481915e-05, + "loss": 0.7184, + "num_input_tokens_seen": 5383856, + "step": 950, + "train_runtime": 6279.2585, + "train_tokens_per_second": 857.403 + }, + { + "epoch": 1.7432093129422506, + "grad_norm": 1.5450001955032349, + "learning_rate": 1.876054453620841e-05, + "loss": 0.6595, + "num_input_tokens_seen": 5412864, + "step": 955, + "train_runtime": 6312.6127, + "train_tokens_per_second": 857.468 + }, + { + "epoch": 1.7523396484820817, + "grad_norm": 1.623189091682434, + "learning_rate": 1.852952387243698e-05, + "loss": 0.6161, + "num_input_tokens_seen": 5441392, + "step": 960, + "train_runtime": 6345.6472, + "train_tokens_per_second": 857.5 + }, + { + "epoch": 1.7614699840219128, + "grad_norm": 1.7493008375167847, + "learning_rate": 1.829909391151103e-05, + "loss": 0.6076, + "num_input_tokens_seen": 5470928, + "step": 965, + "train_runtime": 6379.1343, + "train_tokens_per_second": 857.629 + }, + { + "epoch": 1.770600319561744, + "grad_norm": 1.557199478149414, + "learning_rate": 1.8069275689847466e-05, + "loss": 0.5543, + "num_input_tokens_seen": 5500576, + "step": 970, + "train_runtime": 6412.7424, + "train_tokens_per_second": 857.757 + }, + { + "epoch": 1.779730655101575, + "grad_norm": 1.6990467309951782, + "learning_rate": 1.784009018801634e-05, + "loss": 0.6496, + "num_input_tokens_seen": 5528288, + "step": 975, + "train_runtime": 6445.5057, + "train_tokens_per_second": 857.697 + }, + { + "epoch": 1.788860990641406, + "grad_norm": 1.5374281406402588, + "learning_rate": 1.7611558328825384e-05, + "loss": 0.6315, + "num_input_tokens_seen": 5557472, + "step": 980, + "train_runtime": 6478.8281, + "train_tokens_per_second": 857.79 + }, + { + "epoch": 1.7979913261812372, + "grad_norm": 1.4920860528945923, + "learning_rate": 1.738370097541e-05, + "loss": 0.5654, + "num_input_tokens_seen": 5585120, + "step": 985, + "train_runtime": 6511.6592, + "train_tokens_per_second": 857.711 + }, + { + "epoch": 1.8071216617210681, + "grad_norm": 1.4632899761199951, + "learning_rate": 1.7156538929328593e-05, + "loss": 0.5803, + "num_input_tokens_seen": 5613760, + "step": 990, + "train_runtime": 6544.853, + "train_tokens_per_second": 857.737 + }, + { + "epoch": 1.8162519972608995, + "grad_norm": 1.9237911701202393, + "learning_rate": 1.6930092928663532e-05, + "loss": 0.5516, + "num_input_tokens_seen": 5643504, + "step": 995, + "train_runtime": 6578.4548, + "train_tokens_per_second": 857.877 + }, + { + "epoch": 1.8253823328007304, + "grad_norm": 2.859373092651367, + "learning_rate": 1.6704383646127973e-05, + "loss": 0.653, + "num_input_tokens_seen": 5671936, + "step": 1000, + "train_runtime": 6611.438, + "train_tokens_per_second": 857.897 + }, + { + "epoch": 1.8345126683405615, + "grad_norm": 1.613446593284607, + "learning_rate": 1.6479431687178584e-05, + "loss": 0.6456, + "num_input_tokens_seen": 5701200, + "step": 1005, + "train_runtime": 6646.1194, + "train_tokens_per_second": 857.824 + }, + { + "epoch": 1.8436430038803926, + "grad_norm": 2.326117753982544, + "learning_rate": 1.6255257588134426e-05, + "loss": 0.6778, + "num_input_tokens_seen": 5728032, + "step": 1010, + "train_runtime": 6678.532, + "train_tokens_per_second": 857.678 + }, + { + "epoch": 1.8527733394202237, + "grad_norm": 1.6666271686553955, + "learning_rate": 1.603188181430216e-05, + "loss": 0.6779, + "num_input_tokens_seen": 5756080, + "step": 1015, + "train_runtime": 6711.4743, + "train_tokens_per_second": 857.648 + }, + { + "epoch": 1.8619036749600548, + "grad_norm": 1.2438191175460815, + "learning_rate": 1.580932475810772e-05, + "loss": 0.5039, + "num_input_tokens_seen": 5785760, + "step": 1020, + "train_runtime": 6745.102, + "train_tokens_per_second": 857.772 + }, + { + "epoch": 1.8710340104998857, + "grad_norm": 1.6979848146438599, + "learning_rate": 1.5587606737234654e-05, + "loss": 0.6694, + "num_input_tokens_seen": 5813936, + "step": 1025, + "train_runtime": 6777.9312, + "train_tokens_per_second": 857.774 + }, + { + "epoch": 1.880164346039717, + "grad_norm": 1.7147233486175537, + "learning_rate": 1.5366747992769287e-05, + "loss": 0.5749, + "num_input_tokens_seen": 5844128, + "step": 1030, + "train_runtime": 6811.7365, + "train_tokens_per_second": 857.95 + }, + { + "epoch": 1.889294681579548, + "grad_norm": 1.3455411195755005, + "learning_rate": 1.5146768687352864e-05, + "loss": 0.5602, + "num_input_tokens_seen": 5872512, + "step": 1035, + "train_runtime": 6844.8473, + "train_tokens_per_second": 857.946 + }, + { + "epoch": 1.8984250171193793, + "grad_norm": 1.3454474210739136, + "learning_rate": 1.4927688903340836e-05, + "loss": 0.645, + "num_input_tokens_seen": 5898992, + "step": 1040, + "train_runtime": 