初始化项目，由ModelHub XC社区提供模型
Model: zenlm/zen-nano Source: Original Platform
This commit is contained in:
ModelHub XC
28
checkpoint-240/added_tokens.json
Normal file
28
checkpoint-240/added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
89
checkpoint-240/chat_template.jinja
Normal file
89
checkpoint-240/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 %}
|
||||
60
checkpoint-240/config.json
Normal file
60
checkpoint-240/config.json
Normal file
@@ -0,0 +1,60 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 3072,
|
||||
"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": 40960,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151645,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.56.1",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
checkpoint-240/generation_config.json
Normal file
12
checkpoint-240/generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151645,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.56.1"
|
||||
}
|
||||
151388
checkpoint-240/merges.txt
Normal file
151388
checkpoint-240/merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-240/model.safetensors
Normal file
3
checkpoint-240/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a6a9ae479f1f4509d12d547b8b5eb3c5b6b031dd7ee66f9d0ac74552dec87032
|
||||
size 1192135096
|
||||
3
checkpoint-240/optimizer.pt
Normal file
3
checkpoint-240/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:33fbf37852ca0d8ce03c282d4e8fcf78b26926841dcc48c3663eb133a6ca4ad3
|
||||
size 2384451723
|
||||
3
checkpoint-240/rng_state.pth
Normal file
3
checkpoint-240/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:527276764335e03ea915d0573a9ad59eeff630ed1d94d41b99d98ba5a5610338
|
||||
size 14391
|
||||
3
checkpoint-240/scheduler.pt
Normal file
3
checkpoint-240/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fcb018bb4914c132e9aa57195da03a5a6ab62a5c65ffe18011d8098bbd5e83f7
|
||||
size 1465
|
||||
25
checkpoint-240/special_tokens_map.json
Normal file
25
checkpoint-240/special_tokens_map.json
Normal file
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"additional_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|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|im_end|>"
|
||||
}
|
||||
BIN
checkpoint-240/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
checkpoint-240/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
239
checkpoint-240/tokenizer_config.json
Normal file
239
checkpoint-240/tokenizer_config.json
Normal file
@@ -0,0 +1,239 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_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|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|im_end|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
377
checkpoint-240/trainer_state.json
Normal file
377
checkpoint-240/trainer_state.json
Normal file
@@ -0,0 +1,377 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 10.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 240,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.041666666666666664,
|
||||
"grad_norm": 73.5,
|
||||
"learning_rate": 0.0,
|
||||
"loss": 3.9287,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.20833333333333334,
|
||||
"grad_norm": 80.5,
|
||||
"learning_rate": 4.000000000000001e-06,
|
||||
"loss": 3.994,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.4166666666666667,
|
||||
"grad_norm": 63.75,
|
||||
"learning_rate": 9e-06,
|
||||
"loss": 3.6819,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.625,
|
||||
"grad_norm": 49.25,
|
||||
"learning_rate": 1.4000000000000001e-05,
|
||||
"loss": 2.5702,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.8333333333333334,
|
||||
"grad_norm": 48.75,
|
||||
"learning_rate": 1.9e-05,
|
||||
"loss": 1.4286,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 1.0416666666666667,
|
||||
"grad_norm": 11.3125,
|
||||
