commit ae5ef8740fcf6a24f318310e3ae10a9f3d07e424 Author: ModelHub XC Date: Tue Jul 14 02:06:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: alexredna/TinyLlama-1.1B-Chat-v1.0-reasoning-v2 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ef9800b --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +license: apache-2.0 +base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0 +tags: +- trl +- sft +- generated_from_trainer +datasets: +- generator +model-index: +- name: TinyLlama-1.1B-Chat-v1.0-reasoning-v2 + results: [] +--- + + + +# TinyLlama-1.1B-Chat-v1.0-reasoning-v2 + +This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the generator dataset. +It achieves the following results on the evaluation set: +- Loss: 1.0186 + +## 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: 4e-05 +- train_batch_size: 10 +- eval_batch_size: 4 +- seed: 42 +- distributed_type: multi-GPU +- gradient_accumulation_steps: 10 +- total_train_batch_size: 100 +- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 +- lr_scheduler_type: cosine +- num_epochs: 4 + +### Training results + +| Training Loss | Epoch | Step | Validation Loss | +|:-------------:|:-----:|:----:|:---------------:| +| 1.0456 | 1.0 | 347 | 1.0360 | +| 0.9714 | 2.0 | 695 | 1.0180 | +| 0.9335 | 3.0 | 1042 | 1.0176 | +| 0.9348 | 3.99 | 1388 | 1.0186 | + + +### Framework versions + +- Transformers 4.36.2 +- Pytorch 2.1.0+cu118 +- Datasets 2.14.6 +- Tokenizers 0.15.0 diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..0015ce4 --- /dev/null +++ b/all_results.json @@ -0,0 +1,13 @@ +{ + "epoch": 3.99, + "eval_loss": 1.0186352729797363, + "eval_runtime": 19.987, + "eval_samples": 1771, + "eval_samples_per_second": 13.959, + "eval_steps_per_second": 3.502, + "train_loss": 0.9866050820185747, + "train_runtime": 37340.4665, + "train_samples": 195052, + "train_samples_per_second": 3.722, + "train_steps_per_second": 0.037 +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..ac2958a --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5632, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 22, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.36.2", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/eval_results.json b/eval_results.json new file mode 100644 index 0000000..b763e5c --- /dev/null +++ b/eval_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.99, + "eval_loss": 1.0186352729797363, + "eval_runtime": 19.987, + "eval_samples": 1771, + "eval_samples_per_second": 13.959, + "eval_steps_per_second": 3.502 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..30ae423 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 1, + "eos_token_id": 2, + "max_length": 2048, + "pad_token_id": 0, + "transformers_version": "4.36.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..2b02245 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:952296589bea8d6e696a52fccedaab119430294947b362b5b2fb9a4fc2842f08 +size 2200119864 diff --git a/runs/Jan05_00-15-37_ml-xtx-machine/events.out.tfevents.1704410561.ml-xtx-machine.23653.0 b/runs/Jan05_00-15-37_ml-xtx-machine/events.out.tfevents.1704410561.ml-xtx-machine.23653.0 new file mode 100644 index 0000000..dc972c5 --- /dev/null +++ b/runs/Jan05_00-15-37_ml-xtx-machine/events.out.tfevents.1704410561.ml-xtx-machine.23653.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16ac64c56655a64247630d949b05e442bb20c1a72807094775e7e49585a9677c +size 4880 diff --git a/runs/Jan05_13-41-47_ml-xtx-machine/events.out.tfevents.1704459785.ml-xtx-machine.10909.0 b/runs/Jan05_13-41-47_ml-xtx-machine/events.out.tfevents.1704459785.ml-xtx-machine.10909.0 new file mode 100644 index 0000000..26c9c79 --- /dev/null +++ b/runs/Jan05_13-41-47_ml-xtx-machine/events.out.tfevents.1704459785.ml-xtx-machine.10909.