miiikiik/Qwen3-8B-music-coa-sft
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: miiikiik/Qwen3-8B-music-coa-sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 20:49:10 +08:00
commit 277bab5a50
14 changed files with 622 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View 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
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: other
base_model: Qwen/Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: Qwen3-8B-music-coa-sft
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. -->
# Qwen3-8B-music-coa-sft
This model is a fine-tuned version of [/mnt/tidal-alsh01/usr/zhongmeizhi/meiwangyi/models/Qwen3-8B-onto-fixed-traj](https://huggingface.co//mnt/tidal-alsh01/usr/zhongmeizhi/meiwangyi/models/Qwen3-8B-onto-fixed-traj) on the music_coa_sft dataset.
## 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: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 5.6.0
- Pytorch 2.7.1+cu126
- Datasets 3.4.1
- Tokenizers 0.22.1

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 3.0,
"total_flos": 76776714797056.0,
"train_loss": 0.08690919660139775,
"train_runtime": 2313.134,
"train_samples_per_second": 9.525,
"train_steps_per_second": 0.149
}

85
chat_template.jinja Normal file
View File

@@ -0,0 +1,85 @@
{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set content = message.content %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in message.content %}
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
{{- message.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 %}

71
config.json Normal file
View File

@@ -0,0 +1,71 @@
{
"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": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"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"
],
"max_position_embeddings": 40960,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"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,
"tie_word_embeddings": false,
"transformers_version": "5.6.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

12
generation_config.json Normal file
View 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": "5.6.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:49085b381db57f95f5024195e46a62b6d94e7f61078ac10211fc017ba42f446f
size 16381517208

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
size 11422650

16
tokenizer_config.json Normal file
View File

@@ -0,0 +1,16 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": true,
"local_files_only": 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
View File

@@ -0,0 +1,8 @@
{
"epoch": 3.0,
"total_flos": 76776714797056.0,
"train_loss": 0.08690919660139775,
"train_runtime": 2313.134,
"train_samples_per_second": 9.525,
"train_steps_per_second": 0.149
}

