初始化项目，由ModelHub XC社区提供模型
Model: KKHYA/qwen3-1.7b-fft-if Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.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
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: apache-2.0
|
||||||
|
base_model: Qwen/Qwen3-1.7B
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: qwen3-1.7b-fft-if
|
||||||
|
results: []
|
||||||
|
---
|
||||||
|
|
||||||
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||||
|
should probably proofread and complete it, then remove this comment. -->
|
||||||
|
|
||||||
|
# qwen3-1.7b-fft-if
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) on the mft_tulu3_personas_if, the mft_oasst1, the mft_oasst2, the mft_coconot, the mft_aya and the mft_daring_anteater 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: 1e-05
|
||||||
|
- train_batch_size: 8
|
||||||
|
- eval_batch_size: 8
|
||||||
|
- seed: 42
|
||||||
|
- distributed_type: multi-GPU
|
||||||
|
- num_devices: 8
|
||||||
|
- gradient_accumulation_steps: 2
|
||||||
|
- total_train_batch_size: 128
|
||||||
|
- total_eval_batch_size: 64
|
||||||
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||||
|
- lr_scheduler_type: cosine
|
||||||
|
- lr_scheduler_warmup_steps: 0.1
|
||||||
|
- num_epochs: 2.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 5.2.0
|
||||||
|
- Pytorch 2.11.0+cu130
|
||||||
|
- Datasets 4.0.0
|
||||||
|
- Tokenizers 0.22.2
|
||||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 2.0,
|
||||||
|
"total_flos": 2.312523470065369e+18,
|
||||||
|
"train_loss": 1.0307597314738572,
|
||||||
|
"train_runtime": 2075.8497,
|
||||||
|
"train_samples_per_second": 53.887,
|
||||||
|
"train_steps_per_second": 0.421
|
||||||
|
}
|
||||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
|||||||
|
{%- if tools %}
|
||||||
|
{{- '<|im_start|>system\n' }}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- messages[0].content + '\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||||
|
{%- for tool in tools %}
|
||||||
|
{{- "\n" }}
|
||||||
|
{{- tool | tojson }}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||||
|
{%- else %}
|
||||||
|
{%- if messages[0].role == 'system' %}
|
||||||
|
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||||
|
{%- for message in messages[::-1] %}
|
||||||
|
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||||
|
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||||
|
{%- set ns.multi_step_tool = false %}
|
||||||
|
{%- set ns.last_query_index = index %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- for message in messages %}
|
||||||
|
{%- if message.content is string %}
|
||||||
|
{%- set content = message.content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set content = '' %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||||
|
{%- elif message.role == "assistant" %}
|
||||||
|
{%- set reasoning_content = '' %}
|
||||||
|
{%- if message.reasoning_content is string %}
|
||||||
|
{%- set reasoning_content = message.reasoning_content %}
|
||||||
|
{%- else %}
|
||||||
|
{%- if '</think>' in content %}
|
||||||
|
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||||
|
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if loop.index0 > ns.last_query_index %}
|
||||||
|
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if message.tool_calls %}
|
||||||
|
{%- for tool_call in message.tool_calls %}
|
||||||
|
{%- if (loop.first and content) or (not loop.first) %}
|
||||||
|
{{- '\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- if tool_call.function %}
|
||||||
|
{%- set tool_call = tool_call.function %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<tool_call>\n{"name": "' }}
|
||||||
|
{{- tool_call.name }}
|
||||||
|
{{- '", "arguments": ' }}
|
||||||
|
{%- if tool_call.arguments is string %}
|
||||||
|
{{- tool_call.arguments }}
|
||||||
|
{%- else %}
|
||||||
|
{{- tool_call.arguments | tojson }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '}\n</tool_call>' }}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- elif message.role == "tool" %}
|
||||||
|
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||||
|
{{- '<|im_start|>user' }}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '\n<tool_response>\n' }}
|
||||||
|
{{- content }}
|
||||||
|
{{- '\n</tool_response>' }}
|
||||||
|
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||||
|
{{- '<|im_end|>\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{%- if add_generation_prompt %}
|
||||||
|
{{- '<|im_start|>assistant\n' }}
|
||||||
|
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||||
|
{{- '<think>\n\n</think>\n\n' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endif %}
|
||||||
70
config.json
Normal file
70
config.json
Normal file
@@ -0,0 +1,70 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": null,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"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"
|
||||||
|
],
|
||||||
|
"masked_layers": null,
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 16,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"sliding_window": null,
|
||||||
|
"sparsity_attn": null,
|
||||||
|
"sparsity_mlp": null,
|
||||||
|
"subnet_mode": null,
|
||||||
|
"subnet_type": null,
|
||||||
|
"threshold_attn": null,
|
||||||
|
"threshold_mlp": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"transformers_version": "5.2.0",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": [
|
||||||
|
151645,
|
||||||
|
151643
|
||||||
|
],
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"temperature": 0.6,
|
||||||
|
"top_k": 20,
|
||||||
|
"top_p": 0.95,
|
||||||
|