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89adeae48e15b73128c20ea892493dc6ffb41d8fa317bfd81cf0257020cef718 +size 5050 diff --git a/runs/Jan05_19-28-09_baef1a11cdb4/events.out.tfevents.1704483814.baef1a11cdb4.2661.0 b/runs/Jan05_19-28-09_baef1a11cdb4/events.out.tfevents.1704483814.baef1a11cdb4.2661.0 new file mode 100644 index 0000000..76f2bd2 --- /dev/null +++ b/runs/Jan05_19-28-09_baef1a11cdb4/events.out.tfevents.1704483814.baef1a11cdb4.2661.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efa5d6da1d5a8cb369581f24d5b404f69da3db3581e98c8572a84e6f483aff17 +size 4754 diff --git a/runs/Jan05_19-51-11_baef1a11cdb4/events.out.tfevents.1704485197.baef1a11cdb4.3085.0 b/runs/Jan05_19-51-11_baef1a11cdb4/events.out.tfevents.1704485197.baef1a11cdb4.3085.0 new file mode 100644 index 0000000..e56d249 --- /dev/null +++ b/runs/Jan05_19-51-11_baef1a11cdb4/events.out.tfevents.1704485197.baef1a11cdb4.3085.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84a870c24f7e63ea3d19a0204968d5443b2b62a5d83013fa75e977c5d219f0ec +size 4600 diff --git a/runs/Jan05_20-15-12_baef1a11cdb4/events.out.tfevents.1704486576.baef1a11cdb4.3546.0 b/runs/Jan05_20-15-12_baef1a11cdb4/events.out.tfevents.1704486576.baef1a11cdb4.3546.0 new file mode 100644 index 0000000..01c9757 --- /dev/null +++ b/runs/Jan05_20-15-12_baef1a11cdb4/events.out.tfevents.1704486576.baef1a11cdb4.3546.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b167c8ec4f54ca99c4730377fbf031b6cc4766f3dd2c3d4639c8b8cc03c2bbbf +size 5992 diff --git a/runs/Jan05_20-18-13_ml-xtx-machine/events.out.tfevents.1704483528.ml-xtx-machine.7823.0 b/runs/Jan05_20-18-13_ml-xtx-machine/events.out.tfevents.1704483528.ml-xtx-machine.7823.0 new file mode 100644 index 0000000..8e9bf87 --- /dev/null +++ b/runs/Jan05_20-18-13_ml-xtx-machine/events.out.tfevents.1704483528.ml-xtx-machine.7823.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d446f7e0947d56abbe80f4989d91058e34c900b731aeee2867402d8b0f06bb6f +size 4896 diff --git a/runs/Jan05_21-55-57_12c0322bb846/events.out.tfevents.1704492732.12c0322bb846.2137.0 b/runs/Jan05_21-55-57_12c0322bb846/events.out.tfevents.1704492732.12c0322bb846.2137.0 new file mode 100644 index 0000000..e9157d5 --- /dev/null +++ b/runs/Jan05_21-55-57_12c0322bb846/events.out.tfevents.1704492732.12c0322bb846.2137.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5de6f9f6ecc4a43d0504931b3847421007f877901312069b22ac511fd9e8581c +size 16988 diff --git a/runs/Jan05_21-55-57_12c0322bb846/events.out.tfevents.1704530092.12c0322bb846.2137.1 b/runs/Jan05_21-55-57_12c0322bb846/events.out.tfevents.1704530092.12c0322bb846.2137.1 new file mode 100644 index 0000000..c264d4c --- /dev/null +++ b/runs/Jan05_21-55-57_12c0322bb846/events.out.tfevents.1704530092.12c0322bb846.2137.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342e167a1a34ad3f8f6bf2009bb137b686c9cec915b35284b5fa25946ed64100 +size 359 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..492d4b2 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..942ede1 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,43 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 2048, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..3fdd405 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 3.99, + "train_loss": 0.9866050820185747, + "train_runtime": 37340.4665, + "train_samples": 195052, + "train_samples_per_second": 3.722, + "train_steps_per_second": 0.037 +} \ No newline at end of file diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..5a244cc --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,482 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.9942446043165467, + "eval_steps": 500, + "global_step": 1388, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 3.999994877043978e-05, + "loss": 1.5749, + "step": 1 + }, + { + "epoch": 0.06, + "learning_rate": 3.997951166621575e-05, + "loss": 1.2447, + "step": 20 + }, + { + "epoch": 0.12, + "learning_rate": 3.9918088642045126e-05, + "loss": 1.1636, + "step": 40 + }, + { + "epoch": 0.17, + "learning_rate": 3.981585677303025e-05, + "loss": 1.1379, + "step": 60 + }, + { + "epoch": 0.23, + "learning_rate": 