aasim-m/daft-qwen2.5-coder-3b-instruct-full
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: aasim-m/daft-qwen2.5-coder-3b-instruct-full
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-28 09:50:39 +08:00
commit 3e3401c6eb
14 changed files with 624 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/Qwen2.5-Coder-3B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: 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. -->
# sft
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) on the daft_functions_dedup_sharegpt 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: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 32
- total_train_batch_size: 512
- total_eval_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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 5.2.0
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 3.0,
"total_flos": 3081875480379392.0,
"train_loss": 0.06056562058377327,
"train_runtime": 29609.547,
"train_samples_per_second": 6.685,
"train_steps_per_second": 0.013
}

54
chat_template.jinja Normal file
View File

@@ -0,0 +1,54 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
{%- endif %}
{{- "\n\n# 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' }}
{%- else %}
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n</tool_call>' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) 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' }}
{%- endif %}

69
config.json Normal file
View File

@@ -0,0 +1,69 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 11008,
"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": 32768,
"max_window_layers": 36,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 36,
"num_key_value_heads": 2,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.2.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "5.2.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8b3a0782298f3bc5526de50d9ee1bba89a44248fe431ffc888ea86d6ed217618
size 6171927112

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
size 11421892

30
tokenizer_config.json Normal file
View 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_start|>",
"<|im_end|>": "<|im_end|>",
"<|object_ref_start|>": "<|object_ref_start|>",
"<|object_ref_end|>": "<|object_ref_end|>",
"<|box_start|>": "<|box_start|>",
"<|box_end|>": "<|box_end|>",
"<|quad_start|>": "<|quad_start|>",
"<|quad_end|>": "<|quad_end|>",
"<|vision_start|>": "<|vision_start|>",
"<|vision_end|>": "<|vision_end|>",
"<|vision_pad|>": "<|vision_pad|>",
"<|image_pad|>": "<|image_pad|>",
"<|video_pad|>": "<|video_pad|>"
},
"is_local": false,
"model_max_length": 32768,
"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": 3081875480379392.0,
"train_loss": 0.06056562058377327,
"train_runtime": 29609.547,
"train_samples_per_second": 6.685,
"train_steps_per_second": 0.013
}