"transformers_version": "5.2.0"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b1d204b73a3d3b567a5d3e9dd3e619f25b881821be3324b9be65d694c4e9e18a
|
||||||
|
size 4063515640
|
||||||
1427
qwen3_1.7b_if_fft_20260524_054817.log
Normal file
1427
qwen3_1.7b_if_fft_20260524_054817.log
Normal file
File diff suppressed because one or more lines are too long
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
||||||
|
size 11422650
|
||||||
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"backend": "tokenizers",
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_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|>"
|
||||||
|
],
|
||||||
|
"is_local": false,
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 2.0,
|
||||||
|
"total_flos": 2.312523470065369e+18,
|
||||||
|
"train_loss": 1.0307597314738572,
|
||||||
|
"train_runtime": 2075.8497,
|
||||||
|
"train_samples_per_second": 53.887,
|
||||||
|
"train_steps_per_second": 0.421
|
||||||
|
}
|
||||||
88
trainer_log.jsonl
Normal file
88
trainer_log.jsonl
Normal file
@@ -0,0 +1,88 @@
|
|||||||
|
{"current_steps": 10, "total_steps": 874, "loss": 1.393819236755371, "lr": 1.0227272727272729e-06, "epoch": 0.02288329519450801, "percentage": 1.14, "elapsed_time": "0:00:26", "remaining_time": "0:37:56"}
|
||||||
|
{"current_steps": 20, "total_steps": 874, "loss": 1.384445571899414, "lr": 2.1590909090909092e-06, "epoch": 0.04576659038901602, "percentage": 2.29, "elapsed_time": "0:00:50", "remaining_time": "0:36:03"}
|
||||||
|
{"current_steps": 30, "total_steps": 874, "loss": 1.3395289421081542, "lr": 3.2954545454545456e-06, "epoch": 0.06864988558352403, "percentage": 3.43, "elapsed_time": "0:01:15", "remaining_time": "0:35:33"}
|
||||||
|
{"current_steps": 40, "total_steps": 874, "loss": 1.199374008178711, "lr": 4.4318181818181824e-06, "epoch": 0.09153318077803203, "percentage": 4.58, "elapsed_time": "0:01:40", "remaining_time": "0:34:59"}
|
||||||
|
{"current_steps": 50, "total_steps": 874, "loss": 1.1844324111938476, "lr": 5.568181818181818e-06, "epoch": 0.11441647597254005, "percentage": 5.72, "elapsed_time": "0:02:05", "remaining_time": "0:34:24"}
|
||||||
|
{"current_steps": 60, "total_steps": 874, "loss": 1.1506938934326172, "lr": 6.704545454545454e-06, "epoch": 0.13729977116704806, "percentage": 6.86, "elapsed_time": "0:02:30", "remaining_time": "0:34:01"}
|
||||||
|
{"current_steps": 70, "total_steps": 874, "loss": 1.1342477798461914, "lr": 7.840909090909091e-06, "epoch": 0.16018306636155608, "percentage": 8.01, "elapsed_time": "0:02:56", "remaining_time": "0:33:51"}
|
||||||
|
{"current_steps": 80, "total_steps": 874, "loss": 1.0628189086914062, "lr": 8.977272727272727e-06, "epoch": 0.18306636155606407, "percentage": 9.15, "elapsed_time": "0:03:20", "remaining_time": "0:33:07"}
|
||||||
|
{"current_steps": 90, "total_steps": 874, "loss": 1.055792236328125, "lr": 9.999960061285353e-06, "epoch": 0.20594965675057209, "percentage": 10.3, "elapsed_time": "0:03:43", "remaining_time": "0:32:24"}
|
||||||
|
{"current_steps": 100, "total_steps": 874, "loss": 1.0445270538330078, "lr": 9.995168187508393e-06, "epoch": 0.2288329519450801, "percentage": 11.44, "elapsed_time": "0:04:06", "remaining_time": "0:31:51"}
|
||||||
|
{"current_steps": 110, "total_steps": 874, "loss": 1.0704252243041992, "lr": 9.98239734155262e-06, "epoch": 0.2517162471395881, "percentage": 12.59, "elapsed_time": "0:04:31", "remaining_time": "0:31:23"}
|
||||||
|
{"current_steps": 120, "total_steps": 874, "loss": 1.0515583992004394, "lr": 9.961667922776125e-06, "epoch": 0.2745995423340961, "percentage": 13.73, "elapsed_time": "0:04:54", "remaining_time": "0:30:49"}
|
||||||
|
{"current_steps": 130, "total_steps": 874, "loss": 1.05296049118042, "lr": 9.93301304306814e-06, "epoch": 0.2974828375286041, "percentage": 14.87, "elapsed_time": "0:05:17", "remaining_time": "0:30:19"}
|
||||||
|
{"current_steps": 140, "total_steps": 874, "loss": 1.0407039642333984, "lr": 9.896478473958147e-06, "epoch": 0.32036613272311215, "percentage": 16.02, "elapsed_time": "0:05:41", "remaining_time": "0:29:48"}
|
||||||
|
{"current_steps": 150, "total_steps": 874, "loss": 1.015059471130371, "lr": 9.852122573503283e-06, "epoch": 0.34324942791762014, "percentage": 17.16, "elapsed_time": "0:06:05", "remaining_time": "0:29:22"}
|
||||||
|
{"current_steps": 160, "total_steps": 874, "loss": 1.0180091857910156, "lr": 9.800016193070789e-06, "epoch": 0.36613272311212813, "percentage": 18.31, "elapsed_time": "0:06:28", "remaining_time": "0:28:55"}
|
||||||
|
{"current_steps": 170, "total_steps": 874, "loss": 1.060804843902588, "lr": 9.740242564164433e-06, "epoch": 0.3890160183066362, "percentage": 19.45, "elapsed_time": "0:06:51", "remaining_time": "0:28:23"}
|
||||||
|
{"current_steps": 180, "total_steps": 874, "loss": 0.9985034942626954, "lr": 9.672897165475657e-06, "epoch": 0.41189931350114417, "percentage": 20.59, "elapsed_time": "0:07:15", "remaining_time": "0:28:00"}
|
||||||
|
{"current_steps": 190, "total_steps": 874, "loss": 1.0597731590270996, "lr": 9.59808757037183e-06, "epoch": 0.43478260869565216, "percentage": 21.74, "elapsed_time": "0:07:40", "remaining_time": "0:27:38"}
|
||||||
|
{"current_steps": 200, "total_steps": 874, "loss": 1.024726390838623, "lr": 9.515933275065218e-06, "epoch": 0.4576659038901602, "percentage": 22.88, "elapsed_time": "0:08:02", "remaining_time": "0:27:07"}
|
||||||
|
{"current_steps": 210, "total_steps": 874, "loss": 1.046273422241211, "lr": 9.426565507737139e-06, "epoch": 0.4805491990846682, "percentage": 24.03, "elapsed_time": "0:08:26", "remaining_time": "0:26:41"}
|
||||||
|
