Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- added_tokens.json +24 -0
- chat_template.jinja +7 -0
- config.json +573 -0
- generation_config.json +4 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- preprocessor_config.json +31 -0
- special_tokens_map.json +38 -0
- tokenizer.json +3 -0
- tokenizer_config.json +222 -0
- trainer_state.json +1334 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|AUDIO|>": 151646,
|
| 5 |
+
"<|IMAGE|>": 151655,
|
| 6 |
+
"<|VIDEO|>": 151656,
|
| 7 |
+
"<|audio_bos|>": 151647,
|
| 8 |
+
"<|audio_eos|>": 151648,
|
| 9 |
+
"<|box_end|>": 151649,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|quad_end|>": 151651,
|
| 19 |
+
"<|quad_start|>": 151650,
|
| 20 |
+
"<|repo_name|>": 151663,
|
| 21 |
+
"<|vision_bos|>": 151652,
|
| 22 |
+
"<|vision_eos|>": 151653,
|
| 23 |
+
"<|vision_pad|>": 151654
|
| 24 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set audio_count = namespace(value=0) %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,573 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5OmniForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"enable_audio_output": true,
|
| 6 |
+
"enable_talker": true,
|
| 7 |
+
"model_type": "qwen2_5_omni",
|
| 8 |
+
"talker_config": {
|
| 9 |
+
"_attn_implementation_autoset": true,
|
| 10 |
+
"_name_or_path": "Qwen2.5-Omni-7B/talker",
|
| 11 |
+
"architectures": [
|
| 12 |
+
"Qwen2OmniTalkerForConditionalGeneration"
|
| 13 |
+
],
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"audio_end_token_id": 151648,
|
| 16 |
+
"audio_start_token_id": 151647,
|
| 17 |
+
"audio_token_index": 151646,
|
| 18 |
+
"embedding_size": 3584,
|
| 19 |
+
"head_dim": 128,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 896,
|
| 22 |
+
"image_token_index": 151655,
|
| 23 |
+
"init_std": 0.02,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 18944,
|
| 26 |
+
"max_position_embeddings": 32768,
|
| 27 |
+
"max_window_layers": 28,
|
| 28 |
+
"model_type": "qwen2_5_omni_talker",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 24,
|
| 31 |
+
"num_key_value_heads": 4,
|
| 32 |
+
"position_id_per_seconds": 25,
|
| 33 |
+
"rms_norm_eps": 1e-06,
|
| 34 |
+
"rope_scaling": {
|
| 35 |
+
"mrope_section": [
|
| 36 |
+
16,
|
| 37 |
+
24,
|
| 38 |
+
24
|
| 39 |
+
],
|
| 40 |
+
"rope_type": "default",
|
| 41 |
+
"type": "default"
|
| 42 |
+
},
|
| 43 |
+
"rope_theta": 1000000.0,
|
| 44 |
+
"seconds_per_chunk": 2,
|
| 45 |
+
"sliding_window": 32768,
|
| 46 |
+
"spatial_merge_size": 2,
|
| 47 |
+
"torch_dtype": "float32",
|
| 48 |
+
"tts_codec_end_token_id": 8294,
|
| 49 |
+
"tts_codec_mask_token_id": 8296,
|
| 50 |
+
"tts_codec_pad_token_id": 8292,
|
| 51 |
+
"tts_codec_start_token_id": 8293,
|
| 52 |
+
"tts_text_end_token_id": 151861,
|
| 53 |
+
"tts_text_pad_token_id": 151859,
|
| 54 |
+
"tts_text_start_token_id": 151860,
|
| 55 |
+
"use_cache": true,
|
| 56 |
+
"use_sliding_window": false,
|
| 57 |
+
"video_token_index": 151656,
|
| 58 |
+
"vision_end_token_id": 151653,
|
| 59 |
+
"vision_start_token_id": 151652,
|
| 60 |
+
"vocab_size": 8448
|
| 61 |
+
},
|
| 62 |
+
"thinker_config": {
|
| 63 |
+
"_attn_implementation_autoset": true,
|
| 64 |
+
"_name_or_path": "Qwen2.5-Omni-7B/thinker",
|
| 65 |
+
"architectures": [
|
| 66 |
+
"Qwen2OmniNaViTThinkerForConditionalGeneration"
|
| 67 |
+
],
|
| 68 |
+
"audio_config": {
|
| 69 |
+
"_attn_implementation_autoset": true,
|
| 70 |
+
"_name_or_path": "",
|
| 71 |
+
"activation_dropout": 0.0,
|
| 72 |
+
"activation_function": "gelu",
|
| 73 |
+
"add_cross_attention": false,
|
| 74 |
+
"architectures": null,
|
| 75 |
+
"attention_dropout": 0.0,
|
| 76 |
+
"bad_words_ids": null,
|
| 77 |
+
"begin_suppress_tokens": null,
|
| 78 |
+
"bos_token_id": null,
|
| 79 |
+
"chunk_size_feed_forward": 0,
|
| 80 |
+
"cross_attention_hidden_size": null,
|
| 81 |
+
"d_model": 1280,
|
| 82 |
+
"decoder_start_token_id": null,
|
| 83 |
+
"diversity_penalty": 0.0,
|
| 84 |
+
"do_sample": false,
|
| 85 |
+
"dropout": 0.0,
|
| 86 |
+
"early_stopping": false,
|
| 87 |
+
"encoder_attention_heads": 20,
|
| 88 |
+
"encoder_ffn_dim": 5120,
|
| 89 |
+
"encoder_layerdrop": 0.0,
|
| 90 |
+
"encoder_layers": 32,
|
| 91 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 92 |
+
"eos_token_id": null,
|
| 93 |
+
"exponential_decay_length_penalty": null,
|
| 94 |
+
"finetuning_task": null,
|
| 95 |
+
"forced_bos_token_id": null,
|
| 96 |
+
"forced_eos_token_id": null,
|
| 97 |
+
"id2label": {
|
| 98 |
+
"0": "LABEL_0",
|
| 99 |
+
"1": "LABEL_1"
|
| 100 |
+
},
|
| 101 |
+
"init_std": 0.02,
|
| 102 |
+
"initializer_range": 0.02,
|
| 103 |
+
"is_decoder": false,
|
| 104 |
+
"is_encoder_decoder": false,
|
| 105 |
+
"label2id": {
|
| 106 |
+
"LABEL_0": 0,
|
| 107 |
+
"LABEL_1": 1
|
| 108 |
+
},
|
| 109 |
+
"length_penalty": 1.0,
|
| 110 |
+
"max_length": 20,
|
| 111 |
+
"max_source_positions": 1500,
|
| 112 |
+
"min_length": 0,
|
| 113 |
+
"model_type": "qwen2_5_omni_audio_encoder",
|
| 114 |
+
"n_window": 100,
|
| 115 |
+
"no_repeat_ngram_size": 0,
|
| 116 |
+
"num_beam_groups": 1,
|
| 117 |
+
"num_beams": 1,
|
| 118 |
+
"num_hidden_layers": 32,
|
| 119 |
+
"num_mel_bins": 128,
|
| 120 |
+
"num_return_sequences": 1,
|
| 121 |
+
"output_attentions": false,
|
| 122 |
+
"output_dim": 3584,
|
| 123 |
+
"output_hidden_states": false,
|
| 124 |
+
"output_scores": false,
|
| 125 |
+
"pad_token_id": null,
|
| 126 |
+
"prefix": null,
|
| 127 |
+
"problem_type": null,
|
| 128 |
+
"pruned_heads": {},
|
| 129 |
+
"remove_invalid_values": false,
|
| 130 |
+
"repetition_penalty": 1.0,
|
| 131 |
+
"return_dict": true,
|
| 132 |
+
"return_dict_in_generate": false,
|
| 133 |
+
"scale_embedding": false,
|
| 134 |
+
"sep_token_id": null,
|
| 135 |
+
"suppress_tokens": null,
|
| 136 |
+
"task_specific_params": null,
|
| 137 |
+
"temperature": 1.0,
|
| 138 |
+
"tf_legacy_loss": false,
|
| 139 |
+
"tie_encoder_decoder": false,
|
| 140 |
+
"tie_word_embeddings": true,
|
| 141 |
+
"tokenizer_class": null,
|
| 142 |
+
"top_k": 50,
|
| 143 |
+
"top_p": 1.0,
|
| 144 |
+
"torch_dtype": null,
|
| 145 |
+
"torchscript": false,
|
| 146 |
+
"typical_p": 1.0,
|
| 147 |
+
"use_bfloat16": false
|
| 148 |
+
},
|
| 149 |
+
"audio_end_token_id": 151648,
|
| 150 |
+
"audio_start_token_id": 151647,
|
| 151 |
+
"audio_token_index": 151646,
|
| 152 |
+
"bos_token_id": 151644,
|
| 153 |
+
"eos_token_id": 151645,
|
| 154 |
+
"ignore_index": -100,
|
| 155 |
+
"image_token_index": 151655,
|
| 156 |
+
"init_std": 0.02,
|
| 157 |
+
"initializer_range": 0.02,
|
| 158 |
+
"model_type": "qwen2_5_omni_thinker",
|
| 159 |
+
"pad_token_id": 151643,
|
| 160 |
+
"position_id_per_seconds": 25,
|
| 161 |
+
"seconds_per_chunk": 2,
|
| 162 |
+
"text_config": {
|
| 163 |
+
"_attn_implementation_autoset": false,
|
| 164 |
+
"_name_or_path": "",
|
| 165 |
+
"add_cross_attention": false,
|
| 166 |
+
"architectures": null,
|
| 167 |
+
"attention_dropout": 0.0,
|
| 168 |
+
"bad_words_ids": null,
|
| 169 |
+
"begin_suppress_tokens": null,
|
| 170 |
+
"bos_token_id": null,
|
| 171 |
+
"chunk_size_feed_forward": 0,
|
| 172 |
+
"cross_attention_hidden_size": null,
|
| 173 |
+
"decoder_start_token_id": null,
|
| 174 |
+
"diversity_penalty": 0.0,
|
| 175 |
+
"do_sample": false,
|
| 176 |
+
"early_stopping": false,
|
| 177 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 178 |
+
"eos_token_id": null,
|
| 179 |
+
"exponential_decay_length_penalty": null,
|
| 180 |
+
"finetuning_task": null,
|
| 181 |
+
"forced_bos_token_id": null,
|
| 182 |
+
"forced_eos_token_id": null,
|
| 183 |
+
"hidden_act": "silu",
|
| 184 |
+
"hidden_size": 3584,
|
| 185 |
+
"id2label": {
|
| 186 |
+
"0": "LABEL_0",
|
| 187 |
+
"1": "LABEL_1"
|
| 188 |
+
},
|
| 189 |
+
"init_std": 0.02,
|
| 190 |
+
"initializer_range": 0.02,
|
| 191 |
+
"intermediate_size": 18944,
|
| 192 |
+
"is_decoder": false,
|
| 193 |
+
"is_encoder_decoder": false,
|
| 194 |
+
"label2id": {
|
| 195 |
+
"LABEL_0": 0,
|
| 196 |
+
"LABEL_1": 1
|
| 197 |
+
},
|
| 198 |
+
"length_penalty": 1.0,
|
| 199 |
+
"max_length": 20,
|
| 200 |
+
"max_position_embeddings": 32768,
|
| 201 |
+
"max_window_layers": 28,
|
| 202 |
+
"min_length": 0,
|
| 203 |
+
"model_type": "qwen2_5_omni_text",
|
| 204 |
+
"no_repeat_ngram_size": 0,
|
| 205 |
+
"num_attention_heads": 28,
|
| 206 |
+
"num_beam_groups": 1,
|
| 207 |
+
"num_beams": 1,
|
| 208 |
+
"num_hidden_layers": 28,
|
| 209 |
+
"num_key_value_heads": 4,
|
| 210 |
+
"num_return_sequences": 1,
|
| 211 |
+
"output_attentions": false,
|
| 212 |
+
"output_hidden_states": false,
|
| 213 |
+
"output_scores": false,
|
| 214 |
+
"pad_token_id": null,
|
| 215 |
+
"prefix": null,
|
| 216 |
+
"problem_type": null,
|
| 217 |
+
"pruned_heads": {},
|
| 218 |
+
"remove_invalid_values": false,
|
| 219 |
+
"repetition_penalty": 1.0,
|
| 220 |
+
"return_dict": true,
|
| 221 |
+