"learning_rate": 2.4e-05,
|
||||
"loss": 0.7957,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 9.0625,
|
||||
"learning_rate": 2.9e-05,
|
||||
"loss": 0.7432,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 1.4583333333333333,
|
||||
"grad_norm": 16.5,
|
||||
"learning_rate": 3.4000000000000007e-05,
|
||||
"loss": 0.6508,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 12.75,
|
||||
"learning_rate": 3.9000000000000006e-05,
|
||||
"loss": 0.591,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 1.875,
|
||||
"grad_norm": 6.59375,
|
||||
"learning_rate": 4.4000000000000006e-05,
|
||||
"loss": 0.6682,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 2.0833333333333335,
|
||||
"grad_norm": 11.1875,
|
||||
"learning_rate": 4.9e-05,
|
||||
"loss": 0.4391,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 2.2916666666666665,
|
||||
"grad_norm": 9.5,
|
||||
"learning_rate": 4.8947368421052635e-05,
|
||||
"loss": 0.3461,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"grad_norm": 15.5,
|
||||
"learning_rate": 4.7631578947368424e-05,
|
||||
"loss": 0.4083,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 2.7083333333333335,
|
||||
"grad_norm": 12.0,
|
||||
"learning_rate": 4.6315789473684214e-05,
|
||||
"loss": 0.377,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 2.9166666666666665,
|
||||
"grad_norm": 10.0625,
|
||||
"learning_rate": 4.5e-05,
|
||||
"loss": 0.3861,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 3.125,
|
||||
"grad_norm": 6.78125,
|
||||
"learning_rate": 4.368421052631579e-05,
|
||||
"loss": 0.3271,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 3.3333333333333335,
|
||||
"grad_norm": 5.125,
|
||||
"learning_rate": 4.236842105263158e-05,
|
||||
"loss": 0.2295,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 3.5416666666666665,
|
||||
"grad_norm": 5.75,
|
||||
"learning_rate": 4.105263157894737e-05,
|
||||
"loss": 0.2661,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 3.75,
|
||||
"grad_norm": 10.9375,
|
||||
"learning_rate": 3.973684210526316e-05,
|
||||
"loss": 0.2583,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 3.9583333333333335,
|
||||
"grad_norm": 10.0625,
|
||||
"learning_rate": 3.842105263157895e-05,
|
||||
"loss": 0.2631,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 4.166666666666667,
|
||||
"grad_norm": 6.4375,
|
||||
"learning_rate": 3.710526315789474e-05,
|
||||
"loss": 0.1991,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 4.375,
|
||||
"grad_norm": 6.71875,
|
||||
"learning_rate": 3.578947368421053e-05,
|
||||
"loss": 0.1937,
|
||||
"step": 105
|
||||
},
|
||||
{
|
||||
"epoch": 4.583333333333333,
|
||||
"grad_norm": 5.0,
|
||||
"learning_rate": 3.447368421052632e-05,
|
||||
"loss": 0.1894,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 4.791666666666667,
|
||||
"grad_norm": 10.8125,
|
||||
"learning_rate": 3.3157894736842106e-05,
|
||||
"loss": 0.2233,
|
||||
"step": 115
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"grad_norm": 6.53125,
|
||||
"learning_rate": 3.1842105263157895e-05,
|
||||
"loss": 0.2006,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 5.208333333333333,
|
||||
"grad_norm": 4.59375,
|
||||
"learning_rate": 3.0526315789473684e-05,
|
||||
"loss": 0.1657,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 5.416666666666667,
|
||||
"grad_norm": 4.65625,
|
||||
"learning_rate": 2.9210526315789477e-05,
|
||||
"loss": 0.1937,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 5.625,
|
||||
"grad_norm": 7.90625,
|
||||
"learning_rate": 2.7894736842105263e-05,
|
||||
"loss": 0.1801,
|
||||
"step": 135
|
||||
},
|
||||
{
|
||||
"epoch": 5.833333333333333,
|
||||
"grad_norm": 3.984375,
|
||||
"learning_rate": 2.6578947368421052e-05,
|
||||
"loss": 0.1704,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 6.041666666666667,