{"current_steps": 220, "total_steps": 874, "loss": 0.9727144241333008, "lr": 9.330127018922195e-06, "epoch": 0.5034324942791762, "percentage": 25.17, "elapsed_time": "0:08:49", "remaining_time": "0:26:14"}
|
||||||
|
{"current_steps": 230, "total_steps": 874, "loss": 1.0013788223266602, "lr": 9.226771853487411e-06, "epoch": 0.5263157894736842, "percentage": 26.32, "elapsed_time": "0:09:12", "remaining_time": "0:25:46"}
|
||||||
|
{"current_steps": 240, "total_steps": 874, "loss": 1.0090283393859862, "lr": 9.116665104570513e-06, "epoch": 0.5491990846681922, "percentage": 27.46, "elapsed_time": "0:09:37", "remaining_time": "0:25:25"}
|
||||||
|
{"current_steps": 250, "total_steps": 874, "loss": 1.0333093643188476, "lr": 8.999982649870377e-06, "epoch": 0.5720823798627003, "percentage": 28.6, "elapsed_time": "0:10:01", "remaining_time": "0:25:01"}
|
||||||
|
{"current_steps": 260, "total_steps": 874, "loss": 1.0343000411987304, "lr": 8.876910870710885e-06, "epoch": 0.5949656750572082, "percentage": 29.75, "elapsed_time": "0:10:26", "remaining_time": "0:24:39"}
|
||||||
|
{"current_steps": 270, "total_steps": 874, "loss": 1.0472993850708008, "lr": 8.747646354326948e-06, "epoch": 0.6178489702517163, "percentage": 30.89, "elapsed_time": "0:10:49", "remaining_time": "0:24:12"}
|
||||||
|
{"current_steps": 280, "total_steps": 874, "loss": 1.007988166809082, "lr": 8.612395579848244e-06, "epoch": 0.6407322654462243, "percentage": 32.04, "elapsed_time": "0:11:13", "remaining_time": "0:23:49"}
|
||||||
|
{"current_steps": 290, "total_steps": 874, "loss": 1.014136505126953, "lr": 8.47137458848224e-06, "epoch": 0.6636155606407322, "percentage": 33.18, "elapsed_time": "0:11:37", "remaining_time": "0:23:24"}
|
||||||
|
{"current_steps": 300, "total_steps": 874, "loss": 1.047772216796875, "lr": 8.324808638423353e-06, "epoch": 0.6864988558352403, "percentage": 34.32, "elapsed_time": "0:12:02", "remaining_time": "0:23:02"}
|
||||||
|
{"current_steps": 310, "total_steps": 874, "loss": 0.9750609397888184, "lr": 8.172931845039471e-06, "epoch": 0.7093821510297483, "percentage": 35.47, "elapsed_time": "0:12:25", "remaining_time": "0:22:37"}
|
||||||
|
{"current_steps": 320, "total_steps": 874, "loss": 0.9990760803222656, "lr": 8.01598680691057e-06, "epoch": 0.7322654462242563, "percentage": 36.61, "elapsed_time": "0:12:49", "remaining_time": "0:22:11"}
|
||||||
|
{"current_steps": 330, "total_steps": 874, "loss": 1.0234622955322266, "lr": 7.854224218316761e-06, "epoch": 0.7551487414187643, "percentage": 37.76, "elapsed_time": "0:13:10", "remaining_time": "0:21:43"}
|
||||||
|
{"current_steps": 340, "total_steps": 874, "loss": 1.031675434112549, "lr": 7.687902468794803e-06, "epoch": 0.7780320366132724, "percentage": 38.9, "elapsed_time": "0:13:34", "remaining_time": "0:21:19"}
|
||||||
|
{"current_steps": 350, "total_steps": 874, "loss": 0.9884134292602539, "lr": 7.517287230402639e-06, "epoch": 0.8009153318077803, "percentage": 40.05, "elapsed_time": "0:13:56", "remaining_time": "0:20:52"}
|
||||||
|
{"current_steps": 360, "total_steps": 874, "loss": 0.9715648651123047, "lr": 7.342651033351325e-06, "epoch": 0.8237986270022883, "percentage": 41.19, "elapsed_time": "0:14:19", "remaining_time": "0:20:27"}
|
||||||
|
{"current_steps": 370, "total_steps": 874, "loss": 1.0005844116210938, "lr": 7.164272830682161e-06, "epoch": 0.8466819221967964, "percentage": 42.33, "elapsed_time": "0:14:43", "remaining_time": "0:20:03"}
|
||||||
|
{"current_steps": 380, "total_steps": 874, "loss": 1.0225093841552735, "lr": 6.9824375526843705e-06, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "0:15:07", "remaining_time": "0:19:39"}
|
||||||
|
{"current_steps": 390, "total_steps": 874, "loss": 1.0305269241333008, "lr": 6.797435651765123e-06, "epoch": 0.8924485125858124, "percentage": 44.62, "elapsed_time": "0:15:31", "remaining_time": "0:19:15"}
|
||||||
|
{"current_steps": 400, "total_steps": 874, "loss": 0.965084171295166, "lr": 6.609562638498845e-06, "epoch": 0.9153318077803204, "percentage": 45.77, "elapsed_time": "0:15:56", "remaining_time": "0:18:53"}
|
||||||
|
{"current_steps": 410, "total_steps": 874, "loss": 0.9787817001342773, "lr": 6.419118609596948e-06, "epoch": 0.9382151029748284, "percentage": 46.91, "elapsed_time": "0:16:19", "remaining_time": "0:18:28"}
|
||||||
|
{"current_steps": 420, "total_steps": 874, "loss": 1.0170610427856446, "lr": 6.2264077685519246e-06, "epoch": 0.9610983981693364, "percentage": 48.05, "elapsed_time": "0:16:41", "remaining_time": "0:18:02"}
|
||||||
|
{"current_steps": 430, "total_steps": 874, "loss": 1.024329948425293, "lr": 6.031737939721538e-06, "epoch": 0.9839816933638444, "percentage": 49.2, "elapsed_time": "0:17:06", "remaining_time": "0:17:40"}
|
||||||
|
{"current_steps": 440, "total_steps": 874, "loss": 1.0376602172851563, "lr": 5.835420076629273e-06, "epoch": 1.0068649885583525, "percentage": 50.34, "elapsed_time": "0:17:29", "remaining_time": "0:17:15"}
|
||||||
|
{"current_steps": 450, "total_steps": 874, "loss": 0.982276439666748, "lr": 5.6377677652664345e-06, "epoch": 1.0297482837528604, "percentage": 51.49, "elapsed_time": "0:17:52", "remaining_time": "0:16:50"}
|
||||||
|
{"current_steps": 460, "total_steps": 874, "loss": 1.0728231430053712, "lr": 5.439096723189316e-06, "epoch": 1.0526315789473684, "percentage": 52.63, "elapsed_time": "0:18:18", "remaining_time": "0:16:28"}
|
||||||
|
{"current_steps": 470, "total_steps": 874, "loss": 1.0191450119018555, "lr": 5.239724295211541e-06, "epoch": 1.0755148741418765, "percentage": 53.78, "elapsed_time": "0:18:40", "remaining_time": "0:16:03"}
|
||||||
|
{"current_steps": 480, "total_steps": 874, "loss": 1.0118200302124023, "lr": 5.03996894649711e-06, "epoch": 1.0983981693363845, "percentage": 54.92, "elapsed_time": "0:19:05", "remaining_time": "0:15:40"}
