Add designcoder_qwen3.5_9b_muon_bs16_step3800 (base Qwen3.5-9B, Muon, lr1e-5, global bs16, 2 epochs, step 3800)
Browse files- .gitattributes +1 -0
- designcoder_qwen3.5_9b_muon_bs16_step3800/chat_template.jinja +154 -0
- designcoder_qwen3.5_9b_muon_bs16_step3800/config.json +113 -0
- designcoder_qwen3.5_9b_muon_bs16_step3800/generation_config.json +10 -0
- designcoder_qwen3.5_9b_muon_bs16_step3800/model.safetensors +3 -0
- designcoder_qwen3.5_9b_muon_bs16_step3800/processor_config.json +60 -0
- designcoder_qwen3.5_9b_muon_bs16_step3800/tokenizer.json +3 -0
- designcoder_qwen3.5_9b_muon_bs16_step3800/tokenizer_config.json +34 -0
- designcoder_qwen3.5_9b_muon_bs16_step3800/trainer_state.json +2694 -0
.gitattributes
CHANGED
|
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
designcoder_qwen3.5_4b_muon_bs32_step1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
designcoder_qwen3.5_9b_adamw_bs16_step3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
designcoder_qwen3.5_4b_muon_bs32_step1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
designcoder_qwen3.5_9b_adamw_bs16_step3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
designcoder_qwen3.5_9b_muon_bs16_step3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
designcoder_qwen3.5_9b_muon_bs16_step3800/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 %}
|
designcoder_qwen3.5_9b_muon_bs16_step3800/config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 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": "5.8.0",
|
| 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_vision",
|
| 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 |
+
}
|
designcoder_qwen3.5_9b_muon_bs16_step3800/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": "5.8.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
designcoder_qwen3.5_9b_muon_bs16_step3800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08d6a27506b605935277c3bb5919880c5e971a4d852dc3c724ffb43bf53ae76f
|
| 3 |
+
size 18819722392
|
designcoder_qwen3.5_9b_muon_bs16_step3800/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 |
+
}
|
designcoder_qwen3.5_9b_muon_bs16_step3800/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
designcoder_qwen3.5_9b_muon_bs16_step3800/tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"padding_side": "right",
|
| 26 |
+
"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+",
|
| 27 |
+
"processor_class": "Qwen3VLProcessor",
|
| 28 |
+
"split_special_tokens": false,
|
| 29 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 30 |
+
"unk_token": null,
|
| 31 |
+
"video_token": "<|video_pad|>",
|
| 32 |
+
"vision_bos_token": "<|vision_start|>",
|
| 33 |
+
"vision_eos_token": "<|vision_end|>"
|
| 34 |
+
}
|
designcoder_qwen3.5_9b_muon_bs16_step3800/trainer_state.json
ADDED
|
@@ -0,0 +1,2694 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.005263157894736842,
|
| 14 |
+
"grad_norm": 2.640625,
|
| 15 |
+
"learning_rate": 2.3684210526315792e-07,
|
| 16 |
+
"loss": 0.5265410423278809,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.010526315789473684,
|
| 21 |
+
"grad_norm": 2.765625,
|
| 22 |
+
"learning_rate": 5.000000000000001e-07,
|
| 23 |
+
"loss": 0.5329990863800049,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.015789473684210527,
|
| 28 |
+
"grad_norm": 2.53125,
|
| 29 |
+
"learning_rate": 7.631578947368422e-07,
|
| 30 |
+
"loss": 0.5335685729980468,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.021052631578947368,
|
| 35 |
+
"grad_norm": 2.734375,
|
| 36 |
+
"learning_rate": 1.0263157894736843e-06,
|
| 37 |
+
"loss": 0.5360953330993652,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02631578947368421,
|
| 42 |
+
"grad_norm": 2.546875,
|
| 43 |
+
"learning_rate": 1.2894736842105266e-06,
|
| 44 |