6877.0142, + "train_tokens_per_second": 857.784 + }, + { + "epoch": 1.9075553526592102, + "grad_norm": 1.5111793279647827, + "learning_rate": 1.4709528640969552e-05, + "loss": 0.6209, + "num_input_tokens_seen": 5929632, + "step": 1045, + "train_runtime": 6910.9697, + "train_tokens_per_second": 858.003 + }, + { + "epoch": 1.9166856881990413, + "grad_norm": 1.53132164478302, + "learning_rate": 1.4492307816530375e-05, + "loss": 0.5908, + "num_input_tokens_seen": 5956832, + "step": 1050, + "train_runtime": 6943.4823, + "train_tokens_per_second": 857.903 + }, + { + "epoch": 1.9258160237388724, + "grad_norm": 1.7620954513549805, + "learning_rate": 1.4276046260551462e-05, + "loss": 0.5957, + "num_input_tokens_seen": 5985104, + "step": 1055, + "train_runtime": 6976.3497, + "train_tokens_per_second": 857.913 + }, + { + "epoch": 1.9349463592787035, + "grad_norm": 1.6221617460250854, + "learning_rate": 1.4060763715987418e-05, + "loss": 0.6543, + "num_input_tokens_seen": 6010992, + "step": 1060, + "train_runtime": 7008.2681, + "train_tokens_per_second": 857.7 + }, + { + "epoch": 1.9440766948185346, + "grad_norm": 1.9814153909683228, + "learning_rate": 1.3846479836416929e-05, + "loss": 0.5055, + "num_input_tokens_seen": 6041008, + "step": 1065, + "train_runtime": 7042.0949, + "train_tokens_per_second": 857.842 + }, + { + "epoch": 1.9532070303583655, + "grad_norm": 1.3477661609649658, + "learning_rate": 1.3633214184248521e-05, + "loss": 0.5246, + "num_input_tokens_seen": 6070832, + "step": 1070, + "train_runtime": 7075.8177, + "train_tokens_per_second": 857.969 + }, + { + "epoch": 1.9623373658981969, + "grad_norm": 2.347092390060425, + "learning_rate": 1.342098622893469e-05, + "loss": 0.5412, + "num_input_tokens_seen": 6100064, + "step": 1075, + "train_runtime": 7109.1762, + "train_tokens_per_second": 858.055 + }, + { + "epoch": 1.9714677014380277, + "grad_norm": 1.9612821340560913, + "learning_rate": 1.3209815345194496e-05, + "loss": 0.624, + "num_input_tokens_seen": 6127088, + "step": 1080, + "train_runtime": 7141.5945, + "train_tokens_per_second": 857.944 + }, + { + "epoch": 1.980598036977859, + "grad_norm": 1.7594658136367798, + "learning_rate": 1.2999720811244767e-05, + "loss": 0.5854, + "num_input_tokens_seen": 6154768, + "step": 1085, + "train_runtime": 7174.3094, + "train_tokens_per_second": 857.89 + }, + { + "epoch": 1.98972837251769, + "grad_norm": 1.341110110282898, + "learning_rate": 1.2790721807040216e-05, + "loss": 0.5972, + "num_input_tokens_seen": 6181824, + "step": 1090, + "train_runtime": 7206.6527, + "train_tokens_per_second": 857.794 + }, + { + "epoch": 1.998858708057521, + "grad_norm": 1.0875003337860107, + "learning_rate": 1.2582837412522418e-05, + "loss": 0.5627, + "num_input_tokens_seen": 6211904, + "step": 1095, + "train_runtime": 7240.3539, + "train_tokens_per_second": 857.956 + }, + { + "epoch": 2.0073042684318647, + "grad_norm": 1.4245753288269043, + "learning_rate": 1.2376086605877976e-05, + "loss": 0.544, + "num_input_tokens_seen": 6238272, + "step": 1100, + "train_runtime": 7270.9785, + "train_tokens_per_second": 857.969 + }, + { + "epoch": 2.016434603971696, + "grad_norm": 1.5748745203018188, + "learning_rate": 1.2170488261805978e-05, + "loss": 0.4701, + "num_input_tokens_seen": 6268288, + "step": 1105, + "train_runtime": 7305.8219, + "train_tokens_per_second": 857.985 + }, + { + "epoch": 2.025564939511527, + "grad_norm": 1.5691639184951782, + "learning_rate": 1.1966061149794846e-05, + "loss": 0.4359, + "num_input_tokens_seen": 6299168, + "step": 1110, + "train_runtime": 7339.8668, + "train_tokens_per_second": 858.213 + }, + { + "epoch": 2.0346952750513583, + "grad_norm": 1.7195948362350464, + "learning_rate": 1.176282393240888e-05, + "loss": 0.4436, + "num_input_tokens_seen": 6329296, + "step": 1115, + "train_runtime": 7373.7902, + "train_tokens_per_second": 858.35 + }, + { + "epoch": 2.043825610591189, + "grad_norm": 1.504329800605774, + "learning_rate": 1.1560795163584492e-05, + "loss": 0.5898, + "num_input_tokens_seen": 6356992, + "step": 1120, + "train_runtime": 7406.474, + "train_tokens_per_second": 858.302 + }, + { + "epoch": 2.0529559461310205, + "grad_norm": 1.5670088529586792, + "learning_rate": 1.1359993286936382e-05, + "loss": 0.5882, + "num_input_tokens_seen": 6382256, + "step": 1125, + "train_runtime": 7438.1266, + "train_tokens_per_second": 858.046 + }, + { + "epoch": 2.0620862816708514, + "grad_norm": 1.3568974733352661, + "learning_rate": 1.1160436634073786e-05, + "loss": 0.4388, + "num_input_tokens_seen": 6410016, + "step": 1130, + "train_runtime": 7470.9275, + "train_tokens_per_second": 857.995 + }, + { + "epoch": 2.0712166172106823, + "grad_norm": 