|
||||||
|
{"current_steps": 490, "total_steps": 874, "loss": 0.9734249114990234, "lr": 4.840149753863887e-06, "epoch": 1.1212814645308924, "percentage": 56.06, "elapsed_time": "0:19:27", "remaining_time": "0:15:15"}
|
||||||
|
{"current_steps": 500, "total_steps": 874, "loss": 1.0037405014038085, "lr": 4.640585896110054e-06, "epoch": 1.1441647597254005, "percentage": 57.21, "elapsed_time": "0:19:51", "remaining_time": "0:14:51"}
|
||||||
|
{"current_steps": 510, "total_steps": 874, "loss": 1.0057022094726562, "lr": 4.441596144177681e-06, "epoch": 1.1670480549199085, "percentage": 58.35, "elapsed_time": "0:20:20", "remaining_time": "0:14:31"}
|
||||||
|
{"current_steps": 520, "total_steps": 874, "loss": 0.9841510772705078, "lr": 4.243498351967761e-06, "epoch": 1.1899313501144164, "percentage": 59.5, "elapsed_time": "0:20:42", "remaining_time": "0:14:06"}
|
||||||
|
{"current_steps": 530, "total_steps": 874, "loss": 0.9782192230224609, "lr": 4.046608948620098e-06, "epoch": 1.2128146453089246, "percentage": 60.64, "elapsed_time": "0:21:05", "remaining_time": "0:13:41"}
|
||||||
|
{"current_steps": 540, "total_steps": 874, "loss": 0.9990880966186524, "lr": 3.8512424330689855e-06, "epoch": 1.2356979405034325, "percentage": 61.78, "elapsed_time": "0:21:29", "remaining_time": "0:13:17"}
|
||||||
|
{"current_steps": 550, "total_steps": 874, "loss": 1.003445529937744, "lr": 3.657710871682115e-06, "epoch": 1.2585812356979404, "percentage": 62.93, "elapsed_time": "0:21:54", "remaining_time": "0:12:54"}
|
||||||
|
{"current_steps": 560, "total_steps": 874, "loss": 0.9950039863586426, "lr": 3.466323399785072e-06, "epoch": 1.2814645308924484, "percentage": 64.07, "elapsed_time": "0:22:19", "remaining_time": "0:12:31"}
|
||||||
|
{"current_steps": 570, "total_steps": 874, "loss": 1.0134332656860352, "lr": 3.2773857278677414e-06, "epoch": 1.3043478260869565, "percentage": 65.22, "elapsed_time": "0:22:42", "remaining_time": "0:12:06"}
|
||||||
|
{"current_steps": 580, "total_steps": 874, "loss": 1.0345746994018554, "lr": 3.0911996532612966e-06, "epoch": 1.3272311212814645, "percentage": 66.36, "elapsed_time": "0:23:05", "remaining_time": "0:11:42"}
|
||||||
|
{"current_steps": 590, "total_steps": 874, "loss": 0.9831764221191406, "lr": 2.9080625780658455e-06, "epoch": 1.3501144164759724, "percentage": 67.51, "elapsed_time": "0:23:29", "remaining_time": "0:11:18"}
|
||||||
|
{"current_steps": 600, "total_steps": 874, "loss": 0.971280860900879, "lr": 2.7282670340987465e-06, "epoch": 1.3729977116704806, "percentage": 68.65, "elapsed_time": "0:23:54", "remaining_time": "0:10:54"}
|
||||||
|
{"current_steps": 610, "total_steps": 874, "loss": 1.0130719184875487, "lr": 2.552100215622401e-06, "epoch": 1.3958810068649885, "percentage": 69.79, "elapsed_time": "0:24:16", "remaining_time": "0:10:30"}
|
||||||
|
{"current_steps": 620, "total_steps": 874, "loss": 1.0302873611450196, "lr": 2.379843520597937e-06, "epoch": 1.4187643020594964, "percentage": 70.94, "elapsed_time": "0:24:40", "remaining_time": "0:10:06"}
|
||||||
|
{"current_steps": 630, "total_steps": 874, "loss": 1.044809055328369, "lr": 2.2117721011975366e-06, "epoch": 1.4416475972540046, "percentage": 72.08, "elapsed_time": "0:25:03", "remaining_time": "0:09:42"}
|
||||||
|
{"current_steps": 640, "total_steps": 874, "loss": 1.0100820541381836, "lr": 2.0481544242934105e-06, "epoch": 1.4645308924485125, "percentage": 73.23, "elapsed_time": "0:25:26", "remaining_time": "0:09:17"}
|
||||||
|
{"current_steps": 650, "total_steps": 874, "loss": 0.9954021453857422, "lr": 1.8892518426254363e-06, "epoch": 1.4874141876430205, "percentage": 74.37, "elapsed_time": "0:25:49", "remaining_time": "0:08:53"}
|
||||||
|
{"current_steps": 660, "total_steps": 874, "loss": 1.0388307571411133, "lr": 1.735318177332503e-06, "epoch": 1.5102974828375286, "percentage": 75.51, "elapsed_time": "0:26:12", "remaining_time": "0:08:30"}
|
||||||
|
{"current_steps": 670, "total_steps": 874, "loss": 1.023411178588867, "lr": 1.5865993125143297e-06, "epoch": 1.5331807780320366, "percentage": 76.66, "elapsed_time": "0:26:35", "remaining_time": "0:08:05"}
|
||||||
|
{"current_steps": 680, "total_steps": 874, "loss": 1.0003677368164063, "lr": 1.4433328024714583e-06, "epoch": 1.5560640732265445, "percentage": 77.8, "elapsed_time": "0:26:58", "remaining_time": "0:07:41"}
|
||||||
|
{"current_steps": 690, "total_steps": 874, "loss": 0.9492273330688477, "lr": 1.3057474922507124e-06, "epoch": 1.5789473684210527, "percentage": 78.95, "elapsed_time": "0:27:21", "remaining_time": "0:07:17"}
|
||||||
|
{"current_steps": 700, "total_steps": 874, "loss": 1.0218355178833007, "lr": 1.1740631521023176e-06, "epoch": 1.6018306636155606, "percentage": 80.09, "elapsed_time": "0:27:44", "remaining_time": "0:06:53"}
|
||||||
|
{"current_steps": 710, "total_steps": 874, "loss": 1.0344181060791016, "lr": 1.0484901264325026e-06, "epoch": 1.6247139588100685, "percentage": 81.24, "elapsed_time": "0:28:07", "remaining_time": "0:06:29"}
|
||||||
|
{"current_steps": 720, "total_steps": 874, "loss": 0.945091438293457, "lr": 9.292289978123892e-07, "epoch": 1.6475972540045767, "percentage": 82.38, "elapsed_time": "0:28:29", "remaining_time": "0:06:05"}
|
||||||
|
{"current_steps": 730, "total_steps": 874, "loss": 1.0206674575805663, "lr": 8.16470266579813e-07, "epoch": 1.6704805491990846, "percentage": 83.52, "elapsed_time": "0:28:53", "remaining_time": "0:05:41"}
|
||||||
|
{"current_steps": 740, "total_steps": 874, "loss": 1.003372573852539, "lr": 7.103940465458936e-07, "epoch": 1.6933638443935926, "percentage": 84.67, "elapsed_time": "0:29:18", "remaining_time": "0:05:18"}