+
"loss": 0.5427813053131103,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.031578947368421054,
|
| 49 |
+
"grad_norm": 2.5625,
|
| 50 |
+
"learning_rate": 1.5526315789473686e-06,
|
| 51 |
+
"loss": 0.5317987918853759,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03684210526315789,
|
| 56 |
+
"grad_norm": 2.34375,
|
| 57 |
+
"learning_rate": 1.8157894736842109e-06,
|
| 58 |
+
"loss": 0.51890869140625,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.042105263157894736,
|
| 63 |
+
"grad_norm": 2.265625,
|
| 64 |
+
"learning_rate": 2.078947368421053e-06,
|
| 65 |
+
"loss": 0.5216401576995849,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04736842105263158,
|
| 70 |
+
"grad_norm": 1.984375,
|
| 71 |
+
"learning_rate": 2.342105263157895e-06,
|
| 72 |
+
"loss": 0.5262482166290283,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.05263157894736842,
|
| 77 |
+
"grad_norm": 1.6796875,
|
| 78 |
+
"learning_rate": 2.605263157894737e-06,
|
| 79 |
+
"loss": 0.5215766906738282,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.05789473684210526,
|
| 84 |
+
"grad_norm": 1.3359375,
|
| 85 |
+
"learning_rate": 2.868421052631579e-06,
|
| 86 |
+
"loss": 0.5157586574554444,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06315789473684211,
|
| 91 |
+
"grad_norm": 1.3125,
|
| 92 |
+
"learning_rate": 3.131578947368421e-06,
|
| 93 |
+
"loss": 0.5264471530914306,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.06842105263157895,
|
| 98 |
+
"grad_norm": 1.125,
|
| 99 |
+
"learning_rate": 3.3947368421052636e-06,
|
| 100 |
+
"loss": 0.516934871673584,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.07368421052631578,
|
| 105 |
+
"grad_norm": 1.03125,
|
| 106 |
+
"learning_rate": 3.657894736842106e-06,
|
| 107 |
+
"loss": 0.4959575653076172,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.07894736842105263,
|
| 112 |
+
"grad_norm": 0.9921875,
|
| 113 |
+
"learning_rate": 3.921052631578947e-06,
|
| 114 |
+
"loss": 0.4966397285461426,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.08421052631578947,
|
| 119 |
+
"grad_norm": 0.91015625,
|
| 120 |
+
"learning_rate": 4.18421052631579e-06,
|
| 121 |
+
"loss": 0.49360017776489257,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.08947368421052632,
|
| 126 |
+
"grad_norm": 0.828125,
|
| 127 |
+
"learning_rate": 4.447368421052632e-06,
|
| 128 |
+
"loss": 0.4972525596618652,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.09473684210526316,
|
| 133 |
+
"grad_norm": 0.83203125,
|
| 134 |
+
"learning_rate": 4.710526315789474e-06,
|
| 135 |
+
"loss": 0.4940919876098633,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.1,
|
| 140 |
+
"grad_norm": 0.78125,
|
| 141 |
+
"learning_rate": 4.973684210526316e-06,
|
| 142 |
+
"loss": 0.47759342193603516,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.10526315789473684,
|
| 147 |
+
"grad_norm": 0.74609375,
|
| 148 |
+
"learning_rate": 5.236842105263158e-06,
|
| 149 |
+
"loss": 0.4808234214782715,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.11052631578947368,
|
| 154 |
+
"grad_norm": 0.7578125,
|
| 155 |
+
"learning_rate": 5.500000000000001e-06,
|
| 156 |
+
"loss": 0.48215289115905763,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.11578947368421053,
|
| 161 |
+
"grad_norm": 0.7109375,
|
| 162 |
+
"learning_rate": 5.7631578947368425e-06,
|
| 163 |
+
"loss": 0.4639110088348389,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.12105263157894737,
|
| 168 |
+
"grad_norm": 0.7109375,
|
| 169 |
+
"learning_rate": 6.026315789473684e-06,
|
| 170 |
+
"loss": 0.4647684097290039,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.12631578947368421,
|
| 175 |
+
"grad_norm": 0.72265625,
|
| 176 |
+
"learning_rate": 6.289473684210526e-06,
|
| 177 |
+