1.301599144935608, + "learning_rate": 1.0962143422926929e-05, + "loss": 0.5827, + "num_input_tokens_seen": 6438768, + "step": 1135, + "train_runtime": 7504.1642, + "train_tokens_per_second": 858.026 + }, + { + "epoch": 2.0803469527505136, + "grad_norm": 1.7366254329681396, + "learning_rate": 1.0765131756083899e-05, + "loss": 0.5261, + "num_input_tokens_seen": 6466400, + "step": 1140, + "train_runtime": 7536.8587, + "train_tokens_per_second": 857.97 + }, + { + "epoch": 2.0894772882903445, + "grad_norm": 1.5877344608306885, + "learning_rate": 1.0569419619138012e-05, + "loss": 0.5661, + "num_input_tokens_seen": 6493488, + "step": 1145, + "train_runtime": 7569.2668, + "train_tokens_per_second": 857.875 + }, + { + "epoch": 2.098607623830176, + "grad_norm": 1.3803666830062866, + "learning_rate": 1.0375024879045889e-05, + "loss": 0.538, + "num_input_tokens_seen": 6521104, + "step": 1150, + "train_runtime": 7601.999, + "train_tokens_per_second": 857.814 + }, + { + "epoch": 2.1077379593700067, + "grad_norm": 1.4870142936706543, + "learning_rate": 1.0181965282496289e-05, + "loss": 0.7164, + "num_input_tokens_seen": 6548832, + "step": 1155, + "train_runtime": 7634.8619, + "train_tokens_per_second": 857.754 + }, + { + "epoch": 2.116868294909838, + "grad_norm": 2.605409860610962, + "learning_rate": 9.990258454290055e-06, + "loss": 0.5611, + "num_input_tokens_seen": 6577648, + "step": 1160, + "train_runtime": 7668.0751, + "train_tokens_per_second": 857.796 + }, + { + "epoch": 2.125998630449669, + "grad_norm": 1.7612236738204956, + "learning_rate": 9.799921895731062e-06, + "loss": 0.5341, + "num_input_tokens_seen": 6604720, + "step": 1165, + "train_runtime": 7700.4964, + "train_tokens_per_second": 857.701 + }, + { + "epoch": 2.1351289659895003, + "grad_norm": 1.2417925596237183, + "learning_rate": 9.610972983028493e-06, + "loss": 0.4899, + "num_input_tokens_seen": 6631696, + "step": 1170, + "train_runtime": 7732.822, + "train_tokens_per_second": 857.604 + }, + { + "epoch": 2.144259301529331, + "grad_norm": 1.9707194566726685, + "learning_rate": 9.423428965710554e-06, + "loss": 0.6115, + "num_input_tokens_seen": 6659728, + "step": 1175, + "train_runtime": 7765.6556, + "train_tokens_per_second": 857.587 + }, + { + "epoch": 2.153389637069162, + "grad_norm": 1.5473870038986206, + "learning_rate": 9.237306965049677e-06, + "loss": 0.5713, + "num_input_tokens_seen": 6688928, + "step": 1180, + "train_runtime": 7799.0145, + "train_tokens_per_second": 857.663 + }, + { + "epoch": 2.1625199726089934, + "grad_norm": 1.9179930686950684, + "learning_rate": 9.05262397249955e-06, + "loss": 0.5144, + "num_input_tokens_seen": 6717488, + "step": 1185, + "train_runtime": 7832.0227, + "train_tokens_per_second": 857.695 + }, + { + "epoch": 2.1716503081488243, + "grad_norm": 2.1739985942840576, + "learning_rate": 8.869396848143893e-06, + "loss": 0.5139, + "num_input_tokens_seen": 6746864, + "step": 1190, + "train_runtime": 7865.4644, + "train_tokens_per_second": 857.783 + }, + { + "epoch": 2.1807806436886557, + "grad_norm": 1.552583932876587, + "learning_rate": 8.687642319157279e-06, + "loss": 0.5763, + "num_input_tokens_seen": 6775216, + "step": 1195, + "train_runtime": 7898.5982, + "train_tokens_per_second": 857.774 + }, + { + "epoch": 2.1899109792284865, + "grad_norm": 1.612890362739563, + "learning_rate": 8.507376978278053e-06, + "loss": 0.5669, + "num_input_tokens_seen": 6806496, + "step": 1200, + "train_runtime": 7932.917, + "train_tokens_per_second": 858.007 + }, + { + "epoch": 2.199041314768318, + "grad_norm": 1.8803805112838745, + "learning_rate": 8.328617282293591e-06, + "loss": 0.5508, + "num_input_tokens_seen": 6835744, + "step": 1205, + "train_runtime": 7967.5177, + "train_tokens_per_second": 857.952 + }, + { + "epoch": 2.2081716503081488, + "grad_norm": 1.420291781425476, + "learning_rate": 8.151379550537894e-06, + "loss": 0.5538, + "num_input_tokens_seen": 6864560, + "step": 1210, + "train_runtime": 8000.595, + "train_tokens_per_second": 858.006 + }, + { + "epoch": 2.21730198584798, + "grad_norm": 1.4852449893951416, + "learning_rate": 7.975679963401772e-06, + "loss": 0.4806, + "num_input_tokens_seen": 6893360, + "step": 1215, + "train_runtime": 8033.8187, + "train_tokens_per_second": 858.043 + }, + { + "epoch": 2.226432321387811, + "grad_norm": 1.8254742622375488, + "learning_rate": 7.801534560855703e-06, + "loss": 0.4594, + "num_input_tokens_seen": 6922336, + "step": 1220, + "train_runtime": 8067.0217, + "train_tokens_per_second": 858.103 + }, + { + "epoch": 2.235562656927642, + "grad_norm": 1.6726877689361572, + "learning_rate": 7.628959240985514e-06, + "loss": 0.4625, + "num_input_tokens_seen": 