初始化项目，由ModelHub XC社区提供模型
Model: KKHYA/qwen3-14b-fft-coding Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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
|
||||
eval_coding/fft/saves__qwen3_14b__coding__fft/samples_humaneval_plus_2026-04-30T11-12-27.892956.jsonl 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/Qwen3-14B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: qwen3-14b-fft-coding
|
||||
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. -->
|
||||
|
||||
# qwen3-14b-fft-coding
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B) on the mft_tulu3_personas_code, the mft_evol_codealpaca and the mft_codefeedback 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: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 16
|
||||
- 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: 4.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 5.2.0
|
||||
- Pytorch 2.9.0+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": 4.0,
|
||||
"total_flos": 152338919849984.0,
|
||||
"train_loss": 0.44427714956567643,
|
||||
"train_runtime": 18988.0523,
|
||||
"train_samples_per_second": 6.32,
|
||||
"train_steps_per_second": 0.05
|
||||
}
|
||||
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 %}
|
||||
82
config.json
Normal file
82
config.json
Normal file
@@ -0,0 +1,82 @@
|
||||
{
|
||||
"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": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 17408,
|
||||
"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",
|
||||
"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": 40,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"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": false,
|
||||
"transformers_version": "5.2.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b6e21b03f45f1b1282e7613339e1be7bd1097e3db3790a50b8a4aac2a3cec1e3
|
||||
size 22217071
|
||||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
1187
eval_coding/fft_20260430_105324.log
Normal file
1187
eval_coding/fft_20260430_105324.log
Normal file
File diff suppressed because one or more lines are too long
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:ba121fe79590e2a896250be7b4ebeab86c14bf4f5d5b88ff190463bd750459bf
|
||||
size 29536666272
|
||||
5098
qwen3_14b_coding_fft_20260430_035731.log
Normal file
5098
qwen3_14b_coding_fft_20260430_035731.log
Normal file
File diff suppressed because it is too large
Load Diff
12850
qwen3_14b_coding_fft_20260430_080416.log
Normal file
12850
qwen3_14b_coding_fft_20260430_080416.log
Normal file
File diff suppressed because one or more lines are too long
16395
qwen3_14b_coding_fft_20260430_161911.log
Normal file
16395
qwen3_14b_coding_fft_20260430_161911.log
Normal file
File diff suppressed because it is too large
Load Diff
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": 4.0,
|
||||
"total_flos": 152338919849984.0,
|
||||
"train_loss": 0.44427714956567643,
|
||||
"train_runtime": 18988.0523,
|
||||
"train_samples_per_second": 6.32,
|
||||
"train_steps_per_second": 0.05
|
||||
}
|
||||
95
trainer_log.jsonl
Normal file
95
trainer_log.jsonl
Normal file
@@ -0,0 +1,95 @@
|
||||
{"current_steps": 10, "total_steps": 940, "loss": 0.9603355407714844, "lr": 9.574468085106384e-07, "epoch": 0.042666666666666665, "percentage": 1.06, "elapsed_time": "0:03:18", "remaining_time": "5:08:16"}
|
||||
{"current_steps": 20, "total_steps": 940, "loss": 0.8526813507080078, "lr": 2.021276595744681e-06, "epoch": 0.08533333333333333, "percentage": 2.13, "elapsed_time": "0:06:38", "remaining_time": "5:05:33"}
|
||||
{"current_steps": 30, "total_steps": 940, "loss": 0.7081204414367676, "lr": 3.0851063829787237e-06, "epoch": 0.128, "percentage": 3.19, "elapsed_time": "0:09:54", "remaining_time": "5:00:46"}
|
||||
{"current_steps": 40, "total_steps": 940, "loss": 0.6635202407836914, "lr": 4.148936170212766e-06, "epoch": 0.17066666666666666, "percentage": 4.26, "elapsed_time": "0:13:04", "remaining_time": "4:54:08"}
|
||||
{"current_steps": 50, "total_steps": 940, "loss": 0.6683910369873047, "lr": 5.212765957446809e-06, "epoch": 0.21333333333333335, "percentage": 5.32, "elapsed_time": "0:16:27", "remaining_time": "4:52:51"}
|
||||
{"current_steps": 60, "total_steps": 940, "loss": 0.6275049686431885, "lr": 6.276595744680851e-06, "epoch": 0.256, "percentage": 6.38, "elapsed_time": "0:19:38", "remaining_time": "4:48:07"}
|
||||
{"current_steps": 70, "total_steps": 940, "loss": 0.6528850555419922, "lr": 7.340425531914894e-06, "epoch": 0.2986666666666667, "percentage": 7.45, "elapsed_time": "0:23:08", "remaining_time": "4:47:38"}
|
||||
{"current_steps": 80, "total_steps": 940, "loss": 0.6439791679382324, "lr": 8.404255319148937e-06, "epoch": 0.3413333333333333, "percentage": 8.51, "elapsed_time": "0:26:20", "remaining_time": "4:43:08"}
|
||||
{"current_steps": 90, "total_steps": 940, "loss": 0.6390511989593506, "lr": 9.46808510638298e-06, "epoch": 0.384, "percentage": 9.57, "elapsed_time": "0:29:42", "remaining_time": "4:40:34"}
|
||||
{"current_steps": 100, "total_steps": 940, "loss": 0.6257343292236328, "lr": 9.999138160172624e-06, "epoch": 0.4266666666666667, "percentage": 10.64, "elapsed_time": "0:33:05", "remaining_time": "4:37:59"}
|
||||