"loss": 0.46012086868286134,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.13157894736842105,
|
| 182 |
+
"grad_norm": 0.67578125,
|
| 183 |
+
"learning_rate": 6.55263157894737e-06,
|
| 184 |
+
"loss": 0.4481703281402588,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1368421052631579,
|
| 189 |
+
"grad_norm": 0.70703125,
|
| 190 |
+
"learning_rate": 6.8157894736842115e-06,
|
| 191 |
+
"loss": 0.4428702354431152,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.14210526315789473,
|
| 196 |
+
"grad_norm": 0.64453125,
|
| 197 |
+
"learning_rate": 7.078947368421053e-06,
|
| 198 |
+
"loss": 0.4461805820465088,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.14736842105263157,
|
| 203 |
+
"grad_norm": 0.67578125,
|
| 204 |
+
"learning_rate": 7.342105263157895e-06,
|
| 205 |
+
"loss": 0.4336544990539551,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.15263157894736842,
|
| 210 |
+
"grad_norm": 0.65234375,
|
| 211 |
+
"learning_rate": 7.605263157894738e-06,
|
| 212 |
+
"loss": 0.42908339500427245,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.15789473684210525,
|
| 217 |
+
"grad_norm": 0.71484375,
|
| 218 |
+
"learning_rate": 7.86842105263158e-06,
|
| 219 |
+
"loss": 0.43083953857421875,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.1631578947368421,
|
| 224 |
+
"grad_norm": 0.71484375,
|
| 225 |
+
"learning_rate": 8.131578947368421e-06,
|
| 226 |
+
"loss": 0.42508654594421386,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.16842105263157894,
|
| 231 |
+
"grad_norm": 0.66015625,
|
| 232 |
+
"learning_rate": 8.394736842105263e-06,
|
| 233 |
+
"loss": 0.4288334846496582,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.1736842105263158,
|
| 238 |
+
"grad_norm": 0.6328125,
|
| 239 |
+
"learning_rate": 8.657894736842107e-06,
|
| 240 |
+
"loss": 0.41841821670532225,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.17894736842105263,
|
| 245 |
+
"grad_norm": 0.66015625,
|
| 246 |
+
"learning_rate": 8.921052631578949e-06,
|
| 247 |
+
"loss": 0.4091064453125,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.18421052631578946,
|
| 252 |
+
"grad_norm": 0.671875,
|
| 253 |
+
"learning_rate": 9.18421052631579e-06,
|
| 254 |
+
"loss": 0.4105274200439453,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.18947368421052632,
|
| 259 |
+
"grad_norm": 0.67578125,
|
| 260 |
+
"learning_rate": 9.447368421052632e-06,
|
| 261 |
+
"loss": 0.4175132751464844,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.19473684210526315,
|
| 266 |
+
"grad_norm": 0.62890625,
|
| 267 |
+
"learning_rate": 9.710526315789474e-06,
|
| 268 |
+
"loss": 0.4001775741577148,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.2,
|
| 273 |
+
"grad_norm": 0.69921875,
|
| 274 |
+
"learning_rate": 9.973684210526316e-06,
|
| 275 |
+
"loss": 0.3932699203491211,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.20526315789473684,
|
| 280 |
+
"grad_norm": 0.6796875,
|
| 281 |
+
"learning_rate": 9.999829128320873e-06,
|
| 282 |
+
"loss": 0.38886494636535646,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.21052631578947367,
|
| 287 |
+
"grad_norm": 0.703125,
|
| 288 |
+
"learning_rate": 9.999238475781957e-06,
|
| 289 |
+
"loss": 0.37709574699401854,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.21578947368421053,
|
| 294 |
+
"grad_norm": 0.75,
|
| 295 |
+
"learning_rate": 9.99822598268431e-06,
|
| 296 |
+
"loss": 0.3927562952041626,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.22105263157894736,
|
| 301 |
+
"grad_norm": 0.625,
|
| 302 |
+
"learning_rate": 9.996791734463078e-06,
|
| 303 |
+
"loss": 0.3838310241699219,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.22631578947368422,
|
| 308 |
+
"grad_norm": 0.765625,
|
| 309 |
+
"learning_rate": 9.994935852141503e-06,
