初始化项目,由ModelHub XC社区提供模型

Model: gretelai/DEBUG-emoter-Qwen2.5-0.5B-Instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-02 05:09:14 +08:00
commit 7a4c4d469c
80 changed files with 760969 additions and 0 deletions

View File

@@ -0,0 +1,24 @@
{
"</tool_call>": 151658,
"<tool_call>": 151657,
"<|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
}

29
checkpoint-50/config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 896,
"initializer_range": 0.02,
"intermediate_size": 4864,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 14,
"num_hidden_layers": 24,
"num_key_value_heads": 2,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": true,
"torch_dtype": "float32",
"transformers_version": "4.48.2",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

View File

@@ -0,0 +1,14 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "4.48.2"
}

151388
checkpoint-50/merges.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:20fa3baf6756e94e31dbdf2d129c16029be7c3edad043851b1654b96435a34a5
size 1976163472

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2305c113c394478b5194c70c42e2cae0dd86712b86e88ff56dcdbebe7f7b01be
size 3952505274

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:743d69234c1f9bbe7b75d618de78259f369b365fdc4d0ff60b04407b0ffde02e
size 15024

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17a289e6c01736bc0b4798b4132cb5ef587b566fa27b1ebed6c36bf6371ee37d
size 14960

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4e1c711aa7ab8e083af11f3e41ee95efb2a49034b8306a01aaeabdad27f5da2
size 14960

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f9ef94998045ba904ed0bd8e95574fee171d672e45082ceb2d1086d05632d894
size 15024

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a43513717b8c8325e4e53f3c32e1bc927629699ba294af0630ea787af80b695a
size 1064

View File

@@ -0,0 +1,31 @@
{
"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": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:477179b4bef2f24c88d560fa2dbfd0b5ecef0d9789ddd96759ddbdfc53eb7c29
size 11422164

View File

@@ -0,0 +1,209 @@
{
"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
}
},
"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,
"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",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "left",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

