Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- chat_template.jinja +154 -0
- config.json +113 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- processor_config.json +60 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
- trainer_state.json +2743 -0
- training_args.bin +3 -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
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "float32",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"hidden_size": 4096,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_type": "qwen3_5",
|
| 10 |
+
"pad_token_id": 248044,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_output_gate": true,
|
| 15 |
+
"bos_token_id": null,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 248044,
|
| 18 |
+
"full_attention_interval": 4,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 4096,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 12288,
|
| 24 |
+
"layer_types": [
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention"
|
| 57 |
+
],
|
| 58 |
+
"linear_conv_kernel_dim": 4,
|
| 59 |
+
"linear_key_head_dim": 128,
|
| 60 |
+
"linear_num_key_heads": 16,
|
| 61 |
+
"linear_num_value_heads": 32,
|
| 62 |
+
"linear_value_head_dim": 128,
|
| 63 |
+
"mamba_ssm_dtype": "float32",
|
| 64 |
+
"max_position_embeddings": 262144,
|
| 65 |
+
"mlp_only_layers": [],
|
| 66 |
+
"model_type": "qwen3_5_text",
|
| 67 |
+
"mtp_num_hidden_layers": 1,
|
| 68 |
+
"mtp_use_dedicated_embeddings": false,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_hidden_layers": 32,
|
| 71 |
+
"num_key_value_heads": 4,
|
| 72 |
+
"pad_token_id": null,
|
| 73 |
+
"partial_rotary_factor": 0.25,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_parameters": {
|
| 76 |
+
"mrope_interleaved": true,
|
| 77 |
+
"mrope_section": [
|
| 78 |
+
11,
|
| 79 |
+
11,
|
| 80 |
+
10
|
| 81 |
+
],
|
| 82 |
+
"partial_rotary_factor": 0.25,
|
| 83 |
+
"rope_theta": 10000000,
|
| 84 |
+
"rope_type": "default"
|
| 85 |
+
},
|
| 86 |
+
"tie_word_embeddings": false,
|
| 87 |
+
"use_cache": false,
|
| 88 |
+
"vocab_size": 248320
|
| 89 |
+
},
|
| 90 |
+
"tie_word_embeddings": false,
|
| 91 |
+
"transformers_version": "5.5.3",
|
| 92 |
+
"use_cache": false,
|
| 93 |
+
"video_token_id": 248057,
|
| 94 |
+
"vision_config": {
|
| 95 |
+
"deepstack_visual_indexes": [],
|
| 96 |
+
"depth": 27,
|
| 97 |
+
"dtype": "bfloat16",
|
| 98 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
+
"hidden_size": 1152,
|
| 100 |
+
"in_channels": 3,
|
| 101 |
+
"initializer_range": 0.02,
|
| 102 |
+
"intermediate_size": 4304,
|
| 103 |
+
"model_type": "qwen3_5",
|
| 104 |
+
"num_heads": 16,
|
| 105 |
+
"num_position_embeddings": 2304,
|
| 106 |
+
"out_hidden_size": 4096,
|
| 107 |
+
"patch_size": 16,
|
| 108 |
+
"spatial_merge_size": 2,
|
| 109 |
+
"temporal_patch_size": 2
|
| 110 |
+
},
|
| 111 |
+
"vision_end_token_id": 248054,
|
| 112 |
+
"vision_start_token_id": 248053
|
| 113 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248046,
|
| 5 |
+
248044
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 248044,
|
| 8 |
+
"transformers_version": "5.5.3",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c19e2af7b4f7027b2f01876e9bdbb7cf933f61b5d345a5dd80d5dc832e5e97e
|
| 3 |
+
size 37639354416
|
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 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f90a5f2ed6d30ebfd28acaade74bb026468970204fa5b02eda67c20566c1a648
|
| 3 |
+
size 14709
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e193eae9a0c8ba066f9a575e6dc12f8915bce294cf84caff1060833bddca3d7b
|
| 3 |
+
size 1529
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": true,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "TokenizersBackend",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2743 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 774,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.007751937984496124,
|
| 14 |
+
"grad_norm": 2.372762680053711,
|
| 15 |
+
"learning_rate": 1.935483870967742e-07,
|
| 16 |
+
"loss": 4.068140983581543,
|
| 17 |
+
"step": 2
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.015503875968992248,
|
| 21 |
+
"grad_norm": 0.1989186704158783,
|
| 22 |
+
"learning_rate": 5.806451612903226e-07,
|
| 23 |
+
"loss": 2.024549722671509,
|
| 24 |
+
"step": 4
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.023255813953488372,
|
| 28 |
+
"grad_norm": 0.287252277135849,
|
| 29 |
+
"learning_rate": 9.67741935483871e-07,
|
| 30 |
+
"loss": 1.9417322874069214,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.031007751937984496,
|
| 35 |
+
"grad_norm": 0.3818705379962921,
|
| 36 |
+
"learning_rate": 1.3548387096774193e-06,
|
| 37 |
+
"loss": 1.9495620727539062,
|
| 38 |
+
"step": 8
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03875968992248062,
|
| 42 |
+
"grad_norm": 0.15045583248138428,
|
| 43 |
+
"learning_rate": 1.7419354838709678e-06,
|
| 44 |
+
"loss": 2.319340705871582,
|
| 45 |
+
"step": 10
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.046511627906976744,
|
| 49 |
+
"grad_norm": 2.149204969406128,
|
| 50 |
+
"learning_rate": 2.129032258064516e-06,
|
| 51 |
+
"loss": 3.75003981590271,
|
| 52 |
+
"step": 12
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.05426356589147287,
|
| 56 |
+
"grad_norm": 0.2591269314289093,
|
| 57 |
+
"learning_rate": 2.516129032258065e-06,
|
| 58 |
+
"loss": 1.8552712202072144,
|
| 59 |
+
"step": 14
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06201550387596899,
|
| 63 |
+
"grad_norm": 0.7406859397888184,
|
| 64 |
+
"learning_rate": 2.9032258064516128e-06,
|
| 65 |
+
"loss": 2.239339590072632,
|
| 66 |
+
"step": 16
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.06976744186046512,
|
| 70 |
+
"grad_norm": 0.9925192594528198,
|
| 71 |
+
"learning_rate": 3.2903225806451615e-06,
|
| 72 |
+
"loss": 2.0903704166412354,
|
| 73 |
+
"step": 18
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.07751937984496124,
|
| 77 |
+
"grad_norm": 0.29998043179512024,
|
| 78 |
+
"learning_rate": 3.6774193548387094e-06,
|
| 79 |
+
"loss": 2.208868980407715,
|
| 80 |
+
"step": 20
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08527131782945736,
|
| 84 |
+
"grad_norm": 2.925621747970581,
|
| 85 |
+
"learning_rate": 4.064516129032259e-06,
|
| 86 |
+
"loss": 3.090871810913086,
|
| 87 |
+
"step": 22
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09302325581395349,
|
| 91 |
+
"grad_norm": 0.2913108766078949,
|
| 92 |
+
"learning_rate": 4.451612903225806e-06,
|
| 93 |
+
"loss": 1.8751976490020752,
|
| 94 |
+
"step": 24
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.10077519379844961,
|
| 98 |
+
"grad_norm": 0.645453929901123,
|
| 99 |
+
"learning_rate": 4.838709677419355e-06,
|
| 100 |
+
"loss": 1.761456847190857,
|
| 101 |
+
"step": 26
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.10852713178294573,
|
| 105 |
+
"grad_norm": 0.7114430665969849,
|
| 106 |
+
"learning_rate": 5.2258064516129035e-06,
|
| 107 |
+
"loss": 1.8018805980682373,
|
| 108 |
+
"step": 28
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.11627906976744186,
|
| 112 |
+
"grad_norm": 0.7619907259941101,
|
| 113 |
+
"learning_rate": 5.612903225806452e-06,
|
| 114 |
+
"loss": 1.5239174365997314,
|
| 115 |
+
"step": 30
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.12403100775193798,
|
| 119 |
+
"grad_norm": 0.16530756652355194,
|
| 120 |
+
"learning_rate": 6e-06,
|
| 121 |
+
"loss": 1.5915422439575195,
|
| 122 |
+
"step": 32
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.13178294573643412,
|
| 126 |
+
"grad_norm": 0.16290850937366486,
|
| 127 |
+
"learning_rate": 6.3870967741935485e-06,
|
| 128 |
+
"loss": 2.3932559490203857,
|
| 129 |
+
"step": 34
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.13953488372093023,
|
| 133 |
+
"grad_norm": 0.23374152183532715,
|
| 134 |
+
"learning_rate": 6.774193548387097e-06,
|
| 135 |
+
"loss": 1.4996192455291748,
|
| 136 |
+
"step": 36
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.14728682170542637,
|
| 140 |
+
"grad_norm": 0.26606833934783936,
|
| 141 |
+
"learning_rate": 7.161290322580645e-06,
|
| 142 |
+
"loss": 1.2402312755584717,
|
| 143 |
+
"step": 38
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.15503875968992248,
|
| 147 |
+
"grad_norm": 0.12572336196899414,
|
| 148 |
+
"learning_rate": 7.548387096774193e-06,
|
| 149 |
+
"loss": 1.5890406370162964,
|
| 150 |
+
"step": 40
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.16279069767441862,
|
| 154 |
+
"grad_norm": 0.7024409770965576,
|
| 155 |
+
"learning_rate": 7.935483870967743e-06,
|
| 156 |
+
"loss": 1.1217167377471924,
|
| 157 |
+
"step": 42
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.17054263565891473,
|
| 161 |
+
"grad_norm": 0.1792139858007431,
|
| 162 |
+
"learning_rate": 8.32258064516129e-06,
|
| 163 |
+
"loss": 1.3888567686080933,
|
| 164 |
+
"step": 44
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.17829457364341086,
|
| 168 |
+
"grad_norm": 0.16807198524475098,
|
| 169 |
+
"learning_rate": 8.70967741935484e-06,
|
| 170 |
+
"loss": 1.746845006942749,
|
| 171 |
+
"step": 46
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.18604651162790697,
|
| 175 |
+
"grad_norm": 0.1879073679447174,
|
| 176 |
+
"learning_rate": 9.096774193548387e-06,
|
| 177 |
+
"loss": 0.9335119128227234,
|
| 178 |
+
"step": 48
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1937984496124031,
|
| 182 |
+
"grad_norm": 0.2711307406425476,
|
| 183 |
+
"learning_rate": 9.483870967741934e-06,
|
| 184 |
+
"loss": 0.6987147331237793,
|
| 185 |
+
"step": 50
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.20155038759689922,
|
| 189 |
+
"grad_norm": 0.1467754989862442,
|
| 190 |
+
"learning_rate": 9.870967741935485e-06,
|
| 191 |
+
"loss": 1.1381912231445312,
|
| 192 |
+
"step": 52
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.20930232558139536,
|
| 196 |
+
"grad_norm": 0.5655927062034607,
|
| 197 |
+
"learning_rate": 1.0258064516129032e-05,
|
| 198 |
+
"loss": 0.581324577331543,
|
| 199 |
+
"step": 54
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.21705426356589147,
|
| 203 |
+
"grad_norm": 0.503146767616272,
|
| 204 |
+
"learning_rate": 1.0645161290322582e-05,
|
| 205 |
+
"loss": 1.3841195106506348,
|
| 206 |
+
"step": 56
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.2248062015503876,
|
| 210 |
+
"grad_norm": 0.7577893733978271,
|
| 211 |
+
"learning_rate": 1.1032258064516129e-05,
|
| 212 |
+
"loss": 1.4041730165481567,
|
| 213 |
+
"step": 58
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.23255813953488372,
|
| 217 |
+
"grad_norm": 0.7149530649185181,
|
| 218 |
+
"learning_rate": 1.1419354838709677e-05,
|
| 219 |
+
"loss": 1.1680717468261719,
|
| 220 |
+
"step": 60
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.24031007751937986,
|
| 224 |
+
"grad_norm": 0.14106588065624237,
|
| 225 |
+
"learning_rate": 1.1806451612903226e-05,
|
| 226 |
+
"loss": 1.2515933513641357,
|
| 227 |
+
"step": 62
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.24806201550387597,
|
| 231 |
+
"grad_norm": 0.19908978044986725,
|
| 232 |
+
"learning_rate": 1.2193548387096773e-05,
|
| 233 |
+
"loss": 1.310453176498413,
|
| 234 |
+
"step": 64
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2558139534883721,
|
| 238 |
+
"grad_norm": 0.2537965476512909,
|
| 239 |
+
"learning_rate": 1.2580645161290324e-05,
|
| 240 |
+
"loss": 1.2055346965789795,
|
| 241 |
+
"step": 66
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.26356589147286824,
|
| 245 |
+
"grad_norm": 0.14298808574676514,
|
| 246 |
+
"learning_rate": 1.2967741935483872e-05,
|
| 247 |
+
"loss": 1.178272008895874,
|
| 248 |
+
"step": 68
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2713178294573643,
|
| 252 |
+
"grad_norm": 0.12258580327033997,
|
| 253 |
+
"learning_rate": 1.335483870967742e-05,
|
| 254 |
+
"loss": 1.33051335811615,
|
| 255 |
+
"step": 70
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.27906976744186046,
|
| 259 |
+
"grad_norm": 0.1763555109500885,
|
| 260 |