{"current_steps": 110, "total_steps": 940, "loss": 0.592672061920166, "lr": 9.99224522409411e-06, "epoch": 0.4693333333333333, "percentage": 11.7, "elapsed_time": "0:36:31", "remaining_time": "4:35:36"}
|
||||
{"current_steps": 120, "total_steps": 940, "loss": 0.6212929725646973, "lr": 9.97846885608885e-06, "epoch": 0.512, "percentage": 12.77, "elapsed_time": "0:39:50", "remaining_time": "4:32:12"}
|
||||
{"current_steps": 130, "total_steps": 940, "loss": 0.6225690364837646, "lr": 9.957828051355817e-06, "epoch": 0.5546666666666666, "percentage": 13.83, "elapsed_time": "0:43:18", "remaining_time": "4:29:53"}
|
||||
{"current_steps": 140, "total_steps": 940, "loss": 0.6189698219299317, "lr": 9.930351269950144e-06, "epoch": 0.5973333333333334, "percentage": 14.89, "elapsed_time": "0:46:43", "remaining_time": "4:26:57"}
|
||||
{"current_steps": 150, "total_steps": 940, "loss": 0.6111098289489746, "lr": 9.896076397541676e-06, "epoch": 0.64, "percentage": 15.96, "elapsed_time": "0:49:54", "remaining_time": "4:22:49"}
|
||||
{"current_steps": 160, "total_steps": 940, "loss": 0.6421695709228515, "lr": 9.855050693177286e-06, "epoch": 0.6826666666666666, "percentage": 17.02, "elapsed_time": "0:53:18", "remaining_time": "4:19:54"}
|
||||
{"current_steps": 170, "total_steps": 940, "loss": 0.6056369781494141, "lr": 9.807330724118906e-06, "epoch": 0.7253333333333334, "percentage": 18.09, "elapsed_time": "0:56:47", "remaining_time": "4:17:16"}
|
||||
{"current_steps": 180, "total_steps": 940, "loss": 0.6315202236175537, "lr": 9.752982287847193e-06, "epoch": 0.768, "percentage": 19.15, "elapsed_time": "1:00:08", "remaining_time": "4:13:57"}
|
||||
{"current_steps": 190, "total_steps": 940, "loss": 0.6108819961547851, "lr": 9.692080321338317e-06, "epoch": 0.8106666666666666, "percentage": 20.21, "elapsed_time": "1:03:31", "remaining_time": "4:10:47"}
|
||||
{"current_steps": 200, "total_steps": 940, "loss": 0.6224051475524902, "lr": 9.624708797739002e-06, "epoch": 0.8533333333333334, "percentage": 21.28, "elapsed_time": "1:06:56", "remaining_time": "4:07:40"}
|
||||
{"current_steps": 210, "total_steps": 940, "loss": 0.6080554485321045, "lr": 9.550960610582251e-06, "epoch": 0.896, "percentage": 22.34, "elapsed_time": "1:10:24", "remaining_time": "4:04:45"}
|
||||
{"current_steps": 220, "total_steps": 940, "loss": 0.6155075073242188, "lr": 9.47093744570344e-06, "epoch": 0.9386666666666666, "percentage": 23.4, "elapsed_time": "1:13:38", "remaining_time": "4:01:01"}
|
||||
{"current_steps": 230, "total_steps": 940, "loss": 0.6900673866271972, "lr": 9.384749641033358e-06, "epoch": 0.9813333333333333, "percentage": 24.47, "elapsed_time": "1:16:47", "remaining_time": "3:57:04"}
|
||||
{"current_steps": 240, "total_steps": 940, "loss": 0.5847660064697265, "lr": 9.292516034461517e-06, "epoch": 1.0213333333333334, "percentage": 25.53, "elapsed_time": "1:20:02", "remaining_time": "3:53:28"}
|
||||
{"current_steps": 250, "total_steps": 940, "loss": 0.4798769950866699, "lr": 9.194363799979517e-06, "epoch": 1.064, "percentage": 26.6, "elapsed_time": "1:23:29", "remaining_time": "3:50:25"}
|
||||
{"current_steps": 260, "total_steps": 940, "loss": 0.5030141830444336, "lr": 9.090428272330381e-06, "epoch": 1.1066666666666667, "percentage": 27.66, "elapsed_time": "1:27:04", "remaining_time": "3:47:44"}
|
||||
{"current_steps": 270, "total_steps": 940, "loss": 0.5117604255676269, "lr": 8.980852760405645e-06, "epoch": 1.1493333333333333, "percentage": 28.72, "elapsed_time": "1:30:27", "remaining_time": "3:44:28"}
|
||||
{"current_steps": 280, "total_steps": 940, "loss": 0.5203066349029541, "lr": 8.865788349647496e-06, "epoch": 1.192, "percentage": 29.79, "elapsed_time": "1:33:37", "remaining_time": "3:40:40"}
|
||||
{"current_steps": 290, "total_steps": 940, "loss": 0.49484944343566895, "lr": 8.745393693728395e-06, "epoch": 1.2346666666666666, "percentage": 30.85, "elapsed_time": "1:36:57", "remaining_time": "3:37:19"}
|
||||
{"current_steps": 300, "total_steps": 940, "loss": 0.5042594909667969, "lr": 8.619834795795458e-06, "epoch": 1.2773333333333334, "percentage": 31.91, "elapsed_time": "1:40:10", "remaining_time": "3:33:43"}
|
||||
{"current_steps": 310, "total_steps": 940, "loss": 0.5075913429260254, "lr": 8.489284779581179e-06, "epoch": 1.32, "percentage": 32.98, "elapsed_time": "1:43:44", "remaining_time": "3:30:49"}
|
||||
{"current_steps": 320, "total_steps": 940, "loss": 0.5113458156585693, "lr": 8.353923650696119e-06, "epoch": 1.3626666666666667, "percentage": 34.04, "elapsed_time": "1:46:59", "remaining_time": "3:27:16"}
|
||||
{"current_steps": 330, "total_steps": 940, "loss": 0.5259346961975098, "lr": 8.213938048432697e-06, "epoch": 1.4053333333333333, "percentage": 35.11, "elapsed_time": "1:50:19", "remaining_time": "3:23:55"}
|
||||
{"current_steps": 340, "total_steps": 940, "loss": 0.4647953987121582, "lr": 8.069520988422292e-06, "epoch": 1.448, "percentage": 36.17, "elapsed_time": "1:53:37", "remaining_time": "3:20:30"}
|
||||
{"current_steps": 350, "total_steps": 940, "loss": 0.5107015609741211, "lr": 7.920871596500473e-06, "epoch": 1.4906666666666666, "percentage": 37.23, "elapsed_time": "1:56:50", "remaining_time": "3:16:57"}
|
||||