View File

@@ -0,0 +1,683 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.06666666666666667,
"eval_steps": 500,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"completion_length": 113.171875,
"epoch": 0.0013333333333333333,
"grad_norm": 0.0,
"kl": 0.0,
"learning_rate": 4.998766400914329e-07,
"loss": 0.0,
"reward": 0.0,
"reward_std": 0.0,
"rewards/emotion_reward_func": 0.0,
"rewards/format_reward_func": 0.0,
"step": 1
},
{
"completion_length": 100.609375,
"epoch": 0.0026666666666666666,
"grad_norm": 7.206315517425537,
"kl": 0.0,
"learning_rate": 4.995066821070679e-07,
"loss": 0.0,
"reward": 0.046875,
"reward_std": 0.1875,
"rewards/emotion_reward_func": 0.015625,
"rewards/format_reward_func": 0.03125,
"step": 2
},
{
"completion_length": 130.65625,
"epoch": 0.004,
"grad_norm": 7.190981864929199,
"kl": 0.0008925930160330608,
"learning_rate": 4.9889049115077e-07,
"loss": 0.0,
"reward": 0.0625,
"reward_std": 0.25,
"rewards/emotion_reward_func": 0.015625,
"rewards/format_reward_func": 0.046875,
"step": 3
},
{
"completion_length": 112.484375,
"epoch": 0.005333333333333333,
"grad_norm": 4.745754718780518,
"kl": 0.0009372199856443331,
"learning_rate": 4.980286753286194e-07,
"loss": 0.0,
"reward": 0.046875,
"reward_std": 0.1875,
"rewards/emotion_reward_func": 0.015625,
"rewards/format_reward_func": 0.03125,
"step": 4
},
{
"completion_length": 100.359375,
"epoch": 0.006666666666666667,
"grad_norm": 6.957683086395264,
"kl": 0.0009052860696101561,
"learning_rate": 4.969220851487844e-07,
"loss": 0.0,
"reward": 0.078125,
"reward_std": 0.3125,
"rewards/emotion_reward_func": 0.03125,
"rewards/format_reward_func": 0.046875,
"step": 5
},
{
"completion_length": 109.5625,
"epoch": 0.008,
"grad_norm": 8.517982482910156,
"kl": 0.0011545967281563208,
"learning_rate": 4.955718126821722e-07,
"loss": 0.0,
"reward": 0.140625,
"reward_std": 0.34228479862213135,
"rewards/emotion_reward_func": 0.03125,
"rewards/format_reward_func": 0.109375,
"step": 6
},
{
"completion_length": 117.484375,
"epoch": 0.009333333333333334,
"grad_norm": 2.9639530181884766,
"kl": 0.001261903322301805,
"learning_rate": 4.939791904846868e-07,
"loss": 0.0,
"reward": 0.03125,
"reward_std": 0.125,
"rewards/emotion_reward_func": 0.015625,
"rewards/format_reward_func": 0.015625,
"step": 7
},
{
"completion_length": 118.234375,
"epoch": 0.010666666666666666,
"grad_norm": 8.49864387512207,
"kl": 0.002180565701564774,
"learning_rate": 4.921457902821578e-07,
"loss": 0.0,
"reward": 0.140625,
"reward_std": 0.4436737596988678,
"rewards/emotion_reward_func": 0.046875,
"rewards/format_reward_func": 0.09375,
"step": 8
},
{
"completion_length": 106.546875,
"epoch": 0.012,
"grad_norm": 7.236983299255371,
"kl": 0.0018676594190765172,
"learning_rate": 4.900734214192358e-07,
"loss": 0.0,
"reward": 0.109375,
"reward_std": 0.3186737596988678,
"rewards/emotion_reward_func": 0.03125,
"rewards/format_reward_func": 0.078125,
"step": 9
},
{
"completion_length": 94.640625,
"epoch": 0.013333333333333334,
"grad_norm": 6.612936973571777,
"kl": 0.00287746504181996,
"learning_rate": 4.877641290737883e-07,
"loss": 0.0,
"reward": 0.15625,
"reward_std": 0.38375620543956757,
"rewards/emotion_reward_func": 0.03125,
"rewards/format_reward_func": 0.125,
"step": 10
},
{
"completion_length": 78.453125,
