her_cur_graph_sft_e0
Browse files- .gitattributes +1 -0
- her_cur_graph_sft_e0/.gitattributes +36 -0
- her_cur_graph_sft_e0/all_results.json +8 -0
- her_cur_graph_sft_e0/chat_template.jinja +120 -0
- her_cur_graph_sft_e0/config.json +70 -0
- her_cur_graph_sft_e0/generation_config.json +14 -0
- her_cur_graph_sft_e0/model.safetensors +3 -0
- her_cur_graph_sft_e0/processor_config.json +60 -0
- her_cur_graph_sft_e0/sft.yaml +53 -0
- her_cur_graph_sft_e0/tokenizer.json +3 -0
- her_cur_graph_sft_e0/tokenizer_config.json +32 -0
- her_cur_graph_sft_e0/train_results.json +8 -0
- her_cur_graph_sft_e0/trainer_state.json +400 -0
.gitattributes
CHANGED
|
@@ -47,3 +47,4 @@ her_unfiltered_epoch_0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 47 |
her_unfiltered_sft_e0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 48 |
her_cur_sft_e0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 49 |
her_cur_60_sft_e0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 47 |
her_unfiltered_sft_e0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 48 |
her_cur_sft_e0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 49 |
her_cur_60_sft_e0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
her_cur_graph_sft_e0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
her_cur_graph_sft_e0/.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz 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
|
her_cur_graph_sft_e0/all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.4453900709219858,
|
| 3 |
+
"total_flos": 65016658264064.0,
|
| 4 |
+
"train_loss": 0.637478593751496,
|
| 5 |
+
"train_runtime": 1290.7953,
|
| 6 |
+
"train_samples_per_second": 6.322,
|
| 7 |
+
"train_steps_per_second": 0.395
|
| 8 |
+
}
|
her_cur_graph_sft_e0/chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# 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>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\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" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
her_cur_graph_sft_e0/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_size": 4096,
|
| 9 |
+
"image_token_id": 151655,
|
| 10 |
+
"model_type": "qwen3_vl",
|
| 11 |
+
"pad_token_id": 151643,
|
| 12 |
+
"text_config": {
|
| 13 |
+
"attention_bias": false,
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"bos_token_id": 151643,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 151645,
|
| 18 |
+
"head_dim": 128,
|
| 19 |
+
"hidden_act": "silu",
|
| 20 |
+
"hidden_size": 4096,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 12288,
|
| 23 |
+
"max_position_embeddings": 262144,
|
| 24 |
+
"model_type": "qwen3_vl_text",
|
| 25 |
+
"num_attention_heads": 32,
|
| 26 |
+
"num_hidden_layers": 36,
|
| 27 |
+
"num_key_value_heads": 8,
|
| 28 |
+
"pad_token_id": null,
|
| 29 |
+
"rms_norm_eps": 1e-06,
|
| 30 |
+
"rope_parameters": {
|
| 31 |
+
"mrope_interleaved": true,
|
| 32 |
+
"mrope_section": [
|
| 33 |
+
24,
|
| 34 |
+
20,
|
| 35 |
+
20
|
| 36 |
+
],
|
| 37 |
+
"rope_theta": 5000000,
|
| 38 |
+
"rope_type": "default"
|
| 39 |
+
},
|
| 40 |
+
"use_cache": false,
|
| 41 |
+
"vocab_size": 151936
|
| 42 |
+
},
|
| 43 |
+
"tie_word_embeddings": false,
|
| 44 |
+
"transformers_version": "5.8.0",
|
| 45 |
+
"use_cache": false,
|
| 46 |
+
"video_token_id": 151656,
|
| 47 |
+
"vision_config": {
|
| 48 |
+
"deepstack_visual_indexes": [
|
| 49 |
+
8,
|
| 50 |
+
16,
|
| 51 |
+
24
|
| 52 |
+
],
|
| 53 |
+
"depth": 27,
|
| 54 |
+
"dtype": "bfloat16",
|
| 55 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 56 |
+
"hidden_size": 1152,
|
| 57 |
+
"in_channels": 3,
|
| 58 |
+
"initializer_range": 0.02,
|
| 59 |
+
"intermediate_size": 4304,
|
| 60 |
+
"model_type": "qwen3_vl_vision",
|
| 61 |
+
"num_heads": 16,
|
| 62 |
+
"num_position_embeddings": 2304,
|
| 63 |
+
"out_hidden_size": 4096,
|
| 64 |
+
"patch_size": 16,
|
| 65 |
+
"spatial_merge_size": 2,
|
| 66 |
+
"temporal_patch_size": 2
|
| 67 |
+
},
|
| 68 |
+
"vision_end_token_id": 151653,
|
| 69 |
+
"vision_start_token_id": 151652
|
| 70 |
+
}
|
her_cur_graph_sft_e0/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.0,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "5.8.0"
|
| 14 |
+
}
|
her_cur_graph_sft_e0/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9662b7eb5f1af050374e619b7b83944cc4c1f74cebc0fe5272dfb7921e694fb0
|
| 3 |
+
size 17534340584
|
her_cur_graph_sft_e0/processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
her_cur_graph_sft_e0/sft.yaml
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# LLaMA-Factory full-parameter SFT of Qwen3-VL-8B-Instruct on one HER-final dataset.