+
"learning_rate": 1.3741935483870968e-05,
|
| 261 |
+
"loss": 1.0556892156600952,
|
| 262 |
+
"step": 72
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2868217054263566,
|
| 266 |
+
"grad_norm": 0.28760379552841187,
|
| 267 |
+
"learning_rate": 1.4129032258064516e-05,
|
| 268 |
+
"loss": 1.1506415605545044,
|
| 269 |
+
"step": 74
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.29457364341085274,
|
| 273 |
+
"grad_norm": 0.3192862868309021,
|
| 274 |
+
"learning_rate": 1.4516129032258065e-05,
|
| 275 |
+
"loss": 1.1051461696624756,
|
| 276 |
+
"step": 76
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3023255813953488,
|
| 280 |
+
"grad_norm": 0.17246203124523163,
|
| 281 |
+
"learning_rate": 1.4903225806451612e-05,
|
| 282 |
+
"loss": 1.3540679216384888,
|
| 283 |
+
"step": 78
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.31007751937984496,
|
| 287 |
+
"grad_norm": 0.07415715605020523,
|
| 288 |
+
"learning_rate": 1.529032258064516e-05,
|
| 289 |
+
"loss": 1.1473115682601929,
|
| 290 |
+
"step": 80
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3178294573643411,
|
| 294 |
+
"grad_norm": 0.16899384558200836,
|
| 295 |
+
"learning_rate": 1.567741935483871e-05,
|
| 296 |
+
"loss": 1.3307069540023804,
|
| 297 |
+
"step": 82
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.32558139534883723,
|
| 301 |
+
"grad_norm": 0.16342990100383759,
|
| 302 |
+
"learning_rate": 1.6064516129032258e-05,
|
| 303 |
+
"loss": 0.9781491756439209,
|
| 304 |
+
"step": 84
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3333333333333333,
|
| 308 |
+
"grad_norm": 0.12549830973148346,
|
| 309 |
+
"learning_rate": 1.6451612903225807e-05,
|
| 310 |
+
"loss": 1.1001088619232178,
|
| 311 |
+
"step": 86
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.34108527131782945,
|
| 315 |
+
"grad_norm": 0.13267701864242554,
|
| 316 |
+
"learning_rate": 1.6838709677419356e-05,
|
| 317 |
+
"loss": 1.399463415145874,
|
| 318 |
+
"step": 88
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3488372093023256,
|
| 322 |
+
"grad_norm": 0.4117628037929535,
|
| 323 |
+
"learning_rate": 1.7225806451612906e-05,
|
| 324 |
+
"loss": 0.8339037299156189,
|
| 325 |
+
"step": 90
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.35658914728682173,
|
| 329 |
+
"grad_norm": 0.3214583992958069,
|
| 330 |
+
"learning_rate": 1.761290322580645e-05,
|
| 331 |
+
"loss": 1.1209487915039062,
|
| 332 |
+
"step": 92
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.3643410852713178,
|
| 336 |
+
"grad_norm": 0.1995217651128769,
|
| 337 |
+
"learning_rate": 1.8e-05,
|
| 338 |
+
"loss": 1.0714277029037476,
|
| 339 |
+
"step": 94
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.37209302325581395,
|
| 343 |
+
"grad_norm": 0.0989437848329544,
|
| 344 |
+
"learning_rate": 1.838709677419355e-05,
|
| 345 |
+
"loss": 1.192923903465271,
|
| 346 |
+
"step": 96
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.3798449612403101,
|
| 350 |
+
"grad_norm": 0.1220928430557251,
|
| 351 |
+
"learning_rate": 1.87741935483871e-05,
|
| 352 |
+
"loss": 0.7750011086463928,
|
| 353 |
+
"step": 98
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.3875968992248062,
|
| 357 |
+
"grad_norm": 0.13039161264896393,
|
| 358 |
+
"learning_rate": 1.9161290322580645e-05,
|
| 359 |
+
"loss": 0.6638532280921936,
|
| 360 |
+
"step": 100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3953488372093023,
|
| 364 |
+
"grad_norm": 0.10157541930675507,
|
| 365 |
+
"learning_rate": 1.9548387096774194e-05,
|
| 366 |
+
"loss": 1.3122025728225708,
|
| 367 |
+
"step": 102
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.40310077519379844,
|
| 371 |
+
"grad_norm": 0.08540091663599014,
|
| 372 |
+
"learning_rate": 1.9935483870967743e-05,
|
| 373 |
+
"loss": 1.203364372253418,
|
| 374 |
+
"step": 104
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.4108527131782946,
|
| 378 |
+
"grad_norm": 0.1469828337430954,
|
| 379 |
+
"learning_rate": 2.032258064516129e-05,
|
| 380 |
+
"loss": 1.0173336267471313,
|
| 381 |
+
"step": 106
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.4186046511627907,
|
| 385 |
+
"grad_norm": 0.09850579500198364,
|
| 386 |
+
"learning_rate": 2.0709677419354838e-05,
|
| 387 |
+
"loss": 1.0237982273101807,
|
| 388 |
+
"step": 108
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.4263565891472868,
|
| 392 |
+
"grad_norm": 0.08415781706571579,
|
| 393 |
+
"learning_rate": 2.1096774193548387e-05,
|
| 394 |
+
"loss": 1.0086685419082642,
|
| 395 |
+
"step": 110
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.43410852713178294,
|
| 399 |
+
"grad_norm": 0.08691313862800598,
|
| 400 |
+
"learning_rate": 2.1483870967741936e-05,
|
| 401 |
+
"loss": 0.9078419208526611,
|
| 402 |
+
"step": 112
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.4418604651162791,
|
| 406 |
+
"grad_norm": 0.1410425454378128,
|
| 407 |
+
"learning_rate": 2.1870967741935485e-05,
|
| 408 |
+
"loss": 1.0696989297866821,
|
| 409 |
+
"step": 114
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.4496124031007752,
|
| 413 |
+
"grad_norm": 0.11058277636766434,
|
| 414 |
+
"learning_rate": 2.2258064516129034e-05,
|
| 415 |
+
"loss": 1.0235304832458496,
|
| 416 |
+
"step": 116
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.4573643410852713,
|
| 420 |
+
"grad_norm": 0.17280496656894684,
|
| 421 |
+
"learning_rate": 2.2645161290322584e-05,
|
| 422 |
+
"loss": 0.8430470824241638,
|
| 423 |
+
"step": 118
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.46511627906976744,
|
| 427 |
+
"grad_norm": 0.0914328321814537,
|
| 428 |
+
"learning_rate": 2.303225806451613e-05,
|
| 429 |
+
"loss": 1.2717251777648926,
|
| 430 |
+
"step": 120
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.4728682170542636,
|
| 434 |
+
"grad_norm": 0.10640335828065872,
|
| 435 |
+
"learning_rate": 2.341935483870968e-05,
|
| 436 |
+
"loss": 1.0239697694778442,
|
| 437 |
+
"step": 122
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.4806201550387597,
|
| 441 |
+
"grad_norm": 0.10921759903430939,
|
| 442 |
+
"learning_rate": 2.3806451612903228e-05,
|
| 443 |
+
"loss": 1.2588107585906982,
|
| 444 |
+
"step": 124
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.4883720930232558,
|
| 448 |
+
"grad_norm": 0.21347090601921082,
|
| 449 |
+
"learning_rate": 2.4193548387096773e-05,
|
| 450 |
+
"loss": 1.149160385131836,
|
| 451 |
+
"step": 126
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.49612403100775193,
|
| 455 |
+
"grad_norm": 0.16161420941352844,
|
| 456 |
+
"learning_rate": 2.4580645161290323e-05,
|
| 457 |
+
"loss": 1.1978895664215088,
|
| 458 |
+
"step": 128
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.5038759689922481,
|
| 462 |
+
"grad_norm": 0.11207153648138046,
|
| 463 |
+
"learning_rate": 2.4967741935483872e-05,
|
| 464 |
+
"loss": 1.1477546691894531,
|
| 465 |
+
"step": 130
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.5116279069767442,
|
| 469 |
+
"grad_norm": 0.13203421235084534,
|
| 470 |
+
"learning_rate": 2.535483870967742e-05,
|
| 471 |
+
"loss": 0.684913694858551,
|
| 472 |
+
"step": 132
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5193798449612403,
|
| 476 |
+
"grad_norm": 0.16211755573749542,
|
| 477 |
+
"learning_rate": 2.5741935483870967e-05,
|
| 478 |
+
"loss": 1.135626196861267,
|
| 479 |
+
"step": 134
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.5271317829457365,
|
| 483 |
+
"grad_norm": 0.19277559220790863,
|
| 484 |
+
"learning_rate": 2.6129032258064516e-05,
|
| 485 |
+
"loss": 1.1265920400619507,
|
| 486 |
+
"step": 136
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5348837209302325,
|
| 490 |
+
"grad_norm": 0.12664702534675598,
|
| 491 |
+
"learning_rate": 2.6516129032258065e-05,
|
| 492 |
+
"loss": 1.3438581228256226,
|
| 493 |
+
"step": 138
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5426356589147286,
|
| 497 |
+
"grad_norm": 0.07170073688030243,
|
| 498 |
+
"learning_rate": 2.690322580645161e-05,
|
| 499 |
+
"loss": 1.2673969268798828,
|
| 500 |
+
"step": 140
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5503875968992248,
|
| 504 |
+
"grad_norm": 0.1509476602077484,
|
| 505 |
+
"learning_rate": 2.7290322580645163e-05,
|
| 506 |
+
"loss": 0.6191468834877014,
|
| 507 |
+
"step": 142
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.5581395348837209,
|
| 511 |
+
"grad_norm": 0.08468706905841827,
|
| 512 |
+
"learning_rate": 2.7677419354838713e-05,
|
| 513 |
+
"loss": 1.3681960105895996,
|
| 514 |
+
"step": 144
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.5658914728682171,
|
| 518 |
+
"grad_norm": 0.08381734788417816,
|
| 519 |
+
"learning_rate": 2.806451612903226e-05,
|
| 520 |
+
"loss": 1.0066568851470947,
|
| 521 |
+
"step": 146
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.5736434108527132,
|
| 525 |
+
"grad_norm": 0.0786685049533844,
|
| 526 |
+
"learning_rate": 2.8451612903225808e-05,
|
| 527 |
+
"loss": 0.993072509765625,
|
| 528 |
+
"step": 148
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.5813953488372093,
|
| 532 |
+
"grad_norm": 0.16647084057331085,
|
| 533 |
+
"learning_rate": 2.8838709677419357e-05,
|
| 534 |
+
"loss": 0.9888545274734497,
|
| 535 |
+
"step": 150
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.5891472868217055,
|
| 539 |
+
"grad_norm": 0.0718846470117569,
|
| 540 |
+
"learning_rate": 2.9225806451612906e-05,
|
| 541 |
+
"loss": 1.2481988668441772,
|
| 542 |
+
"step": 152
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.5968992248062015,
|
| 546 |
+
"grad_norm": 0.054430440068244934,
|
| 547 |
+
"learning_rate": 2.961290322580645e-05,
|
| 548 |
+
"loss": 1.2282058000564575,
|
| 549 |
+
"step": 154
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6046511627906976,
|
| 553 |
+
"grad_norm": 0.08397103101015091,
|
| 554 |
+
"learning_rate": 3e-05,
|
| 555 |
+
"loss": 0.7997589111328125,
|
| 556 |
+
"step": 156
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6124031007751938,
|
| 560 |
+
"grad_norm": 0.16056904196739197,
|
| 561 |
+
"learning_rate": 2.9994088909931925e-05,
|
| 562 |
+
"loss": 0.9445045590400696,
|
| 563 |
+
"step": 158
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6201550387596899,
|
| 567 |
+
"grad_norm": 0.0699552372097969,
|
| 568 |
+
"learning_rate": 2.9976361120666653e-05,
|
| 569 |
+
"loss": 1.3003367185592651,
|
| 570 |
+
"step": 160
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.627906976744186,
|
| 574 |
+
"grad_norm": 0.326346755027771,
|
| 575 |
+
"learning_rate": 2.9946833069938937e-05,
|
| 576 |
+
"loss": 1.0931003093719482,
|
| 577 |
+
"step": 162
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6356589147286822,
|
| 581 |
+
"grad_norm": 0.05613398924469948,
|
| 582 |
+
"learning_rate": 2.990553213703777e-05,
|
| 583 |
+
"loss": 1.252951741218567,
|
| 584 |
+
"step": 164
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.6434108527131783,
|
| 588 |
+
"grad_norm": 0.06693823635578156,
|
| 589 |
+
"learning_rate": 2.985249661741952e-05,
|
| 590 |
+
"loss": 0.9843292236328125,
|
| 591 |
+
"step": 166
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.6511627906976745,
|
| 595 |
+
"grad_norm": 0.05880317464470863,
|
| 596 |
+
"learning_rate": 2.9787775687199204e-05,
|
| 597 |
+
"loss": 1.2224986553192139,
|
| 598 |
+
"step": 168
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.6589147286821705,
|
| 602 |
+
"grad_norm": 0.22196456789970398,
|
| 603 |
+
"learning_rate": 2.9711429357552954e-05,
|
| 604 |
+
"loss": 0.6978975534439087,
|
| 605 |
+
"step": 170
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.6666666666666666,
|
| 609 |
+
"grad_norm": 0.11266355961561203,
|
| 610 |
+
"learning_rate": 2.9623528419073845e-05,
|
| 611 |
+
"loss": 1.1819331645965576,
|
| 612 |
+
"step": 172
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.6744186046511628,
|
| 616 |
+
"grad_norm": 0.23993322253227234,
|
| 617 |
+
"learning_rate": 2.952415437613278e-05,
|
| 618 |
+
"loss": 0.9013431668281555,
|
| 619 |
+
"step": 174
