sylee96/qwen3-1.7b-grpo-ckpt100
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: sylee96/qwen3-1.7b-grpo-ckpt100
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-10 07:28:46 +08:00
commit b82592ca22
13 changed files with 152169 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

28
added_tokens.json Normal file
View 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
}

66
chat_template.jinja Normal file
View File

@@ -0,0 +1,66 @@
{%- 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 %}
{%- 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" %}
{{- '<|im_start|>' + message.role + '\n' }}
{% generation %}
{{- content -}}
{%- 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 %}
{% endgeneration %}
{{- '<|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' }}
{% generation %}
{% endgeneration %}
{%- endif %}

60
config.json Normal file
View 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": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"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": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "4.57.6",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"eos_token_id": [
151645,
151643
],
"max_new_tokens": 2048,
"pad_token_id": 151643,
"transformers_version": "4.57.6"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94dfff67a7e5e07e0fc1cc934a5e390eec0921a6e20253acf4c599e2199b36e0
size 3441185608

19
special_tokens_map.json Normal file
View File

@@ -0,0 +1,19 @@
{
"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": "<|im_end|>",
"pad_token": "<|endoftext|>"
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
size 11422821

239
tokenizer_config.json Normal file
View 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": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

314
trainer_state.json Normal file
View File

@@ -0,0 +1,314 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.05518763796909492,
"eval_steps": 500,
"global_step": 100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"clip_ratio/high_max": 0.0009054738155100494,
"clip_ratio/high_mean": 0.00035781565529759975,
"clip_ratio/low_mean": 0.00016371723540942185,
"clip_ratio/low_min": 1.144509224104695e-05,
"clip_ratio/region_mean": 0.0005215328827034682,
"completions/clipped_ratio": 0.4879464626312256,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1021.8,
"completions/mean_length": 802.8379760742188,
"completions/mean_terminated_length": 591.0183349609375,
"completions/min_length": 16.6,
"completions/min_terminated_length": 16.6,
"entropy": 0.6993172228336334,
"epoch": 0.005518763796909493,
"frac_reward_zero_std": 0.648214316368103,
"grad_norm": 0.123046875,
"kl": 0.0009140914742602035,
"learning_rate": 9.994100796397954e-06,
"loss": 0.0096,
"num_tokens": 2134981.0,
"reward": 0.17656995058059693,
"reward_std": 0.3300946533679962,
"rewards/reward_fn/mean": 0.17656994760036468,
"rewards/reward_fn/std": 0.3300946354866028,
"step": 10,
"step_time": 62.725463995942846
},
{
"clip_ratio/high_max": 0.0009650078689446672,
"clip_ratio/high_mean": 0.00040530616533942523,
"clip_ratio/low_mean": 0.00019620073144324123,
"clip_ratio/low_min": 2.9645057293237186e-05,
"clip_ratio/region_mean": 0.0006015069084241986,
"completions/clipped_ratio": 0.5308036029338836,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1019.4,
"completions/mean_length": 814.8719116210938,
"completions/mean_terminated_length": 578.806640625,
"completions/min_length": 10.2,
"completions/min_terminated_length": 10.2,
"entropy": 0.7009260475635528,
"epoch": 0.011037527593818985,
"frac_reward_zero_std": 0.6464286088943482,
"grad_norm": 0.115234375,
"kl": 0.0012107100861612707,
"learning_rate": 9.889612861977855e-06,
"loss": 0.009,
"num_tokens": 4322090.0,
"reward": 0.16465030908584594,
"reward_std": 0.31232678294181826,
"rewards/reward_fn/mean": 0.16465030312538148,
"rewards/reward_fn/std": 0.31232677698135375,
"step": 20,
"step_time": 59.907306081056596
},
{
"clip_ratio/high_max": 0.0007639058487256989,