3.967302551523671e-05, + "loss": 1.1114, + "step": 80 + }, + { + "epoch": 0.29, + "learning_rate": 3.948988750611294e-05, + "loss": 1.1086, + "step": 100 + }, + { + "epoch": 0.35, + "learning_rate": 3.9266817964924905e-05, + "loss": 1.0915, + "step": 120 + }, + { + "epoch": 0.4, + "learning_rate": 3.900427392399429e-05, + "loss": 1.075, + "step": 140 + }, + { + "epoch": 0.46, + "learning_rate": 3.870279329231546e-05, + "loss": 1.0875, + "step": 160 + }, + { + "epoch": 0.52, + "learning_rate": 3.836299375346956e-05, + "loss": 1.0696, + "step": 180 + }, + { + "epoch": 0.58, + "learning_rate": 3.798557150009373e-05, + "loss": 1.0614, + "step": 200 + }, + { + "epoch": 0.63, + "learning_rate": 3.757129980749847e-05, + "loss": 1.0638, + "step": 220 + }, + { + "epoch": 0.69, + "learning_rate": 3.712102744935529e-05, + "loss": 1.0545, + "step": 240 + }, + { + "epoch": 0.75, + "learning_rate": 3.6635676958700946e-05, + "loss": 1.0508, + "step": 260 + }, + { + "epoch": 0.81, + "learning_rate": 3.611624273782092e-05, + "loss": 1.0566, + "step": 280 + }, + { + "epoch": 0.86, + "learning_rate": 3.556378902088484e-05, + "loss": 1.0577, + "step": 300 + }, + { + "epoch": 0.92, + "learning_rate": 3.4979447693508e-05, + "loss": 1.0428, + "step": 320 + }, + { + "epoch": 0.98, + "learning_rate": 3.436441597370635e-05, + "loss": 1.0456, + "step": 340 + }, + { + "epoch": 1.0, + "eval_loss": 1.035969614982605, + "eval_runtime": 20.059, + "eval_samples_per_second": 13.909, + "eval_steps_per_second": 3.49, + "step": 347 + }, + { + "epoch": 1.04, + "learning_rate": 3.371995395899618e-05, + "loss": 1.0082, + "step": 360 + }, + { + "epoch": 1.09, + "learning_rate": 3.304738204466437e-05, + "loss": 0.9889, + "step": 380 + }, + { + "epoch": 1.15, + "learning_rate": 3.234807821849838e-05, + "loss": 0.9786, + "step": 400 + }, + { + "epoch": 1.21, + "learning_rate": 3.162347523751894e-05, + "loss": 0.9881, + "step": 420 + }, + { + "epoch": 1.27, + "learning_rate": 3.0875057692499566e-05, + "loss": 0.9747, + "step": 440 + }, + { + "epoch": 1.32, + "learning_rate": 3.0104358966287503e-05, + "loss": 0.9842, + "step": 460 + }, + { + "epoch": 1.38, + "learning_rate": 2.9312958092157724e-05, + "loss": 0.9846, + "step": 480 + }, + { + "epoch": 1.44, + "learning_rate": 2.850247651863686e-05, + "loss": 0.9801, + "step": 500 + }, + { + "epoch": 1.5, + "learning_rate": 2.767457478742533e-05, + "loss": 0.9834, + "step": 520 + }, + { + "epoch": 1.55, + "learning_rate": 2.6830949131224118e-05, + "loss": 0.9831, + "step": 540 + }, + { + "epoch": 1.61, + "learning_rate": 2.5973327998436527e-05, + "loss": 0.9787, + "step": 560 + }, + { + "epoch": 1.67, + "learning_rate": 2.5103468511865456e-05, + "loss": 0.981, + "step": 580 + }, + { + "epoch": 1.73, + "learning_rate": 2.4223152868661535e-05, + "loss": 0.9845, + "step": 600 + }, + { + "epoch": 1.78, + "learning_rate": 2.3334184688898107e-05, + "loss": 0.9754, + "step": 620 + }, + { + "epoch": 1.84, + "learning_rate": 2.2438385320254234e-05, + "loss": 0.9779, + "step": 640 + }, + { + "epoch": 1.9, + "learning_rate": 2.1537590106376758e-05, + "loss": 0.9737, + "step": 660 + }, + { + "epoch": 1.96, + "learning_rate": 2.0633644626567007e-05, + "loss": 0.9714, + "step": 680 + }, + { + "epoch": 2.0, + "eval_loss": 1.0180176496505737, + "eval_runtime": 20.0699, + "eval_samples_per_second": 13.901, + "eval_steps_per_second": 3.488, + "step": 695 + }, + { + "epoch": 2.01, + "learning_rate": 1.9728400914496288e-05, + "loss": 0.9669, + "step": 700 + }, + { + "epoch": 2.07, + "learning_rate": 1.882371366369749e-05, + "loss": 0.9478, + "step": 720 + }, + { + "epoch": 2.13, + "learning_rate": 1.79214364276071e-05, + "loss": 0.9458, + "step": 740 + }, + { + "epoch": 2.19, + "learning_rate": 1.702341782194301e-05, + "loss": 0.9307, + "step": 760 + }, + { + "epoch": 2.24, + "learning_rate": 1.6131497737198942e-05, + "loss": 0.9435, + "step": 780 + }, + { + "epoch": 