{"current_steps": 360, "total_steps": 940, "loss": 0.4998687744140625, "lr": 7.768194834147362e-06, "epoch": 1.5333333333333332, "percentage": 38.3, "elapsed_time": "2:00:03", "remaining_time": "3:13:25"}
|
||||
{"current_steps": 370, "total_steps": 940, "loss": 0.518181037902832, "lr": 7.611701215881635e-06, "epoch": 1.576, "percentage": 39.36, "elapsed_time": "2:03:31", "remaining_time": "3:10:17"}
|
||||
{"current_steps": 380, "total_steps": 940, "loss": 0.5033650398254395, "lr": 7.4516065189978625e-06, "epoch": 1.6186666666666667, "percentage": 40.43, "elapsed_time": "2:06:48", "remaining_time": "3:06:52"}
|
||||
{"current_steps": 390, "total_steps": 940, "loss": 0.5123775482177735, "lr": 7.288131486047414e-06, "epoch": 1.6613333333333333, "percentage": 41.49, "elapsed_time": "2:10:04", "remaining_time": "3:03:26"}
|
||||
{"current_steps": 400, "total_steps": 940, "loss": 0.4882556438446045, "lr": 7.121501520473137e-06, "epoch": 1.704, "percentage": 42.55, "elapsed_time": "2:13:31", "remaining_time": "3:00:15"}
|
||||
{"current_steps": 410, "total_steps": 940, "loss": 0.48767690658569335, "lr": 6.9519463758174745e-06, "epoch": 1.7466666666666666, "percentage": 43.62, "elapsed_time": "2:16:46", "remaining_time": "2:56:48"}
|
||||
{"current_steps": 420, "total_steps": 940, "loss": 0.5198426246643066, "lr": 6.77969983893257e-06, "epoch": 1.7893333333333334, "percentage": 44.68, "elapsed_time": "2:20:22", "remaining_time": "2:53:47"}
|
||||
{"current_steps": 430, "total_steps": 940, "loss": 0.5152793884277344, "lr": 6.604999407629137e-06, "epoch": 1.8319999999999999, "percentage": 45.74, "elapsed_time": "2:24:00", "remaining_time": "2:50:48"}
|
||||
{"current_steps": 440, "total_steps": 940, "loss": 0.521914005279541, "lr": 6.428085963208567e-06, "epoch": 1.8746666666666667, "percentage": 46.81, "elapsed_time": "2:27:36", "remaining_time": "2:47:44"}
|
||||
{"current_steps": 450, "total_steps": 940, "loss": 0.5165102481842041, "lr": 6.249203438329799e-06, "epoch": 1.9173333333333333, "percentage": 47.87, "elapsed_time": "2:30:56", "remaining_time": "2:44:21"}
|
||||
{"current_steps": 460, "total_steps": 940, "loss": 0.49199323654174804, "lr": 6.0685984806689055e-06, "epoch": 1.96, "percentage": 48.94, "elapsed_time": "2:34:15", "remaining_time": "2:40:58"}
|
||||
{"current_steps": 470, "total_steps": 940, "loss": 0.5182024002075195, "lr": 5.886520112835128e-06, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "2:37:22", "remaining_time": "2:37:22"}
|
||||
{"current_steps": 480, "total_steps": 940, "loss": 0.3669234275817871, "lr": 5.703219389012317e-06, "epoch": 2.042666666666667, "percentage": 51.06, "elapsed_time": "2:40:37", "remaining_time": "2:33:55"}
|
||||
{"current_steps": 490, "total_steps": 940, "loss": 0.3571956634521484, "lr": 5.518949048799176e-06, "epoch": 2.0853333333333333, "percentage": 52.13, "elapsed_time": "2:43:53", "remaining_time": "2:30:30"}
|
||||
{"current_steps": 500, "total_steps": 940, "loss": 0.35114617347717286, "lr": 5.3339631687256085e-06, "epoch": 2.128, "percentage": 53.19, "elapsed_time": "2:47:12", "remaining_time": "2:27:08"}
|
||||
{"current_steps": 510, "total_steps": 940, "loss": 0.3634940624237061, "lr": 5.148516811925684e-06, "epoch": 2.1706666666666665, "percentage": 54.26, "elapsed_time": "2:51:41", "remaining_time": "2:24:45"}
|
||||
{"current_steps": 520, "total_steps": 940, "loss": 0.3606603145599365, "lr": 4.962865676450239e-06, "epoch": 2.2133333333333334, "percentage": 55.32, "elapsed_time": "2:55:05", "remaining_time": "2:21:25"}
|
||||
{"current_steps": 530, "total_steps": 940, "loss": 0.3447108745574951, "lr": 4.777265742704039e-06, "epoch": 2.2560000000000002, "percentage": 56.38, "elapsed_time": "2:58:20", "remaining_time": "2:17:57"}
|
||||
{"current_steps": 540, "total_steps": 940, "loss": 0.37036728858947754, "lr": 4.591972920493638e-06, "epoch": 2.2986666666666666, "percentage": 57.45, "elapsed_time": "3:01:37", "remaining_time": "2:14:32"}
|
||||
{"current_steps": 550, "total_steps": 940, "loss": 0.3504173278808594, "lr": 4.40724269617256e-06, "epoch": 2.3413333333333335, "percentage": 58.51, "elapsed_time": "3:04:51", "remaining_time": "2:11:04"}
|
||||
{"current_steps": 560, "total_steps": 940, "loss": 0.3552720069885254, "lr": 4.223329780370359e-06, "epoch": 2.384, "percentage": 59.57, "elapsed_time": "3:08:04", "remaining_time": "2:07:37"}
|
||||
{"current_steps": 570, "total_steps": 940, "loss": 0.34830622673034667, "lr": 4.04048775679127e-06, "epoch": 2.4266666666666667, "percentage": 60.64, "elapsed_time": "3:11:21", "remaining_time": "2:04:12"}
|
||||
{"current_steps": 580, "total_steps": 940, "loss": 0.3437772512435913, "lr": 3.858968732566685e-06, "epoch": 2.469333333333333, "percentage": 61.7, "elapsed_time": "3:14:46", "remaining_time": "2:00:53"}
|
||||
{"current_steps": 590, "total_steps": 940, "loss": 0.3701408624649048, "lr": 3.6790229906435706e-06, "epoch": 2.512, "percentage": 62.77, "elapsed_time": "3:18:00", "remaining_time": "1:57:27"}
|
||||
{"current_steps": 600, "total_steps": 940, "loss": 0.3588127613067627, "lr": 3.5008986446881088e-06, "epoch": 2.554666666666667, "percentage": 63.83, "elapsed_time": "3:21:44", "remaining_time": "1:54:19"}