"clip_ratio/high_mean": 0.00030917047697585074,
"clip_ratio/low_mean": 0.00016517131589353085,
"clip_ratio/low_min": 3.0255078672780656e-05,
"clip_ratio/region_mean": 0.0004743418045109138,
"completions/clipped_ratio": 0.49821431636810304,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1017.6,
"completions/mean_length": 810.8062744140625,
"completions/mean_terminated_length": 601.0194946289063,
"completions/min_length": 18.2,
"completions/min_terminated_length": 18.2,
"entropy": 0.707157039642334,
"epoch": 0.016556291390728478,
"frac_reward_zero_std": 0.6964286088943481,
"grad_norm": 0.08984375,
"kl": 0.0015323497413191945,
"learning_rate": 9.657180469054213e-06,
"loss": 0.0056,
"num_tokens": 6483648.0,
"reward": 0.15746280252933503,
"reward_std": 0.31524514555931094,
"rewards/reward_fn/mean": 0.15746279954910278,
"rewards/reward_fn/std": 0.315245121717453,
"step": 30,
"step_time": 69.35127711733803
},
{
"clip_ratio/high_max": 0.0010893745173234492,
"clip_ratio/high_mean": 0.0004552829515887424,
"clip_ratio/low_mean": 0.00020492849944275804,
"clip_ratio/low_min": 3.608180813898798e-05,
"clip_ratio/region_mean": 0.0006602114357519895,
"completions/clipped_ratio": 0.4924107313156128,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1022.4,
"completions/mean_length": 801.3585205078125,
"completions/mean_terminated_length": 584.6675537109375,
"completions/min_length": 28.6,
"completions/min_terminated_length": 28.6,
"entropy": 0.7392709702253342,
"epoch": 0.02207505518763797,
"frac_reward_zero_std": 0.650000023841858,
"grad_norm": 0.10205078125,
"kl": 0.001778936560731381,
"learning_rate": 9.302885579019626e-06,
"loss": 0.0102,
"num_tokens": 8664175.0,
"reward": 0.1526116132736206,
"reward_std": 0.3074562013149261,
"rewards/reward_fn/mean": 0.15261160731315612,
"rewards/reward_fn/std": 0.3074561834335327,
"step": 40,
"step_time": 66.20743731297553
},
{
"clip_ratio/high_max": 0.0009445919014979154,
"clip_ratio/high_mean": 0.00039524411113234237,
"clip_ratio/low_mean": 0.00019868952222168446,
"clip_ratio/low_min": 6.7668152041733265e-06,
"clip_ratio/region_mean": 0.0005939336377196013,
"completions/clipped_ratio": 0.4633928775787354,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1021.6,
"completions/mean_length": 785.5151977539062,
"completions/mean_terminated_length": 579.9617919921875,
"completions/min_length": 17.2,
"completions/min_terminated_length": 17.2,
"entropy": 0.7299870848655701,
"epoch": 0.02759381898454746,
"frac_reward_zero_std": 0.6625000357627868,
"grad_norm": 0.13671875,
"kl": 0.0018997497216332703,
"learning_rate": 8.83599887835493e-06,
"loss": 0.0106,
"num_tokens": 10787441.0,
"reward": 0.17087055444717408,
"reward_std": 0.3202264249324799,
"rewards/reward_fn/mean": 0.17087054550647734,
"rewards/reward_fn/std": 0.3202264130115509,
"step": 50,
"step_time": 61.80385860861279
},
{
"clip_ratio/high_max": 0.0008307943062391132,
"clip_ratio/high_mean": 0.00035787131600955034,
"clip_ratio/low_mean": 0.00023181447832030245,
"clip_ratio/low_min": 2.61040790064726e-05,
"clip_ratio/region_mean": 0.0005896858012420126,
"completions/clipped_ratio": 0.4741071581840515,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1011.2,
"completions/mean_length": 792.1500244140625,
"completions/mean_terminated_length": 583.1341064453125,
"completions/min_length": 16.8,
"completions/min_terminated_length": 16.8,
"entropy": 0.8175096482038497,
"epoch": 0.033112582781456956,
"frac_reward_zero_std": 0.6428571581840515,
"grad_norm": 0.1142578125,
"kl": 0.0020997423096559944,
"learning_rate": 8.268737196446264e-06,
"loss": 0.01,
"num_tokens": 12937373.0,
"reward": 0.170543172955513,
"reward_std": 0.30973091125488283,
"rewards/reward_fn/mean": 0.17054316401481628,
"rewards/reward_fn/std": 0.3097309172153473,
"step": 60,
"step_time": 81.64577775509096
},
{
"clip_ratio/high_max": 0.0010142354993149638,
"clip_ratio/high_mean": 0.0004649270667869132,
"clip_ratio/low_mean": 0.0002056810655631125,
"clip_ratio/low_min": 2.441328761051409e-05,
"clip_ratio/region_mean": 0.0006706080996082165,