|
||||||
|
{"current_steps": 750, "total_steps": 874, "loss": 1.002475643157959, "lr": 6.111697772923836e-07, "epoch": 1.7162471395881007, "percentage": 85.81, "elapsed_time": "0:29:41", "remaining_time": "0:04:54"}
|
||||||
|
{"current_steps": 760, "total_steps": 874, "loss": 0.9872116088867188, "lr": 5.189559535193839e-07, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "0:30:03", "remaining_time": "0:04:30"}
|
||||||
|
{"current_steps": 770, "total_steps": 874, "loss": 0.9817548751831054, "lr": 4.338998718757315e-07, "epoch": 1.7620137299771166, "percentage": 88.1, "elapsed_time": "0:30:25", "remaining_time": "0:04:06"}
|
||||||
|
{"current_steps": 780, "total_steps": 874, "loss": 1.0520426750183105, "lr": 3.5613739567645246e-07, "epoch": 1.7848970251716247, "percentage": 89.24, "elapsed_time": "0:30:47", "remaining_time": "0:03:42"}
|
||||||
|
{"current_steps": 790, "total_steps": 874, "loss": 1.01949462890625, "lr": 2.8579273788312433e-07, "epoch": 1.8077803203661327, "percentage": 90.39, "elapsed_time": "0:31:11", "remaining_time": "0:03:18"}
|
||||||
|
{"current_steps": 800, "total_steps": 874, "loss": 0.9677618026733399, "lr": 2.2297826269378653e-07, "epoch": 1.8306636155606406, "percentage": 91.53, "elapsed_time": "0:31:35", "remaining_time": "0:02:55"}
|
||||||
|
{"current_steps": 810, "total_steps": 874, "loss": 1.0336989402770995, "lr": 1.6779430605933233e-07, "epoch": 1.8535469107551488, "percentage": 92.68, "elapsed_time": "0:31:59", "remaining_time": "0:02:31"}
|
||||||
|
{"current_steps": 820, "total_steps": 874, "loss": 1.053194236755371, "lr": 1.203290154130754e-07, "epoch": 1.8764302059496567, "percentage": 93.82, "elapsed_time": "0:32:21", "remaining_time": "0:02:07"}
|
||||||
|
{"current_steps": 830, "total_steps": 874, "loss": 0.9445564270019531, "lr": 8.065820886950404e-08, "epoch": 1.8993135011441646, "percentage": 94.97, "elapsed_time": "0:32:44", "remaining_time": "0:01:44"}
|
||||||
|
{"current_steps": 840, "total_steps": 874, "loss": 1.0015798568725587, "lr": 4.8845254117120265e-08, "epoch": 1.9221967963386728, "percentage": 96.11, "elapsed_time": "0:33:09", "remaining_time": "0:01:20"}
|
||||||
|
{"current_steps": 850, "total_steps": 874, "loss": 0.9959196090698242, "lr": 2.4940967198821553e-08, "epoch": 1.9450800915331807, "percentage": 97.25, "elapsed_time": "0:33:32", "remaining_time": "0:00:56"}
|
||||||
|
{"current_steps": 860, "total_steps": 874, "loss": 0.9756921768188477, "lr": 8.983531341500984e-09, "epoch": 1.9679633867276887, "percentage": 98.4, "elapsed_time": "0:33:55", "remaining_time": "0:00:33"}
|
||||||
|
{"current_steps": 870, "total_steps": 874, "loss": 0.9688234329223633, "lr": 9.984359645276443e-10, "epoch": 1.9908466819221968, "percentage": 99.54, "elapsed_time": "0:34:19", "remaining_time": "0:00:09"}
|
||||||
|
{"current_steps": 874, "total_steps": 874, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:34:34", "remaining_time": "0:00:00"}
|
||||||
652
trainer_state.json
Normal file
652
trainer_state.json
Normal file
@@ -0,0 +1,652 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 2.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 874,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.02288329519450801,
|
||||||
|
"grad_norm": 18.221216778257453,
|
||||||
|
"learning_rate": 1.0227272727272729e-06,
|
||||||
|
"loss": 1.393819236755371,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.04576659038901602,
|
||||||
|
"grad_norm": 14.224119847108293,
|
||||||
|
"learning_rate": 2.1590909090909092e-06,
|
||||||
|
"loss": 1.384445571899414,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.06864988558352403,
|
||||||
|
"grad_norm": 8.084131033987092,
|
||||||
|
"learning_rate": 3.2954545454545456e-06,
|
||||||
|
"loss": 1.3395289421081542,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.09153318077803203,
|
||||||
|
"grad_norm": 4.825162041485144,
|
||||||
|
"learning_rate": 4.4318181818181824e-06,
|
||||||
|
"loss": 1.199374008178711,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.11441647597254005,
|
||||||
|
"grad_norm": 2.620746824810217,
|
||||||
|
"learning_rate": 5.568181818181818e-06,
|
||||||
|
"loss": 1.1844324111938476,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.13729977116704806,
|
||||||
|
"grad_norm": 2.280561836514811,
|
||||||
|
"learning_rate": 6.704545454545454e-06,
|
||||||
|
"loss": 1.1506938934326172,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.16018306636155608,
|
||||||
|
"grad_norm": 1.840017749876338,
|
||||||
|
"learning_rate": 7.840909090909091e-06,
|
||||||
|
"loss": 1.1342477798461914,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.18306636155606407,
|
||||||
|
"grad_norm": 1.4046794648896719,
|
||||||
|
"learning_rate": 8.977272727272727e-06,
|
||||||
|
"loss": 1.0628189086914062,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.20594965675057209,
|
||||||
|
"grad_norm": 1.1261167433814985,
|
||||||
|
"learning_rate": 9.999960061285353e-06,
|
||||||
|
"loss": 1.055792236328125,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2288329519450801,
|
||||||
|
"grad_norm": 1.1859981099000974,
|
||||||
|
"learning_rate": 9.995168187508393e-06,
|
||||||
|
"loss": 1.0445270538330078,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2517162471395881,
|
||||||
|
"grad_norm": 1.050590773848972,
|
||||||
|
"learning_rate": 9.98239734155262e-06,
|
||||||
|
"loss": 1.0704252243041992,
|
||||||
|
"step": 110
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2745995423340961,
|
||||||
|
"grad_norm": 0.9556182185508427,
|
||||||
|
"learning_rate": 9.961667922776125e-06,
|
||||||
|