"return_dict_in_generate": false,
|
| 222 |
+
"rms_norm_eps": 1e-06,
|
| 223 |
+
"rope_scaling": {
|
| 224 |
+
"mrope_section": [
|
| 225 |
+
16,
|
| 226 |
+
24,
|
| 227 |
+
24
|
| 228 |
+
],
|
| 229 |
+
"rope_type": "default",
|
| 230 |
+
"type": "default"
|
| 231 |
+
},
|
| 232 |
+
"rope_theta": 1000000.0,
|
| 233 |
+
"sep_token_id": null,
|
| 234 |
+
"sliding_window": 32768,
|
| 235 |
+
"suppress_tokens": null,
|
| 236 |
+
"task_specific_params": null,
|
| 237 |
+
"temperature": 1.0,
|
| 238 |
+
"tf_legacy_loss": false,
|
| 239 |
+
"tie_encoder_decoder": false,
|
| 240 |
+
"tie_word_embeddings": false,
|
| 241 |
+
"tokenizer_class": null,
|
| 242 |
+
"top_k": 50,
|
| 243 |
+
"top_p": 1.0,
|
| 244 |
+
"torch_dtype": null,
|
| 245 |
+
"torchscript": false,
|
| 246 |
+
"typical_p": 1.0,
|
| 247 |
+
"use_bfloat16": false,
|
| 248 |
+
"use_cache": true,
|
| 249 |
+
"use_sliding_window": false,
|
| 250 |
+
"vocab_size": 152064
|
| 251 |
+
},
|
| 252 |
+
"torch_dtype": "float32",
|
| 253 |
+
"user_token_id": 872,
|
| 254 |
+
"video_token_index": 151656,
|
| 255 |
+
"vision_config": {
|
| 256 |
+
"_attn_implementation_autoset": true,
|
| 257 |
+
"_name_or_path": "",
|
| 258 |
+
"add_cross_attention": false,
|
| 259 |
+
"architectures": null,
|
| 260 |
+
"bad_words_ids": null,
|
| 261 |
+
"begin_suppress_tokens": null,
|
| 262 |
+
"bos_token_id": null,
|
| 263 |
+
"chunk_size_feed_forward": 0,
|
| 264 |
+
"cross_attention_hidden_size": null,
|
| 265 |
+
"decoder_start_token_id": null,
|
| 266 |
+
"depth": 32,
|
| 267 |
+
"diversity_penalty": 0.0,
|
| 268 |
+
"do_sample": false,
|
| 269 |
+
"early_stopping": false,
|
| 270 |
+
"embed_dim": 1280,
|
| 271 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 272 |
+
"eos_token_id": null,
|
| 273 |
+
"exponential_decay_length_penalty": null,
|
| 274 |
+
"finetuning_task": null,
|
| 275 |
+
"forced_bos_token_id": null,
|
| 276 |
+
"forced_eos_token_id": null,
|
| 277 |
+
"fullatt_block_indexes": [
|
| 278 |
+
7,
|
| 279 |
+
15,
|
| 280 |
+
23,
|
| 281 |
+
31
|
| 282 |
+
],
|
| 283 |
+
"hidden_act": "silu",
|
| 284 |
+
"hidden_size": 1280,
|
| 285 |
+
"id2label": {
|
| 286 |
+
"0": "LABEL_0",
|
| 287 |
+
"1": "LABEL_1"
|
| 288 |
+
},
|
| 289 |
+
"in_channels": 3,
|
| 290 |
+
"in_chans": 3,
|
| 291 |
+
"init_std": 0.02,
|
| 292 |
+
"initializer_range": 0.02,
|
| 293 |
+
"intermediate_size": 3420,
|
| 294 |
+
"is_decoder": false,
|
| 295 |
+
"is_encoder_decoder": false,
|
| 296 |
+
"label2id": {
|
| 297 |
+
"LABEL_0": 0,
|
| 298 |
+
"LABEL_1": 1
|
| 299 |
+
},
|
| 300 |
+
"length_penalty": 1.0,
|
| 301 |
+
"max_length": 20,
|
| 302 |
+
"min_length": 0,
|
| 303 |
+
"model_type": "qwen2_5_omni_vision_encoder",
|
| 304 |
+
"no_repeat_ngram_size": 0,
|
| 305 |
+
"num_beam_groups": 1,
|
| 306 |
+
"num_beams": 1,
|
| 307 |
+
"num_heads": 16,
|
| 308 |
+
"num_return_sequences": 1,
|
| 309 |
+
"out_hidden_size": 3584,
|
| 310 |
+
"output_attentions": false,
|
| 311 |
+
"output_hidden_states": false,
|
| 312 |
+
"output_scores": false,
|
| 313 |
+
"pad_token_id": null,
|
| 314 |
+
"patch_size": 14,
|
| 315 |
+
"prefix": null,
|
| 316 |
+
"problem_type": null,
|
| 317 |
+
"pruned_heads": {},
|
| 318 |
+
"remove_invalid_values": false,
|
| 319 |
+
"repetition_penalty": 1.0,
|
| 320 |
+
"return_dict": true,
|
| 321 |
+
"return_dict_in_generate": false,
|
| 322 |
+
"sep_token_id": null,
|
| 323 |
+
"spatial_merge_size": 2,
|
| 324 |
+
"spatial_patch_size": 14,
|
| 325 |
+
"suppress_tokens": null,
|
| 326 |
+
"task_specific_params": null,
|
| 327 |
+
"temperature": 1.0,
|
| 328 |
+
"temporal_patch_size": 2,
|
| 329 |
+
"tf_legacy_loss": false,
|
| 330 |
+
"tie_encoder_decoder": false,
|
| 331 |
+
"tie_word_embeddings": true,
|
| 332 |
+
"tokenizer_class": null,
|
| 333 |
+
"tokens_per_second": 25,
|
| 334 |
+
"top_k": 50,
|
| 335 |
+
"top_p": 1.0,
|
| 336 |
+
"torch_dtype": null,
|
| 337 |
+
"torchscript": false,
|
| 338 |
+
"typical_p": 1.0,
|
| 339 |
+
"use_bfloat16": false,
|
| 340 |
+
"window_size": 112
|
| 341 |
+
},
|
| 342 |
+
"vision_end_token_id": 151653,
|
| 343 |
+
"vision_start_token_id": 151652,
|
| 344 |
+
"vision_token_id": 151654
|
| 345 |
+
},
|
| 346 |
+
"token2wav_config": {
|
| 347 |
+
"_attn_implementation_autoset": true,
|
| 348 |
+
"bigvgan_config": {
|
| 349 |
+
"_attn_implementation_autoset": true,
|
| 350 |
+
"_name_or_path": "",
|
| 351 |
+
"add_cross_attention": false,
|
| 352 |
+
"architectures": null,
|
| 353 |
+
"bad_words_ids": null,
|
| 354 |
+
"begin_suppress_tokens": null,
|
| 355 |
+
"bos_token_id": null,
|
| 356 |
+
"chunk_size_feed_forward": 0,
|
| 357 |
+
"cross_attention_hidden_size": null,
|
| 358 |
+
"decoder_start_token_id": null,
|
| 359 |
+
"diversity_penalty": 0.0,
|
| 360 |
+
"do_sample": false,
|
| 361 |
+
"early_stopping": false,
|
| 362 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 363 |
+
"eos_token_id": null,
|
| 364 |
+
"exponential_decay_length_penalty": null,
|
| 365 |
+
"finetuning_task": null,
|
| 366 |
+
"forced_bos_token_id": null,
|
| 367 |
+
"forced_eos_token_id": null,
|
| 368 |
+
"id2label": {
|
| 369 |
+
"0": "LABEL_0",
|
| 370 |
+
"1": "LABEL_1"
|
| 371 |
+
},
|
| 372 |
+
"is_decoder": false,
|
| 373 |
+
"is_encoder_decoder": false,
|
| 374 |
+
"label2id": {
|
| 375 |
+
"LABEL_0": 0,
|
| 376 |
+
"LABEL_1": 1
|
| 377 |
+
},
|
| 378 |
+
"length_penalty": 1.0,
|
| 379 |
+
"max_length": 20,
|
| 380 |
+
"mel_dim": 80,
|
| 381 |
+
"min_length": 0,
|
| 382 |
+
"model_type": "qwen2_5_omni_bigvgan",
|
| 383 |
+
"no_repeat_ngram_size": 0,
|
| 384 |
+
"num_beam_groups": 1,
|
| 385 |
+
"num_beams": 1,
|
| 386 |
+
"num_return_sequences": 1,
|
| 387 |
+
"output_attentions": false,
|
| 388 |
+
"output_hidden_states": false,
|
| 389 |
+
"output_scores": false,
|
| 390 |
+
"pad_token_id": null,
|
| 391 |
+
"prefix": null,
|
| 392 |
+
"problem_type": null,
|
| 393 |
+
"pruned_heads": {},
|
| 394 |
+
"remove_invalid_values": false,
|
| 395 |
+
"repetition_penalty": 1.0,
|
| 396 |
+
"resblock_dilation_sizes": [
|
| 397 |
+
[
|
| 398 |
+
1,
|
| 399 |
+
3,
|
| 400 |
+
5
|
| 401 |
+
],
|
| 402 |
+
[
|
| 403 |
+
1,
|
| 404 |
+
3,
|
| 405 |
+
5
|
| 406 |
+
],
|
| 407 |
+
[
|
| 408 |
+
1,
|
| 409 |
+
3,
|
| 410 |
+
5
|
| 411 |
+
]
|
| 412 |
+
],
|
| 413 |
+
"resblock_kernel_sizes": [
|
| 414 |
+
3,
|
| 415 |
+
7,
|
| 416 |
+
11
|
| 417 |
+
],
|
| 418 |
+
"return_dict": true,
|
| 419 |
+
"return_dict_in_generate": false,
|
| 420 |
+
"sep_token_id": null,
|
| 421 |
+
"suppress_tokens": null,
|
| 422 |
+
"task_specific_params": null,
|
| 423 |
+
"temperature": 1.0,
|
| 424 |
+
"tf_legacy_loss": false,
|
| 425 |
+
"tie_encoder_decoder": false,
|
| 426 |
+
"tie_word_embeddings": true,
|
| 427 |
+
"tokenizer_class": null,
|
| 428 |
+
"top_k": 50,
|
| 429 |
+
"top_p": 1.0,
|
| 430 |
+
"torch_dtype": null,
|
| 431 |
+
"torchscript": false,
|
| 432 |
+
"typical_p": 1.0,
|
| 433 |
+
"upsample_initial_channel": 1536,
|
| 434 |
+
"upsample_kernel_sizes": [
|
| 435 |
+
11,
|
| 436 |
+
7,
|
| 437 |
+
4,
|
| 438 |
+
4,
|
| 439 |
+
4,
|
| 440 |
+
4
|
| 441 |
+
],
|
| 442 |
+
"upsample_rates": [
|
| 443 |
+
5,
|
| 444 |
+
3,
|
| 445 |
+
2,
|
| 446 |
+
2,
|
| 447 |
+
2,
|
| 448 |
+
2
|
| 449 |
+
],
|
| 450 |
+
"use_bfloat16": false,
|
| 451 |
+
"use_bias_at_final": false
|
| 452 |
+
},
|
| 453 |
+
"dit_config": {
|
| 454 |
+
"_attn_implementation_autoset": true,
|
| 455 |
+
"_name_or_path": "",
|
| 456 |
+
"add_cross_attention": false,
|
| 457 |
+
"architectures": null,
|
| 458 |
+
"bad_words_ids": null,
|
| 459 |
+
"begin_suppress_tokens": null,
|
| 460 |
+
"block_size": 24,
|
| 461 |
+
"bos_token_id": null,
|
| 462 |
+
"chunk_size_feed_forward": 0,
|
| 463 |
+
"cross_attention_hidden_size": null,
|
| 464 |
+
"decoder_start_token_id": null,
|
| 465 |
+
"depth": 22,
|
| 466 |
+
"dim": 1024,
|
| 467 |
+
"diversity_penalty": 0.0,
|
| 468 |
+
"do_sample": false,
|
| 469 |
+
"dropout": 0.1,
|
| 470 |
+
"early_stopping": false,
|
| 471 |
+
"emb_dim": 512,
|
| 472 |
+
"enc_attention_channels": 64,
|
| 473 |
+
"enc_channels": [
|
| 474 |
+
256,
|
| 475 |
+
256,
|
| 476 |
+
256,
|
| 477 |
+
256,
|
| 478 |
+
768
|
| 479 |
+
],
|
| 480 |
+
"enc_dilations": [
|
| 481 |
+
1,
|
| 482 |
+
2,
|
| 483 |
+
3,
|
| 484 |
+
4,
|
| 485 |
+
1
|
| 486 |
+
],
|
| 487 |
+
"enc_dim": 128,
|
| 488 |
+
"enc_emb_dim": 192,
|
| 489 |
+
"enc_global_context": true,
|
| 490 |
+
"enc_kernel_sizes": [
|
| 491 |
+
5,
|
| 492 |
+
3,
|
| 493 |
+
3,
|
| 494 |
+
3,
|
| 495 |
+
1
|
| 496 |
+
],
|
| 497 |
+
"enc_lin_neurons": 192,
|
| 498 |
+
"enc_res2net_scale": 2,
|
| 499 |
+
"enc_se_channels": 64,
|
| 500 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 501 |
+
"eos_token_id": null,
|
| 502 |
+
"exponential_decay_length_penalty": null,
|
| 503 |
+
"ff_mult": 2,
|
| 504 |
+
"finetuning_task": null,
|
| 505 |
+
"forced_bos_token_id": null,
|
| 506 |
+
"forced_eos_token_id": null,