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.6821705426356589,
|
| 623 |
+
"grad_norm": 0.16824588179588318,
|
| 624 |
+
"learning_rate": 2.9413399371305162e-05,
|
| 625 |
+
"loss": 0.9518213272094727,
|
| 626 |
+
"step": 176
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.689922480620155,
|
| 630 |
+
"grad_norm": 0.10848796367645264,
|
| 631 |
+
"learning_rate": 2.9291366099933583e-05,
|
| 632 |
+
"loss": 0.9333250522613525,
|
| 633 |
+
"step": 178
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.6976744186046512,
|
| 637 |
+
"grad_norm": 0.07721789926290512,
|
| 638 |
+
"learning_rate": 2.9158167714905638e-05,
|
| 639 |
+
"loss": 1.0462111234664917,
|
| 640 |
+
"step": 180
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.7054263565891473,
|
| 644 |
+
"grad_norm": 0.07368086278438568,
|
| 645 |
+
"learning_rate": 2.9013927721735172e-05,
|
| 646 |
+
"loss": 1.1160787343978882,
|
| 647 |
+
"step": 182
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.7131782945736435,
|
| 651 |
+
"grad_norm": 0.12432865053415298,
|
| 652 |
+
"learning_rate": 2.885877986404432e-05,
|
| 653 |
+
"loss": 0.9108925461769104,
|
| 654 |
+
"step": 184
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7209302325581395,
|
| 658 |
+
"grad_norm": 0.0682280957698822,
|
| 659 |
+
"learning_rate": 2.86928679995524e-05,
|
| 660 |
+
"loss": 1.3199962377548218,
|
| 661 |
+
"step": 186
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.7286821705426356,
|
| 665 |
+
"grad_norm": 0.0608358271420002,
|
| 666 |
+
"learning_rate": 2.8516345966686766e-05,
|
| 667 |
+
"loss": 1.0051369667053223,
|
| 668 |
+
"step": 188
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.7364341085271318,
|
| 672 |
+
"grad_norm": 0.16042953729629517,
|
| 673 |
+
"learning_rate": 2.832937744193922e-05,
|
| 674 |
+
"loss": 1.0462324619293213,
|
| 675 |
+
"step": 190
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.7441860465116279,
|
| 679 |
+
"grad_norm": 0.09749440848827362,
|
| 680 |
+
"learning_rate": 2.8132135788100312e-05,
|
| 681 |
+
"loss": 1.1752909421920776,
|
| 682 |
+
"step": 192
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.751937984496124,
|
| 686 |
+
"grad_norm": 0.057570479810237885,
|
| 687 |
+
"learning_rate": 2.7924803893512144e-05,
|
| 688 |
+
"loss": 1.2336088418960571,
|
| 689 |
+
"step": 194
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.7596899224806202,
|
| 693 |
+
"grad_norm": 0.05938956141471863,
|
| 694 |
+
"learning_rate": 2.770757400248891e-05,
|
| 695 |
+
"loss": 1.2357627153396606,
|
| 696 |
+
"step": 196
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.7674418604651163,
|
| 700 |
+
"grad_norm": 0.1574079990386963,
|
| 701 |
+
"learning_rate": 2.7480647537062183e-05,
|
| 702 |
+
"loss": 0.6303899884223938,
|
| 703 |
+
"step": 198
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.7751937984496124,
|
| 707 |
+
"grad_norm": 0.7175618410110474,
|
| 708 |
+
"learning_rate": 2.7244234910216427e-05,
|
| 709 |
+
"loss": 1.449771761894226,
|
| 710 |
+
"step": 200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.7829457364341085,
|
| 714 |
+
"grad_norm": 0.12645360827445984,
|
| 715 |
+
"learning_rate": 2.699855533078781e-05,
|
| 716 |
+
"loss": 1.136543869972229,
|
| 717 |
+
"step": 202
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.7906976744186046,
|
| 721 |
+
"grad_norm": 0.1046365350484848,
|
| 722 |
+
"learning_rate": 2.6743836600207206e-05,
|
| 723 |
+
"loss": 1.2583595514297485,
|
| 724 |
+
"step": 204
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.7984496124031008,
|
| 728 |
+
"grad_norm": 0.06069144234061241,
|
| 729 |
+
"learning_rate": 2.6480314901275954e-05,
|
| 730 |
+
"loss": 1.073771595954895,
|
| 731 |
+
"step": 206
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.8062015503875969,
|
| 735 |
+
"grad_norm": 0.08813668042421341,
|
| 736 |
+
"learning_rate": 2.620823457917009e-05,
|
| 737 |
+
"loss": 0.8364643454551697,
|
| 738 |
+
"step": 208
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.813953488372093,
|
| 742 |
+
"grad_norm": 0.1366778016090393,
|
| 743 |
+
"learning_rate": 2.592784791487625e-05,
|
| 744 |
+
"loss": 1.355994701385498,
|
| 745 |
+
"step": 210
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.8217054263565892,
|
| 749 |
+
"grad_norm": 0.06360755860805511,
|
| 750 |
+
"learning_rate": 2.5639414891269164e-05,
|
| 751 |
+
"loss": 1.226666808128357,
|
| 752 |
+
"step": 212
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.8294573643410853,
|
| 756 |
+
"grad_norm": 0.05345217138528824,
|
| 757 |
+
"learning_rate": 2.534320295204785e-05,
|
| 758 |
+
"loss": 0.9844304919242859,
|
| 759 |
+
"step": 214
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.8372093023255814,
|
| 763 |
+
"grad_norm": 0.13714972138404846,
|
| 764 |
+
"learning_rate": 2.5039486753753788e-05,
|
| 765 |
+
"loss": 1.0947370529174805,
|
| 766 |
+
"step": 216
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.8449612403100775,
|
| 770 |
+
"grad_norm": 0.08509152382612228,
|
| 771 |
+
"learning_rate": 2.4728547911101212e-05,
|
| 772 |
+
"loss": 1.341536283493042,
|
| 773 |
+
"step": 218
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.8527131782945736,
|
| 777 |
+
"grad_norm": 0.06335103511810303,
|
| 778 |
+
"learning_rate": 2.4410674735855555e-05,
|
| 779 |
+
"loss": 1.2149854898452759,
|
| 780 |
+
"step": 220
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.8604651162790697,
|
| 784 |
+
"grad_norm": 0.07615257799625397,
|
| 785 |
+
"learning_rate": 2.4086161969502158e-05,
|
| 786 |
+
"loss": 0.5183571577072144,
|
| 787 |
+
"step": 222
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.8682170542635659,
|
| 791 |
+
"grad_norm": 0.05618668347597122,
|
| 792 |
+
"learning_rate": 2.3755310509953208e-05,
|
| 793 |
+
"loss": 1.2107856273651123,
|
| 794 |
+
"step": 224
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.875968992248062,
|
| 798 |
+
"grad_norm": 0.08672861009836197,
|
| 799 |
+
"learning_rate": 2.34184271325462e-05,
|
| 800 |
+
"loss": 1.2980958223342896,
|
| 801 |
+
"step": 226
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.8837209302325582,
|
| 805 |
+
"grad_norm": 0.2590503692626953,
|
| 806 |
+
"learning_rate": 2.3075824205592707e-05,
|
| 807 |
+
"loss": 0.9205237030982971,
|
| 808 |
+
"step": 228
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.8914728682170543,
|
| 812 |
+
"grad_norm": 0.08758358657360077,
|
| 813 |
+
"learning_rate": 2.2727819400741172e-05,
|
| 814 |
+
"loss": 1.058215618133545,
|
| 815 |
+
"step": 230
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.8992248062015504,
|
| 819 |
+
"grad_norm": 0.07180935889482498,
|
| 820 |
+
"learning_rate": 2.2374735398422276e-05,
|
| 821 |
+
"loss": 0.8909934759140015,
|
| 822 |
+
"step": 232
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.9069767441860465,
|
| 826 |
+
"grad_norm": 0.07425983250141144,
|
| 827 |
+
"learning_rate": 2.2016899588650032e-05,
|
| 828 |
+
"loss": 1.3261955976486206,
|
| 829 |
+
"step": 234
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.9147286821705426,
|
| 833 |
+
"grad_norm": 0.10620886832475662,
|
| 834 |
+
"learning_rate": 2.165464376745598e-05,
|
| 835 |
+
"loss": 0.7832080125808716,
|
| 836 |
+
"step": 236
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.9224806201550387,
|
| 840 |
+
"grad_norm": 0.11008700728416443,
|
| 841 |
+
"learning_rate": 2.1288303829238058e-05,
|
| 842 |
+
"loss": 1.243245244026184,
|
| 843 |
+
"step": 238
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.9302325581395349,
|
| 847 |
+
"grad_norm": 0.15069428086280823,
|
| 848 |
+
"learning_rate": 2.091821945530925e-05,
|
| 849 |
+
"loss": 1.0843262672424316,
|
| 850 |
+
"step": 240
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.937984496124031,
|
| 854 |
+
"grad_norm": 0.20396780967712402,
|
| 855 |
+
"learning_rate": 2.0544733798934988e-05,
|
| 856 |
+
"loss": 1.2043696641921997,
|
| 857 |
+
"step": 242
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.9457364341085271,
|
| 861 |
+
"grad_norm": 0.1518591046333313,
|
| 862 |
+
"learning_rate": 2.0168193167151183e-05,
|
| 863 |
+
"loss": 1.0192402601242065,
|
| 864 |
+
"step": 244
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.9534883720930233,
|
| 868 |
+
"grad_norm": 0.08409406244754791,
|
| 869 |
+
"learning_rate": 1.9788946699658032e-05,
|
| 870 |
+
"loss": 0.7911899089813232,
|
| 871 |
+
"step": 246
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.9612403100775194,
|
| 875 |
+
"grad_norm": 0.1363200843334198,
|
| 876 |
+
"learning_rate": 1.9407346045087278e-05,
|
| 877 |
+
"loss": 0.7742171883583069,
|
| 878 |
+
"step": 248
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.9689922480620154,
|
| 882 |
+
"grad_norm": 0.07617780566215515,
|
| 883 |
+
"learning_rate": 1.902374503494311e-05,
|
| 884 |
+
"loss": 1.2457553148269653,
|
| 885 |
+
"step": 250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.9767441860465116,
|
| 889 |
+
"grad_norm": 0.0721699595451355,
|
| 890 |
+
"learning_rate": 1.863849935551905e-05,
|
| 891 |
+
"loss": 1.016923427581787,
|
| 892 |
+
"step": 252
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.9844961240310077,
|
| 896 |
+
"grad_norm": 0.14891768991947174,
|
| 897 |
+
"learning_rate": 1.825196621809499e-05,
|
| 898 |
+
"loss": 0.9890077710151672,
|
| 899 |
+
"step": 254
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.9922480620155039,
|
| 903 |
+
"grad_norm": 0.28671520948410034,
|
| 904 |
+
"learning_rate": 1.7864504027720297e-05,
|
| 905 |
+
"loss": 0.8091475367546082,
|
| 906 |
+
"step": 256
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.0,
|
| 910 |
+
"grad_norm": 0.04788220301270485,
|
| 911 |
+
"learning_rate": 1.747647205088991e-05,
|
| 912 |
+
"loss": 1.1878516674041748,
|
| 913 |
+
"step": 258
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.0077519379844961,
|
| 917 |
+
"grad_norm": 0.06899169087409973,
|
| 918 |
+
"learning_rate": 1.7088230082421763e-05,
|
| 919 |
+
"loss": 0.7679018378257751,
|
| 920 |
+
"step": 260
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.0155038759689923,
|
| 924 |
+
"grad_norm": 0.0531589537858963,
|
| 925 |
+
"learning_rate": 1.67001381118443e-05,
|
| 926 |
+
"loss": 1.128183126449585,
|
| 927 |
+
"step": 262
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.0232558139534884,
|
| 931 |
+
"grad_norm": 0.36434194445610046,
|
| 932 |
+
"learning_rate": 1.6312555989603446e-05,
|
| 933 |
+
"loss": 0.7761940956115723,
|
| 934 |
+
"step": 264
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.0310077519379846,
|
| 938 |
+
"grad_norm": 0.09103479981422424,
|
| 939 |
+
"learning_rate": 1.5925843093398552e-05,
|
| 940 |
+
"loss": 0.6045004725456238,
|
| 941 |
+
"step": 266
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.0387596899224807,
|
| 945 |
+
"grad_norm": 0.13370856642723083,
|
| 946 |
+
"learning_rate": 1.554035799495667e-05,
|
| 947 |
+
"loss": 0.8422982096672058,
|
| 948 |
+
"step": 268
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.0465116279069768,
|
| 952 |
+
"grad_norm": 0.0862463042140007,
|
| 953 |
+
"learning_rate": 1.515645812755415e-05,
|
| 954 |
+
"loss": 1.0801072120666504,
|
| 955 |
+
"step": 270
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.054263565891473,
|
| 959 |
+
"grad_norm": 0.08025830239057541,
|
| 960 |
+
"learning_rate": 1.4774499454593878e-05,
|
| 961 |
+
"loss": 0.5319198966026306,
|
| 962 |
+
"step": 272
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.062015503875969,
|
| 966 |
+
"grad_norm": 0.12001097202301025,
|
| 967 |
+
"learning_rate": 1.4394836139545363e-05,
|
| 968 |
+
"loss": 1.100441575050354,
|
| 969 |
+
"step": 274
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.069767441860465,
|
| 973 |
+
"grad_norm": 0.0670214369893074,
|
| 974 |
+
"learning_rate": 1.4017820217553832e-05,
|
| 975 |
+
"loss": 0.9006233215332031,
|
| 976 |
+
"step": 276
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.0775193798449612,
|
| 980 |
+
"grad_norm": 0.05677079036831856,
|