"loss": 1.0515583992004394,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.2974828375286041,
|
||||||
|
"grad_norm": 1.0596424685797112,
|
||||||
|
"learning_rate": 9.93301304306814e-06,
|
||||||
|
"loss": 1.05296049118042,
|
||||||
|
"step": 130
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.32036613272311215,
|
||||||
|
"grad_norm": 0.9934624870737894,
|
||||||
|
"learning_rate": 9.896478473958147e-06,
|
||||||
|
"loss": 1.0407039642333984,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.34324942791762014,
|
||||||
|
"grad_norm": 0.9296921808311289,
|
||||||
|
"learning_rate": 9.852122573503283e-06,
|
||||||
|
"loss": 1.015059471130371,
|
||||||
|
"step": 150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.36613272311212813,
|
||||||
|
"grad_norm": 1.0926612464245933,
|
||||||
|
"learning_rate": 9.800016193070789e-06,
|
||||||
|
"loss": 1.0180091857910156,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.3890160183066362,
|
||||||
|
"grad_norm": 0.9560875189280538,
|
||||||
|
"learning_rate": 9.740242564164433e-06,
|
||||||
|
"loss": 1.060804843902588,
|
||||||
|
"step": 170
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.41189931350114417,
|
||||||
|
"grad_norm": 1.0082190996618579,
|
||||||
|
"learning_rate": 9.672897165475657e-06,
|
||||||
|
"loss": 0.9985034942626954,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.43478260869565216,
|
||||||
|
"grad_norm": 0.9293505463478718,
|
||||||
|
"learning_rate": 9.59808757037183e-06,
|
||||||
|
"loss": 1.0597731590270996,
|
||||||
|
"step": 190
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4576659038901602,
|
||||||
|
"grad_norm": 0.9174121034502059,
|
||||||
|
"learning_rate": 9.515933275065218e-06,
|
||||||
|
"loss": 1.024726390838623,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4805491990846682,
|
||||||
|
"grad_norm": 0.8785467635869065,
|
||||||
|
"learning_rate": 9.426565507737139e-06,
|
||||||
|
"loss": 1.046273422241211,
|
||||||
|
"step": 210
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5034324942791762,
|
||||||
|
"grad_norm": 0.9212480009396277,
|
||||||
|
"learning_rate": 9.330127018922195e-06,
|
||||||
|
"loss": 0.9727144241333008,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5263157894736842,
|
||||||
|
"grad_norm": 0.9164177333802558,
|
||||||
|
"learning_rate": 9.226771853487411e-06,
|
||||||
|
"loss": 1.0013788223266602,
|
||||||
|
"step": 230
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5491990846681922,
|
||||||
|
"grad_norm": 1.0380197289827424,
|
||||||
|
"learning_rate": 9.116665104570513e-06,
|
||||||
|
"loss": 1.0090283393859862,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5720823798627003,
|
||||||
|
"grad_norm": 1.0045067275254234,
|
||||||
|
"learning_rate": 8.999982649870377e-06,
|
||||||
|
"loss": 1.0333093643188476,
|
||||||
|
"step": 250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.5949656750572082,
|
||||||
|
"grad_norm": 1.0842401366028722,
|
||||||
|
"learning_rate": 8.876910870710885e-06,
|
||||||
|
"loss": 1.0343000411987304,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6178489702517163,
|
||||||
|
"grad_norm": 1.0444944619449643,
|
||||||
|
"learning_rate": 8.747646354326948e-06,
|
||||||
|
"loss": 1.0472993850708008,
|
||||||
|
"step": 270
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6407322654462243,
|
||||||
|
"grad_norm": 0.8966161743607417,
|
||||||
|
"learning_rate": 8.612395579848244e-06,
|
||||||
|
"loss": 1.007988166809082,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6636155606407322,
|
||||||
|
"grad_norm": 1.0512223114619048,
|
||||||
|
"learning_rate": 8.47137458848224e-06,
|
||||||
|
"loss": 1.014136505126953,
|
||||||
|
"step": 290
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6864988558352403,
|
||||||
|
"grad_norm": 0.909017241303456,
|
||||||
|
"learning_rate": 8.324808638423353e-06,
|
||||||
|
"loss": 1.047772216796875,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7093821510297483,
|
||||||
|
"grad_norm": 0.891327607364882,
|
||||||
|
"learning_rate": 8.172931845039471e-06,
|
||||||
|
"loss": 0.9750609397888184,
|
||||||
|
"step": 310
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7322654462242563,
|
||||||
|
"grad_norm": 0.9733547314088673,
|
||||||
|
"learning_rate": 8.01598680691057e-06,
|
||||||
|
"loss": 0.9990760803222656,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7551487414187643,
|
||||||
|
"grad_norm": 0.9568324370937283,
|
||||||
|
"learning_rate": 7.854224218316761e-06,
|
||||||
|
"loss": 1.0234622955322266,
|
||||||
|
"step": 330
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7780320366132724,
|
||||||
|
"grad_norm": 1.2132080107449337,
|
||||||
|
"learning_rate": 7.687902468794803e-06,
|
||||||
|
"loss": 1.031675434112549,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8009153318077803,
|
||||||
|
"grad_norm": 0.8978424025587594,
|
||||||
|
"learning_rate": 7.517287230402639e-06,
|
||||||
|
"loss": 0.9884134292602539,
|
||||||
|
"step": 350
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8237986270022883,
|
||||||
|
"grad_norm": 1.0233402755425876,
|
||||||
|
"learning_rate": 7.342651033351325e-06,
|
||||||
|
"loss": 0.9715648651123047,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8466819221967964,
|
||||||
|
"grad_norm": 0.8907463390137706,
|
||||||
|
"learning_rate": 7.164272830682161e-06,
|
||||||
|
"loss": 1.0005844116210938,
|
||||||
|
"step": 370
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8695652173913043,
|
||||||
|
"grad_norm": 0.9992015638804682,
|
||||||
|
"learning_rate": 6.9824375526843705e-06,
|
||||||
|
"loss": 1.0225093841552735,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8924485125858124,