|
||||
{"current_steps": 610, "total_steps": 940, "loss": 0.3826591968536377, "lr": 3.3248412969804065e-06, "epoch": 2.5973333333333333, "percentage": 64.89, "elapsed_time": "3:25:06", "remaining_time": "1:50:57"}
|
||||
{"current_steps": 620, "total_steps": 940, "loss": 0.35985655784606935, "lr": 3.1510936997719557e-06, "epoch": 2.64, "percentage": 65.96, "elapsed_time": "3:28:24", "remaining_time": "1:47:33"}
|
||||
{"current_steps": 630, "total_steps": 940, "loss": 0.3487427234649658, "lr": 2.9798954205727886e-06, "epoch": 2.6826666666666665, "percentage": 67.02, "elapsed_time": "3:31:39", "remaining_time": "1:44:08"}
|
||||
{"current_steps": 640, "total_steps": 940, "loss": 0.3587791442871094, "lr": 2.811482511829842e-06, "epoch": 2.7253333333333334, "percentage": 68.09, "elapsed_time": "3:35:03", "remaining_time": "1:40:48"}
|
||||
{"current_steps": 650, "total_steps": 940, "loss": 0.3492987394332886, "lr": 2.6460871854519594e-06, "epoch": 2.768, "percentage": 69.15, "elapsed_time": "3:38:28", "remaining_time": "1:37:28"}
|
||||
{"current_steps": 660, "total_steps": 940, "loss": 0.33745241165161133, "lr": 2.483937492630345e-06, "epoch": 2.8106666666666666, "percentage": 70.21, "elapsed_time": "3:41:45", "remaining_time": "1:34:04"}
|
||||
{"current_steps": 670, "total_steps": 940, "loss": 0.36391506195068357, "lr": 2.3252570093959e-06, "epoch": 2.8533333333333335, "percentage": 71.28, "elapsed_time": "3:45:10", "remaining_time": "1:30:44"}
|
||||
{"current_steps": 680, "total_steps": 940, "loss": 0.3687248706817627, "lr": 2.1702645283470238e-06, "epoch": 2.896, "percentage": 72.34, "elapsed_time": "3:48:29", "remaining_time": "1:27:21"}
|
||||
{"current_steps": 690, "total_steps": 940, "loss": 0.36745338439941405, "lr": 2.0191737569729492e-06, "epoch": 2.9386666666666668, "percentage": 73.4, "elapsed_time": "3:51:47", "remaining_time": "1:23:58"}
|
||||
{"current_steps": 700, "total_steps": 940, "loss": 0.34957075119018555, "lr": 1.872193022988526e-06, "epoch": 2.981333333333333, "percentage": 74.47, "elapsed_time": "3:55:06", "remaining_time": "1:20:36"}
|
||||
{"current_steps": 710, "total_steps": 940, "loss": 0.3146792411804199, "lr": 1.7295249870867898e-06, "epoch": 3.021333333333333, "percentage": 75.53, "elapsed_time": "3:58:12", "remaining_time": "1:17:10"}
|
||||
{"current_steps": 720, "total_steps": 940, "loss": 0.2616109371185303, "lr": 1.5913663635053578e-06, "epoch": 3.064, "percentage": 76.6, "elapsed_time": "4:01:28", "remaining_time": "1:13:46"}
|
||||
{"current_steps": 730, "total_steps": 940, "loss": 0.2639318466186523, "lr": 1.457907648791943e-06, "epoch": 3.1066666666666665, "percentage": 77.66, "elapsed_time": "4:04:48", "remaining_time": "1:10:25"}
|
||||
{"current_steps": 740, "total_steps": 940, "loss": 0.23923878669738768, "lr": 1.329332859142967e-06, "epoch": 3.1493333333333333, "percentage": 78.72, "elapsed_time": "4:08:04", "remaining_time": "1:07:02"}
|
||||
{"current_steps": 750, "total_steps": 940, "loss": 0.2671759605407715, "lr": 1.205819276677464e-06, "epoch": 3.192, "percentage": 79.79, "elapsed_time": "4:11:24", "remaining_time": "1:03:41"}
|
||||
{"current_steps": 760, "total_steps": 940, "loss": 0.24742560386657714, "lr": 1.0875372049960697e-06, "epoch": 3.2346666666666666, "percentage": 80.85, "elapsed_time": "4:14:42", "remaining_time": "1:00:19"}
|
||||
{"current_steps": 770, "total_steps": 940, "loss": 0.2519863128662109, "lr": 9.746497343621857e-07, "epoch": 3.2773333333333334, "percentage": 81.91, "elapsed_time": "4:18:06", "remaining_time": "0:56:58"}
|
||||
{"current_steps": 780, "total_steps": 940, "loss": 0.25240919589996336, "lr": 8.673125168290713e-07, "epoch": 3.32, "percentage": 82.98, "elapsed_time": "4:21:25", "remaining_time": "0:53:37"}
|
||||
{"current_steps": 790, "total_steps": 940, "loss": 0.2599855899810791, "lr": 7.656735516229125e-07, "epoch": 3.3626666666666667, "percentage": 84.04, "elapsed_time": "4:24:41", "remaining_time": "0:50:15"}
|
||||
{"current_steps": 800, "total_steps": 940, "loss": 0.2527294635772705, "lr": 6.698729810778065e-07, "epoch": 3.405333333333333, "percentage": 85.11, "elapsed_time": "4:28:09", "remaining_time": "0:46:55"}
|
||||
{"current_steps": 810, "total_steps": 940, "loss": 0.2647819995880127, "lr": 5.800428974040311e-07, "epoch": 3.448, "percentage": 86.17, "elapsed_time": "4:31:32", "remaining_time": "0:43:34"}
|
||||
{"current_steps": 820, "total_steps": 940, "loss": 0.2600534915924072, "lr": 4.963071605560144e-07, "epoch": 3.490666666666667, "percentage": 87.23, "elapsed_time": "4:35:01", "remaining_time": "0:40:14"}
|
||||
{"current_steps": 830, "total_steps": 940, "loss": 0.2649343252182007, "lr": 4.187812274511427e-07, "epoch": 3.533333333333333, "percentage": 88.3, "elapsed_time": "4:38:11", "remaining_time": "0:36:52"}
|
||||
{"current_steps": 840, "total_steps": 940, "loss": 0.2622586965560913, "lr": 3.4757199277490106e-07, "epoch": 3.576, "percentage": 89.36, "elapsed_time": "4:41:30", "remaining_time": "0:33:30"}
|
||||
{"current_steps": 850, "total_steps": 940, "loss": 0.2523667335510254, "lr": 2.8277764159181484e-07, "epoch": 3.618666666666667, "percentage": 90.43, "elapsed_time": "4:44:53", "remaining_time": "0:30:09"}