| 981 |
+
"learning_rate": 1.3643801269022732e-05,
|
| 982 |
+
"loss": 0.9063330292701721,
|
| 983 |
+
"step": 278
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.0852713178294573,
|
| 987 |
+
"grad_norm": 0.06150190904736519,
|
| 988 |
+
"learning_rate": 1.3273126095472361e-05,
|
| 989 |
+
"loss": 0.6792492270469666,
|
| 990 |
+
"step": 280
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.0930232558139534,
|
| 994 |
+
"grad_norm": 0.11940456926822662,
|
| 995 |
+
"learning_rate": 1.2906138397975178e-05,
|
| 996 |
+
"loss": 0.5880073308944702,
|
| 997 |
+
"step": 282
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.1007751937984496,
|
| 1001 |
+
"grad_norm": 0.059427861124277115,
|
| 1002 |
+
"learning_rate": 1.2543178458465887e-05,
|
| 1003 |
+
"loss": 0.6459496021270752,
|
| 1004 |
+
"step": 284
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.1085271317829457,
|
| 1008 |
+
"grad_norm": 0.14358076453208923,
|
| 1009 |
+
"learning_rate": 1.2184582824221902e-05,
|
| 1010 |
+
"loss": 0.6029883027076721,
|
| 1011 |
+
"step": 286
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.1162790697674418,
|
| 1015 |
+
"grad_norm": 0.12145813554525375,
|
| 1016 |
+
"learning_rate": 1.1830683995806694e-05,
|
| 1017 |
+
"loss": 0.5689815282821655,
|
| 1018 |
+
"step": 288
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.124031007751938,
|
| 1022 |
+
"grad_norm": 0.06693974882364273,
|
| 1023 |
+
"learning_rate": 1.14818101187653e-05,
|
| 1024 |
+
"loss": 0.9926015138626099,
|
| 1025 |
+
"step": 290
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.1317829457364341,
|
| 1029 |
+
"grad_norm": 0.05298677831888199,
|
| 1030 |
+
"learning_rate": 1.113828467935807e-05,
|
| 1031 |
+
"loss": 0.599225640296936,
|
| 1032 |
+
"step": 292
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.1395348837209303,
|
| 1036 |
+
"grad_norm": 0.1428927630186081,
|
| 1037 |
+
"learning_rate": 1.080042620461448e-05,
|
| 1038 |
+
"loss": 1.0777664184570312,
|
| 1039 |
+
"step": 294
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.1472868217054264,
|
| 1043 |
+
"grad_norm": 0.33007150888442993,
|
| 1044 |
+
"learning_rate": 1.0468547966985433e-05,
|
| 1045 |
+
"loss": 0.592754065990448,
|
| 1046 |
+
"step": 296
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.1550387596899225,
|
| 1050 |
+
"grad_norm": 0.09632085263729095,
|
| 1051 |
+
"learning_rate": 1.0142957693867676e-05,
|
| 1052 |
+
"loss": 0.8235950469970703,
|
| 1053 |
+
"step": 298
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.1627906976744187,
|
| 1057 |
+
"grad_norm": 0.05365417152643204,
|
| 1058 |
+
"learning_rate": 9.823957282269788e-06,
|
| 1059 |
+
"loss": 0.6445293426513672,
|
| 1060 |
+
"step": 300
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.1705426356589148,
|
| 1064 |
+
"grad_norm": 0.05418482422828674,
|
| 1065 |
+
"learning_rate": 9.51184251888427e-06,
|
| 1066 |
+
"loss": 0.8274694085121155,
|
| 1067 |
+
"step": 302
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.178294573643411,
|
| 1071 |
+
"grad_norm": 0.08142586797475815,
|
| 1072 |
+
"learning_rate": 9.206902805825313e-06,
|
| 1073 |
+
"loss": 0.6243199110031128,
|
| 1074 |
+
"step": 304
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.1860465116279069,
|
| 1078 |
+
"grad_norm": 0.09854786843061447,
|
| 1079 |
+
"learning_rate": 8.909420892286522e-06,
|
| 1080 |
+
"loss": 0.9028869867324829,
|
| 1081 |
+
"step": 306
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.193798449612403,
|
| 1085 |
+
"grad_norm": 0.12125203758478165,
|
| 1086 |
+
"learning_rate": 8.619672612367426e-06,
|
| 1087 |
+
"loss": 1.018742322921753,
|
| 1088 |
+
"step": 308
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.2015503875968991,
|
| 1092 |
+
"grad_norm": 0.05682411789894104,
|
| 1093 |
+
"learning_rate": 8.337926629311901e-06,
|
| 1094 |
+
"loss": 0.8793404698371887,
|
| 1095 |
+
"step": 310
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.2093023255813953,
|
| 1099 |
+
"grad_norm": 0.08018923550844193,
|
| 1100 |
+
"learning_rate": 8.064444186395577e-06,
|
| 1101 |
+
"loss": 0.5548562407493591,
|
| 1102 |
+
"step": 312
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.2170542635658914,
|
| 1106 |
+
"grad_norm": 0.4036023020744324,
|
| 1107 |
+
"learning_rate": 7.799478864693305e-06,
|
| 1108 |
+
"loss": 0.40799465775489807,
|
| 1109 |
+
"step": 314
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.2248062015503876,
|
| 1113 |
+
"grad_norm": 0.09002506732940674,
|
| 1114 |
+
"learning_rate": 7.543276347951186e-06,
|
| 1115 |
+
"loss": 0.854184627532959,
|
| 1116 |
+
"step": 316
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.2325581395348837,
|
| 1120 |
+
"grad_norm": 0.05118729546666145,
|
| 1121 |
+
"learning_rate": 7.2960741947813325e-06,
|
| 1122 |
+
"loss": 0.7614866495132446,
|
| 1123 |
+
"step": 318
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.2403100775193798,
|
| 1127 |
+
"grad_norm": 0.048252079635858536,
|
| 1128 |
+
"learning_rate": 7.058101618390395e-06,
|
| 1129 |
+
"loss": 0.9597308039665222,
|
| 1130 |
+
"step": 320
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.248062015503876,
|
| 1134 |
+
"grad_norm": 0.08246824890375137,
|
| 1135 |
+
"learning_rate": 6.829579274046253e-06,
|
| 1136 |
+
"loss": 1.0625540018081665,
|
| 1137 |
+
"step": 322
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.255813953488372,
|
| 1141 |
+
"grad_norm": 0.10916761308908463,
|
| 1142 |
+
"learning_rate": 6.61071905447989e-06,
|
| 1143 |
+
"loss": 0.5724548101425171,
|
| 1144 |
+
"step": 324
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.2635658914728682,
|
| 1148 |
+
"grad_norm": 0.0720956102013588,
|
| 1149 |
+
"learning_rate": 6.40172389341212e-06,
|
| 1150 |
+
"loss": 0.9105185866355896,
|
| 1151 |
+
"step": 326
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.2713178294573644,
|
| 1155 |
+
"grad_norm": 0.1327294260263443,
|
| 1156 |
+
"learning_rate": 6.202787577387384e-06,
|
| 1157 |
+
"loss": 0.6492634415626526,
|
| 1158 |
+
"step": 328
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.2790697674418605,
|
| 1162 |
+
"grad_norm": 0.055963922291994095,
|
| 1163 |
+
"learning_rate": 6.014094566089114e-06,
|
| 1164 |
+
"loss": 0.6872971653938293,
|
| 1165 |
+
"step": 330
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.2868217054263567,
|
| 1169 |
+
"grad_norm": 0.055926598608493805,
|
| 1170 |
+
"learning_rate": 5.835819821303189e-06,
|
| 1171 |
+
"loss": 0.8940346240997314,
|
| 1172 |
+
"step": 332
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.2945736434108528,
|
| 1176 |
+
"grad_norm": 0.11941412091255188,
|
| 1177 |
+
"learning_rate": 5.6681286446881695e-06,
|
| 1178 |
+
"loss": 0.517791748046875,
|
| 1179 |
+
"step": 334
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.302325581395349,
|
| 1183 |
+
"grad_norm": 0.05569684877991676,
|
| 1184 |
+
"learning_rate": 5.511176524502653e-06,
|
| 1185 |
+
"loss": 0.9667401313781738,
|
| 1186 |
+
"step": 336
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.310077519379845,
|
| 1190 |
+
"grad_norm": 0.04035505652427673,
|
| 1191 |
+
"learning_rate": 5.36510899143194e-06,
|
| 1192 |
+
"loss": 0.6123257875442505,
|
| 1193 |
+
"step": 338
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.3178294573643412,
|
| 1197 |
+
"grad_norm": 0.053604647517204285,
|
| 1198 |
+
"learning_rate": 5.2300614836476425e-06,
|
| 1199 |
+
"loss": 0.8501400947570801,
|
| 1200 |
+
"step": 340
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.3255813953488373,
|
| 1204 |
+
"grad_norm": 0.08587184548377991,
|
| 1205 |
+
"learning_rate": 5.106159221225361e-06,
|
| 1206 |
+
"loss": 0.8949810266494751,
|
| 1207 |
+
"step": 342
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.3333333333333333,
|
| 1211 |
+
"grad_norm": 0.08081138134002686,
|
| 1212 |
+
"learning_rate": 4.993517090036914e-06,
|
| 1213 |
+
"loss": 0.8400573134422302,
|
| 1214 |
+
"step": 344
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.3410852713178294,
|
| 1218 |
+
"grad_norm": 0.5886430740356445,
|
| 1219 |
+
"learning_rate": 4.89223953522472e-06,
|
| 1220 |
+
"loss": 0.24276283383369446,
|
| 1221 |
+
"step": 346
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.3488372093023255,
|
| 1225 |
+
"grad_norm": 0.09961400926113129,
|
| 1226 |
+
"learning_rate": 4.802420464357147e-06,
|
| 1227 |
+
"loss": 0.7755904793739319,
|
| 1228 |
+
"step": 348
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.3565891472868217,
|
| 1232 |
+
"grad_norm": 0.07265698909759521,
|
| 1233 |
+
"learning_rate": 4.724143160354624e-06,
|
| 1234 |
+
"loss": 0.9579305648803711,
|
| 1235 |
+
"step": 350
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.3643410852713178,
|
| 1239 |
+
"grad_norm": 0.057041656225919724,
|
| 1240 |
+
"learning_rate": 4.6574802042672275e-06,
|
| 1241 |
+
"loss": 0.6767364740371704,
|
| 1242 |
+
"step": 352
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.372093023255814,
|
| 1246 |
+
"grad_norm": 0.17740975320339203,
|
| 1247 |
+
"learning_rate": 4.602493407975375e-06,
|
| 1248 |
+
"loss": 0.43329671025276184,
|
| 1249 |
+
"step": 354
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.37984496124031,
|
| 1253 |
+
"grad_norm": 0.10877375304698944,
|
| 1254 |
+
"learning_rate": 4.559233756875995e-06,
|
| 1255 |
+
"loss": 0.9381350874900818,
|
| 1256 |
+
"step": 356
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.3875968992248062,
|
| 1260 |
+
"grad_norm": 0.06163076311349869,
|
| 1261 |
+
"learning_rate": 4.5277413626073554e-06,
|
| 1262 |
+
"loss": 0.6927696466445923,
|
| 1263 |
+
"step": 358
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.3953488372093024,
|
| 1267 |
+
"grad_norm": 0.05219251289963722,
|
| 1268 |
+
"learning_rate": 4.508045425856358e-06,
|
| 1269 |
+
"loss": 0.7913583517074585,
|
| 1270 |
+
"step": 360
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.4031007751937985,
|
| 1274 |
+
"grad_norm": 0.09336534887552261,
|
| 1275 |
+
"learning_rate": 4.500164209282782e-06,
|
| 1276 |
+
"loss": 0.7886365056037903,
|
| 1277 |
+
"step": 362
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.4108527131782946,
|
| 1281 |
+
"grad_norm": 0.05429435521364212,
|
| 1282 |
+
"learning_rate": 4.504105020585611e-06,
|
| 1283 |
+
"loss": 0.7922376394271851,
|
| 1284 |
+
"step": 364
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.4186046511627908,
|
| 1288 |
+
"grad_norm": 0.07881563901901245,
|
| 1289 |
+
"learning_rate": 4.519864205727111e-06,
|
| 1290 |
+
"loss": 0.4149991273880005,
|
| 1291 |
+
"step": 366
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.4263565891472867,
|
| 1295 |
+
"grad_norm": 0.050976116210222244,
|
| 1296 |
+
"learning_rate": 4.547427152320965e-06,
|
| 1297 |
+
"loss": 0.40345892310142517,
|
| 1298 |
+
"step": 368
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.4341085271317828,
|
| 1302 |
+
"grad_norm": 0.13834504783153534,
|
| 1303 |
+
"learning_rate": 4.586768303181312e-06,
|
| 1304 |
+
"loss": 0.8296991586685181,
|
| 1305 |
+
"step": 370
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.441860465116279,
|
| 1309 |
+
"grad_norm": 0.14809437096118927,
|
| 1310 |
+
"learning_rate": 4.637851180020136e-06,
|
| 1311 |
+
"loss": 0.7817572355270386,
|
| 1312 |
+
"step": 372
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.449612403100775,
|
| 1316 |
+
"grad_norm": 0.04827815294265747,
|
| 1317 |
+
"learning_rate": 4.7006284172710145e-06,
|
| 1318 |
+
"loss": 0.7629826664924622,
|
| 1319 |
+
"step": 374
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.4573643410852712,
|
| 1323 |
+
"grad_norm": 0.09472133964300156,
|
| 1324 |
+
"learning_rate": 4.775041806007891e-06,
|
| 1325 |
+
"loss": 0.6470780372619629,
|
| 1326 |
+
"step": 376
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.4651162790697674,
|
| 1330 |
+
"grad_norm": 0.23365041613578796,
|
| 1331 |
+
"learning_rate": 4.861022347918125e-06,
|
| 1332 |
+
"loss": 0.608534038066864,
|
| 1333 |
+
"step": 378