35
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,35 @@
{"current_steps": 10, "total_steps": 345, "loss": 0.6153196334838867, "lr": 2.571428571428571e-06, "epoch": 0.08714596949891068, "percentage": 2.9, "elapsed_time": "0:01:09", "remaining_time": "0:38:47"}
{"current_steps": 20, "total_steps": 345, "loss": 0.28919568061828616, "lr": 5.428571428571429e-06, "epoch": 0.17429193899782136, "percentage": 5.8, "elapsed_time": "0:02:16", "remaining_time": "0:36:57"}
{"current_steps": 30, "total_steps": 345, "loss": 0.17522474527359008, "lr": 8.285714285714287e-06, "epoch": 0.26143790849673204, "percentage": 8.7, "elapsed_time": "0:03:29", "remaining_time": "0:36:36"}
{"current_steps": 40, "total_steps": 345, "loss": 0.14669673442840575, "lr": 9.995892506564461e-06, "epoch": 0.3485838779956427, "percentage": 11.59, "elapsed_time": "0:04:34", "remaining_time": "0:34:52"}
{"current_steps": 50, "total_steps": 345, "loss": 0.12744725942611695, "lr": 9.949760673863846e-06, "epoch": 0.4357298474945534, "percentage": 14.49, "elapsed_time": "0:05:41", "remaining_time": "0:33:37"}
{"current_steps": 60, "total_steps": 345, "loss": 0.11766195297241211, "lr": 9.85283759855301e-06, "epoch": 0.5228758169934641, "percentage": 17.39, "elapsed_time": "0:06:44", "remaining_time": "0:32:02"}
{"current_steps": 70, "total_steps": 345, "loss": 0.10788841247558593, "lr": 9.706117842542517e-06, "epoch": 0.6100217864923747, "percentage": 20.29, "elapsed_time": "0:07:49", "remaining_time": "0:30:42"}
{"current_steps": 80, "total_steps": 345, "loss": 0.09764145016670227, "lr": 9.511106949072588e-06, "epoch": 0.6971677559912854, "percentage": 23.19, "elapsed_time": "0:09:00", "remaining_time": "0:29:50"}
{"current_steps": 90, "total_steps": 345, "loss": 0.10603783130645753, "lr": 9.26980599380213e-06, "epoch": 0.7843137254901961, "percentage": 26.09, "elapsed_time": "0:10:04", "remaining_time": "0:28:31"}
{"current_steps": 100, "total_steps": 345, "loss": 0.09546730518341065, "lr": 8.984691051064576e-06, "epoch": 0.8714596949891068, "percentage": 28.99, "elapsed_time": "0:11:13", "remaining_time": "0:27:29"}
{"current_steps": 110, "total_steps": 345, "loss": 0.092532217502594, "lr": 8.658687785994579e-06, "epoch": 0.9586056644880174, "percentage": 31.88, "elapsed_time": "0:12:12", "remaining_time": "0:26:05"}
{"current_steps": 120, "total_steps": 345, "loss": 0.08056190013885497, "lr": 8.29514143324466e-06, "epoch": 1.0435729847494553, "percentage": 34.78, "elapsed_time": "0:13:14", "remaining_time": "0:24:49"}
{"current_steps": 130, "total_steps": 345, "loss": 0.07299971580505371, "lr": 7.89778247035085e-06, "epoch": 1.130718954248366, "percentage": 37.68, "elapsed_time": "0:14:16", "remaining_time": "0:23:37"}
{"current_steps": 140, "total_steps": 345, "loss": 0.07079986333847046, "lr": 7.470688337985029e-06, "epoch": 1.2178649237472767, "percentage": 40.58, "elapsed_time": "0:15:20", "remaining_time": "0:22:27"}
{"current_steps": 150, "total_steps": 345, "loss": 0.06660881042480468, "lr": 7.018241599895974e-06, "epoch": 1.3050108932461875, "percentage": 43.48, "elapsed_time": "0:16:26", "remaining_time": "0:21:22"}
{"current_steps": 160, "total_steps": 345, "loss": 0.0653923749923706, "lr": 6.545084971874738e-06, "epoch": 1.392156862745098, "percentage": 46.38, "elapsed_time": "0:17:31", "remaining_time": "0:20:16"}
{"current_steps": 170, "total_steps": 345, "loss": 0.06376279592514038, "lr": 6.056073681208038e-06, "epoch": 1.4793028322440087, "percentage": 49.28, "elapsed_time": "0:18:36", "remaining_time": "0:19:09"}