|
| 310 |
+
"loss": 0.3806215524673462,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.23157894736842105,
|
| 315 |
+
"grad_norm": 0.73828125,
|
| 316 |
+
"learning_rate": 9.992658492320728e-06,
|
| 317 |
+
"loss": 0.38055245876312255,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.23684210526315788,
|
| 322 |
+
"grad_norm": 0.734375,
|
| 323 |
+
"learning_rate": 9.989959847166567e-06,
|
| 324 |
+
"loss": 0.37838287353515626,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.24210526315789474,
|
| 329 |
+
"grad_norm": 0.81640625,
|
| 330 |
+
"learning_rate": 9.986840144393297e-06,
|
| 331 |
+
"loss": 0.3766012668609619,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.24736842105263157,
|
| 336 |
+
"grad_norm": 0.73828125,
|
| 337 |
+
"learning_rate": 9.983299647244445e-06,
|
| 338 |
+
"loss": 0.3719737768173218,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.25263157894736843,
|
| 343 |
+
"grad_norm": 0.6796875,
|
| 344 |
+
"learning_rate": 9.97933865447057e-06,
|
| 345 |
+
"loss": 0.3690729856491089,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2578947368421053,
|
| 350 |
+
"grad_norm": 0.6796875,
|
| 351 |
+
"learning_rate": 9.974957500304058e-06,
|
| 352 |
+
"loss": 0.36603174209594724,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2631578947368421,
|
| 357 |
+
"grad_norm": 0.65234375,
|
| 358 |
+
"learning_rate": 9.970156554430919e-06,
|
| 359 |
+
"loss": 0.37082958221435547,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.26842105263157895,
|
| 364 |
+
"grad_norm": 0.75,
|
| 365 |
+
"learning_rate": 9.964936221959592e-06,
|
| 366 |
+
"loss": 0.3672354698181152,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2736842105263158,
|
| 371 |
+
"grad_norm": 0.72265625,
|
| 372 |
+
"learning_rate": 9.959296943386759e-06,
|
| 373 |
+
"loss": 0.35545907020568845,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2789473684210526,
|
| 378 |
+
"grad_norm": 0.68359375,
|
| 379 |
+
"learning_rate": 9.953239194560176e-06,
|
| 380 |
+
"loss": 0.3559886932373047,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.28421052631578947,
|
| 385 |
+
"grad_norm": 0.72265625,
|
| 386 |
+
"learning_rate": 9.946763486638529e-06,
|
| 387 |
+
"loss": 0.3581003904342651,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.2894736842105263,
|
| 392 |
+
"grad_norm": 0.6953125,
|
| 393 |
+
"learning_rate": 9.939870366048289e-06,
|
| 394 |
+
"loss": 0.3564296722412109,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.29473684210526313,
|
| 399 |
+
"grad_norm": 0.640625,
|
| 400 |
+
"learning_rate": 9.932560414437613e-06,
|
| 401 |
+
"loss": 0.34760222434997556,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3,
|
| 406 |
+
"grad_norm": 0.6875,
|
| 407 |
+
"learning_rate": 9.92483424862726e-06,
|
| 408 |
+
"loss": 0.35869345664978025,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.30526315789473685,
|
| 413 |
+
"grad_norm": 0.69921875,
|
| 414 |
+
"learning_rate": 9.916692520558542e-06,
|
| 415 |
+
"loss": 0.3607193470001221,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.3105263157894737,
|
| 420 |
+
"grad_norm": 0.6640625,
|
| 421 |
+
"learning_rate": 9.908135917238321e-06,
|
| 422 |
+
"loss": 0.3511130094528198,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.3157894736842105,
|
| 427 |
+
"grad_norm": 0.6796875,
|
| 428 |
+
"learning_rate": 9.899165160681025e-06,
|
| 429 |
+
"loss": 0.34973719120025637,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.32105263157894737,
|
| 434 |
+
"grad_norm": 0.6953125,
|
| 435 |
+
"learning_rate": 9.889781007847736e-06,
|
| 436 |
+
"loss": 0.34694643020629884,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.3263157894736842,
|
| 441 |
+
"grad_norm": 0.671875,
|
| 442 |
+
"learning_rate": 9.87998425058231e-06,