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.4728682170542635,
|
| 1337 |
+
"grad_norm": 0.04631495103240013,
|
| 1338 |
+
"learning_rate": 4.958490319279778e-06,
|
| 1339 |
+
"loss": 0.7042877078056335,
|
| 1340 |
+
"step": 380
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.4806201550387597,
|
| 1344 |
+
"grad_norm": 0.10502998530864716,
|
| 1345 |
+
"learning_rate": 5.067355344883837e-06,
|
| 1346 |
+
"loss": 0.7883775234222412,
|
| 1347 |
+
"step": 382
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.4883720930232558,
|
| 1351 |
+
"grad_norm": 0.1601502150297165,
|
| 1352 |
+
"learning_rate": 5.187516481832796e-06,
|
| 1353 |
+
"loss": 0.6707104444503784,
|
| 1354 |
+
"step": 384
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.496124031007752,
|
| 1358 |
+
"grad_norm": 0.07128335535526276,
|
| 1359 |
+
"learning_rate": 5.318862313137916e-06,
|
| 1360 |
+
"loss": 0.5789697170257568,
|
| 1361 |
+
"step": 386
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.503875968992248,
|
| 1365 |
+
"grad_norm": 0.051307253539562225,
|
| 1366 |
+
"learning_rate": 5.461271051028392e-06,
|
| 1367 |
+
"loss": 0.7344382405281067,
|
| 1368 |
+
"step": 388
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.5116279069767442,
|
| 1372 |
+
"grad_norm": 0.06438810378313065,
|
| 1373 |
+
"learning_rate": 5.614610649876592e-06,
|
| 1374 |
+
"loss": 0.5874720811843872,
|
| 1375 |
+
"step": 390
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.5193798449612403,
|
| 1379 |
+
"grad_norm": 0.12045904248952866,
|
| 1380 |
+
"learning_rate": 5.778738928634702e-06,
|
| 1381 |
+
"loss": 0.6812347769737244,
|
| 1382 |
+
"step": 392
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.5271317829457365,
|
| 1386 |
+
"grad_norm": 0.12421064078807831,
|
| 1387 |
+
"learning_rate": 5.953503702669238e-06,
|
| 1388 |
+
"loss": 0.7551456689834595,
|
| 1389 |
+
"step": 394
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.5348837209302326,
|
| 1393 |
+
"grad_norm": 0.09568459540605545,
|
| 1394 |
+
"learning_rate": 6.138742924871177e-06,
|
| 1395 |
+
"loss": 0.6949661374092102,
|
| 1396 |
+
"step": 396
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.5426356589147288,
|
| 1400 |
+
"grad_norm": 0.1447361260652542,
|
| 1401 |
+
"learning_rate": 6.334284835910859e-06,
|
| 1402 |
+
"loss": 0.7189986705780029,
|
| 1403 |
+
"step": 398
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.550387596899225,
|
| 1407 |
+
"grad_norm": 0.16750486195087433,
|
| 1408 |
+
"learning_rate": 6.53994812349836e-06,
|
| 1409 |
+
"loss": 0.9427580237388611,
|
| 1410 |
+
"step": 400
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.558139534883721,
|
| 1414 |
+
"grad_norm": 0.171998992562294,
|
| 1415 |
+
"learning_rate": 6.755542090501669e-06,
|
| 1416 |
+
"loss": 0.5628240704536438,
|
| 1417 |
+
"step": 402
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.5658914728682172,
|
| 1421 |
+
"grad_norm": 0.04393970966339111,
|
| 1422 |
+
"learning_rate": 6.98086683176673e-06,
|
| 1423 |
+
"loss": 0.8915067315101624,
|
| 1424 |
+
"step": 404
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.5736434108527133,
|
| 1428 |
+
"grad_norm": 0.06884656846523285,
|
| 1429 |
+
"learning_rate": 7.215713419475466e-06,
|
| 1430 |
+
"loss": 0.8232840299606323,
|
| 1431 |
+
"step": 406
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.5813953488372094,
|
| 1435 |
+
"grad_norm": 0.06587037444114685,
|
| 1436 |
+
"learning_rate": 7.459864096869907e-06,
|
| 1437 |
+
"loss": 0.2791080176830292,
|
| 1438 |
+
"step": 408
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.5891472868217056,
|
| 1442 |
+
"grad_norm": 0.07907220721244812,
|
| 1443 |
+
"learning_rate": 7.713092480162712e-06,
|
| 1444 |
+
"loss": 0.7711836695671082,
|
| 1445 |
+
"step": 410
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.5968992248062015,
|
| 1449 |
+
"grad_norm": 0.07207150012254715,
|
| 1450 |
+
"learning_rate": 7.975163768446994e-06,
|
| 1451 |
+
"loss": 0.7907366156578064,
|
| 1452 |
+
"step": 412
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.6046511627906976,
|
| 1456 |
+
"grad_norm": 0.09880537539720535,
|
| 1457 |
+
"learning_rate": 8.245834961410696e-06,
|
| 1458 |
+
"loss": 0.49653783440589905,
|
| 1459 |
+
"step": 414
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.6124031007751938,
|
| 1463 |
+
"grad_norm": 0.05552729591727257,
|
| 1464 |
+
"learning_rate": 8.524855084653766e-06,
|
| 1465 |
+
"loss": 0.44712162017822266,
|
| 1466 |
+
"step": 416
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.62015503875969,
|
| 1470 |
+
"grad_norm": 0.05235432833433151,
|
| 1471 |
+
"learning_rate": 8.811965422399043e-06,
|
| 1472 |
+
"loss": 0.7449421882629395,
|
| 1473 |
+
"step": 418
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.627906976744186,
|
| 1477 |
+
"grad_norm": 0.06001957878470421,
|
| 1478 |
+
"learning_rate": 9.106899757381288e-06,
|
| 1479 |
+
"loss": 0.7992556095123291,
|
| 1480 |
+
"step": 420
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.6356589147286822,
|
| 1484 |
+
"grad_norm": 0.09635739773511887,
|
| 1485 |
+
"learning_rate": 9.409384617691782e-06,
|
| 1486 |
+
"loss": 0.5354418754577637,
|
| 1487 |
+
"step": 422
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.6434108527131783,
|
| 1491 |
+
"grad_norm": 0.06418698281049728,
|
| 1492 |
+
"learning_rate": 9.719139530349551e-06,
|
| 1493 |
+
"loss": 0.8580225110054016,
|
| 1494 |
+
"step": 424
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.6511627906976745,
|
| 1498 |
+
"grad_norm": 0.06972765177488327,
|
| 1499 |
+
"learning_rate": 1.0035877281364364e-05,
|
| 1500 |
+
"loss": 0.6384758949279785,
|
| 1501 |
+
"step": 426
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.6589147286821704,
|
| 1505 |
+
"grad_norm": 0.08585374802350998,
|
| 1506 |
+
"learning_rate": 1.0359304182050086e-05,
|
| 1507 |
+
"loss": 0.88965904712677,
|
| 1508 |
+
"step": 428
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.6666666666666665,
|
| 1512 |
+
"grad_norm": 0.09853579103946686,
|
| 1513 |
+
"learning_rate": 1.068912034134155e-05,
|
| 1514 |
+
"loss": 0.6674047708511353,
|
| 1515 |
+
"step": 430
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.6744186046511627,
|
| 1519 |
+
"grad_norm": 0.09648997336626053,
|
| 1520 |
+
"learning_rate": 1.1025019943862524e-05,
|
| 1521 |
+
"loss": 0.8478899002075195,
|
| 1522 |
+
"step": 432
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.6821705426356588,
|
| 1526 |
+
"grad_norm": 0.07512516528367996,
|
| 1527 |
+
"learning_rate": 1.1366691533486839e-05,
|
| 1528 |
+
"loss": 0.6321271061897278,
|
| 1529 |
+
"step": 434
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.689922480620155,
|
| 1533 |
+
"grad_norm": 0.052200138568878174,
|
| 1534 |
+
"learning_rate": 1.171381830212979e-05,
|
| 1535 |
+
"loss": 0.6788074970245361,
|
| 1536 |
+
"step": 436
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.697674418604651,
|
| 1540 |
+
"grad_norm": 0.05563069507479668,
|
| 1541 |
+
"learning_rate": 1.2066078383502049e-05,
|
| 1542 |
+
"loss": 0.6934828758239746,
|
| 1543 |
+
"step": 438
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.7054263565891472,
|
| 1547 |
+
"grad_norm": 0.07190771400928497,
|
| 1548 |
+
"learning_rate": 1.242314515155367e-05,
|
| 1549 |
+
"loss": 0.617615282535553,
|
| 1550 |
+
"step": 440
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.7131782945736433,
|
| 1554 |
+
"grad_norm": 0.0535132996737957,
|
| 1555 |
+
"learning_rate": 1.2784687523331521e-05,
|
| 1556 |
+
"loss": 0.7270308136940002,
|
| 1557 |
+
"step": 442
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.7209302325581395,
|
| 1561 |
+
"grad_norm": 0.07645192742347717,
|
| 1562 |
+
"learning_rate": 1.3150370265969243e-05,
|
| 1563 |
+
"loss": 0.5209411978721619,
|
| 1564 |
+
"step": 444
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.7286821705426356,
|
| 1568 |
+
"grad_norm": 0.05032151937484741,
|
| 1569 |
+
"learning_rate": 1.3519854307525166e-05,
|
| 1570 |
+
"loss": 0.8537179231643677,
|
| 1571 |
+
"step": 446
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.7364341085271318,
|
| 1575 |
+
"grad_norm": 0.0833229050040245,
|
| 1576 |
+
"learning_rate": 1.3892797051379974e-05,
|
| 1577 |
+
"loss": 0.8147948980331421,
|
| 1578 |
+
"step": 448
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.744186046511628,
|
| 1582 |
+
"grad_norm": 0.05039038509130478,
|
| 1583 |
+
"learning_rate": 1.4268852693902394e-05,
|
| 1584 |
+
"loss": 0.8937851190567017,
|
| 1585 |
+
"step": 450
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.751937984496124,
|
| 1589 |
+
"grad_norm": 0.046379536390304565,
|
| 1590 |
+
"learning_rate": 1.4647672545088743e-05,
|
| 1591 |
+
"loss": 0.9495609402656555,
|
| 1592 |
+
"step": 452
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.7596899224806202,
|
| 1596 |
+
"grad_norm": 0.15748457610607147,
|
| 1597 |
+
"learning_rate": 1.5028905351878626e-05,
|
| 1598 |
+
"loss": 0.6565471887588501,
|
| 1599 |
+
"step": 454
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.7674418604651163,
|
| 1603 |
+
"grad_norm": 0.06636267155408859,
|
| 1604 |
+
"learning_rate": 1.5412197623847304e-05,
|
| 1605 |
+
"loss": 0.6486067175865173,
|
| 1606 |
+
"step": 456
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.7751937984496124,
|
| 1610 |
+
"grad_norm": 0.2050524801015854,
|
| 1611 |
+
"learning_rate": 1.5797193960972498e-05,
|
| 1612 |
+
"loss": 0.44677096605300903,
|
| 1613 |
+
"step": 458
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.7829457364341086,
|
| 1617 |
+
"grad_norm": 0.06217222660779953,
|
| 1618 |
+
"learning_rate": 1.6183537383171904e-05,
|
| 1619 |
+
"loss": 0.5162793397903442,
|
| 1620 |
+
"step": 460
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.7906976744186047,
|
| 1624 |
+
"grad_norm": 0.040993690490722656,
|
| 1625 |
+
"learning_rate": 1.6570869661305794e-05,
|
| 1626 |
+
"loss": 0.6910752654075623,
|
| 1627 |
+
"step": 462
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.7984496124031009,
|
| 1631 |
+
"grad_norm": 0.08061198890209198,
|
| 1632 |
+
"learning_rate": 1.6958831649337716e-05,
|
| 1633 |
+
"loss": 0.8616082668304443,
|
| 1634 |
+
"step": 464
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.806201550387597,
|
| 1638 |
+
"grad_norm": 0.04601367563009262,
|
| 1639 |
+
"learning_rate": 1.7347063617345443e-05,
|
| 1640 |
+
"loss": 0.7291563153266907,
|
| 1641 |
+
"step": 466
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.8139534883720931,
|
| 1645 |
+
"grad_norm": 0.047357648611068726,
|
| 1646 |
+
"learning_rate": 1.773520558507325e-05,
|
| 1647 |
+
"loss": 0.6221119165420532,
|
| 1648 |
+
"step": 468
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.8217054263565893,
|
| 1652 |
+
"grad_norm": 0.051967669278383255,
|
| 1653 |
+
"learning_rate": 1.812289765571636e-05,
|
| 1654 |
+
"loss": 0.3711574971675873,
|
| 1655 |
+
"step": 470
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.8294573643410854,
|
| 1659 |
+
"grad_norm": 0.06112854182720184,
|
| 1660 |
+
"learning_rate": 1.8509780349628006e-05,
|
| 1661 |
+
"loss": 1.0664476156234741,
|
| 1662 |
+
"step": 472
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.8372093023255816,
|
| 1666 |
+
"grad_norm": 0.05628122389316559,
|
| 1667 |
+
"learning_rate": 1.889549493763964e-05,
|
| 1668 |
+
"loss": 0.517056405544281,
|
| 1669 |
+
"step": 474
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.8449612403100775,
|
| 1673 |
+
"grad_norm": 0.08481237292289734,
|
| 1674 |
+
"learning_rate": 1.9279683773685313e-05,
|
| 1675 |
+
"loss": 0.6204915046691895,
|
| 1676 |
+
"step": 476
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.8527131782945736,
|
| 1680 |
+
"grad_norm": 0.06115817651152611,
|
| 1681 |
+
"learning_rate": 1.9661990626421812e-05,
|
| 1682 |
+
"loss": 0.5971916913986206,
|
| 1683 |
+
"step": 478
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.8604651162790697,
|
| 1687 |
+
"grad_norm": 0.05057134851813316,
|
| 1688 |
+