6952464, + "step": 1225, + "train_runtime": 8100.7878, + "train_tokens_per_second": 858.245 + }, + { + "epoch": 2.2446929924674732, + "grad_norm": 1.6740381717681885, + "learning_rate": 7.457969758541009e-06, + "loss": 0.5248, + "num_input_tokens_seen": 6978480, + "step": 1230, + "train_runtime": 8132.8942, + "train_tokens_per_second": 858.056 + }, + { + "epoch": 2.253823328007304, + "grad_norm": 1.6061497926712036, + "learning_rate": 7.288581723497689e-06, + "loss": 0.5796, + "num_input_tokens_seen": 7006576, + "step": 1235, + "train_runtime": 8165.7446, + "train_tokens_per_second": 858.045 + }, + { + "epoch": 2.2629536635471355, + "grad_norm": 1.6302696466445923, + "learning_rate": 7.12081059963168e-06, + "loss": 0.4509, + "num_input_tokens_seen": 7034848, + "step": 1240, + "train_runtime": 8198.7143, + "train_tokens_per_second": 858.043 + }, + { + "epoch": 2.2720839990869663, + "grad_norm": 2.3190863132476807, + "learning_rate": 6.954671703108034e-06, + "loss": 0.4935, + "num_input_tokens_seen": 7064656, + "step": 1245, + "train_runtime": 8232.3363, + "train_tokens_per_second": 858.159 + }, + { + "epoch": 2.2812143346267977, + "grad_norm": 1.5536160469055176, + "learning_rate": 6.790180201082439e-06, + "loss": 0.5073, + "num_input_tokens_seen": 7093536, + "step": 1250, + "train_runtime": 8265.6241, + "train_tokens_per_second": 858.197 + }, + { + "epoch": 2.2903446701666286, + "grad_norm": 1.4936327934265137, + "learning_rate": 6.627351110316635e-06, + "loss": 0.4892, + "num_input_tokens_seen": 7122352, + "step": 1255, + "train_runtime": 8299.0146, + "train_tokens_per_second": 858.217 + }, + { + "epoch": 2.2994750057064595, + "grad_norm": 1.524456262588501, + "learning_rate": 6.466199295807471e-06, + "loss": 0.5268, + "num_input_tokens_seen": 7149840, + "step": 1260, + "train_runtime": 8331.6714, + "train_tokens_per_second": 858.152 + }, + { + "epoch": 2.308605341246291, + "grad_norm": 1.4873135089874268, + "learning_rate": 6.306739469429859e-06, + "loss": 0.5226, + "num_input_tokens_seen": 7175312, + "step": 1265, + "train_runtime": 8363.3798, + "train_tokens_per_second": 857.944 + }, + { + "epoch": 2.317735676786122, + "grad_norm": 1.4220759868621826, + "learning_rate": 6.1489861885936805e-06, + "loss": 0.4098, + "num_input_tokens_seen": 7205408, + "step": 1270, + "train_runtime": 8397.1884, + "train_tokens_per_second": 858.074 + }, + { + "epoch": 2.326866012325953, + "grad_norm": 1.7989997863769531, + "learning_rate": 5.992953854914838e-06, + "loss": 0.5064, + "num_input_tokens_seen": 7230896, + "step": 1275, + "train_runtime": 8428.9734, + "train_tokens_per_second": 857.862 + }, + { + "epoch": 2.335996347865784, + "grad_norm": 1.6997673511505127, + "learning_rate": 5.838656712900487e-06, + "loss": 0.486, + "num_input_tokens_seen": 7258640, + "step": 1280, + "train_runtime": 8461.701, + "train_tokens_per_second": 857.823 + }, + { + "epoch": 2.3451266834056153, + "grad_norm": 1.655226469039917, + "learning_rate": 5.686108848648624e-06, + "loss": 0.5659, + "num_input_tokens_seen": 7287552, + "step": 1285, + "train_runtime": 8494.9769, + "train_tokens_per_second": 857.866 + }, + { + "epoch": 2.354257018945446, + "grad_norm": 1.5733911991119385, + "learning_rate": 5.535324188562157e-06, + "loss": 0.5572, + "num_input_tokens_seen": 7315152, + "step": 1290, + "train_runtime": 8527.6021, + "train_tokens_per_second": 857.821 + }, + { + "epoch": 2.3633873544852775, + "grad_norm": 1.6711825132369995, + "learning_rate": 5.386316498077492e-06, + "loss": 0.5891, + "num_input_tokens_seen": 7341792, + "step": 1295, + "train_runtime": 8559.7095, + "train_tokens_per_second": 857.715 + }, + { + "epoch": 2.3725176900251084, + "grad_norm": 1.575325846672058, + "learning_rate": 5.239099380407916e-06, + "loss": 0.5121, + "num_input_tokens_seen": 7369360, + "step": 1300, + "train_runtime": 8592.4006, + "train_tokens_per_second": 857.66 + }, + { + "epoch": 2.3816480255649397, + "grad_norm": 1.923042893409729, + "learning_rate": 5.09368627530169e-06, + "loss": 0.4585, + "num_input_tokens_seen": 7399936, + "step": 1305, + "train_runtime": 8627.583, + "train_tokens_per_second": 857.707 + }, + { + "epoch": 2.3907783611047706, + "grad_norm": 1.294421911239624, + "learning_rate": 4.950090457815129e-06, + "loss": 0.5115, + "num_input_tokens_seen": 7426080, + "step": 1310, + "train_runtime": 8659.572, + "train_tokens_per_second": 857.557 + }, + { + "epoch": 2.3999086966446015, + "grad_norm": 1.5188215970993042, + "learning_rate": 4.808325037100691e-06, + "loss": 0.3663, + "num_input_tokens_seen": 7454432, + "step": 1315, + "train_runtime": 8701.6759, + "train_tokens_per_second": 856.666 + }, + { + "epoch": 