|
||||
{"current_steps": 860, "total_steps": 940, "loss": 0.26191320419311526, "lr": 2.2448751396543788e-07, "epoch": 3.6613333333333333, "percentage": 91.49, "elapsed_time": "4:48:13", "remaining_time": "0:26:48"}
|
||||
{"current_steps": 870, "total_steps": 940, "loss": 0.25244143009185793, "lr": 1.7278198177405614e-07, "epoch": 3.7039999999999997, "percentage": 92.55, "elapsed_time": "4:51:42", "remaining_time": "0:23:28"}
|
||||
{"current_steps": 880, "total_steps": 940, "loss": 0.2483151912689209, "lr": 1.2773233789193816e-07, "epoch": 3.7466666666666666, "percentage": 93.62, "elapsed_time": "4:55:17", "remaining_time": "0:20:07"}
|
||||
{"current_steps": 890, "total_steps": 940, "loss": 0.2665947675704956, "lr": 8.940069788894389e-08, "epoch": 3.7893333333333334, "percentage": 94.68, "elapsed_time": "4:58:34", "remaining_time": "0:16:46"}
|
||||
{"current_steps": 900, "total_steps": 940, "loss": 0.25572938919067384, "lr": 5.783991438403802e-08, "epoch": 3.832, "percentage": 95.74, "elapsed_time": "5:02:08", "remaining_time": "0:13:25"}
|
||||
{"current_steps": 910, "total_steps": 940, "loss": 0.25423431396484375, "lr": 3.309350417077972e-08, "epoch": 3.8746666666666667, "percentage": 96.81, "elapsed_time": "5:05:42", "remaining_time": "0:10:04"}
|
||||
{"current_steps": 920, "total_steps": 940, "loss": 0.2418086051940918, "lr": 1.5195588215283773e-08, "epoch": 3.9173333333333336, "percentage": 97.87, "elapsed_time": "5:09:02", "remaining_time": "0:06:43"}
|
||||
{"current_steps": 930, "total_steps": 940, "loss": 0.2599043369293213, "lr": 4.170844609387992e-09, "epoch": 3.96, "percentage": 98.94, "elapsed_time": "5:12:13", "remaining_time": "0:03:21"}
|
||||
{"current_steps": 940, "total_steps": 940, "loss": 0.2301353931427002, "lr": 3.447454388127991e-11, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "5:15:18", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 940, "total_steps": 940, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "5:16:26", "remaining_time": "0:00:00"}
|
||||
701
trainer_state.json
Normal file
701
trainer_state.json
Normal file
@@ -0,0 +1,701 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 4.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 940,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.042666666666666665,
|
||||
"grad_norm": 8.999624900584061,
|
||||
"learning_rate": 9.574468085106384e-07,
|
||||
"loss": 0.9603355407714844,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.08533333333333333,
|
||||
"grad_norm": 2.636704103036297,
|
||||
"learning_rate": 2.021276595744681e-06,
|
||||
"loss": 0.8526813507080078,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.128,
|
||||
"grad_norm": 0.9865915385714896,
|
||||
"learning_rate": 3.0851063829787237e-06,
|
||||
"loss": 0.7081204414367676,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.17066666666666666,
|
||||
"grad_norm": 0.7401367462143341,
|
||||
"learning_rate": 4.148936170212766e-06,
|
||||
"loss": 0.6635202407836914,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.21333333333333335,
|
||||
"grad_norm": 0.669698985531291,
|
||||
"learning_rate": 5.212765957446809e-06,
|
||||
"loss": 0.6683910369873047,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.256,
|
||||
"grad_norm": 0.6360008572056217,
|
||||
"learning_rate": 6.276595744680851e-06,
|
||||
"loss": 0.6275049686431885,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.2986666666666667,
|
||||
"grad_norm": 0.555318435827221,
|
||||
"learning_rate": 7.340425531914894e-06,
|
||||
"loss": 0.6528850555419922,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.3413333333333333,
|
||||
"grad_norm": 0.6058441604473745,
|
||||
"learning_rate": 8.404255319148937e-06,
|
||||
"loss": 0.6439791679382324,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.384,
|
||||
"grad_norm": 0.6475130784871053,
|
||||
"learning_rate": 9.46808510638298e-06,
|
||||
"loss": 0.6390511989593506,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.4266666666666667,
|
||||
"grad_norm": 0.574181881803242,
|
||||
"learning_rate": 9.999138160172624e-06,
|
||||
"loss": 0.6257343292236328,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.4693333333333333,
|
||||
"grad_norm": 0.5905566490874637,
|
||||
"learning_rate": 9.99224522409411e-06,
|
||||
"loss": 0.592672061920166,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.512,
|
||||
"grad_norm": 0.5435503029654155,
|
||||
"learning_rate": 9.97846885608885e-06,
|
||||
"loss": 0.6212929725646973,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.5546666666666666,
|
||||
"grad_norm": 0.5730040949967365,
|
||||
"learning_rate": 9.957828051355817e-06,
|
||||
"loss": 0.6225690364837646,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.5973333333333334,
|
||||
"grad_norm": 0.5899735213380095,
|
||||
"learning_rate": 9.930351269950144e-06,
|
||||
"loss": 0.6189698219299317,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.64,
|
||||
"grad_norm": 0.5525970102466683,
|
||||
"learning_rate": 9.896076397541676e-06,
|
||||
"loss": 0.6111098289489746,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.6826666666666666,
|
||||
"grad_norm": 0.5711039837223352,
|
||||
"learning_rate": 9.855050693177286e-06,