27
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,27 @@
{"current_steps": 130, "total_steps": 387, "loss": 0.11126101016998291, "lr": 8.438497294267117e-06, "epoch": 1.0077594568380213, "percentage": 33.59, "elapsed_time": "0:18:26", "remaining_time": "0:36:26"}
{"current_steps": 140, "total_steps": 387, "loss": 0.10776399374008179, "lr": 8.097241806078616e-06, "epoch": 1.0853540252182348, "percentage": 36.18, "elapsed_time": "0:36:50", "remaining_time": "1:04:59"}
{"current_steps": 150, "total_steps": 387, "loss": 0.10431833267211914, "lr": 7.730761885468486e-06, "epoch": 1.162948593598448, "percentage": 38.76, "elapsed_time": "0:55:23", "remaining_time": "1:27:31"}
{"current_steps": 160, "total_steps": 387, "loss": 0.10304663181304932, "lr": 7.342042203498952e-06, "epoch": 1.2405431619786615, "percentage": 41.34, "elapsed_time": "1:14:02", "remaining_time": "1:45:03"}
{"current_steps": 170, "total_steps": 387, "loss": 0.09784629344940185, "lr": 6.934248555404197e-06, "epoch": 1.3181377303588748, "percentage": 43.93, "elapsed_time": "1:32:53", "remaining_time": "1:58:33"}
{"current_steps": 180, "total_steps": 387, "loss": 0.09537227749824524, "lr": 6.510702077847864e-06, "epoch": 1.3957322987390883, "percentage": 46.51, "elapsed_time": "1:51:08", "remaining_time": "2:07:48"}
{"current_steps": 190, "total_steps": 387, "loss": 0.09520423412322998, "lr": 6.074852201055121e-06, "epoch": 1.4733268671193016, "percentage": 49.1, "elapsed_time": "2:09:17", "remaining_time": "2:14:03"}
{"current_steps": 200, "total_steps": 387, "loss": 0.09088362455368042, "lr": 5.630248556101448e-06, "epoch": 1.5509214354995149, "percentage": 51.68, "elapsed_time": "2:27:46", "remaining_time": "2:18:10"}
{"current_steps": 210, "total_steps": 387, "loss": 0.0899280071258545, "lr": 5.180512066149682e-06, "epoch": 1.6285160038797284, "percentage": 54.26, "elapsed_time": "2:46:36", "remaining_time": "2:20:25"}
{"current_steps": 220, "total_steps": 387, "loss": 0.0881616234779358, "lr": 4.729305457072913e-06, "epoch": 1.706110572259942, "percentage": 56.85, "elapsed_time": "3:04:52", "remaining_time": "2:20:20"}
{"current_steps": 230, "total_steps": 387, "loss": 0.08638249635696411, "lr": 4.280303427629404e-06, "epoch": 1.7837051406401552, "percentage": 59.43, "elapsed_time": "3:23:30", "remaining_time": "2:18:54"}
{"current_steps": 240, "total_steps": 387, "loss": 0.08716154098510742, "lr": 3.8371627221284495e-06, "epoch": 1.8612997090203685, "percentage": 62.02, "elapsed_time": "3:41:53", "remaining_time": "2:15:54"}
{"current_steps": 250, "total_steps": 387, "loss": 0.08580605983734131, "lr": 3.403492349320101e-06, "epoch": 1.938894277400582, "percentage": 64.6, "elapsed_time": "4:00:25", "remaining_time": "2:11:44"}
{"current_steps": 260, "total_steps": 387, "loss": 0.08316840529441834, "lr": 2.982824190050958e-06, "epoch": 2.0155189136760425, "percentage": 67.18, "elapsed_time": "4:18:27", "remaining_time": "2:06:14"}
{"current_steps": 270, "total_steps": 387, "loss": 0.08091338872909545, "lr": 2.5785842330619038e-06, "epoch": 2.093113482056256, "percentage": 69.77, "elapsed_time": "4:37:00", "remaining_time": "2:00:02"}
{"current_steps": 280, "total_steps": 387, "loss": 0.08085420131683349, "lr": 2.1940646731880887e-06, "epoch": 2.1707080504364695, "percentage": 72.35, "elapsed_time": "4:55:04", "remaining_time": "1:52:45"}
{"current_steps": 290, "total_steps": 387, "loss": 0.08156624436378479, "lr": 1.8323970991978823e-06, "epoch": 2.248302618816683, "percentage": 74.94, "elapsed_time": "5:14:09", "remaining_time": "1:45:04"}
{"current_steps": 300, "total_steps": 387, "loss": 0.0808843195438385, "lr": 1.4965269896332884e-06, "epoch": 2.325897187196896, "percentage": 77.52, "elapsed_time": "5:32:45", "remaining_time": "1:36:30"}
{"current_steps": 310, "total_steps": 387, "loss": 0.07979943156242371, "lr": 1.1891897243618184e-06, "epoch": 2.4034917555771096, "percentage": 80.1, "elapsed_time": "5:50:50", "remaining_time": "1:27:08"}
{"current_steps": 320, "total_steps": 387, "loss": 0.08049517869949341, "lr": 9.128883072055411e-07, "epoch": 2.481086323957323, "percentage": 82.69, "elapsed_time": "6:09:14", "remaining_time": "1:17:18"}
{"current_steps": 330, "total_steps": 387, "loss": 0.08011389374732972, "lr": 6.698729810778065e-07, "epoch": 2.558680892337536, "percentage": 85.27, "elapsed_time": "6:27:50", "remaining_time": "1:06:59"}
{"current_steps": 340, "total_steps": 387, "loss": 0.08163015246391296, "lr": 4.6212290164521554e-07, "epoch": 2.6362754607177497, "percentage": 87.86, "elapsed_time": "6:46:09", "remaining_time": "0:56:08"}
{"current_steps": 350, "total_steps": 387, "loss": 0.08051948547363282, "lr": 2.9133001876746004e-07, "epoch": 2.713870029097963, "percentage": 90.44, "elapsed_time": "7:04:35", "remaining_time": "0:44:53"}
{"current_steps": 360, "total_steps": 387, "loss": 0.07719261646270752, "lr": 1.5888529698718347e-07, "epoch": 2.7914645974781767, "percentage": 93.02, "elapsed_time": "7:23:07", "remaining_time": "0:33:14"}
{"current_steps": 370, "total_steps": 387, "loss": 0.08128957152366638, "lr": 6.58673872923693e-08, "epoch": 2.86905916585839, "percentage": 95.61, "elapsed_time": "7:42:08", "remaining_time": "0:21:14"}
{"current_steps": 380, "total_steps": 387, "loss": 0.07743191719055176, "lr": 1.3033842410251074e-08, "epoch": 2.946653734238603, "percentage": 98.19, "elapsed_time": "8:00:28", "remaining_time": "0:08:51"}
{"current_steps": 387, "total_steps": 387, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "8:13:28", "remaining_time": "0:00:00"}