"epoch": 0.014666666666666666,
"grad_norm": 6.714486598968506,
"kl": 0.0037596136680804193,
"learning_rate": 4.852201922385564e-07,
"loss": 0.0,
"reward": 0.15625,
"reward_std": 0.34297704696655273,
"rewards/emotion_reward_func": 0.03125,
"rewards/format_reward_func": 0.125,
"step": 11
},
{
"completion_length": 113.765625,
"epoch": 0.016,
"grad_norm": 6.222474098205566,
"kl": 0.005189417512156069,
"learning_rate": 4.824441214720628e-07,
"loss": 0.0,
"reward": 0.328125,
"reward_std": 0.6560364216566086,
"rewards/emotion_reward_func": 0.109375,
"rewards/format_reward_func": 0.21875,
"step": 12
},
{
"completion_length": 93.890625,
"epoch": 0.017333333333333333,
"grad_norm": 7.199591636657715,
"kl": 0.011019598576240242,
"learning_rate": 4.794386564209952e-07,
"loss": 0.0,
"reward": 0.359375,
"reward_std": 0.647876650094986,
"rewards/emotion_reward_func": 0.125,
"rewards/format_reward_func": 0.234375,
"step": 13
},
{
"completion_length": 93.6875,
"epoch": 0.018666666666666668,
"grad_norm": 7.459893226623535,
"kl": 0.012794358422979712,
"learning_rate": 4.762067631165049e-07,
"loss": 0.0,
"reward": 0.28125,
"reward_std": 0.4561576098203659,
"rewards/emotion_reward_func": 0.015625,
"rewards/format_reward_func": 0.265625,
"step": 14
},
{
"completion_length": 114.03125,
"epoch": 0.02,
"grad_norm": 7.204787731170654,
"kl": 0.01207199739292264,
"learning_rate": 4.7275163104709194e-07,
"loss": 0.0,
"reward": 0.421875,
"reward_std": 0.6076867878437042,
"rewards/emotion_reward_func": 0.0625,
"rewards/format_reward_func": 0.359375,
"step": 15
},
{
"completion_length": 90.1875,
"epoch": 0.021333333333333333,
"grad_norm": 6.9398369789123535,
"kl": 0.012930819648317993,
"learning_rate": 4.6907667001096585e-07,
"loss": 0.0,
"reward": 0.296875,
"reward_std": 0.6791985481977463,
"rewards/emotion_reward_func": 0.125,
"rewards/format_reward_func": 0.171875,
"step": 16
},
{
"completion_length": 100.265625,
"epoch": 0.02266666666666667,
"grad_norm": 7.01741361618042,
"kl": 0.014807499013841152,
"learning_rate": 4.6518550675098587e-07,
"loss": 0.0,
"reward": 0.609375,
"reward_std": 0.7960269749164581,
"rewards/emotion_reward_func": 0.1875,
"rewards/format_reward_func": 0.421875,
"step": 17
},
{
"completion_length": 101.59375,
"epoch": 0.024,
"grad_norm": 6.980762004852295,
"kl": 0.02019192511215806,
"learning_rate": 4.6108198137550377e-07,
"loss": 0.0,
"reward": 0.53125,
"reward_std": 0.6885540634393692,
"rewards/emotion_reward_func": 0.125,
"rewards/format_reward_func": 0.40625,
"step": 18
},
{
"completion_length": 93.859375,
"epoch": 0.025333333333333333,
"grad_norm": 8.390938758850098,
"kl": 0.03694334626197815,
"learning_rate": 4.567701435686404e-07,
"loss": 0.0,
"reward": 0.65625,
"reward_std": 0.651764303445816,
"rewards/emotion_reward_func": 0.125,
"rewards/format_reward_func": 0.53125,
"step": 19
},
{
"completion_length": 85.546875,
"epoch": 0.02666666666666667,
"grad_norm": 8.39484691619873,
"kl": 0.03380461875349283,
"learning_rate": 4.5225424859373684e-07,
"loss": 0.0,
"reward": 0.765625,
"reward_std": 0.7304560542106628,
"rewards/emotion_reward_func": 0.203125,
"rewards/format_reward_func": 0.5625,
"step": 20
},
{
"completion_length": 91.3125,
"epoch": 0.028,
"grad_norm": 6.440164089202881,
"kl": 0.04492605570703745,