|
| 507 |
+
"head_dim": 64,
|
| 508 |
+
"heads": 16,
|
| 509 |
+
"hidden_size": 1024,
|
| 510 |
+
"id2label": {
|
| 511 |
+
"0": "LABEL_0",
|
| 512 |
+
"1": "LABEL_1"
|
| 513 |
+
},
|
| 514 |
+
"is_decoder": false,
|
| 515 |
+
"is_encoder_decoder": false,
|
| 516 |
+
"label2id": {
|
| 517 |
+
"LABEL_0": 0,
|
| 518 |
+
"LABEL_1": 1
|
| 519 |
+
},
|
| 520 |
+
"length_penalty": 1.0,
|
| 521 |
+
"look_ahead_layers": [
|
| 522 |
+
10
|
| 523 |
+
],
|
| 524 |
+
"look_backward_layers": [
|
| 525 |
+
0,
|
| 526 |
+
20
|
| 527 |
+
],
|
| 528 |
+
"max_length": 20,
|
| 529 |
+
"max_position_embeddings": 32768,
|
| 530 |
+
"mel_dim": 80,
|
| 531 |
+
"min_length": 0,
|
| 532 |
+
"model_type": "qwen2_5_omni_dit",
|
| 533 |
+
"no_repeat_ngram_size": 0,
|
| 534 |
+
"num_attention_heads": 16,
|
| 535 |
+
"num_beam_groups": 1,
|
| 536 |
+
"num_beams": 1,
|
| 537 |
+
"num_embeds": 8193,
|
| 538 |
+
"num_hidden_layers": 22,
|
| 539 |
+
"num_return_sequences": 1,
|
| 540 |
+
"output_attentions": false,
|
| 541 |
+
"output_hidden_states": false,
|
| 542 |
+
"output_scores": false,
|
| 543 |
+
"pad_token_id": null,
|
| 544 |
+
"prefix": null,
|
| 545 |
+
"problem_type": null,
|
| 546 |
+
"pruned_heads": {},
|
| 547 |
+
"remove_invalid_values": false,
|
| 548 |
+
"repeats": 2,
|
| 549 |
+
"repetition_penalty": 1.0,
|
| 550 |
+
"return_dict": true,
|
| 551 |
+
"return_dict_in_generate": false,
|
| 552 |
+
"rope_theta": 10000.0,
|
| 553 |
+
"sep_token_id": null,
|
| 554 |
+
"suppress_tokens": null,
|
| 555 |
+
"task_specific_params": null,
|
| 556 |
+
"temperature": 1.0,
|
| 557 |
+
"tf_legacy_loss": false,
|
| 558 |
+
"tie_encoder_decoder": false,
|
| 559 |
+
"tie_word_embeddings": true,
|
| 560 |
+
"tokenizer_class": null,
|
| 561 |
+
"top_k": 50,
|
| 562 |
+
"top_p": 1.0,
|
| 563 |
+
"torch_dtype": "float32",
|
| 564 |
+
"torchscript": false,
|
| 565 |
+
"typical_p": 1.0,
|
| 566 |
+
"use_bfloat16": false
|
| 567 |
+
},
|
| 568 |
+
"model_type": "qwen2_5_omni_token2wav",
|
| 569 |
+
"torch_dtype": "float32"
|
| 570 |
+
},
|
| 571 |
+
"torch_dtype": "bfloat16",
|
| 572 |
+
"transformers_version": "4.52.0.dev0"
|
| 573 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.52.0.dev0"
|
| 4 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0d9ee40adfb51247a39b8a8c27847e3f9d70225cdf14bb59a39a3bda9eaf46c
|
| 3 |
+
size 4985055536
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2292d843757e83cfb44a188a52b35fb79b3579e6d34742e0eefda0810072ddf0
|
| 3 |
+
size 4991496832
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8829933f8ac993965c53d2bfbee09440102e5cc115ee09247c175d1b8d1533d7
|
| 3 |
+
size 4991496936
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8446c19218499b3e543651e3105f65aaef1e45a5d093df7233cf7284c4743e3f
|
| 3 |
+
size 2895740064
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 300,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 128,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.26862954,
|
| 15 |
+
0.26130258,
|
| 16 |
+
0.27577711
|
| 17 |
+
],
|
| 18 |
+
"max_pixels": 12845056,
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"min_pixels": 3136,
|
| 21 |
+
"n_fft": 400,
|
| 22 |
+
"n_samples": 4800000,
|
| 23 |
+
"nb_max_frames": 30000,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"padding_value": 0.0,
|
| 26 |
+
"patch_size": 14,
|
| 27 |
+
"processor_class": "Qwen2_5OmniProcessor",
|
| 28 |
+
"return_attention_mask": true,
|
| 29 |
+
"sampling_rate": 16000,
|
| 30 |
+
"temporal_patch_size": 2
|
| 31 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|AUDIO|>",
|
| 6 |
+
"<|audio_bos|>",
|
| 7 |
+
"<|audio_eos|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_bos|>",
|
| 12 |
+
"<|vision_eos|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|IMAGE|>",
|
| 15 |
+
"<|VIDEO|>"
|
| 16 |
+
],
|
| 17 |
+
"audio_bos_token": "<|audio_bos|>",
|
| 18 |
+
"audio_eos_token": "<|audio_eos|>",
|
| 19 |
+
"audio_token": "<|AUDIO|>",
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"image_token": "<|IMAGE|>",
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<|endoftext|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"video_token": "<|VIDEO|>",
|
| 36 |
+
"vision_bos_token": "<|vision_bos|>",
|
| 37 |
+
"vision_eos_token": "<|vision_eos|>"
|
| 38 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9711e245647e88538786834977dc8afb51172e879ee661352c587cf01efd6b0
|
| 3 |
+
size 11422037
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,222 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|AUDIO|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|audio_bos|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|audio_eos|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_bos|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_eos|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|IMAGE|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|VIDEO|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<tool_call>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "</tool_call>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|fim_prefix|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|fim_middle|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<|fim_suffix|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<|fim_pad|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<|repo_name|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<|file_sep|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"additional_special_tokens": [
|
| 182 |
+
"<|im_start|>",
|
| 183 |
+
"<|im_end|>",
|
| 184 |
+
"<|AUDIO|>",
|
| 185 |
+
"<|audio_bos|>",
|
| 186 |
+
"<|audio_eos|>",
|
| 187 |
+
"<|box_end|>",
|
| 188 |
+
"<|quad_start|>",
|
| 189 |
+
"<|quad_end|>",
|
| 190 |
+
"<|vision_bos|>",
|
| 191 |
+
"<|vision_eos|>",
|
| 192 |
+
"<|vision_pad|>",
|
| 193 |
+
"<|IMAGE|>",
|
| 194 |
+
"<|VIDEO|>"
|
| 195 |
+
],
|
| 196 |
+
"audio_bos_token": "<|audio_bos|>",
|
| 197 |
+
"audio_eos_token": "<|audio_eos|>",
|
| 198 |
+
"audio_token": "<|AUDIO|>",
|
| 199 |
+
"bos_token": null,
|
| 200 |
+
"clean_up_tokenization_spaces": false,
|
| 201 |
+
"eos_token": "<|im_end|>",
|
| 202 |
+
"errors": "replace",
|
| 203 |
+
"extra_special_tokens": {
|
| 204 |
+
"audio_bos_token": "<|audio_bos|>",
|
| 205 |
+
"audio_eos_token": "<|audio_eos|>",
|
| 206 |
+
"audio_token": "<|AUDIO|>",
|
| 207 |
+
"image_token": "<|IMAGE|>",
|
| 208 |
+
"video_token": "<|VIDEO|>",
|
| 209 |
+
"vision_bos_token": "<|vision_bos|>",
|
| 210 |
+
"vision_eos_token": "<|vision_eos|>"
|
| 211 |
+
},
|
| 212 |
+
"image_token": "<|IMAGE|>",
|
| 213 |
+
"model_max_length": 32768,
|
| 214 |
+
"pad_token": "<|endoftext|>",
|
| 215 |
+
"processor_class": "Qwen2_5OmniProcessor",
|
| 216 |
+
"split_special_tokens": false,
|
| 217 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 218 |
+
"unk_token": null,
|
| 219 |
+
"video_token": "<|VIDEO|>",
|
| 220 |
+
"vision_bos_token": "<|vision_bos|>",
|
| 221 |
+
"vision_eos_token": "<|vision_eos|>"
|
| 222 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.009894622272794735,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 100,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"completion_length": 6.0,
|
| 14 |
+
"epoch": 9.894622272794736e-05,
|
| 15 |
+
"grad_norm": 22.976070404052734,
|
| 16 |
+
"kl": 0.0,
|
| 17 |
+
"learning_rate": 1e-06,
|
| 18 |
+
"loss": -0.0,
|
| 19 |
+
"reward": 0.125,
|
| 20 |
+
"reward_std": 0.25,
|
| 21 |
+
"rewards/accuracy_reward": 0.125,
|
| 22 |
+
"rewards/format_reward": 0.0,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"completion_length": 6.5,
|
| 27 |
+
"epoch": 0.00019789244545589471,
|
| 28 |
+
"grad_norm": 32.8896369934082,
|
| 29 |
+
"kl": 0.0035400390625,
|
| 30 |
+
"learning_rate": 9.989999999999999e-07,
|
| 31 |
+
"loss": 0.0001,
|
| 32 |
+
"reward": 0.3125,
|
| 33 |
+
"reward_std": 0.5193375647068024,
|
| 34 |
+
"rewards/accuracy_reward": 0.3125,
|
| 35 |
+
"rewards/format_reward": 0.0,
|
| 36 |
+
"step": 2
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"completion_length": 5.0625,
|
| 40 |
+
"epoch": 0.0002968386681838421,
|
| 41 |
+
"grad_norm": 45.44774627685547,
|
| 42 |
+
"kl": 0.00732421875,
|
| 43 |
+
"learning_rate": 9.98e-07,
|
| 44 |
+
"loss": 0.0003,
|
| 45 |
+
"reward": 0.3125,
|
| 46 |
+
"reward_std": 0.26933756470680237,
|
| 47 |
+
"rewards/accuracy_reward": 0.3125,
|
| 48 |
+
"rewards/format_reward": 0.0,
|
| 49 |
+
"step": 3
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"completion_length": 6.25,
|
| 53 |
+
"epoch": 0.00039578489091178943,
|
| 54 |
+
"grad_norm": 35.005924224853516,
|
| 55 |
+
"kl": 0.003936767578125,
|
| 56 |
+
"learning_rate": 9.97e-07,
|
| 57 |
+
"loss": 0.0002,
|
| 58 |
+
"reward": 0.375,
|
| 59 |
+
"reward_std": 0.39433756470680237,
|
| 60 |
+
"rewards/accuracy_reward": 0.375,
|
| 61 |
+
"rewards/format_reward": 0.0,