309
trainer_state.json Normal file
View File

@@ -0,0 +1,309 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 387,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07759456838021339,
"grad_norm": 1.9683642394428182,
"learning_rate": 2.307692307692308e-06,
"loss": 0.7343237400054932,
"step": 10
},
{
"epoch": 0.15518913676042678,
"grad_norm": 1.4175428237350762,
"learning_rate": 4.871794871794872e-06,
"loss": 0.5461452007293701,
"step": 20
},
{
"epoch": 0.23278370514064015,
"grad_norm": 0.5442834252561063,
"learning_rate": 7.435897435897437e-06,
"loss": 0.3490773677825928,
"step": 30
},
{
"epoch": 0.31037827352085356,
"grad_norm": 0.32322946422972365,
"learning_rate": 1e-05,
"loss": 0.2592954635620117,
"step": 40
},
{
"epoch": 0.3879728419010669,
"grad_norm": 0.24901563193155196,
"learning_rate": 9.979639600327522e-06,
"loss": 0.2136533737182617,
"step": 50
},
{
"epoch": 0.4655674102812803,
"grad_norm": 0.2047675084448879,
"learning_rate": 9.918724219660013e-06,
"loss": 0.18301695585250854,
"step": 60
},
{
"epoch": 0.5431619786614937,
"grad_norm": 0.1694310997257767,
"learning_rate": 9.817749962596115e-06,
"loss": 0.16246029138565063,
"step": 70
},
{
"epoch": 0.6207565470417071,
"grad_norm": 0.22587456656054467,
"learning_rate": 9.677539179628005e-06,
"loss": 0.14934264421463012,
"step": 80
},
{
"epoch": 0.6983511154219205,
"grad_norm": 0.22154973989105028,
"learning_rate": 9.499233769787534e-06,
"loss": 0.134801185131073,
"step": 90
},
{
"epoch": 0.7759456838021338,
"grad_norm": 0.2099862635469814,
"learning_rate": 9.284285880837947e-06,
"loss": 0.13017673492431642,
"step": 100
},
{
"epoch": 0.8535402521823472,
"grad_norm": 0.32230657820182124,
"learning_rate": 9.034446082750352e-06,
"loss": 0.12214579582214355,
"step": 110
},
{
"epoch": 0.9311348205625606,
"grad_norm": 0.324253054340729,
"learning_rate": 8.751749110782013e-06,
"loss": 0.12026152610778809,
"step": 120
},
{
"epoch": 1.0077594568380213,
"grad_norm": 0.20488241588612174,
"learning_rate": 8.438497294267117e-06,
"loss": 0.11126101016998291,
"step": 130
},
{
"epoch": 1.0853540252182348,
"grad_norm": 0.20661218086124847,
"learning_rate": 8.097241806078616e-06,
"loss": 0.10776399374008179,
"step": 140
},
{
"epoch": 1.162948593598448,
"grad_norm": 0.25468202960165104,
"learning_rate": 7.730761885468486e-06,
"loss": 0.10431833267211914,
"step": 150
},
{
"epoch": 1.2405431619786615,
"grad_norm": 0.17930064486716413,
"learning_rate": 7.342042203498952e-06,
"loss": 0.10304663181304932,
"step": 160
},
{
"epoch": 1.3181377303588748,
"grad_norm": 0.20225538073749422,
"learning_rate": 6.934248555404197e-06,
"loss": 0.09784629344940185,
"step": 170
},
{
"epoch": 1.3957322987390883,
"grad_norm": 0.2256721972453044,
"learning_rate": 6.510702077847864e-06,
"loss": 0.09537227749824524,
"step": 180
},
{
"epoch": 1.4733268671193016,
"grad_norm": 0.21487787771920072,
"learning_rate": 6.074852201055121e-06,
"loss": 0.09520423412322998,
"step": 190
},
{
"epoch": 1.5509214354995149,
"grad_norm": 0.17540761321861204,
"learning_rate": 5.630248556101448e-06,
"loss": 0.09088362455368042,
"step": 200
},
{
"epoch": 1.6285160038797284,
"grad_norm": 0.21743503130668765,