{"current_steps": 180, "total_steps": 345, "loss": 0.06115278005599976, "lr": 5.556225645476119e-06, "epoch": 1.5664488017429194, "percentage": 52.17, "elapsed_time": "0:19:45", "remaining_time": "0:18:07"}
{"current_steps": 190, "total_steps": 345, "loss": 0.05721602439880371, "lr": 5.050669981928056e-06, "epoch": 1.65359477124183, "percentage": 55.07, "elapsed_time": "0:20:57", "remaining_time": "0:17:05"}
{"current_steps": 200, "total_steps": 345, "loss": 0.05891573429107666, "lr": 4.544594375797969e-06, "epoch": 1.7407407407407407, "percentage": 57.97, "elapsed_time": "0:22:06", "remaining_time": "0:16:01"}
{"current_steps": 210, "total_steps": 345, "loss": 0.053774547576904294, "lr": 4.043191847634469e-06, "epoch": 1.8278867102396514, "percentage": 60.87, "elapsed_time": "0:23:14", "remaining_time": "0:14:56"}
{"current_steps": 220, "total_steps": 345, "loss": 0.05282905101776123, "lr": 3.55160746588254e-06, "epoch": 1.915032679738562, "percentage": 63.77, "elapsed_time": "0:24:16", "remaining_time": "0:13:47"}
{"current_steps": 230, "total_steps": 345, "loss": 0.04842503666877747, "lr": 3.0748855515189104e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:25:21", "remaining_time": "0:12:40"}
{"current_steps": 240, "total_steps": 345, "loss": 0.030383211374282838, "lr": 2.617917916492776e-06, "epoch": 2.0871459694989105, "percentage": 69.57, "elapsed_time": "0:26:29", "remaining_time": "0:11:35"}
{"current_steps": 250, "total_steps": 345, "loss": 0.027488625049591063, "lr": 2.185393667115513e-06, "epoch": 2.1742919389978215, "percentage": 72.46, "elapsed_time": "0:27:37", "remaining_time": "0:10:30"}
{"current_steps": 260, "total_steps": 345, "loss": 0.02891799509525299, "lr": 1.7817510874845585e-06, "epoch": 2.261437908496732, "percentage": 75.36, "elapsed_time": "0:28:38", "remaining_time": "0:09:21"}
{"current_steps": 270, "total_steps": 345, "loss": 0.025755631923675536, "lr": 1.411132096682606e-06, "epoch": 2.348583877995643, "percentage": 78.26, "elapsed_time": "0:29:39", "remaining_time": "0:08:14"}
{"current_steps": 280, "total_steps": 345, "loss": 0.02339869737625122, "lr": 1.0773397470829145e-06, "epoch": 2.4357298474945535, "percentage": 81.16, "elapsed_time": "0:30:50", "remaining_time": "0:07:09"}
{"current_steps": 290, "total_steps": 345, "loss": 0.02193155437707901, "lr": 7.837991998855899e-07, "epoch": 2.522875816993464, "percentage": 84.06, "elapsed_time": "0:31:55", "remaining_time": "0:06:03"}
{"current_steps": 300, "total_steps": 345, "loss": 0.022859147191047667, "lr": 5.335225783287051e-07, "epoch": 2.610021786492375, "percentage": 86.96, "elapsed_time": "0:32:56", "remaining_time": "0:04:56"}
{"current_steps": 310, "total_steps": 345, "loss": 0.022240425646305084, "lr": 3.290780592278148e-07, "epoch": 2.6971677559912854, "percentage": 89.86, "elapsed_time": "0:34:06", "remaining_time": "0:03:51"}
{"current_steps": 320, "total_steps": 345, "loss": 0.021587590873241424, "lr": 1.725635200065323e-07, "epoch": 2.784313725490196, "percentage": 92.75, "elapsed_time": "0:35:07", "remaining_time": "0:02:44"}
{"current_steps": 330, "total_steps": 345, "loss": 0.020273779332637788, "lr": 6.558501163527964e-08, "epoch": 2.871459694989107, "percentage": 95.65, "elapsed_time": "0:36:20", "remaining_time": "0:01:39"}
{"current_steps": 340, "total_steps": 345, "loss": 0.019534435868263245, "lr": 9.240278374995637e-09, "epoch": 2.9586056644880174, "percentage": 98.55, "elapsed_time": "0:37:25", "remaining_time": "0:00:33"}
{"current_steps": 345, "total_steps": 345, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:38:33", "remaining_time": "0:00:00"}