"completions/clipped_ratio": 0.4513392984867096,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1021.2,
"completions/mean_length": 780.0888671875,
"completions/mean_terminated_length": 579.7443481445313,
"completions/min_length": 17.6,
"completions/min_terminated_length": 17.6,
"entropy": 0.8121535569429398,
"epoch": 0.03863134657836645,
"frac_reward_zero_std": 0.6232143044471741,
"grad_norm": 0.1298828125,
"kl": 0.002086066803894937,
"learning_rate": 7.61594383291065e-06,
"loss": 0.0068,
"num_tokens": 15043532.0,
"reward": 0.1762128084897995,
"reward_std": 0.32508295178413393,
"rewards/reward_fn/mean": 0.17621279656887054,
"rewards/reward_fn/std": 0.3250829458236694,
"step": 70,
"step_time": 67.39459452703595
},
{
"clip_ratio/high_max": 0.0011546267720405012,
"clip_ratio/high_mean": 0.0004448194318683818,
"clip_ratio/low_mean": 0.00022613786859437823,
"clip_ratio/low_min": 3.512381881591864e-05,
"clip_ratio/region_mean": 0.0006709573091939092,
"completions/clipped_ratio": 0.45714287757873534,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1017.6,
"completions/mean_length": 780.5415405273437,
"completions/mean_terminated_length": 574.924560546875,
"completions/min_length": 13.4,
"completions/min_terminated_length": 13.4,
"entropy": 0.8120243638753891,
"epoch": 0.04415011037527594,
"frac_reward_zero_std": 0.6267857432365418,
"grad_norm": 0.125,
"kl": 0.0022045036195777355,
"learning_rate": 6.894700159171535e-06,
"loss": 0.0074,
"num_tokens": 17150985.0,
"reward": 0.18558780550956727,
"reward_std": 0.3320887923240662,
"rewards/reward_fn/mean": 0.1855877935886383,
"rewards/reward_fn/std": 0.3320887744426727,
"step": 80,
"step_time": 69.55923435157165
},
{
"clip_ratio/high_max": 0.0010666975751519204,
"clip_ratio/high_mean": 0.0004059886821778491,
"clip_ratio/low_mean": 0.00018196528690168635,
"clip_ratio/low_min": 1.4905737771186978e-05,
"clip_ratio/region_mean": 0.0005879539618035779,
"completions/clipped_ratio": 0.4683035910129547,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1018.8,
"completions/mean_length": 786.5406616210937,
"completions/mean_terminated_length": 577.4362426757813,
"completions/min_length": 18.8,
"completions/min_terminated_length": 18.8,
"entropy": 0.8206083297729492,
"epoch": 0.04966887417218543,
"frac_reward_zero_std": 0.6660714626312256,
"grad_norm": 0.107421875,
"kl": 0.0022262637387029825,
"learning_rate": 6.123878657343648e-06,
"loss": 0.0095,
"num_tokens": 19265236.0,
"reward": 0.16312500536441804,
"reward_std": 0.3078223645687103,
"rewards/reward_fn/mean": 0.16312500536441804,
"rewards/reward_fn/std": 0.30782235860824586,
"step": 90,
"step_time": 63.29917922359891
},
{
"clip_ratio/high_max": 0.001015995239140466,
"clip_ratio/high_mean": 0.0005060771596617997,
"clip_ratio/low_mean": 0.000221432710532099,
"clip_ratio/low_min": 4.502671981754247e-05,
"clip_ratio/region_mean": 0.0007275098643731326,
"completions/clipped_ratio": 0.45044645071029665,
"completions/max_length": 1024.0,
"completions/max_terminated_length": 1021.4,
"completions/mean_length": 771.9370849609375,
"completions/mean_terminated_length": 565.00205078125,
"completions/min_length": 17.0,
"completions/min_terminated_length": 17.0,
"entropy": 0.8362967848777771,
"epoch": 0.05518763796909492,
"frac_reward_zero_std": 0.6035714626312256,
"grad_norm": 0.09912109375,
"kl": 0.0022062973876018077,
"learning_rate": 5.323649091872179e-06,
"loss": 0.0076,
"num_tokens": 21324495.0,
"reward": 0.19067709147930145,
"reward_std": 0.32638007402420044,
"rewards/reward_fn/mean": 0.19067708551883697,
"rewards/reward_fn/std": 0.32638007402420044,
"step": 100,
"step_time": 47.039065402187404
}
],
"logging_steps": 10,
"max_steps": 200,
"num_input_tokens_seen": 21324495,
"num_train_epochs": 1,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 16,
"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 sha256:33e7d5fae56ad8bc799fdf1a834a3f65976ea03a0e6f75a70197af76e47257f5
size 7697

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long