"learning_rate": 2.0042061009536956e-05,
|
| 1689 |
+
"loss": 0.8469266295433044,
|
| 1690 |
+
"step": 480
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.8682170542635659,
|
| 1694 |
+
"grad_norm": 0.056389980018138885,
|
| 1695 |
+
"learning_rate": 2.041954251043988e-05,
|
| 1696 |
+
"loss": 0.5026958584785461,
|
| 1697 |
+
"step": 482
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.875968992248062,
|
| 1701 |
+
"grad_norm": 0.24311350286006927,
|
| 1702 |
+
"learning_rate": 2.079408511702847e-05,
|
| 1703 |
+
"loss": 0.7969828248023987,
|
| 1704 |
+
"step": 484
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.8837209302325582,
|
| 1708 |
+
"grad_norm": 0.06835257261991501,
|
| 1709 |
+
"learning_rate": 2.1165341542231086e-05,
|
| 1710 |
+
"loss": 0.8827776908874512,
|
| 1711 |
+
"step": 486
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.8914728682170543,
|
| 1715 |
+
"grad_norm": 0.08240044862031937,
|
| 1716 |
+
"learning_rate": 2.15329675460214e-05,
|
| 1717 |
+
"loss": 0.5578112006187439,
|
| 1718 |
+
"step": 488
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.8992248062015504,
|
| 1722 |
+
"grad_norm": 0.18629829585552216,
|
| 1723 |
+
"learning_rate": 2.189662225460808e-05,
|
| 1724 |
+
"loss": 0.6527209281921387,
|
| 1725 |
+
"step": 490
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.9069767441860463,
|
| 1729 |
+
"grad_norm": 0.20755064487457275,
|
| 1730 |
+
"learning_rate": 2.2255968476503105e-05,
|
| 1731 |
+
"loss": 0.5279259085655212,
|
| 1732 |
+
"step": 492
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.9147286821705425,
|
| 1736 |
+
"grad_norm": 0.10236147791147232,
|
| 1737 |
+
"learning_rate": 2.2610673015175764e-05,
|
| 1738 |
+
"loss": 0.5332280397415161,
|
| 1739 |
+
"step": 494
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.9224806201550386,
|
| 1743 |
+
"grad_norm": 0.06894674897193909,
|
| 1744 |
+
"learning_rate": 2.296040697800243e-05,
|
| 1745 |
+
"loss": 0.5644171237945557,
|
| 1746 |
+
"step": 496
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.9302325581395348,
|
| 1750 |
+
"grad_norm": 0.06815814226865768,
|
| 1751 |
+
"learning_rate": 2.3304846081225598e-05,
|
| 1752 |
+
"loss": 0.4328697621822357,
|
| 1753 |
+
"step": 498
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.937984496124031,
|
| 1757 |
+
"grad_norm": 0.05157966539263725,
|
| 1758 |
+
"learning_rate": 2.3643670950639452e-05,
|
| 1759 |
+
"loss": 1.0288827419281006,
|
| 1760 |
+
"step": 500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.945736434108527,
|
| 1764 |
+
"grad_norm": 0.09934229403734207,
|
| 1765 |
+
"learning_rate": 2.3976567417723124e-05,
|
| 1766 |
+
"loss": 0.7295251488685608,
|
| 1767 |
+
"step": 502
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.9534883720930232,
|
| 1771 |
+
"grad_norm": 0.048644986003637314,
|
| 1772 |
+
"learning_rate": 2.4303226810947168e-05,
|
| 1773 |
+
"loss": 0.6065406203269958,
|
| 1774 |
+
"step": 504
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.9612403100775193,
|
| 1778 |
+
"grad_norm": 0.04483645409345627,
|
| 1779 |
+
"learning_rate": 2.462334624198297e-05,
|
| 1780 |
+
"loss": 0.9802693724632263,
|
| 1781 |
+
"step": 506
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.9689922480620154,
|
| 1785 |
+
"grad_norm": 0.04317508637905121,
|
| 1786 |
+
"learning_rate": 2.4936628886549827e-05,
|
| 1787 |
+
"loss": 0.7508119344711304,
|
| 1788 |
+
"step": 508
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.9767441860465116,
|
| 1792 |
+
"grad_norm": 0.04037319868803024,
|
| 1793 |
+
"learning_rate": 2.524278425963931e-05,
|
| 1794 |
+
"loss": 0.9507177472114563,
|
| 1795 |
+
"step": 510
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.9844961240310077,
|
| 1799 |
+
"grad_norm": 0.09510686993598938,
|
| 1800 |
+
"learning_rate": 2.5541528484861597e-05,
|
| 1801 |
+
"loss": 0.7446141242980957,
|
| 1802 |
+
"step": 512
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.9922480620155039,
|
| 1806 |
+
"grad_norm": 0.05790317803621292,
|
| 1807 |
+
"learning_rate": 2.583258455766412e-05,
|
| 1808 |
+
"loss": 1.0172169208526611,
|
| 1809 |
+
"step": 514
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.0,
|
| 1813 |
+
"grad_norm": 0.06235863268375397,
|
| 1814 |
+
"learning_rate": 2.6115682602178452e-05,
|
| 1815 |
+
"loss": 0.8593966364860535,
|
| 1816 |
+
"step": 516
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.007751937984496,
|
| 1820 |
+
"grad_norm": 0.10687481611967087,
|
| 1821 |
+
"learning_rate": 2.6390560121457266e-05,
|
| 1822 |
+
"loss": 0.49814847111701965,
|
| 1823 |
+
"step": 518
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.0155038759689923,
|
| 1827 |
+
"grad_norm": 0.06080131232738495,
|
| 1828 |
+
"learning_rate": 2.665696224086932e-05,
|
| 1829 |
+
"loss": 0.6426661610603333,
|
| 1830 |
+
"step": 520
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.0232558139534884,
|
| 1834 |
+
"grad_norm": 0.05089246854186058,
|
| 1835 |
+
"learning_rate": 2.6914641944426832e-05,
|
| 1836 |
+
"loss": 0.3929331600666046,
|
| 1837 |
+
"step": 522
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.0310077519379846,
|
| 1841 |
+
"grad_norm": 0.052005868405103683,
|
| 1842 |
+
"learning_rate": 2.7163360303826028e-05,
|
| 1843 |
+
"loss": 0.7454217672348022,
|
| 1844 |
+
"step": 524
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.0387596899224807,
|
| 1848 |
+
"grad_norm": 0.08798030763864517,
|
| 1849 |
+
"learning_rate": 2.7402886699988654e-05,
|
| 1850 |
+
"loss": 0.555336594581604,
|
| 1851 |
+
"step": 526
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.046511627906977,
|
| 1855 |
+
"grad_norm": 0.08520969748497009,
|
| 1856 |
+
"learning_rate": 2.7632999036898793e-05,
|
| 1857 |
+
"loss": 0.7960832118988037,
|
| 1858 |
+
"step": 528
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.054263565891473,
|
| 1862 |
+
"grad_norm": 0.11796343326568604,
|
| 1863 |
+
"learning_rate": 2.7853483947536958e-05,
|
| 1864 |
+
"loss": 0.32746729254722595,
|
| 1865 |
+
"step": 530
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.062015503875969,
|
| 1869 |
+
"grad_norm": 0.08845008909702301,
|
| 1870 |
+
"learning_rate": 2.806413699172034e-05,
|
| 1871 |
+
"loss": 0.6935387253761292,
|
| 1872 |
+
"step": 532
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.0697674418604652,
|
| 1876 |
+
"grad_norm": 0.0798339694738388,
|
| 1877 |
+
"learning_rate": 2.8264762845665833e-05,
|
| 1878 |
+
"loss": 0.43687596917152405,
|
| 1879 |
+
"step": 534
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.0775193798449614,
|
| 1883 |
+
"grad_norm": 0.13349516689777374,
|
| 1884 |
+
"learning_rate": 2.8455175483100068e-05,
|
| 1885 |
+
"loss": 0.5209518671035767,
|
| 1886 |
+
"step": 536
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.0852713178294575,
|
| 1890 |
+
"grad_norm": 0.09369954466819763,
|
| 1891 |
+
"learning_rate": 2.8635198347748558e-05,
|
| 1892 |
+
"loss": 0.6955545544624329,
|
| 1893 |
+
"step": 538
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.0930232558139537,
|
| 1897 |
+
"grad_norm": 0.05283479019999504,
|
| 1898 |
+
"learning_rate": 2.8804664517043884e-05,
|
| 1899 |
+
"loss": 0.5326330661773682,
|
| 1900 |
+
"step": 540
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.10077519379845,
|
| 1904 |
+
"grad_norm": 0.08794603496789932,
|
| 1905 |
+
"learning_rate": 2.896341685690131e-05,
|
| 1906 |
+
"loss": 0.2991466224193573,
|
| 1907 |
+
"step": 542
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.108527131782946,
|
| 1911 |
+
"grad_norm": 0.061321720480918884,
|
| 1912 |
+
"learning_rate": 2.911130816741817e-05,
|
| 1913 |
+
"loss": 0.6528932452201843,
|
| 1914 |
+
"step": 544
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.116279069767442,
|
| 1918 |
+
"grad_norm": 0.054165348410606384,
|
| 1919 |
+
"learning_rate": 2.9248201319362058e-05,
|
| 1920 |
+
"loss": 0.4507254660129547,
|
| 1921 |
+
"step": 546
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.124031007751938,
|
| 1925 |
+
"grad_norm": 0.049841977655887604,
|
| 1926 |
+
"learning_rate": 2.937396938132106e-05,
|
| 1927 |
+
"loss": 0.5575969219207764,
|
| 1928 |
+
"step": 548
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.1317829457364343,
|
| 1932 |
+
"grad_norm": 0.0796908587217331,
|
| 1933 |
+
"learning_rate": 2.94884957373984e-05,
|
| 1934 |
+
"loss": 0.34075814485549927,
|
| 1935 |
+
"step": 550
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.13953488372093,
|
| 1939 |
+
"grad_norm": 0.0508221872150898,
|
| 1940 |
+
"learning_rate": 2.959167419534217e-05,
|
| 1941 |
+
"loss": 0.6530574560165405,
|
| 1942 |
+
"step": 552
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.147286821705426,
|
| 1946 |
+
"grad_norm": 0.04539173096418381,
|
| 1947 |
+
"learning_rate": 2.968340908500995e-05,
|
| 1948 |
+
"loss": 0.6907740831375122,
|
| 1949 |
+
"step": 554
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.1550387596899223,
|
| 1953 |
+
"grad_norm": 0.058205924928188324,
|
| 1954 |
+
"learning_rate": 2.9763615347076983e-05,
|
| 1955 |
+
"loss": 0.44485923647880554,
|
| 1956 |
+
"step": 556
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.1627906976744184,
|
| 1960 |
+
"grad_norm": 0.06929825246334076,
|
| 1961 |
+
"learning_rate": 2.9832218611905778e-05,
|
| 1962 |
+
"loss": 0.8006160259246826,
|
| 1963 |
+
"step": 558
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.1705426356589146,
|
| 1967 |
+
"grad_norm": 0.04289000853896141,
|
| 1968 |
+
"learning_rate": 2.98891552685038e-05,
|
| 1969 |
+
"loss": 0.4540764391422272,
|
| 1970 |
+
"step": 560
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.1782945736434107,
|
| 1974 |
+
"grad_norm": 0.09553489089012146,
|
| 1975 |
+
"learning_rate": 2.993437252350551e-05,
|
| 1976 |
+
"loss": 0.6768143177032471,
|
| 1977 |
+
"step": 562
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.186046511627907,
|
| 1981 |
+
"grad_norm": 0.07250722497701645,
|
| 1982 |
+
"learning_rate": 2.9967828450123938e-05,
|
| 1983 |
+
"loss": 0.37812501192092896,
|
| 1984 |
+
"step": 564
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.193798449612403,
|
| 1988 |
+
"grad_norm": 0.06566791236400604,
|
| 1989 |
+
"learning_rate": 2.998949202702644e-05,
|
| 1990 |
+
"loss": 0.42279544472694397,
|
| 1991 |
+
"step": 566
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.201550387596899,
|
| 1995 |
+
"grad_norm": 0.04562269151210785,
|
| 1996 |
+
"learning_rate": 2.9999343167098628e-05,
|
| 1997 |
+
"loss": 0.5368779301643372,
|
| 1998 |
+
"step": 568
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.2093023255813953,
|
| 2002 |
+
"grad_norm": 0.18373429775238037,
|
| 2003 |
+
"learning_rate": 2.999737273606972e-05,
|
| 2004 |
+
"loss": 0.2325422167778015,
|
| 2005 |
+
"step": 570
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.2170542635658914,
|
| 2009 |
+
"grad_norm": 0.089279904961586,
|
| 2010 |
+
"learning_rate": 2.9983582560982107e-05,
|
| 2011 |
+
"loss": 0.5718221664428711,
|
| 2012 |
+
"step": 572
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.2248062015503876,
|
| 2016 |
+
"grad_norm": 0.05974709987640381,
|
| 2017 |
+
"learning_rate": 2.9957985428497287e-05,
|
| 2018 |
+
"loss": 0.20123861730098724,
|
| 2019 |
+
"step": 574
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.2325581395348837,
|
| 2023 |
+
"grad_norm": 0.09997298568487167,
|
| 2024 |
+
"learning_rate": 2.992060507303966e-05,
|
| 2025 |
+
"loss": 0.4844609797000885,
|
| 2026 |
+
"step": 576
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.24031007751938,
|
| 2030 |
+
"grad_norm": 0.06058935075998306,
|
| 2031 |
+
"learning_rate": 2.98714761547893e-05,
|
| 2032 |
+
"loss": 0.6003465056419373,
|
| 2033 |
+
"step": 578
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.248062015503876,
|
| 2037 |
+
"grad_norm": 0.10959988087415695,
|
| 2038 |
+
"learning_rate": 2.981064422754395e-05,
|
| 2039 |
+
"loss": 0.49536406993865967,
|
| 2040 |
+
"step": 580