|
||||
"loss": 0.6421695709228515,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.7253333333333334,
|
||||
"grad_norm": 0.5616230459173172,
|
||||
"learning_rate": 9.807330724118906e-06,
|
||||
"loss": 0.6056369781494141,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.768,
|
||||
"grad_norm": 0.5976781995767532,
|
||||
"learning_rate": 9.752982287847193e-06,
|
||||
"loss": 0.6315202236175537,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.8106666666666666,
|
||||
"grad_norm": 0.5178875267856328,
|
||||
"learning_rate": 9.692080321338317e-06,
|
||||
"loss": 0.6108819961547851,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.8533333333333334,
|
||||
"grad_norm": 0.5372603896789684,
|
||||
"learning_rate": 9.624708797739002e-06,
|
||||
"loss": 0.6224051475524902,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.896,
|
||||
"grad_norm": 0.5947283222378256,
|
||||
"learning_rate": 9.550960610582251e-06,
|
||||
"loss": 0.6080554485321045,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.9386666666666666,
|
||||
"grad_norm": 0.5535038239517683,
|
||||
"learning_rate": 9.47093744570344e-06,
|
||||
"loss": 0.6155075073242188,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.9813333333333333,
|
||||
"grad_norm": 0.6431070900946148,
|
||||
"learning_rate": 9.384749641033358e-06,
|
||||
"loss": 0.6900673866271972,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 1.0213333333333334,
|
||||
"grad_norm": 0.5827801730730351,
|
||||
"learning_rate": 9.292516034461517e-06,
|
||||
"loss": 0.5847660064697265,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 1.064,
|
||||
"grad_norm": 0.5426769543406595,
|
||||
"learning_rate": 9.194363799979517e-06,
|
||||
"loss": 0.4798769950866699,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 1.1066666666666667,
|
||||
"grad_norm": 0.5643710578769041,
|
||||
"learning_rate": 9.090428272330381e-06,
|
||||
"loss": 0.5030141830444336,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 1.1493333333333333,
|
||||
"grad_norm": 0.639872823627873,
|
||||
"learning_rate": 8.980852760405645e-06,
|
||||
"loss": 0.5117604255676269,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 1.192,
|
||||
"grad_norm": 0.586196190491155,
|
||||
"learning_rate": 8.865788349647496e-06,
|
||||
"loss": 0.5203066349029541,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 1.2346666666666666,
|
||||
"grad_norm": 0.5440685701114154,
|
||||
"learning_rate": 8.745393693728395e-06,
|
||||
"loss": 0.49484944343566895,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 1.2773333333333334,
|
||||
"grad_norm": 0.600205428025161,
|
||||
"learning_rate": 8.619834795795458e-06,
|
||||
"loss": 0.5042594909667969,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 1.32,
|
||||
"grad_norm": 0.5811654003465344,
|
||||
"learning_rate": 8.489284779581179e-06,
|
||||
"loss": 0.5075913429260254,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 1.3626666666666667,
|
||||
"grad_norm": 0.5388406938464266,
|
||||
"learning_rate": 8.353923650696119e-06,
|
||||
"loss": 0.5113458156585693,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 1.4053333333333333,
|
||||
"grad_norm": 0.6016476237889334,
|
||||
"learning_rate": 8.213938048432697e-06,
|
||||
"loss": 0.5259346961975098,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 1.448,
|
||||
"grad_norm": 0.588862463698428,
|
||||
"learning_rate": 8.069520988422292e-06,
|
||||
"loss": 0.4647953987121582,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 1.4906666666666666,
|
||||
"grad_norm": 0.6117968442301682,
|
||||
"learning_rate": 7.920871596500473e-06,
|
||||
"loss": 0.5107015609741211,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 1.5333333333333332,
|
||||
"grad_norm": 0.6314351969836132,
|
||||
"learning_rate": 7.768194834147362e-06,
|
||||
"loss": 0.4998687744140625,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 1.576,
|
||||
"grad_norm": 0.5999986531996214,
|
||||
"learning_rate": 7.611701215881635e-06,
|
||||
"loss": 0.518181037902832,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 1.6186666666666667,
|
||||
"grad_norm": 0.5931911048454541,
|
||||
"learning_rate": 7.4516065189978625e-06,
|
||||
"loss": 0.5033650398254395,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 1.6613333333333333,
|
||||
"grad_norm": 0.6266374937456085,
|
||||
"learning_rate": 7.288131486047414e-06,
|
||||
"loss": 0.5123775482177735,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 1.704,
|
||||
"grad_norm": 0.5717503598353061,
|
||||
"learning_rate": 7.121501520473137e-06,
|
||||
"loss": 0.4882556438446045,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 1.7466666666666666,
|
||||
"grad_norm": 0.6003251003283733,
|
||||
"learning_rate": 6.9519463758174745e-06,
|
||||
"loss": 0.48767690658569335,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 1.7893333333333334,
|
||||
"grad_norm": 0.593730463299211,
|
||||
"learning_rate": 6.77969983893257e-06,
|
||||
"loss": 0.5198426246643066,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 1.8319999999999999,
|
||||
"grad_norm": 0.573986464962402,
|
||||
"learning_rate": 6.604999407629137e-06,
|
||||