"learning_rate": 5.180512066149682e-06,
"loss": 0.0899280071258545,
"step": 210
},
{
"epoch": 1.706110572259942,
"grad_norm": 0.20331687416060285,
"learning_rate": 4.729305457072913e-06,
"loss": 0.0881616234779358,
"step": 220
},
{
"epoch": 1.7837051406401552,
"grad_norm": 0.15781467110120098,
"learning_rate": 4.280303427629404e-06,
"loss": 0.08638249635696411,
"step": 230
},
{
"epoch": 1.8612997090203685,
"grad_norm": 0.1623620489054104,
"learning_rate": 3.8371627221284495e-06,
"loss": 0.08716154098510742,
"step": 240
},
{
"epoch": 1.938894277400582,
"grad_norm": 0.15611783173066054,
"learning_rate": 3.403492349320101e-06,
"loss": 0.08580605983734131,
"step": 250
},
{
"epoch": 2.0155189136760425,
"grad_norm": 0.15287072067575233,
"learning_rate": 2.982824190050958e-06,
"loss": 0.08316840529441834,
"step": 260
},
{
"epoch": 2.093113482056256,
"grad_norm": 0.1853136112632167,
"learning_rate": 2.5785842330619038e-06,
"loss": 0.08091338872909545,
"step": 270
},
{
"epoch": 2.1707080504364695,
"grad_norm": 0.14114872525549504,
"learning_rate": 2.1940646731880887e-06,
"loss": 0.08085420131683349,
"step": 280
},
{
"epoch": 2.248302618816683,
"grad_norm": 0.13643528182686213,
"learning_rate": 1.8323970991978823e-06,
"loss": 0.08156624436378479,
"step": 290
},
{
"epoch": 2.325897187196896,
"grad_norm": 0.14573681730374075,
"learning_rate": 1.4965269896332884e-06,
"loss": 0.0808843195438385,
"step": 300
},
{
"epoch": 2.4034917555771096,
"grad_norm": 0.1466398992341211,
"learning_rate": 1.1891897243618184e-06,
"loss": 0.07979943156242371,
"step": 310
},
{
"epoch": 2.481086323957323,
"grad_norm": 0.12798260710398743,
"learning_rate": 9.128883072055411e-07,
"loss": 0.08049517869949341,
"step": 320
},
{
"epoch": 2.558680892337536,
"grad_norm": 0.13826353734235647,
"learning_rate": 6.698729810778065e-07,
"loss": 0.08011389374732972,
"step": 330
},
{
"epoch": 2.6362754607177497,
"grad_norm": 0.1305401343538733,
"learning_rate": 4.6212290164521554e-07,
"loss": 0.08163015246391296,
"step": 340
},
{
"epoch": 2.713870029097963,
"grad_norm": 0.12804004522045906,
"learning_rate": 2.9133001876746004e-07,
"loss": 0.08051948547363282,
"step": 350
},
{
"epoch": 2.7914645974781767,
"grad_norm": 0.12808224007612634,
"learning_rate": 1.5888529698718347e-07,
"loss": 0.07719261646270752,
"step": 360
},
{
"epoch": 2.86905916585839,
"grad_norm": 0.12117673381149041,
"learning_rate": 6.58673872923693e-08,
"loss": 0.08128957152366638,
"step": 370
},
{
"epoch": 2.946653734238603,
"grad_norm": 0.124324493318766,
"learning_rate": 1.3033842410251074e-08,
"loss": 0.07743191719055176,
"step": 380
},
{
"epoch": 3.0,
"step": 387,
"total_flos": 3081875480379392.0,
"train_loss": 0.06056562058377327,
"train_runtime": 29609.547,
"train_samples_per_second": 6.685,
"train_steps_per_second": 0.013
}
],
"logging_steps": 10,
"max_steps": 387,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 40,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3081875480379392.0,
"train_batch_size": 4,
"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 sha256:183e7b3bdde253f2571677062e7c65704a64af443b29948fe6b9d366ccf011e3
size 7377

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 32 KiB