2.409039032184433, + "grad_norm": 1.4130005836486816, + "learning_rate": 4.6684029552101886e-06, + "loss": 0.4918, + "num_input_tokens_seen": 7484848, + "step": 1320, + "train_runtime": 8735.6362, + "train_tokens_per_second": 856.818 + }, + { + "epoch": 2.4181693677242637, + "grad_norm": 1.4493566751480103, + "learning_rate": 4.530336985913333e-06, + "loss": 0.4168, + "num_input_tokens_seen": 7514592, + "step": 1325, + "train_runtime": 8769.282, + "train_tokens_per_second": 856.922 + }, + { + "epoch": 2.427299703264095, + "grad_norm": 1.8940752744674683, + "learning_rate": 4.394139733531555e-06, + "loss": 0.4658, + "num_input_tokens_seen": 7545680, + "step": 1330, + "train_runtime": 8803.6245, + "train_tokens_per_second": 857.111 + }, + { + "epoch": 2.436430038803926, + "grad_norm": 1.8865268230438232, + "learning_rate": 4.259823631787346e-06, + "loss": 0.4081, + "num_input_tokens_seen": 7575472, + "step": 1335, + "train_runtime": 8837.4345, + "train_tokens_per_second": 857.203 + }, + { + "epoch": 2.4455603743437573, + "grad_norm": 1.537660002708435, + "learning_rate": 4.127400942669141e-06, + "loss": 0.4739, + "num_input_tokens_seen": 7604016, + "step": 1340, + "train_runtime": 8870.4991, + "train_tokens_per_second": 857.225 + }, + { + "epoch": 2.454690709883588, + "grad_norm": 1.0611555576324463, + "learning_rate": 3.996883755311917e-06, + "loss": 0.3149, + "num_input_tokens_seen": 7636112, + "step": 1345, + "train_runtime": 8905.1047, + "train_tokens_per_second": 857.498 + }, + { + "epoch": 2.463821045423419, + "grad_norm": 2.0281214714050293, + "learning_rate": 3.868283984893542e-06, + "loss": 0.565, + "num_input_tokens_seen": 7665152, + "step": 1350, + "train_runtime": 8938.4023, + "train_tokens_per_second": 857.553 + }, + { + "epoch": 2.4729513809632504, + "grad_norm": 1.5192010402679443, + "learning_rate": 3.741613371547023e-06, + "loss": 0.4656, + "num_input_tokens_seen": 7692112, + "step": 1355, + "train_runtime": 8970.7428, + "train_tokens_per_second": 857.467 + }, + { + "epoch": 2.4820817165030817, + "grad_norm": 1.6683508157730103, + "learning_rate": 3.6168834792887103e-06, + "loss": 0.4552, + "num_input_tokens_seen": 7720064, + "step": 1360, + "train_runtime": 9003.5935, + "train_tokens_per_second": 857.443 + }, + { + "epoch": 2.4912120520429126, + "grad_norm": 1.5640547275543213, + "learning_rate": 3.494105694962596e-06, + "loss": 0.4571, + "num_input_tokens_seen": 7751040, + "step": 1365, + "train_runtime": 9037.7684, + "train_tokens_per_second": 857.628 + }, + { + "epoch": 2.5003423875827435, + "grad_norm": 2.0412251949310303, + "learning_rate": 3.373291227200806e-06, + "loss": 0.5344, + "num_input_tokens_seen": 7776944, + "step": 1370, + "train_runtime": 9069.7333, + "train_tokens_per_second": 857.461 + }, + { + "epoch": 2.509472723122575, + "grad_norm": 1.6897809505462646, + "learning_rate": 3.2544511054003246e-06, + "loss": 0.501, + "num_input_tokens_seen": 7804880, + "step": 1375, + "train_runtime": 9102.5099, + "train_tokens_per_second": 857.443 + }, + { + "epoch": 2.5186030586624057, + "grad_norm": 1.7537122964859009, + "learning_rate": 3.1375961787160983e-06, + "loss": 0.5723, + "num_input_tokens_seen": 7834144, + "step": 1380, + "train_runtime": 9135.9522, + "train_tokens_per_second": 857.507 + }, + { + "epoch": 2.527733394202237, + "grad_norm": 1.6396698951721191, + "learning_rate": 3.0227371150706035e-06, + "loss": 0.5347, + "num_input_tokens_seen": 7862112, + "step": 1385, + "train_runtime": 9168.7182, + "train_tokens_per_second": 857.493 + }, + { + "epoch": 2.536863729742068, + "grad_norm": 1.4223724603652954, + "learning_rate": 2.9098844001799407e-06, + "loss": 0.4727, + "num_input_tokens_seen": 7889648, + "step": 1390, + "train_runtime": 9201.3802, + "train_tokens_per_second": 857.442 + }, + { + "epoch": 2.5459940652818993, + "grad_norm": 2.2084455490112305, + "learning_rate": 2.7990483365965825e-06, + "loss": 0.6187, + "num_input_tokens_seen": 7917840, + "step": 1395, + "train_runtime": 9234.3184, + "train_tokens_per_second": 857.436 + }, + { + "epoch": 2.55512440082173, + "grad_norm": 1.9658094644546509, + "learning_rate": 2.6902390427688273e-06, + "loss": 0.5945, + "num_input_tokens_seen": 7945968, + "step": 1400, + "train_runtime": 9267.0379, + "train_tokens_per_second": 857.444 + }, + { + "epoch": 2.564254736361561, + "grad_norm": 1.4048709869384766, + "learning_rate": 2.5834664521170504e-06, + "loss": 0.5123, + "num_input_tokens_seen": 7976608, + "step": 1405, + "train_runtime": 9302.2298, + "train_tokens_per_second": 857.494 + }, + { + "epoch": 2.5733850719013924, + "grad_norm": 1.8931680917739868, + "learning_rate": 2.4787403121268955e-06, + "loss": 