"learning_rate": 4.475387530939226e-07,
"loss": 0.0,
"reward": 0.765625,
"reward_std": 0.5731314420700073,
"rewards/emotion_reward_func": 0.078125,
"rewards/format_reward_func": 0.6875,
"step": 21
},
{
"completion_length": 91.0625,
"epoch": 0.029333333333333333,
"grad_norm": 6.099334716796875,
"kl": 0.040256964042782784,
"learning_rate": 4.426283106939473e-07,
"loss": 0.0,
"reward": 1.1875,
"reward_std": 0.6744011342525482,
"rewards/emotion_reward_func": 0.390625,
"rewards/format_reward_func": 0.796875,
"step": 22
},
{
"completion_length": 79.328125,
"epoch": 0.030666666666666665,
"grad_norm": 7.1284871101379395,
"kl": 0.04640346672385931,
"learning_rate": 4.375277674076149e-07,
"loss": 0.0,
"reward": 1.21875,
"reward_std": 0.7463032901287079,
"rewards/emotion_reward_func": 0.4375,
"rewards/format_reward_func": 0.78125,
"step": 23
},
{
"completion_length": 71.84375,
"epoch": 0.032,
"grad_norm": 6.066468715667725,
"kl": 0.07137730903923512,
"learning_rate": 4.3224215685535287e-07,
"loss": 0.0001,
"reward": 1.328125,
"reward_std": 0.8113406747579575,
"rewards/emotion_reward_func": 0.546875,
"rewards/format_reward_func": 0.78125,
"step": 24
},
{
"completion_length": 101.0625,
"epoch": 0.03333333333333333,
"grad_norm": 5.047848224639893,
"kl": 0.0665823919698596,
"learning_rate": 4.2677669529663686e-07,
"loss": 0.0001,
"reward": 0.828125,
"reward_std": 0.5247472077608109,
"rewards/emotion_reward_func": 0.078125,
"rewards/format_reward_func": 0.75,
"step": 25
},
{
"completion_length": 68.1875,
"epoch": 0.034666666666666665,
"grad_norm": 6.7862958908081055,
"kl": 0.07357331551611423,
"learning_rate": 4.2113677648217216e-07,
"loss": 0.0001,
"reward": 1.515625,
"reward_std": 0.7178780436515808,
"rewards/emotion_reward_func": 0.671875,
"rewards/format_reward_func": 0.84375,
"step": 26
},
{
"completion_length": 73.5625,
"epoch": 0.036,
"grad_norm": 6.041502475738525,
"kl": 0.0839837146922946,
"learning_rate": 4.1532796633091294e-07,
"loss": 0.0001,
"reward": 1.0,
"reward_std": 0.5787727609276772,
"rewards/emotion_reward_func": 0.1875,
"rewards/format_reward_func": 0.8125,
"step": 27
},
{
"completion_length": 75.515625,
"epoch": 0.037333333333333336,
"grad_norm": 5.880768299102783,
"kl": 0.07887133583426476,
"learning_rate": 4.0935599743717244e-07,
"loss": 0.0001,
"reward": 1.265625,
"reward_std": 0.6387931928038597,
"rewards/emotion_reward_func": 0.390625,
"rewards/format_reward_func": 0.875,
"step": 28
},
{
"completion_length": 84.65625,
"epoch": 0.03866666666666667,
"grad_norm": 4.456689357757568,
"kl": 0.05541729833930731,
"learning_rate": 4.0322676341324414e-07,
"loss": 0.0001,
"reward": 1.546875,
"reward_std": 0.6021395623683929,
"rewards/emotion_reward_func": 0.6875,
"rewards/format_reward_func": 0.859375,
"step": 29
},
{
"completion_length": 72.03125,
"epoch": 0.04,
"grad_norm": 6.281215667724609,
"kl": 0.07642886973917484,
"learning_rate": 3.9694631307311825e-07,
"loss": 0.0001,
"reward": 1.421875,
"reward_std": 0.6625982969999313,
"rewards/emotion_reward_func": 0.515625,
"rewards/format_reward_func": 0.90625,
"step": 30
},
{
"completion_length": 64.96875,
"epoch": 0.04133333333333333,
"grad_norm": 6.267475128173828,
"kl": 0.07545926049351692,
"learning_rate": 3.9052084446303265e-07,
"loss": 0.0001,
"reward": 1.28125,