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.255813953488372,
|
| 2044 |
+
"grad_norm": 0.03991486132144928,
|
| 2045 |
+
"learning_rate": 2.9738165696480244e-05,
|
| 2046 |
+
"loss": 0.27629104256629944,
|
| 2047 |
+
"step": 582
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.2635658914728682,
|
| 2051 |
+
"grad_norm": 0.054911598563194275,
|
| 2052 |
+
"learning_rate": 2.9654107765853097e-05,
|
| 2053 |
+
"loss": 0.8991298675537109,
|
| 2054 |
+
"step": 584
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.2713178294573644,
|
| 2058 |
+
"grad_norm": 0.15896278619766235,
|
| 2059 |
+
"learning_rate": 2.955854837668194e-05,
|
| 2060 |
+
"loss": 0.4965202808380127,
|
| 2061 |
+
"step": 586
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.2790697674418605,
|
| 2065 |
+
"grad_norm": 0.04574244096875191,
|
| 2066 |
+
"learning_rate": 2.9451576134481485e-05,
|
| 2067 |
+
"loss": 0.8411018252372742,
|
| 2068 |
+
"step": 588
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.2868217054263567,
|
| 2072 |
+
"grad_norm": 0.049831654876470566,
|
| 2073 |
+
"learning_rate": 2.9333290227104026e-05,
|
| 2074 |
+
"loss": 0.39420267939567566,
|
| 2075 |
+
"step": 590
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.294573643410853,
|
| 2079 |
+
"grad_norm": 0.04978864639997482,
|
| 2080 |
+
"learning_rate": 2.9203800332769538e-05,
|
| 2081 |
+
"loss": 0.6820889115333557,
|
| 2082 |
+
"step": 592
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.302325581395349,
|
| 2086 |
+
"grad_norm": 0.047215450555086136,
|
| 2087 |
+
"learning_rate": 2.906322651836873e-05,
|
| 2088 |
+
"loss": 0.5932551622390747,
|
| 2089 |
+
"step": 594
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.310077519379845,
|
| 2093 |
+
"grad_norm": 0.225591778755188,
|
| 2094 |
+
"learning_rate": 2.891169912813347e-05,
|
| 2095 |
+
"loss": 0.6146702170372009,
|
| 2096 |
+
"step": 596
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.317829457364341,
|
| 2100 |
+
"grad_norm": 0.039774637669324875,
|
| 2101 |
+
"learning_rate": 2.8749358662777702e-05,
|
| 2102 |
+
"loss": 0.5908256769180298,
|
| 2103 |
+
"step": 598
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.3255813953488373,
|
| 2107 |
+
"grad_norm": 0.04213051497936249,
|
| 2108 |
+
"learning_rate": 2.857635564922104e-05,
|
| 2109 |
+
"loss": 0.3715899884700775,
|
| 2110 |
+
"step": 600
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.3333333333333335,
|
| 2114 |
+
"grad_norm": 0.15360774099826813,
|
| 2115 |
+
"learning_rate": 2.8392850501015662e-05,
|
| 2116 |
+
"loss": 0.5040525794029236,
|
| 2117 |
+
"step": 602
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.3410852713178296,
|
| 2121 |
+
"grad_norm": 0.03753961622714996,
|
| 2122 |
+
"learning_rate": 2.819901336960611e-05,
|
| 2123 |
+
"loss": 0.6956257820129395,
|
| 2124 |
+
"step": 604
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.3488372093023258,
|
| 2128 |
+
"grad_norm": 0.11748861521482468,
|
| 2129 |
+
"learning_rate": 2.7995023986559807e-05,
|
| 2130 |
+
"loss": 0.5580706000328064,
|
| 2131 |
+
"step": 606
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.356589147286822,
|
| 2135 |
+
"grad_norm": 0.07652665674686432,
|
| 2136 |
+
"learning_rate": 2.7781071496914573e-05,
|
| 2137 |
+
"loss": 0.7142091989517212,
|
| 2138 |
+
"step": 608
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.3643410852713176,
|
| 2142 |
+
"grad_norm": 0.08042655140161514,
|
| 2143 |
+
"learning_rate": 2.755735428379772e-05,
|
| 2144 |
+
"loss": 0.6314153075218201,
|
| 2145 |
+
"step": 610
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.3720930232558137,
|
| 2149 |
+
"grad_norm": 0.07687707245349884,
|
| 2150 |
+
"learning_rate": 2.7324079784479287e-05,
|
| 2151 |
+
"loss": 0.37621596455574036,
|
| 2152 |
+
"step": 612
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.37984496124031,
|
| 2156 |
+
"grad_norm": 0.0547901950776577,
|
| 2157 |
+
"learning_rate": 2.7081464298030026e-05,
|
| 2158 |
+
"loss": 0.43838873505592346,
|
| 2159 |
+
"step": 614
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.387596899224806,
|
| 2163 |
+
"grad_norm": 0.046424973756074905,
|
| 2164 |
+
"learning_rate": 2.6829732784762465e-05,
|
| 2165 |
+
"loss": 0.6145251989364624,
|
| 2166 |
+
"step": 616
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.395348837209302,
|
| 2170 |
+
"grad_norm": 0.054426416754722595,
|
| 2171 |
+
"learning_rate": 2.656911865764097e-05,
|
| 2172 |
+
"loss": 0.8150652050971985,
|
| 2173 |
+
"step": 618
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.4031007751937983,
|
| 2177 |
+
"grad_norm": 0.04885483533143997,
|
| 2178 |
+
"learning_rate": 2.629986356585431e-05,
|
| 2179 |
+
"loss": 0.5932292342185974,
|
| 2180 |
+
"step": 620
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.4108527131782944,
|
| 2184 |
+
"grad_norm": 0.08931045234203339,
|
| 2185 |
+
"learning_rate": 2.602221717075134e-05,
|
| 2186 |
+
"loss": 0.27623146772384644,
|
| 2187 |
+
"step": 622
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.4186046511627906,
|
| 2191 |
+
"grad_norm": 0.198171466588974,
|
| 2192 |
+
"learning_rate": 2.5736436914347484e-05,
|
| 2193 |
+
"loss": 0.49001190066337585,
|
| 2194 |
+
"step": 624
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.4263565891472867,
|
| 2198 |
+
"grad_norm": 0.06653870642185211,
|
| 2199 |
+
"learning_rate": 2.544278778061694e-05,
|
| 2200 |
+
"loss": 0.362051784992218,
|
| 2201 |
+
"step": 626
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.434108527131783,
|
| 2205 |
+
"grad_norm": 0.045915715396404266,
|
| 2206 |
+
"learning_rate": 2.514154204979152e-05,
|
| 2207 |
+
"loss": 0.7866628766059875,
|
| 2208 |
+
"step": 628
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.441860465116279,
|
| 2212 |
+
"grad_norm": 0.17191638052463531,
|
| 2213 |
+
"learning_rate": 2.483297904589437e-05,
|
| 2214 |
+
"loss": 0.4470142424106598,
|
| 2215 |
+
"step": 630
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 2.449612403100775,
|
| 2219 |
+
"grad_norm": 0.05101427063345909,
|
| 2220 |
+
"learning_rate": 2.451738487774237e-05,
|
| 2221 |
+
"loss": 0.5275189876556396,
|
| 2222 |
+
"step": 632
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.4573643410852712,
|
| 2226 |
+
"grad_norm": 0.21946240961551666,
|
| 2227 |
+
"learning_rate": 2.419505217365756e-05,
|
| 2228 |
+
"loss": 0.4540758728981018,
|
| 2229 |
+
"step": 634
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 2.4651162790697674,
|
| 2233 |
+
"grad_norm": 0.04593559727072716,
|
| 2234 |
+
"learning_rate": 2.3866279810133385e-05,
|
| 2235 |
+
"loss": 0.6065298914909363,
|
| 2236 |
+
"step": 636
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.4728682170542635,
|
| 2240 |
+
"grad_norm": 0.059740740805864334,
|
| 2241 |
+
"learning_rate": 2.3531372634707517e-05,
|
| 2242 |
+
"loss": 0.4904002249240875,
|
| 2243 |
+
"step": 638
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 2.4806201550387597,
|
| 2247 |
+
"grad_norm": 0.050732191652059555,
|
| 2248 |
+
"learning_rate": 2.3190641183298133e-05,
|
| 2249 |
+
"loss": 0.5315344929695129,
|
| 2250 |
+
"step": 640
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.488372093023256,
|
| 2254 |
+
"grad_norm": 0.08542405068874359,
|
| 2255 |
+
"learning_rate": 2.2844401392265773e-05,
|
| 2256 |
+
"loss": 0.5050536394119263,
|
| 2257 |
+
"step": 642
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.496124031007752,
|
| 2261 |
+
"grad_norm": 0.05612539127469063,
|
| 2262 |
+
"learning_rate": 2.2492974305467652e-05,
|
| 2263 |
+
"loss": 0.6769103407859802,
|
| 2264 |
+
"step": 644
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.503875968992248,
|
| 2268 |
+
"grad_norm": 0.08466104418039322,
|
| 2269 |
+
"learning_rate": 2.213668577657632e-05,
|
| 2270 |
+
"loss": 0.6569755673408508,
|
| 2271 |
+
"step": 646
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.511627906976744,
|
| 2275 |
+
"grad_norm": 0.06182940676808357,
|
| 2276 |
+
"learning_rate": 2.177586616693837e-05,
|
| 2277 |
+
"loss": 0.8741461038589478,
|
| 2278 |
+
"step": 648
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.5193798449612403,
|
| 2282 |
+
"grad_norm": 0.10157312452793121,
|
| 2283 |
+
"learning_rate": 2.141085003925353e-05,
|
| 2284 |
+
"loss": 0.25412437319755554,
|
| 2285 |
+
"step": 650
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.5271317829457365,
|
| 2289 |
+
"grad_norm": 0.048401493579149246,
|
| 2290 |
+
"learning_rate": 2.1041975847358226e-05,
|
| 2291 |
+
"loss": 0.5729293823242188,
|
| 2292 |
+
"step": 652
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.5348837209302326,
|
| 2296 |
+
"grad_norm": 0.04819415509700775,
|
| 2297 |
+
"learning_rate": 2.066958562240101e-05,
|
| 2298 |
+
"loss": 0.38875052332878113,
|
| 2299 |
+
"step": 654
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.5426356589147288,
|
| 2303 |
+
"grad_norm": 0.055878717452287674,
|
| 2304 |
+
"learning_rate": 2.029402465570114e-05,
|
| 2305 |
+
"loss": 0.5112055540084839,
|
| 2306 |
+
"step": 656
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.550387596899225,
|
| 2310 |
+
"grad_norm": 0.07780204713344574,
|
| 2311 |
+
"learning_rate": 1.9915641178584115e-05,
|
| 2312 |
+
"loss": 0.6484737992286682,
|
| 2313 |
+
"step": 658
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.558139534883721,
|
| 2317 |
+
"grad_norm": 0.05842196196317673,
|
| 2318 |
+
"learning_rate": 1.953478603949128e-05,
|
| 2319 |
+
"loss": 0.6154912114143372,
|
| 2320 |
+
"step": 660
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.565891472868217,
|
| 2324 |
+
"grad_norm": 0.060033708810806274,
|
| 2325 |
+
"learning_rate": 1.9151812378662645e-05,
|
| 2326 |
+
"loss": 0.6602538228034973,
|
| 2327 |
+
"step": 662
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 2.5736434108527133,
|
| 2331 |
+
"grad_norm": 0.06244450435042381,
|
| 2332 |
+
"learning_rate": 1.8767075300694745e-05,
|
| 2333 |
+
"loss": 0.3542620837688446,
|
| 2334 |
+
"step": 664
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.5813953488372094,
|
| 2338 |
+
"grad_norm": 0.04792879521846771,
|
| 2339 |
+
"learning_rate": 1.8380931545277047e-05,
|
| 2340 |
+
"loss": 0.5548843145370483,
|
| 2341 |
+
"step": 666
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.5891472868217056,
|
| 2345 |
+
"grad_norm": 0.06219867989420891,
|
| 2346 |
+
"learning_rate": 1.7993739156412294e-05,
|
| 2347 |
+
"loss": 0.4414609968662262,
|
| 2348 |
+
"step": 668
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.5968992248062017,
|
| 2352 |
+
"grad_norm": 0.20640681684017181,
|
| 2353 |
+
"learning_rate": 1.7605857150427447e-05,
|
| 2354 |
+
"loss": 0.5872040390968323,
|
| 2355 |
+
"step": 670
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 2.604651162790698,
|
| 2359 |
+
"grad_norm": 0.10361964255571365,
|
| 2360 |
+
"learning_rate": 1.7217645183082965e-05,
|
| 2361 |
+
"loss": 0.42644187808036804,
|
| 2362 |
+
"step": 672
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 2.612403100775194,
|
| 2366 |
+
"grad_norm": 0.04928445816040039,
|
| 2367 |
+
"learning_rate": 1.682946321608938e-05,
|
| 2368 |
+
"loss": 0.7362091541290283,
|
| 2369 |
+
"step": 674
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 2.62015503875969,
|
| 2373 |
+
"grad_norm": 0.047589972615242004,
|
| 2374 |
+
"learning_rate": 1.6441671183339962e-05,
|
| 2375 |
+
"loss": 0.6339392066001892,
|
| 2376 |
+
"step": 676
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 2.6279069767441863,
|
| 2380 |
+
"grad_norm": 0.0819360688328743,
|
| 2381 |
+
"learning_rate": 1.605462865716936e-05,
|
| 2382 |
+
"loss": 0.9860416650772095,
|
| 2383 |
+
"step": 678
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 2.6356589147286824,
|
| 2387 |
+
"grad_norm": 0.04943787679076195,
|
| 2388 |
+
"learning_rate": 1.566869451494735e-05,
|
| 2389 |
+
"loss": 0.8548033237457275,
|
| 2390 |
+
"step": 680
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 2.6434108527131785,
|
| 2394 |
+