|
| 62 |
+
"step": 4
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"completion_length": 4.5625,
|
| 66 |
+
"epoch": 0.0004947311136397368,
|
| 67 |
+
"grad_norm": 39.57672882080078,
|
| 68 |
+
"kl": 0.00762176513671875,
|
| 69 |
+
"learning_rate": 9.959999999999999e-07,
|
| 70 |
+
"loss": 0.0003,
|
| 71 |
+
"reward": 0.625,
|
| 72 |
+
"reward_std": 0.39433756470680237,
|
| 73 |
+
"rewards/accuracy_reward": 0.625,
|
| 74 |
+
"rewards/format_reward": 0.0,
|
| 75 |
+
"step": 5
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"completion_length": 4.125,
|
| 79 |
+
"epoch": 0.0005936773363676842,
|
| 80 |
+
"grad_norm": 23.2183837890625,
|
| 81 |
+
"kl": 0.03729248046875,
|
| 82 |
+
"learning_rate": 9.95e-07,
|
| 83 |
+
"loss": 0.0015,
|
| 84 |
+
"reward": 0.5625,
|
| 85 |
+
"reward_std": 0.375,
|
| 86 |
+
"rewards/accuracy_reward": 0.5625,
|
| 87 |
+
"rewards/format_reward": 0.0,
|
| 88 |
+
"step": 6
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"completion_length": 3.3125,
|
| 92 |
+
"epoch": 0.0006926235590956315,
|
| 93 |
+
"grad_norm": 47.74429702758789,
|
| 94 |
+
"kl": 0.06170654296875,
|
| 95 |
+
"learning_rate": 9.94e-07,
|
| 96 |
+
"loss": 0.0025,
|
| 97 |
+
"reward": 0.4375,
|
| 98 |
+
"reward_std": 0.41367512941360474,
|
| 99 |
+
"rewards/accuracy_reward": 0.4375,
|
| 100 |
+
"rewards/format_reward": 0.0,
|
| 101 |
+
"step": 7
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"completion_length": 3.8125,
|
| 105 |
+
"epoch": 0.0007915697818235789,
|
| 106 |
+
"grad_norm": 49.124691009521484,
|
| 107 |
+
"kl": 0.09912109375,
|
| 108 |
+
"learning_rate": 9.929999999999999e-07,
|
| 109 |
+
"loss": 0.004,
|
| 110 |
+
"reward": 0.3125,
|
| 111 |
+
"reward_std": 0.375,
|
| 112 |
+
"rewards/accuracy_reward": 0.3125,
|
| 113 |
+
"rewards/format_reward": 0.0,
|
| 114 |
+
"step": 8
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"completion_length": 3.5625,
|
| 118 |
+
"epoch": 0.0008905160045515262,
|
| 119 |
+
"grad_norm": 43.116676330566406,
|
| 120 |
+
"kl": 0.02130126953125,
|
| 121 |
+
"learning_rate": 9.92e-07,
|
| 122 |
+
"loss": 0.0009,
|
| 123 |
+
"reward": 0.4375,
|
| 124 |
+
"reward_std": 0.5193375647068024,
|
| 125 |
+
"rewards/accuracy_reward": 0.4375,
|
| 126 |
+
"rewards/format_reward": 0.0,
|
| 127 |
+
"step": 9
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"completion_length": 3.5625,
|
| 131 |
+
"epoch": 0.0009894622272794737,
|
| 132 |
+
"grad_norm": 42.24452209472656,
|
| 133 |
+
"kl": 0.030517578125,
|
| 134 |
+
"learning_rate": 9.91e-07,
|
| 135 |
+
"loss": 0.0012,
|
| 136 |
+
"reward": 0.4375,
|
| 137 |
+
"reward_std": 0.26933756470680237,
|
| 138 |
+
"rewards/accuracy_reward": 0.4375,
|
| 139 |
+
"rewards/format_reward": 0.0,
|
| 140 |
+
"step": 10
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"completion_length": 4.5625,
|
| 144 |
+
"epoch": 0.001088408450007421,
|
| 145 |
+
"grad_norm": 9.293623924255371,
|
| 146 |
+
"kl": 0.386474609375,
|
| 147 |
+
"learning_rate": 9.9e-07,
|
| 148 |
+
"loss": 0.0155,
|
| 149 |
+
"reward": 0.75,
|
| 150 |
+
"reward_std": 0.25,
|
| 151 |
+
"rewards/accuracy_reward": 0.75,
|
| 152 |
+
"rewards/format_reward": 0.0,
|
| 153 |
+
"step": 11
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"completion_length": 2.75,
|
| 157 |
+
"epoch": 0.0011873546727353683,
|
| 158 |
+
"grad_norm": 27.51582908630371,
|
| 159 |
+
"kl": 0.119140625,
|
| 160 |
+
"learning_rate": 9.89e-07,
|
| 161 |
+
"loss": 0.0048,
|
| 162 |
+
"reward": 0.9375,
|
| 163 |
+
"reward_std": 0.125,
|
| 164 |
+
"rewards/accuracy_reward": 0.9375,
|
| 165 |
+
"rewards/format_reward": 0.0,
|
| 166 |
+
"step": 12
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"completion_length": 4.125,
|
| 170 |
+
"epoch": 0.0012863008954633157,
|
| 171 |
+
"grad_norm": 42.183692932128906,
|
| 172 |
+
"kl": 1.232391357421875,
|
| 173 |
+
"learning_rate": 9.88e-07,
|
| 174 |
+
"loss": 0.0494,
|
| 175 |
+
"reward": 0.375,
|
| 176 |
+
"reward_std": 0.39433756470680237,
|
| 177 |
+
"rewards/accuracy_reward": 0.375,
|
| 178 |
+
"rewards/format_reward": 0.0,
|
| 179 |
+
"step": 13
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"completion_length": 3.75,
|
| 183 |
+
"epoch": 0.001385247118191263,
|
| 184 |
+
"grad_norm": 16.871009826660156,
|
| 185 |
+
"kl": 0.02880859375,
|
| 186 |
+
"learning_rate": 9.87e-07,
|
| 187 |
+
"loss": 0.0012,
|
| 188 |
+
"reward": 0.8125,
|
| 189 |
+
"reward_std": 0.125,
|
| 190 |
+
"rewards/accuracy_reward": 0.8125,
|
| 191 |
+
"rewards/format_reward": 0.0,
|
| 192 |
+
"step": 14
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"completion_length": 3.1875,
|
| 196 |
+
"epoch": 0.0014841933409192104,
|
| 197 |
+
"grad_norm": 9.070819854736328,
|
| 198 |
+
"kl": 0.31671142578125,
|
| 199 |
+
"learning_rate": 9.86e-07,
|
| 200 |
+
"loss": 0.0127,
|
| 201 |
+
"reward": 0.5,
|
| 202 |
+
"reward_std": 0.0,
|
| 203 |
+
"rewards/accuracy_reward": 0.5,
|
| 204 |
+
"rewards/format_reward": 0.0,
|
| 205 |
+
"step": 15
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"completion_length": 3.875,
|
| 209 |
+
"epoch": 0.0015831395636471577,
|
| 210 |
+
"grad_norm": 34.1285285949707,
|
| 211 |
+
"kl": 0.1123046875,
|
| 212 |
+
"learning_rate": 9.849999999999999e-07,
|
| 213 |
+
"loss": 0.0045,
|
| 214 |
+
"reward": 0.8125,
|
| 215 |
+
"reward_std": 0.26933756470680237,
|
| 216 |
+
"rewards/accuracy_reward": 0.8125,
|
| 217 |
+
"rewards/format_reward": 0.0,
|
| 218 |
+
"step": 16
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"completion_length": 4.5,
|
| 222 |
+
"epoch": 0.001682085786375105,
|
| 223 |
+
"grad_norm": 28.27692985534668,
|
| 224 |
+
"kl": 0.06103515625,
|
| 225 |
+
"learning_rate": 9.84e-07,
|
| 226 |
+
"loss": 0.0024,
|
| 227 |
+
"reward": 0.375,
|
| 228 |
+
"reward_std": 0.14433756470680237,
|
| 229 |
+
"rewards/accuracy_reward": 0.375,
|
| 230 |
+
"rewards/format_reward": 0.0,
|
| 231 |
+
"step": 17
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"completion_length": 3.625,
|
| 235 |
+
"epoch": 0.0017810320091030524,
|
| 236 |
+
"grad_norm": 43.93234634399414,
|
| 237 |
+
"kl": 0.04833984375,
|
| 238 |
+
"learning_rate": 9.83e-07,
|
| 239 |
+
"loss": 0.0019,
|
| 240 |
+
"reward": 0.4375,
|
| 241 |
+
"reward_std": 0.375,
|
| 242 |
+
"rewards/accuracy_reward": 0.4375,
|
| 243 |
+
"rewards/format_reward": 0.0,
|
| 244 |
+
"step": 18
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"completion_length": 4.875,
|
| 248 |
+
"epoch": 0.001879978231831,
|
| 249 |
+
"grad_norm": 35.52457046508789,
|
| 250 |
+
"kl": 0.1285400390625,
|
| 251 |
+
"learning_rate": 9.819999999999999e-07,
|
| 252 |
+
"loss": 0.0052,
|
| 253 |
+
"reward": 0.25,
|
| 254 |
+
"reward_std": 0.25,
|
| 255 |
+
"rewards/accuracy_reward": 0.25,
|
| 256 |
+
"rewards/format_reward": 0.0,
|
| 257 |
+
"step": 19
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"completion_length": 4.6875,
|
| 261 |
+
"epoch": 0.0019789244545589473,
|
| 262 |
+
"grad_norm": 5.439634799957275,
|
| 263 |
+
"kl": 0.283935546875,
|
| 264 |
+
"learning_rate": 9.81e-07,
|
| 265 |
+
"loss": 0.0114,
|
| 266 |
+
"reward": 0.9375,
|
| 267 |
+
"reward_std": 0.125,
|
| 268 |
+
"rewards/accuracy_reward": 0.9375,
|
| 269 |
+
"rewards/format_reward": 0.0,
|
| 270 |
+
"step": 20
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"completion_length": 2.875,
|
| 274 |
+
"epoch": 0.0020778706772868944,
|
| 275 |
+
"grad_norm": 35.29671859741211,
|
| 276 |
+
"kl": 0.076904296875,
|
| 277 |
+
"learning_rate": 9.8e-07,
|
| 278 |
+
"loss": 0.0031,
|
| 279 |
+
"reward": 0.75,
|
| 280 |
+
"reward_std": 0.25,
|
| 281 |
+
"rewards/accuracy_reward": 0.75,
|
| 282 |
+
"rewards/format_reward": 0.0,
|
| 283 |
+
"step": 21
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"completion_length": 3.1875,
|
| 287 |
+
"epoch": 0.002176816900014842,
|
| 288 |
+
"grad_norm": 0.33881574869155884,
|
| 289 |
+
"kl": 0.03955078125,
|
| 290 |
+
"learning_rate": 9.789999999999999e-07,
|
| 291 |
+
"loss": 0.0016,
|
| 292 |
+
"reward": 0.5,
|
| 293 |
+
"reward_std": 0.0,
|
| 294 |
+
"rewards/accuracy_reward": 0.5,
|
| 295 |
+
"rewards/format_reward": 0.0,
|
| 296 |
+
"step": 22
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"completion_length": 3.875,
|
| 300 |
+
"epoch": 0.002275763122742789,
|
| 301 |
+
"grad_norm": 18.542280197143555,
|
| 302 |
+
"kl": 0.13916015625,
|
| 303 |
+
"learning_rate": 9.78e-07,
|
| 304 |
+
"loss": 0.0056,
|
| 305 |
+
"reward": 0.875,
|
| 306 |
+
"reward_std": 0.14433756470680237,
|
| 307 |
+
"rewards/accuracy_reward": 0.875,
|
| 308 |
+
"rewards/format_reward": 0.0,
|
| 309 |
+
"step": 23
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"completion_length": 3.9375,
|
| 313 |
+
"epoch": 0.0023747093454707367,
|
| 314 |
+
"grad_norm": 22.113807678222656,
|
| 315 |
+
"kl": 0.46295166015625,
|
| 316 |
+
"learning_rate": 9.77e-07,
|