"reward_std": 0.5209204778075218,
"rewards/emotion_reward_func": 0.34375,
"rewards/format_reward_func": 0.9375,
"step": 31
},
{
"completion_length": 74.28125,
"epoch": 0.042666666666666665,
"grad_norm": 6.10364294052124,
"kl": 0.08546704892069101,
"learning_rate": 3.839566987447491e-07,
"loss": 0.0001,
"reward": 1.59375,
"reward_std": 0.7168828397989273,
"rewards/emotion_reward_func": 0.71875,
"rewards/format_reward_func": 0.875,
"step": 32
},
{
"completion_length": 70.03125,
"epoch": 0.044,
"grad_norm": 4.039772033691406,
"kl": 0.06002845522016287,
"learning_rate": 3.7726035393759283e-07,
"loss": 0.0001,
"reward": 1.3125,
"reward_std": 0.2808031141757965,
"rewards/emotion_reward_func": 0.390625,
"rewards/format_reward_func": 0.921875,
"step": 33
},
{
"completion_length": 83.109375,
"epoch": 0.04533333333333334,
"grad_norm": 6.683216094970703,
"kl": 0.0706396009773016,
"learning_rate": 3.704384185254288e-07,
"loss": 0.0001,
"reward": 1.421875,
"reward_std": 0.7211004346609116,
"rewards/emotion_reward_func": 0.578125,
"rewards/format_reward_func": 0.84375,
"step": 34
},
{
"completion_length": 72.765625,
"epoch": 0.04666666666666667,
"grad_norm": 6.402747631072998,
"kl": 0.10811681114137173,
"learning_rate": 3.634976249348867e-07,
"loss": 0.0001,
"reward": 1.28125,
"reward_std": 0.5904398858547211,
"rewards/emotion_reward_func": 0.375,
"rewards/format_reward_func": 0.90625,
"step": 35
},
{
"completion_length": 78.734375,
"epoch": 0.048,
"grad_norm": 5.202386856079102,
"kl": 0.07850308250635862,
"learning_rate": 3.5644482289126813e-07,
"loss": 0.0001,
"reward": 1.09375,
"reward_std": 0.5113069340586662,
"rewards/emotion_reward_func": 0.203125,
"rewards/format_reward_func": 0.890625,
"step": 36
},
{
"completion_length": 68.953125,
"epoch": 0.04933333333333333,
"grad_norm": 7.1071085929870605,
"kl": 0.08383779786527157,
"learning_rate": 3.492869726586951e-07,
"loss": 0.0001,
"reward": 1.1875,
"reward_std": 0.4691474586725235,
"rewards/emotion_reward_func": 0.21875,
"rewards/format_reward_func": 0.96875,
"step": 37
},
{
"completion_length": 65.734375,
"epoch": 0.050666666666666665,
"grad_norm": 6.272955417633057,
"kl": 0.06441066134721041,
"learning_rate": 3.4203113817116953e-07,
"loss": 0.0001,
"reward": 1.75,
"reward_std": 0.41095855832099915,
"rewards/emotion_reward_func": 0.765625,
"rewards/format_reward_func": 0.984375,
"step": 38
},
{
"completion_length": 69.9375,
"epoch": 0.052,
"grad_norm": 3.7793548107147217,
"kl": 0.06628133170306683,
"learning_rate": 3.346844800613229e-07,
"loss": 0.0001,
"reward": 1.078125,
"reward_std": 0.21347813308238983,
"rewards/emotion_reward_func": 0.109375,
"rewards/format_reward_func": 0.96875,
"step": 39
},
{
"completion_length": 64.34375,
"epoch": 0.05333333333333334,
"grad_norm": 6.500398635864258,
"kl": 0.06995576526969671,
"learning_rate": 3.272542485937368e-07,
"loss": 0.0001,
"reward": 1.546875,
"reward_std": 0.47020626068115234,
"rewards/emotion_reward_func": 0.5625,
"rewards/format_reward_func": 0.984375,
"step": 40
},
{
"completion_length": 73.375,
"epoch": 0.05466666666666667,
"grad_norm": 4.637302875518799,
"kl": 0.06445631105452776,
"learning_rate": 3.1974777650980734e-07,
"loss": 0.0001,
"reward": 1.578125,
"reward_std": 0.38923946768045425,
"rewards/emotion_reward_func": 0.609375,