"loss": 0.5152793884277344,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 1.8746666666666667,
|
||||
"grad_norm": 0.6292349528099412,
|
||||
"learning_rate": 6.428085963208567e-06,
|
||||
"loss": 0.521914005279541,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 1.9173333333333333,
|
||||
"grad_norm": 0.6478722794091921,
|
||||
"learning_rate": 6.249203438329799e-06,
|
||||
"loss": 0.5165102481842041,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 1.96,
|
||||
"grad_norm": 0.5570760020319501,
|
||||
"learning_rate": 6.0685984806689055e-06,
|
||||
"loss": 0.49199323654174804,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 0.9597148964135244,
|
||||
"learning_rate": 5.886520112835128e-06,
|
||||
"loss": 0.5182024002075195,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 2.042666666666667,
|
||||
"grad_norm": 0.7599076030225683,
|
||||
"learning_rate": 5.703219389012317e-06,
|
||||
"loss": 0.3669234275817871,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 2.0853333333333333,
|
||||
"grad_norm": 0.6864314007799437,
|
||||
"learning_rate": 5.518949048799176e-06,
|
||||
"loss": 0.3571956634521484,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 2.128,
|
||||
"grad_norm": 0.6616396360754778,
|
||||
"learning_rate": 5.3339631687256085e-06,
|
||||
"loss": 0.35114617347717286,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 2.1706666666666665,
|
||||
"grad_norm": 0.7257990883487906,
|
||||
"learning_rate": 5.148516811925684e-06,
|
||||
"loss": 0.3634940624237061,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 2.2133333333333334,
|
||||
"grad_norm": 0.7153343933001038,
|
||||
"learning_rate": 4.962865676450239e-06,
|
||||
"loss": 0.3606603145599365,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 2.2560000000000002,
|
||||
"grad_norm": 0.6808533640895508,
|
||||
"learning_rate": 4.777265742704039e-06,
|
||||
"loss": 0.3447108745574951,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 2.2986666666666666,
|
||||
"grad_norm": 0.715150230691381,
|
||||
"learning_rate": 4.591972920493638e-06,
|
||||
"loss": 0.37036728858947754,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 2.3413333333333335,
|
||||
"grad_norm": 0.7301247118374748,
|
||||
"learning_rate": 4.40724269617256e-06,
|
||||
"loss": 0.3504173278808594,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 2.384,
|
||||
"grad_norm": 0.7579764542403585,
|
||||
"learning_rate": 4.223329780370359e-06,
|
||||
"loss": 0.3552720069885254,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 2.4266666666666667,
|
||||
"grad_norm": 0.665681730147191,
|
||||
"learning_rate": 4.04048775679127e-06,
|
||||
"loss": 0.34830622673034667,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 2.469333333333333,
|
||||
"grad_norm": 0.6942115980596211,
|
||||
"learning_rate": 3.858968732566685e-06,
|
||||
"loss": 0.3437772512435913,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 2.512,
|
||||
"grad_norm": 0.7356178016396235,
|
||||
"learning_rate": 3.6790229906435706e-06,
|
||||
"loss": 0.3701408624649048,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 2.554666666666667,
|
||||
"grad_norm": 0.76371891979336,
|
||||
"learning_rate": 3.5008986446881088e-06,
|
||||
"loss": 0.3588127613067627,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 2.5973333333333333,
|
||||
"grad_norm": 0.7924639034556639,
|
||||
"learning_rate": 3.3248412969804065e-06,
|
||||
"loss": 0.3826591968536377,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 2.64,
|
||||
"grad_norm": 0.7415843408514342,
|
||||
"learning_rate": 3.1510936997719557e-06,
|
||||
"loss": 0.35985655784606935,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 2.6826666666666665,
|
||||
"grad_norm": 0.7404620123688074,
|
||||
"learning_rate": 2.9798954205727886e-06,
|
||||
"loss": 0.3487427234649658,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 2.7253333333333334,
|
||||
"grad_norm": 0.7520085742772266,
|
||||
"learning_rate": 2.811482511829842e-06,
|
||||
"loss": 0.3587791442871094,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 2.768,
|
||||
"grad_norm": 0.7426608142495378,
|
||||
"learning_rate": 2.6460871854519594e-06,
|
||||
"loss": 0.3492987394332886,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 2.8106666666666666,
|
||||
"grad_norm": 0.7396983944629798,
|
||||
"learning_rate": 2.483937492630345e-06,
|
||||
"loss": 0.33745241165161133,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 2.8533333333333335,
|
||||
"grad_norm": 0.7484300928063685,
|
||||
"learning_rate": 2.3252570093959e-06,
|
||||
"loss": 0.36391506195068357,
|
||||
"step": 670
|
||||
},
|
||||
{
|
||||
"epoch": 2.896,
|
||||
"grad_norm": 0.7073190633237699,
|
||||
"learning_rate": 2.1702645283470238e-06,
|
||||
"loss": 0.3687248706817627,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 2.9386666666666668,
|
||||
"grad_norm": 0.7068579075999436,
|
||||
"learning_rate": 2.0191737569729492e-06,
|
||||
"loss": 0.36745338439941405,
|
||||
"step": 690
|
||||
},
|
||||
{
|
||||
"epoch": 2.981333333333333,
|
||||
"grad_norm": 0.7173146292749063,
|
||||
"learning_rate": 1.872193022988526e-06,
|
||||
"loss": 0.34957075119018555,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 3.021333333333333,
|
||||
"grad_norm": 0.8300783812815867,