| 317 |
+
"loss": 0.0185,
|
| 318 |
+
"reward": 0.5625,
|
| 319 |
+
"reward_std": 0.125,
|
| 320 |
+
"rewards/accuracy_reward": 0.5625,
|
| 321 |
+
"rewards/format_reward": 0.0,
|
| 322 |
+
"step": 24
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"completion_length": 2.875,
|
| 326 |
+
"epoch": 0.002473655568198684,
|
| 327 |
+
"grad_norm": 28.871366500854492,
|
| 328 |
+
"kl": 0.0540771484375,
|
| 329 |
+
"learning_rate": 9.759999999999998e-07,
|
| 330 |
+
"loss": 0.0022,
|
| 331 |
+
"reward": 0.75,
|
| 332 |
+
"reward_std": 0.25,
|
| 333 |
+
"rewards/accuracy_reward": 0.75,
|
| 334 |
+
"rewards/format_reward": 0.0,
|
| 335 |
+
"step": 25
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"completion_length": 2.75,
|
| 339 |
+
"epoch": 0.0025726017909266314,
|
| 340 |
+
"grad_norm": 13.429852485656738,
|
| 341 |
+
"kl": 0.0830078125,
|
| 342 |
+
"learning_rate": 9.75e-07,
|
| 343 |
+
"loss": 0.0033,
|
| 344 |
+
"reward": 0.9375,
|
| 345 |
+
"reward_std": 0.125,
|
| 346 |
+
"rewards/accuracy_reward": 0.9375,
|
| 347 |
+
"rewards/format_reward": 0.0,
|
| 348 |
+
"step": 26
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"completion_length": 3.3125,
|
| 352 |
+
"epoch": 0.002671548013654579,
|
| 353 |
+
"grad_norm": 25.259496688842773,
|
| 354 |
+
"kl": 0.08380126953125,
|
| 355 |
+
"learning_rate": 9.74e-07,
|
| 356 |
+
"loss": 0.0034,
|
| 357 |
+
"reward": 0.9375,
|
| 358 |
+
"reward_std": 0.125,
|
| 359 |
+
"rewards/accuracy_reward": 0.9375,
|
| 360 |
+
"rewards/format_reward": 0.0,
|
| 361 |
+
"step": 27
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"completion_length": 4.6875,
|
| 365 |
+
"epoch": 0.002770494236382526,
|
| 366 |
+
"grad_norm": 35.60582733154297,
|
| 367 |
+
"kl": 0.017974853515625,
|
| 368 |
+
"learning_rate": 9.729999999999998e-07,
|
| 369 |
+
"loss": 0.0007,
|
| 370 |
+
"reward": 0.875,
|
| 371 |
+
"reward_std": 0.14433756470680237,
|
| 372 |
+
"rewards/accuracy_reward": 0.875,
|
| 373 |
+
"rewards/format_reward": 0.0,
|
| 374 |
+
"step": 28
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"completion_length": 2.625,
|
| 378 |
+
"epoch": 0.0028694404591104736,
|
| 379 |
+
"grad_norm": 35.21329116821289,
|
| 380 |
+
"kl": 0.107421875,
|
| 381 |
+
"learning_rate": 9.72e-07,
|
| 382 |
+
"loss": 0.0043,
|
| 383 |
+
"reward": 0.625,
|
| 384 |
+
"reward_std": 0.25,
|
| 385 |
+
"rewards/accuracy_reward": 0.625,
|
| 386 |
+
"rewards/format_reward": 0.0,
|
| 387 |
+
"step": 29
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"completion_length": 3.4375,
|
| 391 |
+
"epoch": 0.0029683866818384207,
|
| 392 |
+
"grad_norm": 41.33916091918945,
|
| 393 |
+
"kl": 0.14288330078125,
|
| 394 |
+
"learning_rate": 9.709999999999999e-07,
|
| 395 |
+
"loss": 0.0057,
|
| 396 |
+
"reward": 0.8125,
|
| 397 |
+
"reward_std": 0.26933756470680237,
|
| 398 |
+
"rewards/accuracy_reward": 0.8125,
|
| 399 |
+
"rewards/format_reward": 0.0,
|
| 400 |
+
"step": 30
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"completion_length": 3.1875,
|
| 404 |
+
"epoch": 0.0030673329045663683,
|
| 405 |
+
"grad_norm": 35.675777435302734,
|
| 406 |
+
"kl": 0.1474609375,
|
| 407 |
+
"learning_rate": 9.7e-07,
|
| 408 |
+
"loss": 0.0059,
|
| 409 |
+
"reward": 0.625,
|
| 410 |
+
"reward_std": 0.25,
|
| 411 |
+
"rewards/accuracy_reward": 0.625,
|
| 412 |
+
"rewards/format_reward": 0.0,
|
| 413 |
+
"step": 31
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"completion_length": 4.0,
|
| 417 |
+
"epoch": 0.0031662791272943154,
|
| 418 |
+
"grad_norm": 18.264066696166992,
|
| 419 |
+
"kl": 0.087646484375,
|
| 420 |
+
"learning_rate": 9.69e-07,
|
| 421 |
+
"loss": 0.0035,
|
| 422 |
+
"reward": 0.9375,
|
| 423 |
+
"reward_std": 0.125,
|
| 424 |
+
"rewards/accuracy_reward": 0.9375,
|
| 425 |
+
"rewards/format_reward": 0.0,
|
| 426 |
+
"step": 32
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"completion_length": 3.5,
|
| 430 |
+
"epoch": 0.003265225350022263,
|
| 431 |
+
"grad_norm": 0.011650191619992256,
|
| 432 |
+
"kl": 0.0262451171875,
|
| 433 |
+
"learning_rate": 9.679999999999999e-07,
|
| 434 |
+
"loss": 0.001,
|
| 435 |
+
"reward": 1.0,
|
| 436 |
+
"reward_std": 0.0,
|
| 437 |
+
"rewards/accuracy_reward": 1.0,
|
| 438 |
+
"rewards/format_reward": 0.0,
|
| 439 |
+
"step": 33
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"completion_length": 3.5,
|
| 443 |
+
"epoch": 0.00336417157275021,
|
| 444 |
+
"grad_norm": 52.62285614013672,
|
| 445 |
+
"kl": 0.115966796875,
|
| 446 |
+
"learning_rate": 9.67e-07,
|
| 447 |
+
"loss": 0.0046,
|
| 448 |
+
"reward": 0.5625,
|
| 449 |
+
"reward_std": 0.125,
|
| 450 |
+
"rewards/accuracy_reward": 0.5625,
|
| 451 |
+
"rewards/format_reward": 0.0,
|
| 452 |
+
"step": 34
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"completion_length": 3.625,
|
| 456 |
+
"epoch": 0.0034631177954781577,
|
| 457 |
+
"grad_norm": 82.99117279052734,
|
| 458 |
+
"kl": 3.158203125,
|
| 459 |
+
"learning_rate": 9.66e-07,
|
| 460 |
+
"loss": 0.1264,
|
| 461 |
+
"reward": 0.4375,
|
| 462 |
+
"reward_std": 0.125,
|
| 463 |
+
"rewards/accuracy_reward": 0.4375,
|
| 464 |
+
"rewards/format_reward": 0.0,
|
| 465 |
+
"step": 35
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"completion_length": 2.4375,
|
| 469 |
+
"epoch": 0.003562064018206105,
|
| 470 |
+
"grad_norm": 33.630123138427734,
|
| 471 |
+
"kl": 0.109375,
|
| 472 |
+
"learning_rate": 9.649999999999999e-07,
|
| 473 |
+
"loss": 0.0044,
|
| 474 |
+
"reward": 0.9375,
|
| 475 |
+
"reward_std": 0.125,
|
| 476 |
+
"rewards/accuracy_reward": 0.9375,
|
| 477 |
+
"rewards/format_reward": 0.0,
|
| 478 |
+
"step": 36
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"completion_length": 3.1875,
|
| 482 |
+
"epoch": 0.0036610102409340524,
|
| 483 |
+
"grad_norm": 31.628652572631836,
|
| 484 |
+
"kl": 0.61328125,
|
| 485 |
+
"learning_rate": 9.64e-07,
|
| 486 |
+
"loss": 0.0246,
|
| 487 |
+
"reward": 0.625,
|
| 488 |
+
"reward_std": 0.14433756470680237,
|
| 489 |
+
"rewards/accuracy_reward": 0.625,
|
| 490 |
+
"rewards/format_reward": 0.0,
|
| 491 |
+
"step": 37
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"completion_length": 4.1875,
|
| 495 |
+
"epoch": 0.003759956463662,
|
| 496 |
+
"grad_norm": 19.04951286315918,
|
| 497 |
+
"kl": 0.2353515625,
|
| 498 |
+
"learning_rate": 9.63e-07,
|
| 499 |
+
"loss": 0.0095,
|
| 500 |
+
"reward": 0.8125,
|
| 501 |
+
"reward_std": 0.26933756470680237,
|
| 502 |
+
"rewards/accuracy_reward": 0.8125,
|
| 503 |
+
"rewards/format_reward": 0.0,
|
| 504 |
+
"step": 38
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"completion_length": 4.3125,
|
| 508 |
+
"epoch": 0.003858902686389947,
|
| 509 |
+
"grad_norm": 26.543506622314453,
|
| 510 |
+
"kl": 0.0684814453125,
|
| 511 |
+
"learning_rate": 9.619999999999999e-07,
|
| 512 |
+
"loss": 0.0027,
|
| 513 |
+
"reward": 0.875,
|
| 514 |
+
"reward_std": 0.25,
|
| 515 |
+
"rewards/accuracy_reward": 0.875,
|
| 516 |
+
"rewards/format_reward": 0.0,
|
| 517 |
+
"step": 39
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"completion_length": 4.0,
|
| 521 |
+
"epoch": 0.003957848909117895,
|
| 522 |
+
"grad_norm": 13.690553665161133,
|
| 523 |
+
"kl": 0.13409423828125,
|
| 524 |
+
"learning_rate": 9.61e-07,
|
| 525 |
+
"loss": 0.0054,
|
| 526 |
+
"reward": 0.5625,
|
| 527 |
+
"reward_std": 0.125,
|
| 528 |
+
"rewards/accuracy_reward": 0.5625,
|
| 529 |
+
"rewards/format_reward": 0.0,
|
| 530 |
+
"step": 40
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"completion_length": 3.6875,
|
| 534 |
+
"epoch": 0.004056795131845842,
|
| 535 |
+
"grad_norm": 13.923758506774902,
|
| 536 |
+
"kl": 0.0458984375,
|
| 537 |
+
"learning_rate": 9.6e-07,
|
| 538 |
+
"loss": 0.0018,
|
| 539 |
+
"reward": 0.9375,
|
| 540 |
+
"reward_std": 0.125,
|
| 541 |
+
"rewards/accuracy_reward": 0.9375,
|
| 542 |
+
"rewards/format_reward": 0.0,
|
| 543 |
+
"step": 41
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"completion_length": 5.875,
|
| 547 |
+
"epoch": 0.004155741354573789,
|
| 548 |
+
"grad_norm": 18.20030403137207,
|
| 549 |
+
"kl": 0.115478515625,
|
| 550 |
+
"learning_rate": 9.589999999999998e-07,
|
| 551 |
+
"loss": 0.0046,
|
| 552 |
+
"reward": 0.625,
|
| 553 |
+
"reward_std": 0.14433756470680237,
|
| 554 |
+
"rewards/accuracy_reward": 0.625,
|
| 555 |
+
"rewards/format_reward": 0.0,
|
| 556 |
+
"step": 42
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"completion_length": 2.75,
|
| 560 |
+
"epoch": 0.004254687577301737,
|
| 561 |
+
"grad_norm": 43.371185302734375,
|
| 562 |
+
"kl": 0.097412109375,
|
| 563 |
+
"learning_rate": 9.58e-07,
|
| 564 |
+
"loss": 0.0039,
|
| 565 |
+
"reward": 0.625,
|
| 566 |
+
"reward_std": 0.14433756470680237,
|
| 567 |
+
"rewards/accuracy_reward": 0.625,
|
| 568 |
+
"rewards/format_reward": 0.0,
|
| 569 |
+
"step": 43
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"completion_length": 3.1875,