281
trainer_state.json Normal file
View File

@@ -0,0 +1,281 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 345,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08714596949891068,
"grad_norm": 5.177986166517991,
"learning_rate": 2.571428571428571e-06,
"loss": 0.6153196334838867,
"step": 10
},
{
"epoch": 0.17429193899782136,
"grad_norm": 1.44175757217302,
"learning_rate": 5.428571428571429e-06,
"loss": 0.28919568061828616,
"step": 20
},
{
"epoch": 0.26143790849673204,
"grad_norm": 0.9165793261415883,
"learning_rate": 8.285714285714287e-06,
"loss": 0.17522474527359008,
"step": 30
},
{
"epoch": 0.3485838779956427,
"grad_norm": 0.6521905966085462,
"learning_rate": 9.995892506564461e-06,
"loss": 0.14669673442840575,
"step": 40
},
{
"epoch": 0.4357298474945534,
"grad_norm": 0.607127669832236,
"learning_rate": 9.949760673863846e-06,
"loss": 0.12744725942611695,
"step": 50
},
{
"epoch": 0.5228758169934641,
"grad_norm": 0.5498782876340255,
"learning_rate": 9.85283759855301e-06,
"loss": 0.11766195297241211,
"step": 60
},
{
"epoch": 0.6100217864923747,
"grad_norm": 0.5918131618600547,
"learning_rate": 9.706117842542517e-06,
"loss": 0.10788841247558593,
"step": 70
},
{
"epoch": 0.6971677559912854,
"grad_norm": 0.4439997345152047,
"learning_rate": 9.511106949072588e-06,
"loss": 0.09764145016670227,
"step": 80
},
{
"epoch": 0.7843137254901961,
"grad_norm": 0.5075520825167553,
"learning_rate": 9.26980599380213e-06,
"loss": 0.10603783130645753,
"step": 90
},
{
"epoch": 0.8714596949891068,
"grad_norm": 0.5140097183992045,
"learning_rate": 8.984691051064576e-06,
"loss": 0.09546730518341065,
"step": 100
},
{
"epoch": 0.9586056644880174,
"grad_norm": 0.5703007918047962,
"learning_rate": 8.658687785994579e-06,
"loss": 0.092532217502594,
"step": 110
},
{
"epoch": 1.0435729847494553,
"grad_norm": 0.5044506688179623,
"learning_rate": 8.29514143324466e-06,
"loss": 0.08056190013885497,
"step": 120
},
{
"epoch": 1.130718954248366,
"grad_norm": 0.45897327652678604,
"learning_rate": 7.89778247035085e-06,
"loss": 0.07299971580505371,
"step": 130
},
{
"epoch": 1.2178649237472767,
"grad_norm": 0.512980363314234,
"learning_rate": 7.470688337985029e-06,
"loss": 0.07079986333847046,
"step": 140
},
{
"epoch": 1.3050108932461875,
"grad_norm": 0.47351565581785493,
"learning_rate": 7.018241599895974e-06,
"loss": 0.06660881042480468,
"step": 150
},
{
"epoch": 1.392156862745098,
"grad_norm": 0.5370628072208776,
"learning_rate": 6.545084971874738e-06,
"loss": 0.0653923749923706,
"step": 160
},
{
"epoch": 1.4793028322440087,
"grad_norm": 0.48059037186135045,
"learning_rate": 6.056073681208038e-06,
"loss": 0.06376279592514038,
"step": 170
},
{
"epoch": 1.5664488017429194,
"grad_norm": 0.5064023315317826,
"learning_rate": 5.556225645476119e-06,
"loss": 0.06115278005599976,
"step": 180
},
{
"epoch": 1.65359477124183,
"grad_norm": 0.42527473207127103,
"learning_rate": 5.050669981928056e-06,
"loss": 0.05721602439880371,
"step": 190
},
{
"epoch": 1.7407407407407407,
"grad_norm": 0.6697126311013827,
"learning_rate": 4.544594375797969e-06,
"loss": 0.05891573429107666,
"step": 200
},
{
"epoch": 1.8278867102396514,
"grad_norm": 0.5279032397256536,
"learning_rate": 4.043191847634469e-06,
"loss": 0.053774547576904294,
"step": 210
},
{
"epoch": 1.915032679738562,
"grad_norm": 0.5503203177829016,
"learning_rate": 3.55160746588254e-06,
"loss": 0.05282905101776123,
"step": 220
},
{
"epoch": 2.0,
"grad_norm": 0.5834909575577394,
"learning_rate": 3.0748855515189104e-06,
"loss": 0.04842503666877747,
"step": 230
},
{
"epoch": 2.0871459694989105,
"grad_norm": 0.45637637277474224,
"learning_rate": 2.617917916492776e-06,
"loss": 0.030383211374282838,
"step": 240
},
{
"epoch": 2.1742919389978215,
"grad_norm": 0.5460303567191565,
"learning_rate": 2.185393667115513e-06,
"loss": 0.027488625049591063,
"step": 250
},
{
"epoch": 2.261437908496732,
"grad_norm": 0.5299369784489509,
"learning_rate": 1.7817510874845585e-06,
"loss": 0.02891799509525299,
"step": 260
},
{
"epoch": 2.348583877995643,
"grad_norm": 0.47946594564717776,
"learning_rate": 1.411132096682606e-06,
"loss": 0.025755631923675536,
"step": 270
},
{
"epoch": 2.4357298474945535,
"grad_norm": 0.5587855844190783,
"learning_rate": 1.0773397470829145e-06,
"loss": 0.02339869737625122,
"step": 280
},
{
"epoch": 2.522875816993464,
"grad_norm": 0.5415169503522139,
"learning_rate": 7.837991998855899e-07,
"loss": 0.02193155437707901,
"step": 290
},
{
"epoch": 2.610021786492375,
"grad_norm": 0.5047370934641092,
"learning_rate": 5.335225783287051e-07,
"loss": 0.022859147191047667,
"step": 300
},
{
"epoch": 2.6971677559912854,
"grad_norm": 0.5339811061748208,
"learning_rate": 3.290780592278148e-07,
"loss": 0.022240425646305084,
"step": 310
},
{
"epoch": 2.784313725490196,
"grad_norm": 0.5269387231320517,
"learning_rate": 1.725635200065323e-07,
"loss": 0.021587590873241424,
"step": 320
},
{
"epoch": 2.871459694989107,
"grad_norm": 0.4475061358613248,
"learning_rate": 6.558501163527964e-08,
"loss": 0.020273779332637788,
"step": 330
},
{
"epoch": 2.9586056644880174,
"grad_norm": 0.38102973450948285,
"learning_rate": 9.240278374995637e-09,
"loss": 0.019534435868263245,
"step": 340
},
{
"epoch": 3.0,
"step": 345,
"total_flos": 76776714797056.0,
"train_loss": 0.08690919660139775,
"train_runtime": 2313.134,
"train_samples_per_second": 9.525,
"train_steps_per_second": 0.149
}
],
"logging_steps": 10,
"max_steps": 345,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 76776714797056.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:67d769ee4536f0f8d9ef008b0a55032c2f50341f48b3ac9af78bde5aabaf1ce5
size 7761

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 34 KiB