|
||||
"grad_norm": 3.8125,
|
||||
"learning_rate": 2.5263157894736845e-05,
|
||||
"loss": 0.168,
|
||||
"step": 145
|
||||
},
|
||||
{
|
||||
"epoch": 6.25,
|
||||
"grad_norm": 5.15625,
|
||||
"learning_rate": 2.394736842105263e-05,
|
||||
"loss": 0.1395,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 6.458333333333333,
|
||||
"grad_norm": 4.25,
|
||||
"learning_rate": 2.2631578947368423e-05,
|
||||
"loss": 0.1426,
|
||||
"step": 155
|
||||
},
|
||||
{
|
||||
"epoch": 6.666666666666667,
|
||||
"grad_norm": 4.8125,
|
||||
"learning_rate": 2.1315789473684212e-05,
|
||||
"loss": 0.1591,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 6.875,
|
||||
"grad_norm": 5.3125,
|
||||
"learning_rate": 2e-05,
|
||||
"loss": 0.1656,
|
||||
"step": 165
|
||||
},
|
||||
{
|
||||
"epoch": 7.083333333333333,
|
||||
"grad_norm": 3.53125,
|
||||
"learning_rate": 1.868421052631579e-05,
|
||||
"loss": 0.1505,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 7.291666666666667,
|
||||
"grad_norm": 4.875,
|
||||
"learning_rate": 1.736842105263158e-05,
|
||||
"loss": 0.1356,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 7.5,
|
||||
"grad_norm": 3.890625,
|
||||
"learning_rate": 1.605263157894737e-05,
|
||||
"loss": 0.1359,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 7.708333333333333,
|
||||
"grad_norm": 3.59375,
|
||||
"learning_rate": 1.4736842105263157e-05,
|
||||
"loss": 0.1444,
|
||||
"step": 185
|
||||
},
|
||||
{
|
||||
"epoch": 7.916666666666667,
|
||||
"grad_norm": 4.5,
|
||||
"learning_rate": 1.3421052631578948e-05,
|
||||
"loss": 0.1446,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 8.125,
|
||||
"grad_norm": 3.375,
|
||||
"learning_rate": 1.2105263157894737e-05,
|
||||
"loss": 0.1381,
|
||||
"step": 195
|
||||
},
|
||||
{
|
||||
"epoch": 8.333333333333334,
|
||||
"grad_norm": 4.03125,
|
||||
"learning_rate": 1.0789473684210526e-05,
|
||||
"loss": 0.1372,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 8.541666666666666,
|
||||
"grad_norm": 3.921875,
|
||||
"learning_rate": 9.473684210526317e-06,
|
||||
"loss": 0.1354,
|
||||
"step": 205
|
||||
},
|
||||
{
|
||||
"epoch": 8.75,
|
||||
"grad_norm": 4.03125,
|
||||
"learning_rate": 8.157894736842106e-06,
|
||||
"loss": 0.1321,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 8.958333333333334,
|
||||
"grad_norm": 3.390625,
|
||||
"learning_rate": 6.842105263157896e-06,
|
||||
"loss": 0.1351,
|
||||
"step": 215
|
||||
},
|
||||
{
|
||||
"epoch": 9.166666666666666,
|
||||
"grad_norm": 3.96875,
|
||||
"learning_rate": 5.526315789473684e-06,
|
||||
"loss": 0.1331,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 9.375,
|
||||
"grad_norm": 3.84375,
|
||||
"learning_rate": 4.210526315789474e-06,
|
||||
"loss": 0.129,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"epoch": 9.583333333333334,
|
||||
"grad_norm": 3.953125,
|
||||
"learning_rate": 2.8947368421052634e-06,
|
||||
"loss": 0.1285,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 9.791666666666666,
|
||||
"grad_norm": 3.828125,
|
||||
"learning_rate": 1.5789473684210528e-06,
|
||||
"loss": 0.1367,
|
||||
"step": 235
|
||||
},
|
||||
{
|
||||
"epoch": 10.0,
|
||||
"grad_norm": 6.5,
|
||||
"learning_rate": 2.6315789473684213e-07,
|
||||
"loss": 0.1335,
|
||||
"step": 240
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 240,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 10,
|
||||
"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": 635964531671040.0,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-240/training_args.bin
Normal file
3
checkpoint-240/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c57dd6ee21e08885a384c25251b744c7c77828bafa879ca11b2116f30c68c8c3
|
||||
size 5713
|
||||
1
checkpoint-240/vocab.json
Normal file
1
checkpoint-240/vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user