0.4564, + "num_input_tokens_seen": 8005312, + "step": 1410, + "train_runtime": 9335.3807, + "train_tokens_per_second": 857.524 + }, + { + "epoch": 2.5825154074412233, + "grad_norm": 1.8574892282485962, + "learning_rate": 2.3760701834593806e-06, + "loss": 0.5329, + "num_input_tokens_seen": 8032320, + "step": 1415, + "train_runtime": 9367.8306, + "train_tokens_per_second": 857.437 + }, + { + "epoch": 2.5916457429810547, + "grad_norm": 1.5250113010406494, + "learning_rate": 2.2754654390780924e-06, + "loss": 0.5803, + "num_input_tokens_seen": 8059600, + "step": 1420, + "train_runtime": 9400.4807, + "train_tokens_per_second": 857.36 + }, + { + "epoch": 2.6007760785208855, + "grad_norm": 1.251405954360962, + "learning_rate": 2.1769352633935175e-06, + "loss": 0.4759, + "num_input_tokens_seen": 8090544, + "step": 1425, + "train_runtime": 9434.7027, + "train_tokens_per_second": 857.53 + }, + { + "epoch": 2.609906414060717, + "grad_norm": 2.3054699897766113, + "learning_rate": 2.0804886514245726e-06, + "loss": 0.4964, + "num_input_tokens_seen": 8117472, + "step": 1430, + "train_runtime": 9467.0753, + "train_tokens_per_second": 857.442 + }, + { + "epoch": 2.6190367496005478, + "grad_norm": 1.6009160280227661, + "learning_rate": 1.986134407977416e-06, + "loss": 0.4652, + "num_input_tokens_seen": 8145360, + "step": 1435, + "train_runtime": 9499.7537, + "train_tokens_per_second": 857.429 + }, + { + "epoch": 2.6281670851403787, + "grad_norm": 1.5399287939071655, + "learning_rate": 1.8938811468416695e-06, + "loss": 0.5859, + "num_input_tokens_seen": 8171552, + "step": 1440, + "train_runtime": 9531.6877, + "train_tokens_per_second": 857.304 + }, + { + "epoch": 2.63729742068021, + "grad_norm": 1.5960819721221924, + "learning_rate": 1.8037372900040289e-06, + "loss": 0.6222, + "num_input_tokens_seen": 8199280, + "step": 1445, + "train_runtime": 9564.4618, + "train_tokens_per_second": 857.265 + }, + { + "epoch": 2.6464277562200413, + "grad_norm": 1.9178729057312012, + "learning_rate": 1.7157110668794108e-06, + "loss": 0.3722, + "num_input_tokens_seen": 8226656, + "step": 1450, + "train_runtime": 9596.9118, + "train_tokens_per_second": 857.219 + }, + { + "epoch": 2.6555580917598722, + "grad_norm": 1.9778716564178467, + "learning_rate": 1.6298105135596569e-06, + "loss": 0.5299, + "num_input_tokens_seen": 8255232, + "step": 1455, + "train_runtime": 9630.1532, + "train_tokens_per_second": 857.227 + }, + { + "epoch": 2.664688427299703, + "grad_norm": 1.8453866243362427, + "learning_rate": 1.5460434720799278e-06, + "loss": 0.447, + "num_input_tokens_seen": 8281744, + "step": 1460, + "train_runtime": 9662.2517, + "train_tokens_per_second": 857.124 + }, + { + "epoch": 2.6738187628395345, + "grad_norm": 1.5484800338745117, + "learning_rate": 1.464417589702774e-06, + "loss": 0.3965, + "num_input_tokens_seen": 8310384, + "step": 1465, + "train_runtime": 9695.4301, + "train_tokens_per_second": 857.144 + }, + { + "epoch": 2.6829490983793653, + "grad_norm": 1.297414779663086, + "learning_rate": 1.3849403182199988e-06, + "loss": 0.4579, + "num_input_tokens_seen": 8340384, + "step": 1470, + "train_runtime": 9729.2243, + "train_tokens_per_second": 857.251 + }, + { + "epoch": 2.6920794339191967, + "grad_norm": 1.7842596769332886, + "learning_rate": 1.3076189132723764e-06, + "loss": 0.5361, + "num_input_tokens_seen": 8368224, + "step": 1475, + "train_runtime": 9761.9824, + "train_tokens_per_second": 857.226 + }, + { + "epoch": 2.7012097694590276, + "grad_norm": 1.3124113082885742, + "learning_rate": 1.2324604336872658e-06, + "loss": 0.4439, + "num_input_tokens_seen": 8398976, + "step": 1480, + "train_runtime": 9796.1279, + "train_tokens_per_second": 857.377 + }, + { + "epoch": 2.710340104998859, + "grad_norm": 1.8986421823501587, + "learning_rate": 1.159471740834195e-06, + "loss": 0.3843, + "num_input_tokens_seen": 8426000, + "step": 1485, + "train_runtime": 9828.5258, + "train_tokens_per_second": 857.3 + }, + { + "epoch": 2.71947044053869, + "grad_norm": 1.2986937761306763, + "learning_rate": 1.0886594979984816e-06, + "loss": 0.4191, + "num_input_tokens_seen": 8452800, + "step": 1490, + "train_runtime": 9860.8783, + "train_tokens_per_second": 857.206 + }, + { + "epoch": 2.7286007760785207, + "grad_norm": 1.4023627042770386, + "learning_rate": 1.0200301697729204e-06, + "loss": 0.4898, + "num_input_tokens_seen": 8478592, + "step": 1495, + "train_runtime": 9892.7604, + "train_tokens_per_second": 857.05 + }, + { + "epoch": 2.737731111618352, + "grad_norm": 1.7444908618927002, + "learning_rate": 9.535900214676097e-07, + "loss": 0.4288, + "num_input_tokens_seen": 8506240, + "step": 1500, + "train_runtime": 