|
||||||
|
"grad_norm": 0.9423403157154376,
|
||||||
|
"learning_rate": 6.797435651765123e-06,
|
||||||
|
"loss": 1.0305269241333008,
|
||||||
|
"step": 390
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9153318077803204,
|
||||||
|
"grad_norm": 0.9312149542771266,
|
||||||
|
"learning_rate": 6.609562638498845e-06,
|
||||||
|
"loss": 0.965084171295166,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9382151029748284,
|
||||||
|
"grad_norm": 0.8994648058485575,
|
||||||
|
"learning_rate": 6.419118609596948e-06,
|
||||||
|
"loss": 0.9787817001342773,
|
||||||
|
"step": 410
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9610983981693364,
|
||||||
|
"grad_norm": 0.9292959943014952,
|
||||||
|
"learning_rate": 6.2264077685519246e-06,
|
||||||
|
"loss": 1.0170610427856446,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.9839816933638444,
|
||||||
|
"grad_norm": 1.0057392492482709,
|
||||||
|
"learning_rate": 6.031737939721538e-06,
|
||||||
|
"loss": 1.024329948425293,
|
||||||
|
"step": 430
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0068649885583525,
|
||||||
|
"grad_norm": 1.0121140233740662,
|
||||||
|
"learning_rate": 5.835420076629273e-06,
|
||||||
|
"loss": 1.0376602172851563,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0297482837528604,
|
||||||
|
"grad_norm": 0.8930268980879296,
|
||||||
|
"learning_rate": 5.6377677652664345e-06,
|
||||||
|
"loss": 0.982276439666748,
|
||||||
|
"step": 450
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0526315789473684,
|
||||||
|
"grad_norm": 0.9716965280324289,
|
||||||
|
"learning_rate": 5.439096723189316e-06,
|
||||||
|
"loss": 1.0728231430053712,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0755148741418765,
|
||||||
|
"grad_norm": 0.9065141249929061,
|
||||||
|
"learning_rate": 5.239724295211541e-06,
|
||||||
|
"loss": 1.0191450119018555,
|
||||||
|
"step": 470
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0983981693363845,
|
||||||
|
"grad_norm": 0.8012852118037016,
|
||||||
|
"learning_rate": 5.03996894649711e-06,
|
||||||
|
"loss": 1.0118200302124023,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1212814645308924,
|
||||||
|
"grad_norm": 0.9890053077086055,
|
||||||
|
"learning_rate": 4.840149753863887e-06,
|
||||||
|
"loss": 0.9734249114990234,
|
||||||
|
"step": 490
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1441647597254005,
|
||||||
|
"grad_norm": 0.9130820112985458,
|
||||||
|
"learning_rate": 4.640585896110054e-06,
|
||||||
|
"loss": 1.0037405014038085,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1670480549199085,
|
||||||
|
"grad_norm": 0.8720442088124731,
|
||||||
|
"learning_rate": 4.441596144177681e-06,
|
||||||
|
"loss": 1.0057022094726562,
|
||||||
|
"step": 510
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1899313501144164,
|
||||||
|
"grad_norm": 0.8993378778714946,
|
||||||
|
"learning_rate": 4.243498351967761e-06,
|
||||||
|
"loss": 0.9841510772705078,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2128146453089246,
|
||||||
|
"grad_norm": 1.009853776998259,
|
||||||
|
"learning_rate": 4.046608948620098e-06,
|
||||||
|
"loss": 0.9782192230224609,
|
||||||
|
"step": 530
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2356979405034325,
|
||||||
|
"grad_norm": 0.9221177344151149,
|
||||||
|
"learning_rate": 3.8512424330689855e-06,
|
||||||
|
"loss": 0.9990880966186524,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2585812356979404,
|
||||||
|
"grad_norm": 1.0454378267485458,
|
||||||
|
"learning_rate": 3.657710871682115e-06,
|
||||||
|
"loss": 1.003445529937744,
|
||||||
|
"step": 550
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2814645308924484,
|
||||||
|
"grad_norm": 0.8805351505795899,
|
||||||
|
"learning_rate": 3.466323399785072e-06,
|
||||||
|
"loss": 0.9950039863586426,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3043478260869565,
|
||||||
|
"grad_norm": 0.9440338584576333,
|
||||||
|
"learning_rate": 3.2773857278677414e-06,
|
||||||
|
"loss": 1.0134332656860352,
|
||||||
|
"step": 570
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3272311212814645,
|
||||||
|
"grad_norm": 0.9837635767810521,
|
||||||
|
"learning_rate": 3.0911996532612966e-06,
|
||||||
|
"loss": 1.0345746994018554,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3501144164759724,
|
||||||
|
"grad_norm": 1.0390562356673976,
|
||||||
|
"learning_rate": 2.9080625780658455e-06,
|
||||||
|
"loss": 0.9831764221191406,
|
||||||
|
"step": 590
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3729977116704806,
|
||||||
|
"grad_norm": 0.8741142160541207,
|
||||||
|
"learning_rate": 2.7282670340987465e-06,
|
||||||
|
"loss": 0.971280860900879,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3958810068649885,
|
||||||
|
"grad_norm": 1.0166482283158509,
|
||||||
|
"learning_rate": 2.552100215622401e-06,
|
||||||
|
"loss": 1.0130719184875487,
|
||||||
|
"step": 610
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4187643020594964,
|
||||||
|
"grad_norm": 1.0532152530341887,
|
||||||
|
"learning_rate": 2.379843520597937e-06,
|
||||||
|
"loss": 1.0302873611450196,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4416475972540046,
|
||||||
|
"grad_norm": 0.8906594744109658,
|
||||||
|
"learning_rate": 2.2117721011975366e-06,
|
||||||
|
"loss": 1.044809055328369,
|
||||||
|
"step": 630
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4645308924485125,
|
||||||
|
"grad_norm": 0.9182197471145602,
|
||||||
|
"learning_rate": 2.0481544242934105e-06,
|
||||||
|
"loss": 1.0100820541381836,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4874141876430205,
|
||||||
|
"grad_norm": 0.9591797893121556,
|
||||||