"grad_norm": 0.04377022013068199,
|
| 2395 |
+
"learning_rate": 1.5284226606317093e-05,
|
| 2396 |
+
"loss": 0.44147443771362305,
|
| 2397 |
+
"step": 682
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 2.6511627906976747,
|
| 2401 |
+
"grad_norm": 0.07998047769069672,
|
| 2402 |
+
"learning_rate": 1.4901581421386185e-05,
|
| 2403 |
+
"loss": 0.6076138615608215,
|
| 2404 |
+
"step": 684
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 2.6589147286821704,
|
| 2408 |
+
"grad_norm": 0.06454984098672867,
|
| 2409 |
+
"learning_rate": 1.4521113760178527e-05,
|
| 2410 |
+
"loss": 0.5302262902259827,
|
| 2411 |
+
"step": 686
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 2.6666666666666665,
|
| 2415 |
+
"grad_norm": 0.04626493155956268,
|
| 2416 |
+
"learning_rate": 1.414317640365306e-05,
|
| 2417 |
+
"loss": 0.34584927558898926,
|
| 2418 |
+
"step": 688
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 2.6744186046511627,
|
| 2422 |
+
"grad_norm": 0.051621273159980774,
|
| 2423 |
+
"learning_rate": 1.3768119786594849e-05,
|
| 2424 |
+
"loss": 0.409042626619339,
|
| 2425 |
+
"step": 690
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 2.682170542635659,
|
| 2429 |
+
"grad_norm": 0.04060710594058037,
|
| 2430 |
+
"learning_rate": 1.3396291672681374e-05,
|
| 2431 |
+
"loss": 0.6091200113296509,
|
| 2432 |
+
"step": 692
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 2.689922480620155,
|
| 2436 |
+
"grad_norm": 0.08434680104255676,
|
| 2437 |
+
"learning_rate": 1.3028036832025761e-05,
|
| 2438 |
+
"loss": 0.5412120819091797,
|
| 2439 |
+
"step": 694
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 2.697674418604651,
|
| 2443 |
+
"grad_norm": 0.08353015780448914,
|
| 2444 |
+
"learning_rate": 1.2663696721495657e-05,
|
| 2445 |
+
"loss": 0.4864289462566376,
|
| 2446 |
+
"step": 696
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 2.705426356589147,
|
| 2450 |
+
"grad_norm": 0.05606602877378464,
|
| 2451 |
+
"learning_rate": 1.2303609168104158e-05,
|
| 2452 |
+
"loss": 0.6230313777923584,
|
| 2453 |
+
"step": 698
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 2.7131782945736433,
|
| 2457 |
+
"grad_norm": 0.05251370370388031,
|
| 2458 |
+
"learning_rate": 1.1948108055766654e-05,
|
| 2459 |
+
"loss": 0.5568596124649048,
|
| 2460 |
+
"step": 700
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 2.7209302325581395,
|
| 2464 |
+
"grad_norm": 0.06997047364711761,
|
| 2465 |
+
"learning_rate": 1.159752301571363e-05,
|
| 2466 |
+
"loss": 0.6038510799407959,
|
| 2467 |
+
"step": 702
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.7286821705426356,
|
| 2471 |
+
"grad_norm": 0.055278290063142776,
|
| 2472 |
+
"learning_rate": 1.1252179120846778e-05,
|
| 2473 |
+
"loss": 0.4581022262573242,
|
| 2474 |
+
"step": 704
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 2.7364341085271318,
|
| 2478 |
+
"grad_norm": 0.09902060031890869,
|
| 2479 |
+
"learning_rate": 1.0912396584321704e-05,
|
| 2480 |
+
"loss": 0.3432044982910156,
|
| 2481 |
+
"step": 706
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 2.744186046511628,
|
| 2485 |
+
"grad_norm": 0.039606984704732895,
|
| 2486 |
+
"learning_rate": 1.0578490462636758e-05,
|
| 2487 |
+
"loss": 0.47076573967933655,
|
| 2488 |
+
"step": 708
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 2.751937984496124,
|
| 2492 |
+
"grad_norm": 0.0477338470518589,
|
| 2493 |
+
"learning_rate": 1.0250770363503242e-05,
|
| 2494 |
+
"loss": 0.5192364454269409,
|
| 2495 |
+
"step": 710
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 2.75968992248062,
|
| 2499 |
+
"grad_norm": 0.05086624622344971,
|
| 2500 |
+
"learning_rate": 9.929540158767916e-06,
|
| 2501 |
+
"loss": 0.5344876050949097,
|
| 2502 |
+
"step": 712
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 2.7674418604651163,
|
| 2506 |
+
"grad_norm": 0.054383717477321625,
|
| 2507 |
+
"learning_rate": 9.615097702653961e-06,
|
| 2508 |
+
"loss": 0.43612009286880493,
|
| 2509 |
+
"step": 714
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 2.7751937984496124,
|
| 2513 |
+
"grad_norm": 0.14214906096458435,
|
| 2514 |
+
"learning_rate": 9.307734555581662e-06,
|
| 2515 |
+
"loss": 0.3253142535686493,
|
| 2516 |
+
"step": 716
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 2.7829457364341086,
|
| 2520 |
+
"grad_norm": 0.0564068928360939,
|
| 2521 |
+
"learning_rate": 9.007735713824893e-06,
|
| 2522 |
+
"loss": 0.6681756973266602,
|
| 2523 |
+
"step": 718
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 2.7906976744186047,
|
| 2527 |
+
"grad_norm": 0.06708779186010361,
|
| 2528 |
+
"learning_rate": 8.715379345254077e-06,
|
| 2529 |
+
"loss": 0.5442537665367126,
|
| 2530 |
+
"step": 720
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 2.798449612403101,
|
| 2534 |
+
"grad_norm": 0.0515008307993412,
|
| 2535 |
+
"learning_rate": 8.43093653141064e-06,
|
| 2536 |
+
"loss": 0.4479949176311493,
|
| 2537 |
+
"step": 722
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 2.806201550387597,
|
| 2541 |
+
"grad_norm": 0.05638190731406212,
|
| 2542 |
+
"learning_rate": 8.15467101615213e-06,
|
| 2543 |
+
"loss": 0.5014258623123169,
|
| 2544 |
+
"step": 724
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 2.813953488372093,
|
| 2548 |
+
"grad_norm": 0.10201210528612137,
|
| 2549 |
+
"learning_rate": 7.886838961101036e-06,
|
| 2550 |
+
"loss": 0.46058180928230286,
|
| 2551 |
+
"step": 726
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 2.8217054263565893,
|
| 2555 |
+
"grad_norm": 0.04419756308197975,
|
| 2556 |
+
"learning_rate": 7.627688708124106e-06,
|
| 2557 |
+
"loss": 0.5526507496833801,
|
| 2558 |
+
"step": 728
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 2.8294573643410854,
|
| 2562 |
+
"grad_norm": 0.04845201596617699,
|
| 2563 |
+
"learning_rate": 7.377460549062367e-06,
|
| 2564 |
+
"loss": 0.5275202989578247,
|
| 2565 |
+
"step": 730
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 2.8372093023255816,
|
| 2569 |
+
"grad_norm": 0.04706037789583206,
|
| 2570 |
+
"learning_rate": 7.13638650292535e-06,
|
| 2571 |
+
"loss": 0.507082998752594,
|
| 2572 |
+
"step": 732
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 2.8449612403100772,
|
| 2576 |
+
"grad_norm": 0.09409839659929276,
|
| 2577 |
+
"learning_rate": 6.904690100756159e-06,
|
| 2578 |
+
"loss": 0.47032397985458374,
|
| 2579 |
+
"step": 734
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 2.8527131782945734,
|
| 2583 |
+
"grad_norm": 0.052645258605480194,
|
| 2584 |
+
"learning_rate": 6.682586178366833e-06,
|
| 2585 |
+
"loss": 0.5226138830184937,
|
| 2586 |
+
"step": 736
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 2.8604651162790695,
|
| 2590 |
+
"grad_norm": 0.1135181188583374,
|
| 2591 |
+
"learning_rate": 6.470280677136127e-06,
|
| 2592 |
+
"loss": 0.47321808338165283,
|
| 2593 |
+
"step": 738
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 2.8682170542635657,
|
| 2597 |
+
"grad_norm": 0.17483681440353394,
|
| 2598 |
+
"learning_rate": 6.267970453054588e-06,
|
| 2599 |
+
"loss": 0.3441992700099945,
|
| 2600 |
+
"step": 740
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 2.875968992248062,
|
| 2604 |
+
"grad_norm": 0.0963001623749733,
|
| 2605 |
+
"learning_rate": 6.075843094193802e-06,
|
| 2606 |
+
"loss": 0.4783623516559601,
|
| 2607 |
+
"step": 742
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 2.883720930232558,
|
| 2611 |
+
"grad_norm": 0.06458084285259247,
|
| 2612 |
+
"learning_rate": 5.894076746769099e-06,
|
| 2613 |
+
"loss": 0.55689537525177,
|
| 2614 |
+
"step": 744
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 2.891472868217054,
|
| 2618 |
+
"grad_norm": 0.08305259048938751,
|
| 2619 |
+
"learning_rate": 5.722839949957098e-06,
|
| 2620 |
+
"loss": 0.46318957209587097,
|
| 2621 |
+
"step": 746
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 2.89922480620155,
|
| 2625 |
+
"grad_norm": 0.04614809900522232,
|
| 2626 |
+
"learning_rate": 5.56229147962116e-06,
|
| 2627 |
+
"loss": 0.5878427624702454,
|
| 2628 |
+
"step": 748
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 2.9069767441860463,
|
| 2632 |
+
"grad_norm": 0.06380455940961838,
|
| 2633 |
+
"learning_rate": 5.412580201089678e-06,
|
| 2634 |
+
"loss": 0.3637682795524597,
|
| 2635 |
+
"step": 750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 2.9147286821705425,
|
| 2639 |
+
"grad_norm": 0.08269240707159042,
|
| 2640 |
+
"learning_rate": 5.273844931123672e-06,
|
| 2641 |
+
"loss": 0.5682251453399658,
|
| 2642 |
+
"step": 752
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 2.9224806201550386,
|
| 2646 |
+
"grad_norm": 0.04752229154109955,
|
| 2647 |
+
"learning_rate": 5.146214309201799e-06,
|
| 2648 |
+
"loss": 0.4354322850704193,
|
| 2649 |
+
"step": 754
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 2.9302325581395348,
|
| 2653 |
+
"grad_norm": 0.08373939245939255,
|
| 2654 |
+
"learning_rate": 5.029806678241959e-06,
|
| 2655 |
+
"loss": 0.801591694355011,
|
| 2656 |
+
"step": 756
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 2.937984496124031,
|
| 2660 |
+
"grad_norm": 0.047429829835891724,
|
| 2661 |
+
"learning_rate": 4.924729974870227e-06,
|
| 2662 |
+
"loss": 0.6289284229278564,
|
| 2663 |
+
"step": 758
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 2.945736434108527,
|
| 2667 |
+
"grad_norm": 0.07736939191818237,
|
| 2668 |
+
"learning_rate": 4.831081629338789e-06,
|
| 2669 |
+
"loss": 0.6334935426712036,
|
| 2670 |
+
"step": 760
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 2.953488372093023,
|
| 2674 |
+
"grad_norm": 0.04397986829280853,
|
| 2675 |
+
"learning_rate": 4.74894847518571e-06,
|
| 2676 |
+
"loss": 0.6884579658508301,
|
| 2677 |
+
"step": 762
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 2.9612403100775193,
|
| 2681 |
+
"grad_norm": 0.05032786726951599,
|
| 2682 |
+
"learning_rate": 4.678406668720287e-06,
|
| 2683 |
+
"loss": 0.7347701191902161,
|
| 2684 |
+
"step": 764
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 2.9689922480620154,
|
| 2688 |
+
"grad_norm": 0.11958435922861099,
|
| 2689 |
+
"learning_rate": 4.61952161840865e-06,
|
| 2690 |
+
"loss": 0.24074648320674896,
|
| 2691 |
+
"step": 766
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 2.9767441860465116,
|
| 2695 |
+
"grad_norm": 0.078817218542099,
|
| 2696 |
+
"learning_rate": 4.572347924225084e-06,
|
| 2697 |
+
"loss": 0.32004672288894653,
|
| 2698 |
+
"step": 768
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 2.9844961240310077,
|
| 2702 |
+
"grad_norm": 0.036485981196165085,
|
| 2703 |
+
"learning_rate": 4.536929327025298e-06,
|
| 2704 |
+
"loss": 0.3227121829986572,
|
| 2705 |
+
"step": 770
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 2.992248062015504,
|
| 2709 |
+
"grad_norm": 0.041053567081689835,
|
| 2710 |
+
"learning_rate": 4.51329866798861e-06,
|
| 2711 |
+
"loss": 0.6057068109512329,
|
| 2712 |
+
"step": 772
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 3.0,
|
| 2716 |
+
"grad_norm": 0.11451369524002075,
|
| 2717 |
+
"learning_rate": 4.501477858166617e-06,
|
| 2718 |
+
"loss": 0.16319799423217773,
|
| 2719 |
+
"step": 774
|
| 2720 |
+
}
|
| 2721 |
+
],
|
| 2722 |
+
"logging_steps": 2,
|
| 2723 |
+
"max_steps": 774,
|
| 2724 |
+
"num_input_tokens_seen": 0,
|
| 2725 |
+
"num_train_epochs": 3,
|
| 2726 |
+
"save_steps": 99999,
|
| 2727 |
+
"stateful_callbacks": {
|
| 2728 |
+
"TrainerControl": {
|
| 2729 |
+
"args": {
|
| 2730 |
+
"should_epoch_stop": false,
|
| 2731 |
+
"should_evaluate": false,
|
| 2732 |
+
"should_log": false,
|
| 2733 |
+
"should_save": true,
|
| 2734 |
+
"should_training_stop": true
|
| 2735 |
+
},
|
| 2736 |
+
"attributes": {}
|
| 2737 |
+
}
|
| 2738 |
+
},
|
| 2739 |
+
"total_flos": 3.2487544184132076e+18,
|
| 2740 |
+
"train_batch_size": 1,
|
| 2741 |
+
"trial_name": null,
|
| 2742 |
+
"trial_params": null
|
| 2743 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b5648e387ff09f6051c8be8a24456da06c12660d8b77124f42004c1f0aaf38d
|
| 3 |
+
size 5649
|