|
| 2 |
+
# Four L40S (46 GB), one run at a time: DeepSpeed ZeRO-3 with optimizer offload to host
|
| 3 |
+
# RAM (~130 GB per run, so two runs do not fit in 372 GB); the vision tower and projector
|
| 4 |
+
# stay frozen (LLaMA-Factory's default for VLMs), the LLM trains.
|
| 5 |
+
# Filled per run by launch_sft.sh: her_final_filtered_b801010_gscene, /root/sft_data/her_final_filtered_b801010_gscene_k1024, /root/runs/her_final_filtered_b801010_gscene.
|
| 6 |
+
### model
|
| 7 |
+
model_name_or_path: /root/models/Qwen3-VL-8B-Instruct
|
| 8 |
+
template: qwen3_vl_nothink
|
| 9 |
+
trust_remote_code: true
|
| 10 |
+
image_max_pixels: 65536 # frames are 256x256 already; never upscale
|
| 11 |
+
image_min_pixels: 4096
|
| 12 |
+
|
| 13 |
+
### method
|
| 14 |
+
stage: sft
|
| 15 |
+
do_train: true
|
| 16 |
+
finetuning_type: full
|
| 17 |
+
freeze_vision_tower: true
|
| 18 |
+
freeze_multi_modal_projector: true
|
| 19 |
+
freeze_language_model: false
|
| 20 |
+
deepspeed: /root/LlamaFactory/examples/deepspeed/ds_z3_config.json
|
| 21 |
+
|
| 22 |
+
### dataset
|
| 23 |
+
dataset: her_final_filtered_b801010_gscene
|
| 24 |
+
dataset_dir: /root/sft_data/her_final_filtered_b801010_gscene_k1024
|
| 25 |
+
media_dir: /root/viewagent_private
|
| 26 |
+
cutoff_len: 8192
|
| 27 |
+
overwrite_cache: true
|
| 28 |
+
preprocessing_num_workers: 16
|
| 29 |
+
dataloader_num_workers: 4
|
| 30 |
+
|
| 31 |
+
### output
|
| 32 |
+
output_dir: /root/runs/her_final_filtered_b801010_gscene
|
| 33 |
+
logging_steps: 10
|
| 34 |
+
save_strategy: steps
|
| 35 |
+
save_steps: 170
|
| 36 |
+
save_total_limit: 3
|
| 37 |
+
save_only_model: true
|
| 38 |
+
plot_loss: true
|
| 39 |
+
overwrite_output_dir: true
|
| 40 |
+
report_to: none
|
| 41 |
+
|
| 42 |
+
### train
|
| 43 |
+
per_device_train_batch_size: 1
|
| 44 |
+
gradient_accumulation_steps: 2
|
| 45 |
+
max_steps: 510 # equal update budget for both runs (~1 pass over 8,173 rows)
|
| 46 |
+
learning_rate: 1.0e-5
|
| 47 |
+
lr_scheduler_type: cosine
|
| 48 |
+
warmup_ratio: 0.03
|
| 49 |
+
weight_decay: 0.01
|
| 50 |
+
bf16: true
|
| 51 |
+
gradient_checkpointing: true
|
| 52 |
+
ddp_timeout: 180000000
|
| 53 |
+
seed: 0
|
her_cur_graph_sft_e0/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
+
size 11422650
|
her_cur_graph_sft_e0/tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": true,
|
| 24 |
+
"local_files_only": false,
|
| 25 |
+
"model_max_length": 262144,
|
| 26 |
+
"pad_token": "<|endoftext|>",
|
| 27 |
+
"padding_side": "right",
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"split_special_tokens": false,
|
| 30 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 31 |
+
"unk_token": null
|
| 32 |
+
}
|
her_cur_graph_sft_e0/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.4453900709219858,
|
| 3 |
+
"total_flos": 65016658264064.0,
|
| 4 |
+
"train_loss": 0.637478593751496,
|
| 5 |
+
"train_runtime": 1290.7953,
|
| 6 |
+
"train_samples_per_second": 6.322,
|
| 7 |
+
"train_steps_per_second": 0.395
|
| 8 |
+
}
|
her_cur_graph_sft_e0/trainer_state.json
ADDED
|
@@ -0,0 +1,400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.4453900709219858,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 510,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.028368794326241134,
|
| 14 |
+
"grad_norm": 6.132689638128779,
|
| 15 |
+
"learning_rate": 5.625e-06,
|
| 16 |
+
"loss": 0.8627668380737304,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.05673758865248227,
|
| 21 |
+
"grad_norm": 4.085870077517127,
|
| 22 |
+
"learning_rate": 9.999090054896397e-06,
|
| 23 |
+
"loss": 0.7853320121765137,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0851063829787234,
|
| 28 |