|
| 573 |
+
"epoch": 0.004353633800029684,
|
| 574 |
+
"grad_norm": 69.18988037109375,
|
| 575 |
+
"kl": 0.15380859375,
|
| 576 |
+
"learning_rate": 9.57e-07,
|
| 577 |
+
"loss": 0.0062,
|
| 578 |
+
"reward": 0.5625,
|
| 579 |
+
"reward_std": 0.26933756470680237,
|
| 580 |
+
"rewards/accuracy_reward": 0.5625,
|
| 581 |
+
"rewards/format_reward": 0.0,
|
| 582 |
+
"step": 44
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"completion_length": 3.5,
|
| 586 |
+
"epoch": 0.004452580022757631,
|
| 587 |
+
"grad_norm": 42.821083068847656,
|
| 588 |
+
"kl": 0.29052734375,
|
| 589 |
+
"learning_rate": 9.559999999999998e-07,
|
| 590 |
+
"loss": 0.0116,
|
| 591 |
+
"reward": 0.8125,
|
| 592 |
+
"reward_std": 0.26933756470680237,
|
| 593 |
+
"rewards/accuracy_reward": 0.8125,
|
| 594 |
+
"rewards/format_reward": 0.0,
|
| 595 |
+
"step": 45
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"completion_length": 2.75,
|
| 599 |
+
"epoch": 0.004551526245485578,
|
| 600 |
+
"grad_norm": 0.00253496621735394,
|
| 601 |
+
"kl": 0.042724609375,
|
| 602 |
+
"learning_rate": 9.55e-07,
|
| 603 |
+
"loss": 0.0017,
|
| 604 |
+
"reward": 0.75,
|
| 605 |
+
"reward_std": 0.0,
|
| 606 |
+
"rewards/accuracy_reward": 0.75,
|
| 607 |
+
"rewards/format_reward": 0.0,
|
| 608 |
+
"step": 46
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"completion_length": 2.75,
|
| 612 |
+
"epoch": 0.004650472468213526,
|
| 613 |
+
"grad_norm": 28.470979690551758,
|
| 614 |
+
"kl": 0.1875,
|
| 615 |
+
"learning_rate": 9.539999999999999e-07,
|
| 616 |
+
"loss": 0.0075,
|
| 617 |
+
"reward": 0.6875,
|
| 618 |
+
"reward_std": 0.125,
|
| 619 |
+
"rewards/accuracy_reward": 0.6875,
|
| 620 |
+
"rewards/format_reward": 0.0,
|
| 621 |
+
"step": 47
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"completion_length": 3.125,
|
| 625 |
+
"epoch": 0.004749418690941473,
|
| 626 |
+
"grad_norm": 78.60997772216797,
|
| 627 |
+
"kl": 0.44921875,
|
| 628 |
+
"learning_rate": 9.529999999999999e-07,
|
| 629 |
+
"loss": 0.018,
|
| 630 |
+
"reward": 0.8125,
|
| 631 |
+
"reward_std": 0.26933756470680237,
|
| 632 |
+
"rewards/accuracy_reward": 0.8125,
|
| 633 |
+
"rewards/format_reward": 0.0,
|
| 634 |
+
"step": 48
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"completion_length": 3.5,
|
| 638 |
+
"epoch": 0.0048483649136694205,
|
| 639 |
+
"grad_norm": 0.15050888061523438,
|
| 640 |
+
"kl": 0.028778076171875,
|
| 641 |
+
"learning_rate": 9.52e-07,
|
| 642 |
+
"loss": 0.0011,
|
| 643 |
+
"reward": 1.0,
|
| 644 |
+
"reward_std": 0.0,
|
| 645 |
+
"rewards/accuracy_reward": 1.0,
|
| 646 |
+
"rewards/format_reward": 0.0,
|
| 647 |
+
"step": 49
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"completion_length": 3.6875,
|
| 651 |
+
"epoch": 0.004947311136397368,
|
| 652 |
+
"grad_norm": 8.970772743225098,
|
| 653 |
+
"kl": 0.3662109375,
|
| 654 |
+
"learning_rate": 9.509999999999999e-07,
|
| 655 |
+
"loss": 0.0146,
|
| 656 |
+
"reward": 0.4375,
|
| 657 |
+
"reward_std": 0.125,
|
| 658 |
+
"rewards/accuracy_reward": 0.4375,
|
| 659 |
+
"rewards/format_reward": 0.0,
|
| 660 |
+
"step": 50
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"completion_length": 3.5,
|
| 664 |
+
"epoch": 0.005046257359125316,
|
| 665 |
+
"grad_norm": 42.177669525146484,
|
| 666 |
+
"kl": 0.20263671875,
|
| 667 |
+
"learning_rate": 9.499999999999999e-07,
|
| 668 |
+
"loss": 0.0081,
|
| 669 |
+
"reward": 0.875,
|
| 670 |
+
"reward_std": 0.14433756470680237,
|
| 671 |
+
"rewards/accuracy_reward": 0.875,
|
| 672 |
+
"rewards/format_reward": 0.0,
|
| 673 |
+
"step": 51
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"completion_length": 3.125,
|
| 677 |
+
"epoch": 0.005145203581853263,
|
| 678 |
+
"grad_norm": 11.261039733886719,
|
| 679 |
+
"kl": 0.14239501953125,
|
| 680 |
+
"learning_rate": 9.489999999999999e-07,
|
| 681 |
+
"loss": 0.0057,
|
| 682 |
+
"reward": 0.6875,
|
| 683 |
+
"reward_std": 0.125,
|
| 684 |
+
"rewards/accuracy_reward": 0.6875,
|
| 685 |
+
"rewards/format_reward": 0.0,
|
| 686 |
+
"step": 52
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"completion_length": 3.25,
|
| 690 |
+
"epoch": 0.00524414980458121,
|
| 691 |
+
"grad_norm": 0.3226803243160248,
|
| 692 |
+
"kl": 0.0335235595703125,
|
| 693 |
+
"learning_rate": 9.479999999999999e-07,
|
| 694 |
+
"loss": 0.0013,
|
| 695 |
+
"reward": 0.75,
|
| 696 |
+
"reward_std": 0.0,
|
| 697 |
+
"rewards/accuracy_reward": 0.75,
|
| 698 |
+
"rewards/format_reward": 0.0,
|
| 699 |
+
"step": 53
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"completion_length": 2.9375,
|
| 703 |
+
"epoch": 0.005343096027309158,
|
| 704 |
+
"grad_norm": 27.19357681274414,
|
| 705 |
+
"kl": 0.1173553466796875,
|
| 706 |
+
"learning_rate": 9.469999999999999e-07,
|
| 707 |
+
"loss": 0.0047,
|
| 708 |
+
"reward": 0.9375,
|
| 709 |
+
"reward_std": 0.125,
|
| 710 |
+
"rewards/accuracy_reward": 0.9375,
|
| 711 |
+
"rewards/format_reward": 0.0,
|
| 712 |
+
"step": 54
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"completion_length": 2.25,
|
| 716 |
+
"epoch": 0.005442042250037105,
|
| 717 |
+
"grad_norm": 0.14267660677433014,
|
| 718 |
+
"kl": 0.0958251953125,
|
| 719 |
+
"learning_rate": 9.459999999999999e-07,
|
| 720 |
+
"loss": 0.0038,
|
| 721 |
+
"reward": 0.75,
|
| 722 |
+
"reward_std": 0.0,
|
| 723 |
+
"rewards/accuracy_reward": 0.75,
|
| 724 |
+
"rewards/format_reward": 0.0,
|
| 725 |
+
"step": 55
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"completion_length": 3.125,
|
| 729 |
+
"epoch": 0.005540988472765052,
|
| 730 |
+
"grad_norm": 1.3845109939575195,
|
| 731 |
+
"kl": 0.070556640625,
|
| 732 |
+
"learning_rate": 9.45e-07,
|
| 733 |
+
"loss": 0.0028,
|
| 734 |
+
"reward": 0.75,
|
| 735 |
+
"reward_std": 0.0,
|
| 736 |
+
"rewards/accuracy_reward": 0.75,
|
| 737 |
+
"rewards/format_reward": 0.0,
|
| 738 |
+
"step": 56
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"completion_length": 3.5,
|
| 742 |
+
"epoch": 0.005639934695492999,
|
| 743 |
+
"grad_norm": 0.3318254351615906,
|
| 744 |
+
"kl": 0.07275390625,
|
| 745 |
+
"learning_rate": 9.439999999999999e-07,
|
| 746 |
+
"loss": 0.0029,
|
| 747 |
+
"reward": 0.75,
|
| 748 |
+
"reward_std": 0.0,
|
| 749 |
+
"rewards/accuracy_reward": 0.75,
|
| 750 |
+
"rewards/format_reward": 0.0,
|
| 751 |
+
"step": 57
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"completion_length": 3.5,
|
| 755 |
+
"epoch": 0.005738880918220947,
|
| 756 |
+
"grad_norm": 79.56658172607422,
|
| 757 |
+
"kl": 0.147705078125,
|
| 758 |
+
"learning_rate": 9.429999999999999e-07,
|
| 759 |
+
"loss": 0.0059,
|
| 760 |
+
"reward": 0.625,
|
| 761 |
+
"reward_std": 0.14433756470680237,
|
| 762 |
+
"rewards/accuracy_reward": 0.625,
|
| 763 |
+
"rewards/format_reward": 0.0,
|
| 764 |
+
"step": 58
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"completion_length": 3.25,
|
| 768 |
+
"epoch": 0.005837827140948894,
|
| 769 |
+
"grad_norm": 29.595632553100586,
|
| 770 |
+
"kl": 0.08984375,
|
| 771 |
+
"learning_rate": 9.419999999999999e-07,
|
| 772 |
+
"loss": 0.0036,
|
| 773 |
+
"reward": 0.9375,
|
| 774 |
+
"reward_std": 0.125,
|
| 775 |
+
"rewards/accuracy_reward": 0.9375,
|
| 776 |
+
"rewards/format_reward": 0.0,
|
| 777 |
+
"step": 59
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"completion_length": 3.375,
|
| 781 |
+
"epoch": 0.0059367733636768415,
|
| 782 |
+
"grad_norm": 1.569680094718933,
|
| 783 |
+
"kl": 0.1719970703125,
|
| 784 |
+
"learning_rate": 9.409999999999999e-07,
|
| 785 |
+
"loss": 0.0069,
|
| 786 |
+
"reward": 0.5,
|
| 787 |
+
"reward_std": 0.0,
|
| 788 |
+
"rewards/accuracy_reward": 0.5,
|
| 789 |
+
"rewards/format_reward": 0.0,
|
| 790 |
+
"step": 60
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"completion_length": 3.4375,
|
| 794 |
+
"epoch": 0.006035719586404789,
|
| 795 |
+
"grad_norm": 20.28252601623535,
|
| 796 |
+
"kl": 0.01580810546875,
|
| 797 |
+
"learning_rate": 9.399999999999999e-07,
|
| 798 |
+
"loss": 0.0006,
|
| 799 |
+
"reward": 0.6875,
|
| 800 |
+
"reward_std": 0.125,
|
| 801 |
+
"rewards/accuracy_reward": 0.6875,
|
| 802 |
+
"rewards/format_reward": 0.0,
|
| 803 |
+
"step": 61
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"completion_length": 4.0,
|
| 807 |
+
"epoch": 0.006134665809132737,
|
| 808 |
+
"grad_norm": 0.009604735299944878,
|
| 809 |
+
"kl": 0.016845703125,
|
| 810 |
+
"learning_rate": 9.389999999999999e-07,
|
| 811 |
+
"loss": 0.0007,
|
| 812 |
+
"reward": 1.0,
|
| 813 |
+
"reward_std": 0.0,
|
| 814 |
+
"rewards/accuracy_reward": 1.0,
|
| 815 |
+
"rewards/format_reward": 0.0,
|
| 816 |
+
"step": 62
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"completion_length": 3.0,
|
| 820 |
+
"epoch": 0.006233612031860684,
|
| 821 |
+
"grad_norm": 0.054051682353019714,
|
| 822 |
+
"kl": 0.1220703125,
|
| 823 |
+
"learning_rate": 9.379999999999998e-07,
|
