初始化项目，由ModelHub XC社区提供模型
Model: acstener/BlazingCleanup-Qwen2.5-1.5B-FT-v1 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
21
README.md
Normal file
21
README.md
Normal file
@@ -0,0 +1,21 @@
|
|||||||
|
---
|
||||||
|
base_model: unsloth/Qwen2.5-1.5B-Instruct
|
||||||
|
tags:
|
||||||
|
- text-generation-inference
|
||||||
|
- transformers
|
||||||
|
- unsloth
|
||||||
|
- qwen2
|
||||||
|
license: apache-2.0
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
---
|
||||||
|
|
||||||
|
# Uploaded finetuned model
|
||||||
|
|
||||||
|
- **Developed by:** acstener
|
||||||
|
- **License:** apache-2.0
|
||||||
|
- **Finetuned from model :** unsloth/Qwen2.5-1.5B-Instruct
|
||||||
|
|
||||||
|
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
||||||
|
|
||||||
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
||||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal 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 %}
|
||||||
62
config.json
Normal file
62
config.json
Normal file
@@ -0,0 +1,62 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": null,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 1536,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 8960,
|
||||||
|
"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"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 21,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 12,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 2,
|
||||||
|
"pad_token_id": 151665,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_parameters": {
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"rope_type": "default"
|
||||||
|
},
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": true,
|
||||||
|
"unsloth_fixed": true,
|
||||||
|
"unsloth_version": "2026.3.11",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151936
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ebdff82c9f0a0efec2d0fd362b124e1754f1210d6718711427b78fd78d897a5b
|
||||||
|
size 3087467144
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31
|
||||||
|
size 11422356
|
||||||
16
tokenizer_config.json
Normal file
16
tokenizer_config.json
Normal 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": false,
|
||||||
|
"model_max_length": 32768,
|
||||||
|
"pad_token": "<|PAD_TOKEN|>",
|
||||||
|
"padding_side": "left",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null,
|
||||||
|
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"
|
||||||
|
}
|
||||||
354
train_metrics.json
Normal file
354
train_metrics.json
Normal file
@@ -0,0 +1,354 @@
|
|||||||
|
{
|
||||||
|
"training_loss": 1.2225627280771731,
|
||||||
|
"eval_loss": 0.4609449803829193,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"loss": 4.197445869445801,
|
||||||
|
"grad_norm": 28.397323608398438,
|
||||||
|
"learning_rate": 0.0,
|
||||||
|
"epoch": 0.12903225806451613,
|
||||||
|
"step": 1
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 4.092413902282715,
|
||||||
|
"grad_norm": 27.681936264038086,
|
||||||
|
"learning_rate": 1e-05,
|
||||||
|
"epoch": 0.25806451612903225,
|
||||||
|
"step": 2
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 3.8777694702148438,
|
||||||
|
"grad_norm": 22.097108840942383,
|
||||||
|
"learning_rate": 2e-05,
|
||||||
|
"epoch": 0.3870967741935484,
|
||||||
|
"step": 3
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 3.503629684448242,
|
||||||
|
"grad_norm": 6.258087635040283,
|
||||||
|
"learning_rate": 3e-05,
|
||||||
|
"epoch": 0.5161290322580645,
|
||||||
|
"step": 4
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 3.2292399406433105,
|
||||||
|
"grad_norm": 3.871248483657837,
|
||||||
|
"learning_rate": 4e-05,
|
||||||
|
"epoch": 0.6451612903225806,
|
||||||
|
"step": 5
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 3.076737642288208,
|
||||||
|
"grad_norm": 3.4568703174591064,
|
||||||
|
"learning_rate": 5e-05,
|
||||||
|
"epoch": 0.7741935483870968,
|
||||||
|
"step": 6
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 2.9121265411376953,
|
||||||
|
"grad_norm": 3.3284857273101807,
|
||||||
|
"learning_rate": 6e-05,
|
||||||
|
"epoch": 0.9032258064516129,
|
||||||
|
"step": 7
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 2.713679790496826,
|
||||||
|
"grad_norm": 3.1837189197540283,
|
||||||
|
"learning_rate": 7e-05,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"eval_loss": 2.303722381591797,
|
||||||
|
"eval_runtime": 2.6108,
|
||||||
|
"eval_samples_per_second": 9.193,
|
||||||
|
"eval_steps_per_second": 2.298,
|
||||||
|
"epoch": 1.0,
|
||||||
|
"step": 8