+
"grad_norm": 2.9311626403487248,
|
| 29 |
+
"learning_rate": 9.98292246503335e-06,
|
| 30 |
+
"loss": 0.7662538528442383,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.11347517730496454,
|
| 35 |
+
"grad_norm": 3.9220451893963038,
|
| 36 |
+
"learning_rate": 9.946609117610508e-06,
|
| 37 |
+
"loss": 0.7464823722839355,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.14184397163120568,
|
| 42 |
+
"grad_norm": 2.9684800206911692,
|
| 43 |
+
"learning_rate": 9.89029682604881e-06,
|
| 44 |
+
"loss": 0.7260494709014893,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1702127659574468,
|
| 49 |
+
"grad_norm": 3.1531860626211006,
|
| 50 |
+
"learning_rate": 9.814213258705813e-06,
|
| 51 |
+
"loss": 0.727284288406372,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.19858156028368795,
|
| 56 |
+
"grad_norm": 2.6916704816297083,
|
| 57 |
+
"learning_rate": 9.71866601842156e-06,
|
| 58 |
+
"loss": 0.7098471641540527,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22695035460992907,
|
| 63 |
+
"grad_norm": 2.752954212510242,
|
| 64 |
+
"learning_rate": 9.604041398892528e-06,
|
| 65 |
+
"loss": 0.7180390357971191,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2553191489361702,
|
| 70 |
+
"grad_norm": 2.4868681686112937,
|
| 71 |
+
"learning_rate": 9.470802822901558e-06,
|
| 72 |
+
"loss": 0.7006837844848632,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.28368794326241137,
|
| 77 |
+
"grad_norm": 2.3827057558743903,
|
| 78 |
+
"learning_rate": 9.31948896871795e-06,
|
| 79 |
+
"loss": 0.6941119194030761,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3120567375886525,
|
| 84 |
+
"grad_norm": 2.6046665445343726,
|
| 85 |
+
"learning_rate": 9.150711592242627e-06,
|
| 86 |
+
"loss": 0.7072453975677491,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3404255319148936,
|
| 91 |
+
"grad_norm": 2.493772052870914,
|
| 92 |
+
"learning_rate": 8.965153053703325e-06,
|
| 93 |
+
"loss": 0.6780774116516113,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.36879432624113473,
|
| 98 |
+
"grad_norm": 2.175076327448151,
|
| 99 |
+
"learning_rate": 8.763563558899317e-06,
|
| 100 |
+
"loss": 0.71751708984375,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3971631205673759,
|
| 105 |
+
"grad_norm": 2.6187369664726274,
|
| 106 |
+
"learning_rate": 8.546758126149148e-06,
|
| 107 |
+
"loss": 0.7045199871063232,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.425531914893617,
|
| 112 |
+
"grad_norm": 2.315371206983041,
|
| 113 |
+
"learning_rate": 8.315613291203977e-06,
|
| 114 |
+
"loss": 0.6888079643249512,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.45390070921985815,
|
| 119 |
+
"grad_norm": 2.464256455225966,
|
| 120 |
+
"learning_rate": 8.071063563448341e-06,
|
| 121 |
+
"loss": 0.7159054756164551,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.48226950354609927,
|
| 126 |
+
"grad_norm": 2.4889396952877467,
|
| 127 |
+
"learning_rate": 7.814097647715848e-06,
|
| 128 |
+
"loss": 0.6865799427032471,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.5106382978723404,
|
| 133 |
+
"grad_norm": 2.11130791547089,
|
| 134 |
+
"learning_rate": 7.5457544469948164e-06,
|
| 135 |
+
"loss": 0.6901509284973144,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.5390070921985816,
|
| 140 |
+
"grad_norm": 2.2122281966218673,
|
| 141 |
+
"learning_rate": 7.267118862184767e-06,
|
| 142 |
+
"loss": 0.685690975189209,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5673758865248227,
|
| 147 |
+
"grad_norm": 2.1210129639541146,
|
| 148 |
+
"learning_rate": 6.9793174058851805e-06,
|
| 149 |
+
"loss": 0.6467048645019531,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.5957446808510638,