| 824 |
+
"loss": 0.0049,
|
| 825 |
+
"reward": 1.0,
|
| 826 |
+
"reward_std": 0.0,
|
| 827 |
+
"rewards/accuracy_reward": 1.0,
|
| 828 |
+
"rewards/format_reward": 0.0,
|
| 829 |
+
"step": 63
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"completion_length": 3.25,
|
| 833 |
+
"epoch": 0.006332558254588631,
|
| 834 |
+
"grad_norm": 43.524681091308594,
|
| 835 |
+
"kl": 0.41552734375,
|
| 836 |
+
"learning_rate": 9.37e-07,
|
| 837 |
+
"loss": 0.0166,
|
| 838 |
+
"reward": 0.5625,
|
| 839 |
+
"reward_std": 0.125,
|
| 840 |
+
"rewards/accuracy_reward": 0.5625,
|
| 841 |
+
"rewards/format_reward": 0.0,
|
| 842 |
+
"step": 64
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"completion_length": 3.3125,
|
| 846 |
+
"epoch": 0.006431504477316579,
|
| 847 |
+
"grad_norm": 19.583276748657227,
|
| 848 |
+
"kl": 0.4501953125,
|
| 849 |
+
"learning_rate": 9.36e-07,
|
| 850 |
+
"loss": 0.018,
|
| 851 |
+
"reward": 0.6875,
|
| 852 |
+
"reward_std": 0.125,
|
| 853 |
+
"rewards/accuracy_reward": 0.6875,
|
| 854 |
+
"rewards/format_reward": 0.0,
|
| 855 |
+
"step": 65
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"completion_length": 3.5,
|
| 859 |
+
"epoch": 0.006530450700044526,
|
| 860 |
+
"grad_norm": 29.74109649658203,
|
| 861 |
+
"kl": 0.42333984375,
|
| 862 |
+
"learning_rate": 9.35e-07,
|
| 863 |
+
"loss": 0.0169,
|
| 864 |
+
"reward": 0.625,
|
| 865 |
+
"reward_std": 0.25,
|
| 866 |
+
"rewards/accuracy_reward": 0.625,
|
| 867 |
+
"rewards/format_reward": 0.0,
|
| 868 |
+
"step": 66
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"completion_length": 3.5625,
|
| 872 |
+
"epoch": 0.006629396922772473,
|
| 873 |
+
"grad_norm": 51.01466369628906,
|
| 874 |
+
"kl": 0.45574951171875,
|
| 875 |
+
"learning_rate": 9.34e-07,
|
| 876 |
+
"loss": 0.0182,
|
| 877 |
+
"reward": 0.9375,
|
| 878 |
+
"reward_std": 0.125,
|
| 879 |
+
"rewards/accuracy_reward": 0.9375,
|
| 880 |
+
"rewards/format_reward": 0.0,
|
| 881 |
+
"step": 67
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"completion_length": 2.875,
|
| 885 |
+
"epoch": 0.00672834314550042,
|
| 886 |
+
"grad_norm": 40.87276840209961,
|
| 887 |
+
"kl": 0.11376953125,
|
| 888 |
+
"learning_rate": 9.33e-07,
|
| 889 |
+
"loss": 0.0046,
|
| 890 |
+
"reward": 0.9375,
|
| 891 |
+
"reward_std": 0.125,
|
| 892 |
+
"rewards/accuracy_reward": 0.9375,
|
| 893 |
+
"rewards/format_reward": 0.0,
|
| 894 |
+
"step": 68
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"completion_length": 4.375,
|
| 898 |
+
"epoch": 0.006827289368228368,
|
| 899 |
+
"grad_norm": 920.1598510742188,
|
| 900 |
+
"kl": 30.021240234375,
|
| 901 |
+
"learning_rate": 9.32e-07,
|
| 902 |
+
"loss": 1.1998,
|
| 903 |
+
"reward": 0.6875,
|
| 904 |
+
"reward_std": 0.125,
|
| 905 |
+
"rewards/accuracy_reward": 0.6875,
|
| 906 |
+
"rewards/format_reward": 0.0,
|
| 907 |
+
"step": 69
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"completion_length": 3.25,
|
| 911 |
+
"epoch": 0.006926235590956315,
|
| 912 |
+
"grad_norm": 0.07895195484161377,
|
| 913 |
+
"kl": 0.0203857421875,
|
| 914 |
+
"learning_rate": 9.31e-07,
|
| 915 |
+
"loss": 0.0008,
|
| 916 |
+
"reward": 0.75,
|
| 917 |
+
"reward_std": 0.0,
|
| 918 |
+
"rewards/accuracy_reward": 0.75,
|
| 919 |
+
"rewards/format_reward": 0.0,
|
| 920 |
+
"step": 70
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"completion_length": 2.9375,
|
| 924 |
+
"epoch": 0.0070251818136842625,
|
| 925 |
+
"grad_norm": 72.71320343017578,
|
| 926 |
+
"kl": 0.9306640625,
|
| 927 |
+
"learning_rate": 9.3e-07,
|
| 928 |
+
"loss": 0.0373,
|
| 929 |
+
"reward": 0.6875,
|
| 930 |
+
"reward_std": 0.125,
|
| 931 |
+
"rewards/accuracy_reward": 0.6875,
|
| 932 |
+
"rewards/format_reward": 0.0,
|
| 933 |
+
"step": 71
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"completion_length": 3.5,
|
| 937 |
+
"epoch": 0.00712412803641221,
|
| 938 |
+
"grad_norm": 0.04532546177506447,
|
| 939 |
+
"kl": 0.07568359375,
|
| 940 |
+
"learning_rate": 9.29e-07,
|
| 941 |
+
"loss": 0.003,
|
| 942 |
+
"reward": 0.75,
|
| 943 |
+
"reward_std": 0.0,
|
| 944 |
+
"rewards/accuracy_reward": 0.75,
|
| 945 |
+
"rewards/format_reward": 0.0,
|
| 946 |
+
"step": 72
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"completion_length": 3.5,
|
| 950 |
+
"epoch": 0.007223074259140158,
|
| 951 |
+
"grad_norm": 59.64799118041992,
|
| 952 |
+
"kl": 0.309326171875,
|
| 953 |
+
"learning_rate": 9.28e-07,
|
| 954 |
+
"loss": 0.0123,
|
| 955 |
+
"reward": 0.625,
|
| 956 |
+
"reward_std": 0.14433756470680237,
|
| 957 |
+
"rewards/accuracy_reward": 0.625,
|
| 958 |
+
"rewards/format_reward": 0.0,
|
| 959 |
+
"step": 73
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"completion_length": 4.25,
|
| 963 |
+
"epoch": 0.007322020481868105,
|
| 964 |
+
"grad_norm": 0.022819090634584427,
|
| 965 |
+
"kl": 0.129150390625,
|
| 966 |
+
"learning_rate": 9.27e-07,
|
| 967 |
+
"loss": 0.0052,
|
| 968 |
+
"reward": 0.75,
|
| 969 |
+
"reward_std": 0.0,
|
| 970 |
+
"rewards/accuracy_reward": 0.75,
|
| 971 |
+
"rewards/format_reward": 0.0,
|
| 972 |
+
"step": 74
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"completion_length": 2.5,
|
| 976 |
+
"epoch": 0.007420966704596052,
|
| 977 |
+
"grad_norm": 0.4349958598613739,
|
| 978 |
+
"kl": 0.1767578125,
|
| 979 |
+
"learning_rate": 9.26e-07,
|
| 980 |
+
"loss": 0.0071,
|
| 981 |
+
"reward": 0.75,
|
| 982 |
+
"reward_std": 0.0,
|
| 983 |
+
"rewards/accuracy_reward": 0.75,
|
| 984 |
+
"rewards/format_reward": 0.0,
|
| 985 |
+
"step": 75
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"completion_length": 3.25,
|
| 989 |
+
"epoch": 0.007519912927324,
|
| 990 |
+
"grad_norm": 0.9703753590583801,
|
| 991 |
+
"kl": 0.1021728515625,
|
| 992 |
+
"learning_rate": 9.25e-07,
|
| 993 |
+
"loss": 0.0041,
|
| 994 |
+
"reward": 1.0,
|
| 995 |
+
"reward_std": 0.0,
|
| 996 |
+
"rewards/accuracy_reward": 1.0,
|
| 997 |
+
"rewards/format_reward": 0.0,
|
| 998 |
+
"step": 76
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"completion_length": 3.6875,
|
| 1002 |
+
"epoch": 0.007618859150051947,
|
| 1003 |
+
"grad_norm": 0.20156638324260712,
|
| 1004 |
+
"kl": 0.0416259765625,
|
| 1005 |
+
"learning_rate": 9.24e-07,
|
| 1006 |
+
"loss": 0.0017,
|
| 1007 |
+
"reward": 0.5,
|
| 1008 |
+
"reward_std": 0.0,
|
| 1009 |
+
"rewards/accuracy_reward": 0.5,
|
| 1010 |
+
"rewards/format_reward": 0.0,
|
| 1011 |
+
"step": 77
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"completion_length": 3.0,
|
| 1015 |
+
"epoch": 0.007717805372779894,
|
| 1016 |
+
"grad_norm": 0.1729861944913864,
|
| 1017 |
+
"kl": 0.1273193359375,
|
| 1018 |
+
"learning_rate": 9.23e-07,
|
| 1019 |
+
"loss": 0.0051,
|
| 1020 |
+
"reward": 0.5,
|
| 1021 |
+
"reward_std": 0.0,
|
| 1022 |
+
"rewards/accuracy_reward": 0.5,
|
| 1023 |
+
"rewards/format_reward": 0.0,
|
| 1024 |
+
"step": 78
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"completion_length": 2.75,
|
| 1028 |
+
"epoch": 0.007816751595507841,
|
| 1029 |
+
"grad_norm": 0.019643617793917656,
|
| 1030 |
+
"kl": 0.0714111328125,
|
| 1031 |
+
"learning_rate": 9.22e-07,
|
| 1032 |
+
"loss": 0.0029,
|
| 1033 |
+
"reward": 0.75,
|
| 1034 |
+
"reward_std": 0.0,
|
| 1035 |
+
"rewards/accuracy_reward": 0.75,
|
| 1036 |
+
"rewards/format_reward": 0.0,
|
| 1037 |
+
"step": 79
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"completion_length": 3.25,
|
| 1041 |
+
"epoch": 0.00791569781823579,
|
| 1042 |
+
"grad_norm": 0.017483701929450035,
|
| 1043 |
+
"kl": 0.23956298828125,
|
| 1044 |
+
"learning_rate": 9.21e-07,
|
| 1045 |
+
"loss": 0.0096,
|
| 1046 |
+
"reward": 1.0,
|
| 1047 |
+
"reward_std": 0.0,
|
| 1048 |
+
"rewards/accuracy_reward": 1.0,
|
| 1049 |
+
"rewards/format_reward": 0.0,
|
| 1050 |
+
"step": 80
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"completion_length": 3.75,
|
| 1054 |
+
"epoch": 0.008014644040963735,
|
| 1055 |
+
"grad_norm": 0.02477215975522995,
|
| 1056 |
+
"kl": 0.056396484375,
|
| 1057 |
+
"learning_rate": 9.2e-07,
|
| 1058 |
+
"loss": 0.0023,
|
| 1059 |
+
"reward": 1.0,
|
| 1060 |
+
"reward_std": 0.0,
|
| 1061 |
+
"rewards/accuracy_reward": 1.0,
|
| 1062 |
+
"rewards/format_reward": 0.0,
|
| 1063 |
+
"step": 81
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"completion_length": 2.25,
|
| 1067 |
+
"epoch": 0.008113590263691683,
|
| 1068 |
+
"grad_norm": 57.296180725097656,
|
| 1069 |
+
"kl": 0.0313720703125,
|
| 1070 |
+
"learning_rate": 9.19e-07,
|
| 1071 |
+
"loss": 0.0013,
|
| 1072 |
+
"reward": 0.875,
|
| 1073 |
+
"reward_std": 0.14433756470680237,
|
| 1074 |
+
"rewards/accuracy_reward": 0.875,
|
| 1075 |
+
"rewards/format_reward": 0.0,
|
| 1076 |
+
"step": 82
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"completion_length": 2.75,
|
| 1080 |
+
"epoch": 0.008212536486419631,
|
| 1081 |
+
"grad_norm": 0.0005820893566124141,
|
| 1082 |
+
"kl": 0.030029296875,