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 2.473531723022461,
|
||||||
|
"grad_norm": 3.07153582572937,
|
||||||
|
"learning_rate": 8e-05,
|
||||||
|
"epoch": 1.129032258064516,
|
||||||
|
"step": 9
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 2.1877307891845703,
|
||||||
|
"grad_norm": 2.458406448364258,
|
||||||
|
"learning_rate": 9e-05,
|
||||||
|
"epoch": 1.2580645161290323,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 1.8962702751159668,
|
||||||
|
"grad_norm": 2.583014965057373,
|
||||||
|
"learning_rate": 0.0001,
|
||||||
|
"epoch": 1.3870967741935485,
|
||||||
|
"step": 11
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 1.522033452987671,
|
||||||
|
"grad_norm": 2.4323620796203613,
|
||||||
|
"learning_rate": 9.972609476841367e-05,
|
||||||
|
"epoch": 1.5161290322580645,
|
||||||
|
"step": 12
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 1.2446801662445068,
|
||||||
|
"grad_norm": 2.317019462585449,
|
||||||
|
"learning_rate": 9.890738003669029e-05,
|
||||||
|
"epoch": 1.6451612903225805,
|
||||||
|
"step": 13
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.9725565910339355,
|
||||||
|
"grad_norm": 2.204679489135742,
|
||||||
|
"learning_rate": 9.755282581475769e-05,
|
||||||
|
"epoch": 1.7741935483870968,
|
||||||
|
"step": 14
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.7646273374557495,
|
||||||
|
"grad_norm": 2.1791882514953613,
|
||||||
|
"learning_rate": 9.567727288213005e-05,
|
||||||
|
"epoch": 1.903225806451613,
|
||||||
|
"step": 15
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.6507037878036499,
|
||||||
|
"grad_norm": 2.528223752975464,
|
||||||
|
"learning_rate": 9.330127018922194e-05,
|
||||||
|
"epoch": 2.0,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"eval_loss": 0.5809889435768127,
|
||||||
|
"eval_runtime": 2.1977,
|
||||||
|
"eval_samples_per_second": 10.921,
|
||||||
|
"eval_steps_per_second": 2.73,
|
||||||
|
"epoch": 2.0,
|
||||||
|
"step": 16
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.5388383269309998,
|
||||||
|
"grad_norm": 1.2982324361801147,
|
||||||
|
"learning_rate": 9.045084971874738e-05,
|
||||||
|
"epoch": 2.129032258064516,
|
||||||
|
"step": 17
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.4493573307991028,
|
||||||
|
"grad_norm": 0.6475956439971924,
|
||||||
|
"learning_rate": 8.715724127386972e-05,
|
||||||
|
"epoch": 2.258064516129032,
|
||||||
|
"step": 18
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.47298651933670044,
|
||||||
|
"grad_norm": 0.5114660263061523,
|
||||||
|
"learning_rate": 8.345653031794292e-05,
|
||||||
|
"epoch": 2.3870967741935485,
|
||||||
|
"step": 19
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.4046781659126282,
|
||||||
|
"grad_norm": 0.40222474932670593,
|
||||||
|
"learning_rate": 7.938926261462366e-05,
|
||||||
|
"epoch": 2.5161290322580645,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.47141924500465393,
|
||||||
|
"grad_norm": 0.39228641986846924,
|
||||||
|
"learning_rate": 7.500000000000001e-05,
|
||||||
|
"epoch": 2.6451612903225805,
|
||||||
|
"step": 21
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.4083420932292938,
|
||||||
|
"grad_norm": 0.3217116594314575,
|
||||||
|
"learning_rate": 7.033683215379002e-05,
|
||||||
|
"epoch": 2.774193548387097,
|
||||||
|
"step": 22
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.4131239652633667,
|
||||||
|
"grad_norm": 0.35026267170906067,
|
||||||
|
"learning_rate": 6.545084971874738e-05,
|
||||||
|
"epoch": 2.903225806451613,
|
||||||
|
"step": 23
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.3474363386631012,
|
||||||
|
"grad_norm": 0.3523545563220978,
|
||||||
|
"learning_rate": 6.0395584540887963e-05,
|
||||||
|
"epoch": 3.0,
|
||||||
|
"step": 24
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"eval_loss": 0.4813229739665985,
|
||||||
|
"eval_runtime": 2.2109,
|
||||||
|
"eval_samples_per_second": 10.855,
|
||||||
|
"eval_steps_per_second": 2.714,
|
||||||
|
"epoch": 3.0,
|
||||||
|
"step": 24
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.4284741282463074,
|
||||||
|
"grad_norm": 0.34906816482543945,
|
||||||
|
"learning_rate": 5.522642316338268e-05,
|
||||||
|
"epoch": 3.129032258064516,
|
||||||
|
"step": 25
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.440382719039917,
|
||||||
|
"grad_norm": 0.27476829290390015,
|
||||||
|
"learning_rate": 5e-05,
|
||||||
|
"epoch": 3.258064516129032,
|
||||||
|
"step": 26
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.36974847316741943,
|