|
||||
"learning_rate": 1.7295249870867898e-06,
|
||||
"loss": 0.3146792411804199,
|
||||
"step": 710
|
||||
},
|
||||
{
|
||||
"epoch": 3.064,
|
||||
"grad_norm": 1.070273747301605,
|
||||
"learning_rate": 1.5913663635053578e-06,
|
||||
"loss": 0.2616109371185303,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 3.1066666666666665,
|
||||
"grad_norm": 0.801956283142561,
|
||||
"learning_rate": 1.457907648791943e-06,
|
||||
"loss": 0.2639318466186523,
|
||||
"step": 730
|
||||
},
|
||||
{
|
||||
"epoch": 3.1493333333333333,
|
||||
"grad_norm": 0.8000993958690409,
|
||||
"learning_rate": 1.329332859142967e-06,
|
||||
"loss": 0.23923878669738768,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 3.192,
|
||||
"grad_norm": 0.8249305995327736,
|
||||
"learning_rate": 1.205819276677464e-06,
|
||||
"loss": 0.2671759605407715,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 3.2346666666666666,
|
||||
"grad_norm": 0.9324101657605222,
|
||||
"learning_rate": 1.0875372049960697e-06,
|
||||
"loss": 0.24742560386657714,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 3.2773333333333334,
|
||||
"grad_norm": 0.798009630439176,
|
||||
"learning_rate": 9.746497343621857e-07,
|
||||
"loss": 0.2519863128662109,
|
||||
"step": 770
|
||||
},
|
||||
{
|
||||
"epoch": 3.32,
|
||||
"grad_norm": 0.8369262323406452,
|
||||
"learning_rate": 8.673125168290713e-07,
|
||||
"loss": 0.25240919589996336,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 3.3626666666666667,
|
||||
"grad_norm": 0.7616838883796991,
|
||||
"learning_rate": 7.656735516229125e-07,
|
||||
"loss": 0.2599855899810791,
|
||||
"step": 790
|
||||
},
|
||||
{
|
||||
"epoch": 3.405333333333333,
|
||||
"grad_norm": 0.8666710182114363,
|
||||
"learning_rate": 6.698729810778065e-07,
|
||||
"loss": 0.2527294635772705,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 3.448,
|
||||
"grad_norm": 0.79311539703412,
|
||||
"learning_rate": 5.800428974040311e-07,
|
||||
"loss": 0.2647819995880127,
|
||||
"step": 810
|
||||
},
|
||||
{
|
||||
"epoch": 3.490666666666667,
|
||||
"grad_norm": 0.9179905441651993,
|
||||
"learning_rate": 4.963071605560144e-07,
|
||||
"loss": 0.2600534915924072,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 3.533333333333333,
|
||||
"grad_norm": 0.9272013641675249,
|
||||
"learning_rate": 4.187812274511427e-07,
|
||||
"loss": 0.2649343252182007,
|
||||
"step": 830
|
||||
},
|
||||
{
|
||||
"epoch": 3.576,
|
||||
"grad_norm": 0.8183105373770141,
|
||||
"learning_rate": 3.4757199277490106e-07,
|
||||
"loss": 0.2622586965560913,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 3.618666666666667,
|
||||
"grad_norm": 0.7939545039336852,
|
||||
"learning_rate": 2.8277764159181484e-07,
|
||||
"loss": 0.2523667335510254,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"epoch": 3.6613333333333333,
|
||||
"grad_norm": 0.9010122576415565,
|
||||
"learning_rate": 2.2448751396543788e-07,
|
||||
"loss": 0.26191320419311526,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 3.7039999999999997,
|
||||
"grad_norm": 0.8710705871093096,
|
||||
"learning_rate": 1.7278198177405614e-07,
|
||||
"loss": 0.25244143009185793,
|
||||
"step": 870
|
||||
},
|
||||
{
|
||||
"epoch": 3.7466666666666666,
|
||||
"grad_norm": 0.8006138211679082,
|
||||
"learning_rate": 1.2773233789193816e-07,
|
||||
"loss": 0.2483151912689209,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 3.7893333333333334,
|
||||
"grad_norm": 0.8465843943197577,
|
||||
"learning_rate": 8.940069788894389e-08,
|
||||
"loss": 0.2665947675704956,
|
||||
"step": 890
|
||||
},
|
||||
{
|
||||
"epoch": 3.832,
|
||||
"grad_norm": 0.8011024381853885,
|
||||
"learning_rate": 5.783991438403802e-08,
|
||||
"loss": 0.25572938919067384,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 3.8746666666666667,
|
||||
"grad_norm": 0.799485639611528,
|
||||
"learning_rate": 3.309350417077972e-08,
|
||||
"loss": 0.25423431396484375,
|
||||
"step": 910
|
||||
},
|
||||
{
|
||||
"epoch": 3.9173333333333336,
|
||||
"grad_norm": 0.8056040335409604,
|
||||
"learning_rate": 1.5195588215283773e-08,
|
||||
"loss": 0.2418086051940918,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 3.96,
|
||||
"grad_norm": 0.8601769661004041,
|
||||
"learning_rate": 4.170844609387992e-09,
|
||||
"loss": 0.2599043369293213,
|
||||
"step": 930
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"grad_norm": 1.3803589385885682,
|
||||
"learning_rate": 3.447454388127991e-11,
|
||||
"loss": 0.2301353931427002,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 4.0,
|
||||
"step": 940,
|
||||
"total_flos": 152338919849984.0,
|
||||
"train_loss": 0.44427714956567643,
|
||||
"train_runtime": 18988.0523,
|
||||
"train_samples_per_second": 6.32,
|
||||
"train_steps_per_second": 0.05
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 940,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 4,
|
||||
"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": 152338919849984.0,
|
||||
"train_batch_size": 1,
|
||||
"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 sha256:37c9c4e3be2bbb83d11f0ae6fbeed934549f8fe2149ec95c7529f834a4f4336c
|
||||
size 7377
|
||||
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