|
| 154 |
+
"grad_norm": 2.2055793809452515,
|
| 155 |
+
"learning_rate": 6.683513647949826e-06,
|
| 156 |
+
"loss": 0.6823623657226563,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.624113475177305,
|
| 161 |
+
"grad_norm": 2.1671413171317133,
|
| 162 |
+
"learning_rate": 6.38090351122006e-06,
|
| 163 |
+
"loss": 0.6667772769927979,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6524822695035462,
|
| 168 |
+
"grad_norm": 2.1529583341759886,
|
| 169 |
+
"learning_rate": 6.072710436456293e-06,
|
| 170 |
+
"loss": 0.6731852531433106,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.6808510638297872,
|
| 175 |
+
"grad_norm": 2.1785919543024117,
|
| 176 |
+
"learning_rate": 5.760180436015604e-06,
|
| 177 |
+
"loss": 0.6794678688049316,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.7092198581560284,
|
| 182 |
+
"grad_norm": 2.105733035779225,
|
| 183 |
+
"learning_rate": 5.444577056273284e-06,
|
| 184 |
+
"loss": 0.6663173198699951,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.7375886524822695,
|
| 189 |
+
"grad_norm": 2.298597670477467,
|
| 190 |
+
"learning_rate": 5.1271762691550375e-06,
|
| 191 |
+
"loss": 0.6715749263763428,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.7659574468085106,
|
| 196 |
+
"grad_norm": 2.078988356255949,
|
| 197 |
+
"learning_rate": 4.809261313433176e-06,
|
| 198 |
+
"loss": 0.663114356994629,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7943262411347518,
|
| 203 |
+
"grad_norm": 2.1703594387224463,
|
| 204 |
+
"learning_rate": 4.492117506643256e-06,
|
| 205 |
+
"loss": 0.6314117431640625,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.8226950354609929,
|
| 210 |
+
"grad_norm": 2.281408769492139,
|
| 211 |
+
"learning_rate": 4.17702704859633e-06,
|
| 212 |
+
"loss": 0.660633659362793,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.851063829787234,
|
| 217 |
+
"grad_norm": 2.1955709005214086,
|
| 218 |
+
"learning_rate": 3.865263837496072e-06,
|
| 219 |
+
"loss": 0.6319204330444336,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.8794326241134752,
|
| 224 |
+
"grad_norm": 2.194361166260252,
|
| 225 |
+
"learning_rate": 3.5580883196189265e-06,
|
| 226 |
+
"loss": 0.6750846862792969,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.9078014184397163,
|
| 231 |
+
"grad_norm": 2.1226453359752946,
|
| 232 |
+
"learning_rate": 3.256742393379909e-06,
|
| 233 |
+
"loss": 0.667458438873291,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.9361702127659575,
|
| 238 |
+
"grad_norm": 1.9487696196851718,
|
| 239 |
+
"learning_rate": 2.9624443883866403e-06,
|
| 240 |
+
"loss": 0.6458759307861328,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.9645390070921985,
|
| 245 |
+
"grad_norm": 1.9521276402087668,
|
| 246 |
+
"learning_rate": 2.6763841397811576e-06,
|
| 247 |
+
"loss": 0.6739749908447266,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.9929078014184397,
|
| 252 |
+
"grad_norm": 2.0380313282400713,
|
| 253 |
+
"learning_rate": 2.3997181777836955e-06,
|
| 254 |
+
"loss": 0.6208441734313965,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0198581560283688,
|
| 259 |
+
"grad_norm": 1.8347238465517284,
|
| 260 |
+
"learning_rate": 2.1335650518869555e-06,
|
| 261 |
+
"loss": 0.5579001426696777,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.04822695035461,
|
| 266 |
+
"grad_norm": 2.190975391390031,
|
| 267 |
+
"learning_rate": 1.8790008086049534e-06,
|
| 268 |
+
"loss": 0.5388619899749756,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.076595744680851,
|
| 273 |
+
"grad_norm": 1.9047399754898637,
|
| 274 |
+
"learning_rate": 1.6370546410597066e-06,
|
| 275 |
+
"loss": 0.5155890464782715,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1049645390070921,