|
| 443 |
+
"loss": 0.3488326549530029,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.33157894736842103,
|
| 448 |
+
"grad_norm": 0.65625,
|
| 449 |
+
"learning_rate": 9.869775715544563e-06,
|
| 450 |
+
"loss": 0.34894604682922364,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3368421052631579,
|
| 455 |
+
"grad_norm": 0.640625,
|
| 456 |
+
"learning_rate": 9.859156264140516e-06,
|
| 457 |
+
"loss": 0.34157140254974366,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.34210526315789475,
|
| 462 |
+
"grad_norm": 0.640625,
|
| 463 |
+
"learning_rate": 9.84812679244971e-06,
|
| 464 |
+
"loss": 0.34499416351318357,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.3473684210526316,
|
| 469 |
+
"grad_norm": 0.921875,
|
| 470 |
+
"learning_rate": 9.836688231149593e-06,
|
| 471 |
+
"loss": 0.35079469680786135,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.3526315789473684,
|
| 476 |
+
"grad_norm": 0.64453125,
|
| 477 |
+
"learning_rate": 9.824841545436983e-06,
|
| 478 |
+
"loss": 0.34972991943359377,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.35789473684210527,
|
| 483 |
+
"grad_norm": 0.66015625,
|
| 484 |
+
"learning_rate": 9.812587734946637e-06,
|
| 485 |
+
"loss": 0.3461646795272827,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.3631578947368421,
|
| 490 |
+
"grad_norm": 0.66015625,
|
| 491 |
+
"learning_rate": 9.799927833666887e-06,
|
| 492 |
+
"loss": 0.34224634170532225,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.3684210526315789,
|
| 497 |
+
"grad_norm": 0.6875,
|
| 498 |
+
"learning_rate": 9.7868629098524e-06,
|
| 499 |
+
"loss": 0.3424330234527588,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.3736842105263158,
|
| 504 |
+
"grad_norm": 0.64453125,
|
| 505 |
+
"learning_rate": 9.773394065934033e-06,
|
| 506 |
+
"loss": 0.3356307029724121,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.37894736842105264,
|
| 511 |
+
"grad_norm": 0.7109375,
|
| 512 |
+
"learning_rate": 9.759522438425813e-06,
|
| 513 |
+
"loss": 0.34045701026916503,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.38421052631578945,
|
| 518 |
+
"grad_norm": 0.73828125,
|
| 519 |
+
"learning_rate": 9.745249197829033e-06,
|
| 520 |
+
"loss": 0.3457850694656372,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.3894736842105263,
|
| 525 |
+
"grad_norm": 0.74609375,
|
| 526 |
+
"learning_rate": 9.730575548533483e-06,
|
| 527 |
+
"loss": 0.3392923831939697,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.39473684210526316,
|
| 532 |
+
"grad_norm": 0.67578125,
|
| 533 |
+
"learning_rate": 9.715502728715827e-06,
|
| 534 |
+
"loss": 0.3369739055633545,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.4,
|
| 539 |
+
"grad_norm": 0.734375,
|
| 540 |
+
"learning_rate": 9.700032010235124e-06,
|
| 541 |
+
"loss": 0.337469744682312,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.4052631578947368,
|
| 546 |
+
"grad_norm": 0.66796875,
|
| 547 |
+
"learning_rate": 9.684164698525503e-06,
|
| 548 |
+
"loss": 0.33764631748199464,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.4105263157894737,
|
| 553 |
+
"grad_norm": 0.6953125,
|
| 554 |
+
"learning_rate": 9.667902132486009e-06,
|
| 555 |
+
"loss": 0.3402730703353882,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.41578947368421054,
|
| 560 |
+
"grad_norm": 0.66015625,
|
| 561 |
+
"learning_rate": 9.651245684367635e-06,
|
| 562 |
+
"loss": 0.3302119493484497,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.42105263157894735,
|
| 567 |
+
"grad_norm": 0.64453125,
|
| 568 |
+
"learning_rate": 9.634196759657518e-06,
|
| 569 |
+
"loss": 0.33098368644714354,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.4263157894736842,
|
| 574 |
+
"grad_norm": 0.6484375,
|
| 575 |
+