9925.5818, + "train_tokens_per_second": 857.002 + }, + { + "epoch": 2.746861447158183, + "grad_norm": 1.5377986431121826, + "learning_rate": 8.893451185379958e-07, + "loss": 0.4114, + "num_input_tokens_seen": 8533840, + "step": 1505, + "train_runtime": 9959.5353, + "train_tokens_per_second": 856.851 + }, + { + "epoch": 2.7559917826980143, + "grad_norm": 1.6170401573181152, + "learning_rate": 8.273013260311379e-07, + "loss": 0.4987, + "num_input_tokens_seen": 8559296, + "step": 1510, + "train_runtime": 9991.2783, + "train_tokens_per_second": 856.677 + }, + { + "epoch": 2.765122118237845, + "grad_norm": 2.0063154697418213, + "learning_rate": 7.674643080502724e-07, + "loss": 0.4648, + "num_input_tokens_seen": 8587664, + "step": 1515, + "train_runtime": 10761.2574, + "train_tokens_per_second": 798.017 + }, + { + "epoch": 2.7742524537776765, + "grad_norm": 1.877916693687439, + "learning_rate": 7.098395272377295e-07, + "loss": 0.5213, + "num_input_tokens_seen": 8614480, + "step": 1520, + "train_runtime": 10793.6481, + "train_tokens_per_second": 798.106 + }, + { + "epoch": 2.7833827893175074, + "grad_norm": 1.7010425329208374, + "learning_rate": 6.544322442762318e-07, + "loss": 0.499, + "num_input_tokens_seen": 8642960, + "step": 1525, + "train_runtime": 10826.7994, + "train_tokens_per_second": 798.293 + }, + { + "epoch": 2.7925131248573383, + "grad_norm": 1.5449343919754028, + "learning_rate": 6.012475174086485e-07, + "loss": 0.4285, + "num_input_tokens_seen": 8671248, + "step": 1530, + "train_runtime": 10859.8866, + "train_tokens_per_second": 798.466 + }, + { + "epoch": 2.8016434603971696, + "grad_norm": 1.7787251472473145, + "learning_rate": 5.502902019762002e-07, + "loss": 0.4615, + "num_input_tokens_seen": 8698912, + "step": 1535, + "train_runtime": 10892.5607, + "train_tokens_per_second": 798.61 + }, + { + "epoch": 2.810773795937001, + "grad_norm": 1.502289891242981, + "learning_rate": 5.015649499752279e-07, + "loss": 0.4648, + "num_input_tokens_seen": 8726896, + "step": 1540, + "train_runtime": 10925.4558, + "train_tokens_per_second": 798.767 + }, + { + "epoch": 2.819904131476832, + "grad_norm": 1.522641658782959, + "learning_rate": 4.5507620963247954e-07, + "loss": 0.4858, + "num_input_tokens_seen": 8751920, + "step": 1545, + "train_runtime": 10956.9252, + "train_tokens_per_second": 798.757 + }, + { + "epoch": 2.8290344670166627, + "grad_norm": 2.1871094703674316, + "learning_rate": 4.1082822499903253e-07, + "loss": 0.4944, + "num_input_tokens_seen": 8780080, + "step": 1550, + "train_runtime": 10989.8787, + "train_tokens_per_second": 798.924 + }, + { + "epoch": 2.838164802556494, + "grad_norm": 1.5429576635360718, + "learning_rate": 3.6882503556285307e-07, + "loss": 0.4598, + "num_input_tokens_seen": 8804880, + "step": 1555, + "train_runtime": 11021.2763, + "train_tokens_per_second": 798.898 + }, + { + "epoch": 2.847295138096325, + "grad_norm": 1.883806586265564, + "learning_rate": 3.290704758800139e-07, + "loss": 0.4981, + "num_input_tokens_seen": 8834736, + "step": 1560, + "train_runtime": 11055.0559, + "train_tokens_per_second": 799.158 + }, + { + "epoch": 2.8564254736361563, + "grad_norm": 1.7535673379898071, + "learning_rate": 2.915681752246241e-07, + "loss": 0.5183, + "num_input_tokens_seen": 8862544, + "step": 1565, + "train_runtime": 11087.6895, + "train_tokens_per_second": 799.314 + }, + { + "epoch": 2.865555809175987, + "grad_norm": 2.0906741619110107, + "learning_rate": 2.563215572575273e-07, + "loss": 0.4789, + "num_input_tokens_seen": 8892720, + "step": 1570, + "train_runtime": 11121.4717, + "train_tokens_per_second": 799.599 + }, + { + "epoch": 2.8746861447158185, + "grad_norm": 1.9282186031341553, + "learning_rate": 2.2333383971372413e-07, + "loss": 0.4666, + "num_input_tokens_seen": 8918880, + "step": 1575, + "train_runtime": 11153.5256, + "train_tokens_per_second": 799.647 + }, + { + "epoch": 2.8838164802556494, + "grad_norm": 1.4631140232086182, + "learning_rate": 1.9260803410863226e-07, + "loss": 0.4199, + "num_input_tokens_seen": 8952352, + "step": 1580, + "train_runtime": 11188.7542, + "train_tokens_per_second": 800.121 + }, + { + "epoch": 2.8929468157954803, + "grad_norm": 1.2672832012176514, + "learning_rate": 1.641469454631561e-07, + "loss": 0.4318, + "num_input_tokens_seen": 8981984, + "step": 1585, + "train_runtime": 11222.3784, + "train_tokens_per_second": 800.364 + }, + { + "epoch": 2.9020771513353116, + "grad_norm": 1.3364146947860718, + "learning_rate": 1.3795317204761128e-07, + "loss": 0.36, + "num_input_tokens_seen": 9012864, + "step": 1590, + "train_runtime": 11256.7019, + "train_tokens_per_second": 800.666 + }, + { + "epoch": 2.9112074868751425, + "grad_norm": 