|
| 1083 |
+
"learning_rate": 9.18e-07,
|
| 1084 |
+
"loss": 0.0012,
|
| 1085 |
+
"reward": 0.75,
|
| 1086 |
+
"reward_std": 0.0,
|
| 1087 |
+
"rewards/accuracy_reward": 0.75,
|
| 1088 |
+
"rewards/format_reward": 0.0,
|
| 1089 |
+
"step": 83
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"completion_length": 2.75,
|
| 1093 |
+
"epoch": 0.008311482709147578,
|
| 1094 |
+
"grad_norm": 0.007898775860667229,
|
| 1095 |
+
"kl": 0.0718994140625,
|
| 1096 |
+
"learning_rate": 9.17e-07,
|
| 1097 |
+
"loss": 0.0029,
|
| 1098 |
+
"reward": 1.0,
|
| 1099 |
+
"reward_std": 0.0,
|
| 1100 |
+
"rewards/accuracy_reward": 1.0,
|
| 1101 |
+
"rewards/format_reward": 0.0,
|
| 1102 |
+
"step": 84
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"completion_length": 5.25,
|
| 1106 |
+
"epoch": 0.008410428931875526,
|
| 1107 |
+
"grad_norm": 17.927873611450195,
|
| 1108 |
+
"kl": 0.056640625,
|
| 1109 |
+
"learning_rate": 9.16e-07,
|
| 1110 |
+
"loss": 0.0023,
|
| 1111 |
+
"reward": 0.8125,
|
| 1112 |
+
"reward_std": 0.125,
|
| 1113 |
+
"rewards/accuracy_reward": 0.8125,
|
| 1114 |
+
"rewards/format_reward": 0.0,
|
| 1115 |
+
"step": 85
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"completion_length": 2.9375,
|
| 1119 |
+
"epoch": 0.008509375154603474,
|
| 1120 |
+
"grad_norm": 0.6610168814659119,
|
| 1121 |
+
"kl": 0.05419921875,
|
| 1122 |
+
"learning_rate": 9.15e-07,
|
| 1123 |
+
"loss": 0.0022,
|
| 1124 |
+
"reward": 1.0,
|
| 1125 |
+
"reward_std": 0.0,
|
| 1126 |
+
"rewards/accuracy_reward": 1.0,
|
| 1127 |
+
"rewards/format_reward": 0.0,
|
| 1128 |
+
"step": 86
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"completion_length": 6.0625,
|
| 1132 |
+
"epoch": 0.00860832137733142,
|
| 1133 |
+
"grad_norm": 35.296607971191406,
|
| 1134 |
+
"kl": 1.230712890625,
|
| 1135 |
+
"learning_rate": 9.14e-07,
|
| 1136 |
+
"loss": 0.0497,
|
| 1137 |
+
"reward": 0.625,
|
| 1138 |
+
"reward_std": 0.25,
|
| 1139 |
+
"rewards/accuracy_reward": 0.625,
|
| 1140 |
+
"rewards/format_reward": 0.0,
|
| 1141 |
+
"step": 87
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"completion_length": 2.5,
|
| 1145 |
+
"epoch": 0.008707267600059368,
|
| 1146 |
+
"grad_norm": 0.06378056854009628,
|
| 1147 |
+
"kl": 0.06463623046875,
|
| 1148 |
+
"learning_rate": 9.13e-07,
|
| 1149 |
+
"loss": 0.0026,
|
| 1150 |
+
"reward": 1.0,
|
| 1151 |
+
"reward_std": 0.0,
|
| 1152 |
+
"rewards/accuracy_reward": 1.0,
|
| 1153 |
+
"rewards/format_reward": 0.0,
|
| 1154 |
+
"step": 88
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"completion_length": 3.1875,
|
| 1158 |
+
"epoch": 0.008806213822787316,
|
| 1159 |
+
"grad_norm": 227.54002380371094,
|
| 1160 |
+
"kl": 0.4443359375,
|
| 1161 |
+
"learning_rate": 9.12e-07,
|
| 1162 |
+
"loss": 0.0178,
|
| 1163 |
+
"reward": 0.4375,
|
| 1164 |
+
"reward_std": 0.125,
|
| 1165 |
+
"rewards/accuracy_reward": 0.4375,
|
| 1166 |
+
"rewards/format_reward": 0.0,
|
| 1167 |
+
"step": 89
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"completion_length": 2.75,
|
| 1171 |
+
"epoch": 0.008905160045515262,
|
| 1172 |
+
"grad_norm": 0.0024500866420567036,
|
| 1173 |
+
"kl": 0.0645751953125,
|
| 1174 |
+
"learning_rate": 9.109999999999999e-07,
|
| 1175 |
+
"loss": 0.0026,
|
| 1176 |
+
"reward": 0.75,
|
| 1177 |
+
"reward_std": 0.0,
|
| 1178 |
+
"rewards/accuracy_reward": 0.75,
|
| 1179 |
+
"rewards/format_reward": 0.0,
|
| 1180 |
+
"step": 90
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"completion_length": 3.0,
|
| 1184 |
+
"epoch": 0.00900410626824321,
|
| 1185 |
+
"grad_norm": 33.444313049316406,
|
| 1186 |
+
"kl": 0.10693359375,
|
| 1187 |
+
"learning_rate": 9.1e-07,
|
| 1188 |
+
"loss": 0.0043,
|
| 1189 |
+
"reward": 0.9375,
|
| 1190 |
+
"reward_std": 0.125,
|
| 1191 |
+
"rewards/accuracy_reward": 0.9375,
|
| 1192 |
+
"rewards/format_reward": 0.0,
|
| 1193 |
+
"step": 91
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"completion_length": 3.6875,
|
| 1197 |
+
"epoch": 0.009103052490971156,
|
| 1198 |
+
"grad_norm": 19.867097854614258,
|
| 1199 |
+
"kl": 0.14208984375,
|
| 1200 |
+
"learning_rate": 9.09e-07,
|
| 1201 |
+
"loss": 0.0057,
|
| 1202 |
+
"reward": 0.6875,
|
| 1203 |
+
"reward_std": 0.125,
|
| 1204 |
+
"rewards/accuracy_reward": 0.6875,
|
| 1205 |
+
"rewards/format_reward": 0.0,
|
| 1206 |
+
"step": 92
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"completion_length": 3.625,
|
| 1210 |
+
"epoch": 0.009201998713699104,
|
| 1211 |
+
"grad_norm": 3.6420788764953613,
|
| 1212 |
+
"kl": 0.177490234375,
|
| 1213 |
+
"learning_rate": 9.08e-07,
|
| 1214 |
+
"loss": 0.0071,
|
| 1215 |
+
"reward": 0.75,
|
| 1216 |
+
"reward_std": 0.0,
|
| 1217 |
+
"rewards/accuracy_reward": 0.75,
|
| 1218 |
+
"rewards/format_reward": 0.0,
|
| 1219 |
+
"step": 93
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"completion_length": 2.0,
|
| 1223 |
+
"epoch": 0.009300944936427052,
|
| 1224 |
+
"grad_norm": 0.008027822710573673,
|
| 1225 |
+
"kl": 0.13671875,
|
| 1226 |
+
"learning_rate": 9.07e-07,
|
| 1227 |
+
"loss": 0.0055,
|
| 1228 |
+
"reward": 1.0,
|
| 1229 |
+
"reward_std": 0.0,
|
| 1230 |
+
"rewards/accuracy_reward": 1.0,
|
| 1231 |
+
"rewards/format_reward": 0.0,
|
| 1232 |
+
"step": 94
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"completion_length": 3.625,
|
| 1236 |
+
"epoch": 0.009399891159154999,
|
| 1237 |
+
"grad_norm": 51.053592681884766,
|
| 1238 |
+
"kl": 0.162353515625,
|
| 1239 |
+
"learning_rate": 9.06e-07,
|
| 1240 |
+
"loss": 0.0065,
|
| 1241 |
+
"reward": 0.8125,
|
| 1242 |
+
"reward_std": 0.125,
|
| 1243 |
+
"rewards/accuracy_reward": 0.8125,
|
| 1244 |
+
"rewards/format_reward": 0.0,
|
| 1245 |
+
"step": 95
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"completion_length": 2.5,
|
| 1249 |
+
"epoch": 0.009498837381882947,
|
| 1250 |
+
"grad_norm": 0.0023729894310235977,
|
| 1251 |
+
"kl": 0.025390625,
|
| 1252 |
+
"learning_rate": 9.05e-07,
|
| 1253 |
+
"loss": 0.001,
|
| 1254 |
+
"reward": 1.0,
|
| 1255 |
+
"reward_std": 0.0,
|
| 1256 |
+
"rewards/accuracy_reward": 1.0,
|
| 1257 |
+
"rewards/format_reward": 0.0,
|
| 1258 |
+
"step": 96
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"completion_length": 3.0,
|
| 1262 |
+
"epoch": 0.009597783604610895,
|
| 1263 |
+
"grad_norm": 0.1433296650648117,
|
| 1264 |
+
"kl": 0.1759033203125,
|
| 1265 |
+
"learning_rate": 9.039999999999999e-07,
|
| 1266 |
+
"loss": 0.0071,
|
| 1267 |
+
"reward": 0.75,
|
| 1268 |
+
"reward_std": 0.0,
|
| 1269 |
+
"rewards/accuracy_reward": 0.75,
|
| 1270 |
+
"rewards/format_reward": 0.0,
|
| 1271 |
+
"step": 97
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"completion_length": 3.25,
|
| 1275 |
+
"epoch": 0.009696729827338841,
|
| 1276 |
+
"grad_norm": 46.357540130615234,
|
| 1277 |
+
"kl": 0.344024658203125,
|
| 1278 |
+
"learning_rate": 9.03e-07,
|
| 1279 |
+
"loss": 0.0137,
|
| 1280 |
+
"reward": 0.9375,
|
| 1281 |
+
"reward_std": 0.125,
|
| 1282 |
+
"rewards/accuracy_reward": 0.9375,
|
| 1283 |
+
"rewards/format_reward": 0.0,
|
| 1284 |
+
"step": 98
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"completion_length": 4.5625,
|
| 1288 |
+
"epoch": 0.009795676050066789,
|
| 1289 |
+
"grad_norm": 25.5620059967041,
|
| 1290 |
+
"kl": 0.1181640625,
|
| 1291 |
+
"learning_rate": 9.02e-07,
|
| 1292 |
+
"loss": 0.0047,
|
| 1293 |
+
"reward": 0.625,
|
| 1294 |
+
"reward_std": 0.25,
|
| 1295 |
+
"rewards/accuracy_reward": 0.625,
|
| 1296 |
+
"rewards/format_reward": 0.0,
|
| 1297 |
+
"step": 99
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"completion_length": 3.8125,
|
| 1301 |
+
"epoch": 0.009894622272794735,
|
| 1302 |
+
"grad_norm": 31.894678115844727,
|
| 1303 |
+
"kl": 0.300445556640625,
|
| 1304 |
+
"learning_rate": 9.01e-07,
|
| 1305 |
+
"loss": 0.012,
|
| 1306 |
+
"reward": 0.3125,
|
| 1307 |
+
"reward_std": 0.125,
|
| 1308 |
+
"rewards/accuracy_reward": 0.3125,
|
| 1309 |
+
"rewards/format_reward": 0.0,
|
| 1310 |
+
"step": 100
|
| 1311 |
+
}
|
| 1312 |
+
],
|
| 1313 |
+
"logging_steps": 1,
|
| 1314 |
+
"max_steps": 1000,
|
| 1315 |
+
"num_input_tokens_seen": 0,
|
| 1316 |
+
"num_train_epochs": 1,
|
| 1317 |
+
"save_steps": 100,
|
| 1318 |
+
"stateful_callbacks": {
|
| 1319 |
+
"TrainerControl": {
|
| 1320 |
+
"args": {
|
| 1321 |
+
"should_epoch_stop": false,
|
| 1322 |
+
"should_evaluate": false,
|
| 1323 |
+
"should_log": false,
|
| 1324 |
+
"should_save": true,
|
| 1325 |
+
"should_training_stop": false
|
| 1326 |
+
},
|
| 1327 |
+
"attributes": {}
|
| 1328 |
+
}
|
| 1329 |
+
},
|
| 1330 |
+
"total_flos": 0.0,
|
| 1331 |
+
"train_batch_size": 1,
|
| 1332 |
+
"trial_name": null,
|
| 1333 |
+
"trial_params": null
|
| 1334 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1d0ba6ded401880180ab6835c807229a4439da32a3caf4936063f399388c048
|
| 3 |
+
size 7864
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|