2.3, + "learning_rate": 1.5247503569015413e-05, + "loss": 0.945, + "step": 800 + }, + { + "epoch": 2.36, + "learning_rate": 1.437324647415053e-05, + "loss": 0.9416, + "step": 820 + }, + { + "epoch": 2.42, + "learning_rate": 1.3510517659721583e-05, + "loss": 0.9476, + "step": 840 + }, + { + "epoch": 2.47, + "learning_rate": 1.2661084713320093e-05, + "loss": 0.946, + "step": 860 + }, + { + "epoch": 2.53, + "learning_rate": 1.182668798151939e-05, + "loss": 0.9414, + "step": 880 + }, + { + "epoch": 2.59, + "learning_rate": 1.1009037004194424e-05, + "loss": 0.9439, + "step": 900 + }, + { + "epoch": 2.65, + "learning_rate": 1.020980701195946e-05, + "loss": 0.9486, + "step": 920 + }, + { + "epoch": 2.71, + "learning_rate": 9.430635493899609e-06, + "loss": 0.949, + "step": 940 + }, + { + "epoch": 2.76, + "learning_rate": 8.673118842628595e-06, + "loss": 0.9376, + "step": 960 + }, + { + "epoch": 2.82, + "learning_rate": 7.938809083546264e-06, + "loss": 0.9432, + "step": 980 + }, + { + "epoch": 2.88, + "learning_rate": 7.229210694997113e-06, + "loss": 0.9457, + "step": 1000 + }, + { + "epoch": 2.94, + "learning_rate": 6.545777525844883e-06, + "loss": 0.9357, + "step": 1020 + }, + { + "epoch": 2.99, + "learning_rate": 5.889909816778458e-06, + "loss": 0.9335, + "step": 1040 + }, + { + "epoch": 3.0, + "eval_loss": 1.0176299810409546, + "eval_runtime": 20.0069, + "eval_samples_per_second": 13.945, + "eval_steps_per_second": 3.499, + "step": 1042 + }, + { + "epoch": 3.05, + "learning_rate": 5.262951331452011e-06, + "loss": 0.937, + "step": 1060 + }, + { + "epoch": 3.11, + "learning_rate": 4.6661866033371506e-06, + "loss": 0.9351, + "step": 1080 + }, + { + "epoch": 3.17, + "learning_rate": 4.100838303927914e-06, + "loss": 0.9415, + "step": 1100 + }, + { + "epoch": 3.22, + "learning_rate": 3.5680647376905666e-06, + "loss": 0.9293, + "step": 1120 + }, + { + "epoch": 3.28, + "learning_rate": 3.0689574688907607e-06, + "loss": 0.9304, + "step": 1140 + }, + { + "epoch": 3.34, + "learning_rate": 2.604539085160218e-06, + "loss": 0.9254, + "step": 1160 + }, + { + "epoch": 3.4, + "learning_rate": 2.1757611023850876e-06, + "loss": 0.9293, + "step": 1180 + }, + { + "epoch": 3.45, + "learning_rate": 1.7835020152084116e-06, + "loss": 0.9391, + "step": 1200 + }, + { + "epoch": 3.51, + "learning_rate": 1.4285654971409902e-06, + "loss": 0.9363, + "step": 1220 + }, + { + "epoch": 3.57, + "learning_rate": 1.1116787539682571e-06, + "loss": 0.9506, + "step": 1240 + }, + { + "epoch": 3.63, + "learning_rate": 8.334910338268054e-07, + "loss": 0.9226, + "step": 1260 + }, + { + "epoch": 3.68, + "learning_rate": 5.945722970031332e-07, + "loss": 0.9305, + "step": 1280 + }, + { + "epoch": 3.74, + "learning_rate": 3.9541204817997283e-07, + "loss": 0.9306, + "step": 1300 + }, + { + "epoch": 3.8, + "learning_rate": 2.3641833352276768e-07, + "loss": 0.9344, + "step": 1320 + }, + { + "epoch": 3.86, + "learning_rate": 1.1791690466107286e-07, + "loss": 0.93, + "step": 1340 + }, + { + "epoch": 3.91, + "learning_rate": 4.0150551277724494e-08, + "loss": 0.9344, + "step": 1360 + }, + { + "epoch": 3.97, + "learning_rate": 3.2786036732557203e-09, + "loss": 0.9348, + "step": 1380 + }, + { + "epoch": 3.99, + "eval_loss": 1.0186352729797363, + "eval_runtime": 19.987, + "eval_samples_per_second": 13.959, + "eval_steps_per_second": 3.502, + "step": 1388 + }, + { + "epoch": 3.99, + "step": 1388, + "total_flos": 1.7642090681398723e+18, + "train_loss": 0.9866050820185747, + "train_runtime": 37340.4665, + "train_samples_per_second": 3.722, + "train_steps_per_second": 0.037 + } + ], + "logging_steps": 20, + "max_steps": 1388, + "num_input_tokens_seen": 0, + "num_train_epochs": 4, + "save_steps": 80, + "total_flos": 1.7642090681398723e+18, + "train_batch_size": 10, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..a1f30f0 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e17cbf8f3c0a176c6460d28bc958b598d7474046216c4028081f81e032aebe6 +size 4856