||||||
|
"grad_norm": 0.2999092936515808,
|
||||||
|
"learning_rate": 4.477357683661734e-05,
|
||||||
|
"epoch": 3.3870967741935485,
|
||||||
|
"step": 27
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.3683726489543915,
|
||||||
|
"grad_norm": 0.4260818660259247,
|
||||||
|
"learning_rate": 3.960441545911204e-05,
|
||||||
|
"epoch": 3.5161290322580645,
|
||||||
|
"step": 28
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.3738524913787842,
|
||||||
|
"grad_norm": 0.3270018398761749,
|
||||||
|
"learning_rate": 3.4549150281252636e-05,
|
||||||
|
"epoch": 3.6451612903225805,
|
||||||
|
"step": 29
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.3474452793598175,
|
||||||
|
"grad_norm": 0.2512679696083069,
|
||||||
|
"learning_rate": 2.9663167846209998e-05,
|
||||||
|
"epoch": 3.774193548387097,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.38277819752693176,
|
||||||
|
"grad_norm": 0.2715815305709839,
|
||||||
|
"learning_rate": 2.500000000000001e-05,
|
||||||
|
"epoch": 3.903225806451613,
|
||||||
|
"step": 31
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.38639724254608154,
|
||||||
|
"grad_norm": 0.31645700335502625,
|
||||||
|
"learning_rate": 2.061073738537635e-05,
|
||||||
|
"epoch": 4.0,
|
||||||
|
"step": 32
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"eval_loss": 0.4651392996311188,
|
||||||
|
"eval_runtime": 2.2208,
|
||||||
|
"eval_samples_per_second": 10.807,
|
||||||
|
"eval_steps_per_second": 2.702,
|
||||||
|
"epoch": 4.0,
|
||||||
|
"step": 32
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.34431296586990356,
|
||||||
|
"grad_norm": 0.25423043966293335,
|
||||||
|
"learning_rate": 1.6543469682057106e-05,
|
||||||
|
"epoch": 4.129032258064516,
|
||||||
|
"step": 33
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.34334394335746765,
|
||||||
|
"grad_norm": 0.328544557094574,
|
||||||
|
"learning_rate": 1.2842758726130283e-05,
|
||||||
|
"epoch": 4.258064516129032,
|
||||||
|
"step": 34
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.36162328720092773,
|
||||||
|
"grad_norm": 0.2698550522327423,
|
||||||
|
"learning_rate": 9.549150281252633e-06,
|
||||||
|
"epoch": 4.387096774193548,
|
||||||
|
"step": 35
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.3885972201824188,
|
||||||
|
"grad_norm": 0.3081808090209961,
|
||||||
|
"learning_rate": 6.698729810778065e-06,
|
||||||
|
"epoch": 4.516129032258064,
|
||||||
|
"step": 36
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.38622862100601196,
|
||||||
|
"grad_norm": 0.2773016691207886,
|
||||||
|
"learning_rate": 4.322727117869951e-06,
|
||||||
|
"epoch": 4.645161290322581,
|
||||||
|
"step": 37
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.4032401740550995,
|
||||||
|
"grad_norm": 0.24623064696788788,
|
||||||
|
"learning_rate": 2.4471741852423237e-06,
|
||||||
|
"epoch": 4.774193548387097,
|
||||||
|
"step": 38
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.371090829372406,
|
||||||
|
"grad_norm": 0.29499495029449463,
|
||||||
|
"learning_rate": 1.0926199633097157e-06,
|
||||||
|
"epoch": 4.903225806451613,
|
||||||
|
"step": 39
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"loss": 0.3852619528770447,
|
||||||
|
"grad_norm": 0.30445531010627747,
|
||||||
|
"learning_rate": 2.7390523158633554e-07,
|
||||||
|
"epoch": 5.0,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"eval_loss": 0.4609449803829193,
|
||||||
|
"eval_runtime": 2.2172,
|
||||||
|
"eval_samples_per_second": 10.824,
|
||||||
|
"eval_steps_per_second": 2.706,
|
||||||
|
"epoch": 5.0,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"train_runtime": 310.3912,
|
||||||
|
"train_samples_per_second": 1.997,
|
||||||
|
"train_steps_per_second": 0.129,
|
||||||
|
"total_flos": 2205575534638080.0,
|
||||||
|
"train_loss": 1.2225627280771731,
|
||||||
|
"epoch": 5.0,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"eval_loss": 0.4609449803829193,
|
||||||
|
"eval_runtime": 2.1914,
|
||||||
|
"eval_samples_per_second": 10.952,
|
||||||
|
"eval_steps_per_second": 2.738,
|
||||||
|
"epoch": 5.0,
|
||||||
|
"step": 40
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"config": {
|
||||||
|
"base_model": "unsloth/Qwen2.5-1.5B-Instruct",
|
||||||
|
"lora_r": 32,
|
||||||
|
"lora_alpha": 64,
|
||||||
|
"target_modules": "all-linear",
|
||||||
|
"packing": true,
|
||||||
|
"num_epochs": 5,
|
||||||
|
"learning_rate": 0.0001,
|
||||||
|
"max_seq_length": 512,
|
||||||
|
"load_in_4bit": false
|
||||||
|
}
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user