"rewards/format_reward_func": 0.96875,
"step": 41
},
{
"completion_length": 69.875,
"epoch": 0.056,
"grad_norm": 5.5001220703125,
"kl": 0.06374164298176765,
"learning_rate": 3.121724717912138e-07,
"loss": 0.0001,
"reward": 1.671875,
"reward_std": 0.18616947531700134,
"rewards/emotion_reward_func": 0.671875,
"rewards/format_reward_func": 1.0,
"step": 42
},
{
"completion_length": 65.75,
"epoch": 0.05733333333333333,
"grad_norm": 5.561408996582031,
"kl": 0.11185399815440178,
"learning_rate": 3.0453581034913565e-07,
"loss": 0.0001,
"reward": 1.125,
"reward_std": 0.4263191595673561,
"rewards/emotion_reward_func": 0.1875,
"rewards/format_reward_func": 0.9375,
"step": 43
},
{
"completion_length": 57.59375,
"epoch": 0.058666666666666666,
"grad_norm": 6.903532028198242,
"kl": 0.08089348301291466,
"learning_rate": 2.968453286464312e-07,
"loss": 0.0001,
"reward": 1.75,
"reward_std": 0.3838024437427521,
"rewards/emotion_reward_func": 0.765625,
"rewards/format_reward_func": 0.984375,
"step": 44
},
{
"completion_length": 81.0625,
"epoch": 0.06,
"grad_norm": 5.9377288818359375,
"kl": 0.06169276125729084,
"learning_rate": 2.8910861626005773e-07,
"loss": 0.0001,
"reward": 1.375,
"reward_std": 0.5583916157484055,
"rewards/emotion_reward_func": 0.421875,
"rewards/format_reward_func": 0.953125,
"step": 45
},
{
"completion_length": 64.09375,
"epoch": 0.06133333333333333,
"grad_norm": 6.421321392059326,
"kl": 0.08067317306995392,
"learning_rate": 2.8133330839107604e-07,
"loss": 0.0001,
"reward": 1.484375,
"reward_std": 0.6873095482587814,
"rewards/emotion_reward_func": 0.59375,
"rewards/format_reward_func": 0.890625,
"step": 46
},
{
"completion_length": 65.859375,
"epoch": 0.06266666666666666,
"grad_norm": 5.465454578399658,
"kl": 0.08742601610720158,
"learning_rate": 2.735270783296286e-07,
"loss": 0.0001,
"reward": 1.421875,
"reward_std": 0.37412673234939575,
"rewards/emotion_reward_func": 0.4375,
"rewards/format_reward_func": 0.984375,
"step": 47
},
{
"completion_length": 61.734375,
"epoch": 0.064,
"grad_norm": 6.597202777862549,
"kl": 0.09020566754043102,
"learning_rate": 2.6569762988232837e-07,
"loss": 0.0001,
"reward": 1.203125,
"reward_std": 0.4003961533308029,
"rewards/emotion_reward_func": 0.265625,
"rewards/format_reward_func": 0.9375,
"step": 48
},
{
"completion_length": 63.21875,
"epoch": 0.06533333333333333,
"grad_norm": 5.847234725952148,
"kl": 0.09095379617065191,
"learning_rate": 2.5785268976953204e-07,
"loss": 0.0001,
"reward": 1.375,
"reward_std": 0.3876233473420143,
"rewards/emotion_reward_func": 0.390625,
"rewards/format_reward_func": 0.984375,
"step": 49
},
{
"completion_length": 59.890625,
"epoch": 0.06666666666666667,
"grad_norm": 7.6002936363220215,
"kl": 0.08561510033905506,
"learning_rate": 2.5e-07,
"loss": 0.0001,
"reward": 1.25,
"reward_std": 0.3925696462392807,
"rewards/emotion_reward_func": 0.28125,
"rewards/format_reward_func": 0.96875,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"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": 4,
"trial_name": null,
"trial_params": null
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fc6e728504ceeed070362223f2228cf2aa1bf386361fcc0c0d4d877e62196c58
size 5752

1
checkpoint-50/vocab.json Normal file

File diff suppressed because one or more lines are too long