|
| 280 |
+
"grad_norm": 2.3056979394946384,
|
| 281 |
+
"learning_rate": 1.4087047279943267e-06,
|
| 282 |
+
"loss": 0.504695987701416,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.1333333333333333,
|
| 287 |
+
"grad_norm": 2.053625759379908,
|
| 288 |
+
"learning_rate": 1.1948742790352342e-06,
|
| 289 |
+
"loss": 0.5041792869567872,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.1617021276595745,
|
| 294 |
+
"grad_norm": 2.0725689885741834,
|
| 295 |
+
"learning_rate": 9.964278021923107e-07,
|
| 296 |
+
"loss": 0.5126749992370605,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.1900709219858157,
|
| 301 |
+
"grad_norm": 2.167639691066008,
|
| 302 |
+
"learning_rate": 8.141676086873574e-07,
|
| 303 |
+
"loss": 0.5149785995483398,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2184397163120568,
|
| 308 |
+
"grad_norm": 1.8964951907525895,
|
| 309 |
+
"learning_rate": 6.488305692417074e-07,
|
| 310 |
+
"loss": 0.5093233585357666,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.2468085106382978,
|
| 315 |
+
"grad_norm": 2.225599987027735,
|
| 316 |
+
"learning_rate": 5.010851349371704e-07,
|
| 317 |
+
"loss": 0.5300761222839355,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.275177304964539,
|
| 322 |
+
"grad_norm": 2.015578617004842,
|
| 323 |
+
"learning_rate": 3.715286346948671e-07,
|
| 324 |
+
"loss": 0.5126487731933593,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3035460992907801,
|
| 329 |
+
"grad_norm": 1.9465678878333235,
|
| 330 |
+
"learning_rate": 2.6068486029813154e-07,
|
| 331 |
+
"loss": 0.5156026840209961,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.3319148936170213,
|
| 336 |
+
"grad_norm": 1.8767359860835502,
|
| 337 |
+
"learning_rate": 1.69001948723142e-07,
|
| 338 |
+
"loss": 0.5065423488616944,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.3602836879432625,
|
| 343 |
+
"grad_norm": 2.106599888072292,
|
| 344 |
+
"learning_rate": 9.685057033892998e-08,
|
| 345 |
+
"loss": 0.49912776947021487,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.3886524822695034,
|
| 350 |
+
"grad_norm": 1.9293663183097982,
|
| 351 |
+
"learning_rate": 4.45224303018027e-08,
|
| 352 |
+
"loss": 0.5037864685058594,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.4170212765957446,
|
| 357 |
+
"grad_norm": 1.9924790289376344,
|
| 358 |
+
"learning_rate": 1.2229089202987487e-08,
|
| 359 |
+
"loss": 0.5050028800964356,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.4453900709219858,
|
| 364 |
+
"grad_norm": 1.966863518897763,
|
| 365 |
+
"learning_rate": 1.011077375662195e-10,
|
| 366 |
+
"loss": 0.5123636245727539,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.4453900709219858,
|
| 371 |
+
"step": 510,
|
| 372 |
+
"total_flos": 65016658264064.0,
|
| 373 |
+
"train_loss": 0.637478593751496,
|
| 374 |
+
"train_runtime": 1290.7953,
|
| 375 |
+
"train_samples_per_second": 6.322,
|
| 376 |
+
"train_steps_per_second": 0.395
|
| 377 |
+
}
|
| 378 |
+
],
|
| 379 |
+
"logging_steps": 10,
|
| 380 |
+
"max_steps": 510,
|
| 381 |
+
"num_input_tokens_seen": 0,
|
| 382 |
+
"num_train_epochs": 2,
|
| 383 |
+
"save_steps": 170,
|
| 384 |
+
"stateful_callbacks": {
|
| 385 |
+
"TrainerControl": {
|
| 386 |
+
"args": {
|
| 387 |
+
"should_epoch_stop": false,
|
| 388 |
+
"should_evaluate": false,
|
| 389 |
+
"should_log": false,
|
| 390 |
+
"should_save": true,
|
| 391 |
+
"should_training_stop": true
|
| 392 |
+
},
|
| 393 |
+
"attributes": {}
|
| 394 |
+
}
|
| 395 |
+
},
|
| 396 |
+
"total_flos": 65016658264064.0,
|
| 397 |
+
"train_batch_size": 1,
|
| 398 |
+
"trial_name": null,
|
| 399 |
+
"trial_params": null
|
| 400 |
+
}
|