|
"learning_rate": 1.8892518426254363e-06,
|
||||||
|
"loss": 0.9954021453857422,
|
||||||
|
"step": 650
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5102974828375286,
|
||||||
|
"grad_norm": 0.9536465128393342,
|
||||||
|
"learning_rate": 1.735318177332503e-06,
|
||||||
|
"loss": 1.0388307571411133,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5331807780320366,
|
||||||
|
"grad_norm": 0.9851344067069513,
|
||||||
|
"learning_rate": 1.5865993125143297e-06,
|
||||||
|
"loss": 1.023411178588867,
|
||||||
|
"step": 670
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5560640732265445,
|
||||||
|
"grad_norm": 0.9120096357238873,
|
||||||
|
"learning_rate": 1.4433328024714583e-06,
|
||||||
|
"loss": 1.0003677368164063,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5789473684210527,
|
||||||
|
"grad_norm": 0.8397516139080035,
|
||||||
|
"learning_rate": 1.3057474922507124e-06,
|
||||||
|
"loss": 0.9492273330688477,
|
||||||
|
"step": 690
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6018306636155606,
|
||||||
|
"grad_norm": 0.9803332570244476,
|
||||||
|
"learning_rate": 1.1740631521023176e-06,
|
||||||
|
"loss": 1.0218355178833007,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6247139588100685,
|
||||||
|
"grad_norm": 1.0071220717489042,
|
||||||
|
"learning_rate": 1.0484901264325026e-06,
|
||||||
|
"loss": 1.0344181060791016,
|
||||||
|
"step": 710
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6475972540045767,
|
||||||
|
"grad_norm": 0.8809638651282645,
|
||||||
|
"learning_rate": 9.292289978123892e-07,
|
||||||
|
"loss": 0.945091438293457,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6704805491990846,
|
||||||
|
"grad_norm": 1.0138393788661297,
|
||||||
|
"learning_rate": 8.16470266579813e-07,
|
||||||
|
"loss": 1.0206674575805663,
|
||||||
|
"step": 730
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6933638443935926,
|
||||||
|
"grad_norm": 0.9183367430377967,
|
||||||
|
"learning_rate": 7.103940465458936e-07,
|
||||||
|
"loss": 1.003372573852539,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7162471395881007,
|
||||||
|
"grad_norm": 0.9808017585038956,
|
||||||
|
"learning_rate": 6.111697772923836e-07,
|
||||||
|
"loss": 1.002475643157959,
|
||||||
|
"step": 750
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7391304347826086,
|
||||||
|
"grad_norm": 0.8875163328550894,
|
||||||
|
"learning_rate": 5.189559535193839e-07,
|
||||||
|
"loss": 0.9872116088867188,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7620137299771166,
|
||||||
|
"grad_norm": 1.0241092820794546,
|
||||||
|
"learning_rate": 4.338998718757315e-07,
|
||||||
|
"loss": 0.9817548751831054,
|
||||||
|
"step": 770
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7848970251716247,
|
||||||
|
"grad_norm": 0.9245308929706272,
|
||||||
|
"learning_rate": 3.5613739567645246e-07,
|
||||||
|
"loss": 1.0520426750183105,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8077803203661327,
|
||||||
|
"grad_norm": 0.9500733954150005,
|
||||||
|
"learning_rate": 2.8579273788312433e-07,
|
||||||
|
"loss": 1.01949462890625,
|
||||||
|
"step": 790
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8306636155606406,
|
||||||
|
"grad_norm": 0.9550573822974243,
|
||||||
|
"learning_rate": 2.2297826269378653e-07,
|
||||||
|
"loss": 0.9677618026733399,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8535469107551488,
|
||||||
|
"grad_norm": 0.8418605949321986,
|
||||||
|
"learning_rate": 1.6779430605933233e-07,
|
||||||
|
"loss": 1.0336989402770995,
|
||||||
|
"step": 810
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8764302059496567,
|
||||||
|
"grad_norm": 0.9224184199250552,
|
||||||
|
"learning_rate": 1.203290154130754e-07,
|
||||||
|
"loss": 1.053194236755371,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8993135011441646,
|
||||||
|
"grad_norm": 0.8702703264528128,
|
||||||
|
"learning_rate": 8.065820886950404e-08,
|
||||||
|
"loss": 0.9445564270019531,
|
||||||
|
"step": 830
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9221967963386728,
|
||||||
|
"grad_norm": 0.8676834240948701,
|
||||||
|
"learning_rate": 4.8845254117120265e-08,
|
||||||
|
"loss": 1.0015798568725587,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9450800915331807,
|
||||||
|
"grad_norm": 1.0429643813275697,
|
||||||
|
"learning_rate": 2.4940967198821553e-08,
|
||||||
|
"loss": 0.9959196090698242,
|
||||||
|
"step": 850
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9679633867276887,
|
||||||
|
"grad_norm": 0.9433672959674375,
|
||||||
|
"learning_rate": 8.983531341500984e-09,
|
||||||
|
"loss": 0.9756921768188477,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9908466819221968,
|
||||||
|
"grad_norm": 1.0526736161532493,
|
||||||
|
"learning_rate": 9.984359645276443e-10,
|
||||||
|
"loss": 0.9688234329223633,
|
||||||
|
"step": 870
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.0,
|
||||||
|
"step": 874,
|
||||||
|
"total_flos": 2.312523470065369e+18,
|
||||||
|
"train_loss": 1.0307597314738572,
|
||||||
|
"train_runtime": 2075.8497,
|
||||||
|
"train_samples_per_second": 53.887,
|
||||||
|
"train_steps_per_second": 0.421
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 10,
|
||||||
|
"max_steps": 874,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 2,
|
||||||
|
"save_steps": 500,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 2.312523470065369e+18,
|
||||||
|
"train_batch_size": 8,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:421177c7c64d41d3d05d4878e6e987397129fabf5068646605ca7e63da1a5c07
|
||||||
|
size 7185
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
Reference in New Issue
Block a user