1.5411438941955566, + "learning_rate": 1.140291051445197e-07, + "loss": 0.4392, + "num_input_tokens_seen": 9040848, + "step": 1595, + "train_runtime": 11289.6253, + "train_tokens_per_second": 800.81 + }, + { + "epoch": 2.920337822414974, + "grad_norm": 1.6634502410888672, + "learning_rate": 9.237692883031502e-08, + "loss": 0.4489, + "num_input_tokens_seen": 9071104, + "step": 1600, + "train_runtime": 11323.3685, + "train_tokens_per_second": 801.096 + }, + { + "epoch": 2.9294681579548048, + "grad_norm": 1.9743751287460327, + "learning_rate": 7.29986197759408e-08, + "loss": 0.5492, + "num_input_tokens_seen": 9101904, + "step": 1605, + "train_runtime": 11358.5692, + "train_tokens_per_second": 801.325 + }, + { + "epoch": 2.938598493494636, + "grad_norm": 1.0921943187713623, + "learning_rate": 5.589594706640055e-08, + "loss": 0.503, + "num_input_tokens_seen": 9131728, + "step": 1610, + "train_runtime": 11392.3267, + "train_tokens_per_second": 801.568 + }, + { + "epoch": 2.947728829034467, + "grad_norm": 1.501896858215332, + "learning_rate": 4.1070472039259065e-08, + "loss": 0.4689, + "num_input_tokens_seen": 9162144, + "step": 1615, + "train_runtime": 11426.2624, + "train_tokens_per_second": 801.85 + }, + { + "epoch": 2.956859164574298, + "grad_norm": 1.5929884910583496, + "learning_rate": 2.8523548142103673e-08, + "loss": 0.542, + "num_input_tokens_seen": 9189808, + "step": 1620, + "train_runtime": 11458.9394, + "train_tokens_per_second": 801.977 + }, + { + "epoch": 2.965989500114129, + "grad_norm": 1.3482941389083862, + "learning_rate": 1.825632080897366e-08, + "loss": 0.3969, + "num_input_tokens_seen": 9220032, + "step": 1625, + "train_runtime": 11492.8101, + "train_tokens_per_second": 802.243 + }, + { + "epoch": 2.9751198356539605, + "grad_norm": 1.901435136795044, + "learning_rate": 1.026972735581333e-08, + "loss": 0.496, + "num_input_tokens_seen": 9248592, + "step": 1630, + "train_runtime": 11525.8653, + "train_tokens_per_second": 802.421 + }, + { + "epoch": 2.9842501711937914, + "grad_norm": 1.747241735458374, + "learning_rate": 4.564496894882142e-09, + "loss": 0.5585, + "num_input_tokens_seen": 9276416, + "step": 1635, + "train_runtime": 11558.7218, + "train_tokens_per_second": 802.547 + }, + { + "epoch": 2.9933805067336223, + "grad_norm": 1.4872362613677979, + "learning_rate": 1.1411502681996088e-09, + "loss": 0.4553, + "num_input_tokens_seen": 9306352, + "step": 1640, + "train_runtime": 11592.3707, + "train_tokens_per_second": 802.8 + }, + { + "epoch": 3.0, + "num_input_tokens_seen": 9328224, + "step": 1644, + "total_flos": 8.278651518536909e+16, + "train_loss": 0.7471618294860904, + "train_runtime": 11618.0265, + "train_samples_per_second": 2.263, + "train_steps_per_second": 0.142 + } + ], + "logging_steps": 5, + "max_steps": 1644, + "num_input_tokens_seen": 9328224, + "num_train_epochs": 3, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 8.278651518536909e+16, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +} diff --git a/train_2026-01-03/training_args.bin b/train_2026-01-03/training_args.bin new file mode 100644 index 0000000..f255cae --- /dev/null +++ b/train_2026-01-03/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1c49abbca48ff5cef0283d6103fb9370193dff725b5232b4da7a83cdcabbca6 +size 5752 diff --git a/train_2026-01-03/training_args.yaml b/train_2026-01-03/training_args.yaml new file mode 100644 index 0000000..6450ff6 --- /dev/null +++ b/train_2026-01-03/training_args.yaml @@ -0,0 +1,34 @@ +bf16: true +cutoff_len: 2048 +dataset: gpu_aiAgent_zh,gpu_aiAgent_others +dataset_dir: data +ddp_timeout: 180000000 +do_train: true +enable_thinking: true +finetuning_type: lora +flash_attn: auto +gradient_accumulation_steps: 8 +include_num_input_tokens_seen: true +learning_rate: 5.0e-05 +logging_steps: 5 +lora_alpha: 128 +lora_dropout: 0 +lora_rank: 64 +lora_target: all +lr_scheduler_type: cosine +max_grad_norm: 1.0 +max_samples: 100000 +model_name_or_path: Qwen/Qwen3-1.7B-Base +num_train_epochs: 3.0 +optim: adamw_torch +output_dir: saves/Qwen3-1.7B-Base/lora/train_2026-01-03 +packing: false +per_device_train_batch_size: 2 +plot_loss: true +preprocessing_num_workers: 16 +report_to: none +save_steps: 100 +stage: sft +template: default +trust_remote_code: true +warmup_steps: 0 diff --git a/train_2026-01-03/training_loss.png b/train_2026-01-03/training_loss.png new file mode 100644 index 0000000..d87e8d5 Binary files /dev/null and b/train_2026-01-03/training_loss.png differ diff --git a/train_2026-01-03/vocab.json b/train_2026-01-03/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/train_2026-01-03/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833