"learning_rate": 9.616756796960354e-06,
|
| 576 |
+
"loss": 0.33663296699523926,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.43157894736842106,
|
| 581 |
+
"grad_norm": 0.69140625,
|
| 582 |
+
"learning_rate": 9.59892726787699e-06,
|
| 583 |
+
"loss": 0.33926751613616946,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.4368421052631579,
|
| 588 |
+
"grad_norm": 0.65625,
|
| 589 |
+
"learning_rate": 9.580709676880268e-06,
|
| 590 |
+
"loss": 0.3309003829956055,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.4421052631578947,
|
| 595 |
+
"grad_norm": 0.67578125,
|
| 596 |
+
"learning_rate": 9.562105561188069e-06,
|
| 597 |
+
"loss": 0.32626454830169677,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.4473684210526316,
|
| 602 |
+
"grad_norm": 0.67578125,
|
| 603 |
+
"learning_rate": 9.543116490633596e-06,
|
| 604 |
+
"loss": 0.3341776132583618,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.45263157894736844,
|
| 609 |
+
"grad_norm": 0.66796875,
|
| 610 |
+
"learning_rate": 9.523744067532919e-06,
|
| 611 |
+
"loss": 0.3330094814300537,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.45789473684210524,
|
| 616 |
+
"grad_norm": 0.68359375,
|
| 617 |
+
"learning_rate": 9.50398992654976e-06,
|
| 618 |
+
"loss": 0.3262917518615723,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.4631578947368421,
|
| 623 |
+
"grad_norm": 0.73828125,
|
| 624 |
+
"learning_rate": 9.483855734557563e-06,
|
| 625 |
+
"loss": 0.33661460876464844,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.46842105263157896,
|
| 630 |
+
"grad_norm": 0.6484375,
|
| 631 |
+
"learning_rate": 9.46334319049885e-06,
|
| 632 |
+
"loss": 0.3267409086227417,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.47368421052631576,
|
| 637 |
+
"grad_norm": 0.671875,
|
| 638 |
+
"learning_rate": 9.442454025241847e-06,
|
| 639 |
+
"loss": 0.3229888677597046,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.4789473684210526,
|
| 644 |
+
"grad_norm": 0.6640625,
|
| 645 |
+
"learning_rate": 9.421190001434445e-06,
|
| 646 |
+
"loss": 0.3298530101776123,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.4842105263157895,
|
| 651 |
+
"grad_norm": 0.6328125,
|
| 652 |
+
"learning_rate": 9.399552913355454e-06,
|
| 653 |
+
"loss": 0.3356186389923096,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.48947368421052634,
|
| 658 |
+
"grad_norm": 0.6640625,
|
| 659 |
+
"learning_rate": 9.377544586763216e-06,
|
| 660 |
+
"loss": 0.32946929931640623,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.49473684210526314,
|
| 665 |
+
"grad_norm": 0.671875,
|
| 666 |
+
"learning_rate": 9.355166878741526e-06,
|
| 667 |
+
"loss": 0.3330683708190918,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.5,
|
| 672 |
+
"grad_norm": 0.6796875,
|
| 673 |
+
"learning_rate": 9.332421677542949e-06,
|
| 674 |
+
"loss": 0.331757116317749,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.5052631578947369,
|
| 679 |
+
"grad_norm": 0.70703125,
|
| 680 |
+
"learning_rate": 9.309310902429471e-06,
|
| 681 |
+
"loss": 0.3249687194824219,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5105263157894737,
|
| 686 |
+
"grad_norm": 0.6640625,
|
| 687 |
+
"learning_rate": 9.285836503510562e-06,
|
| 688 |
+
"loss": 0.32373843193054197,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.5157894736842106,
|
| 693 |
+
"grad_norm": 0.67578125,
|
| 694 |
+
"learning_rate": 9.262000461578618e-06,
|
| 695 |
+
"loss": 0.3232883453369141,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.5210526315789473,
|
| 700 |
+
"grad_norm": 0.69140625,
|
| 701 |
+
"learning_rate": 9.23780478794182e-06,
|
| 702 |
+
"loss": 0.32159950733184817,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.5263157894736842,
|
| 707 |
+
"grad_norm": 0.6171875,
|
| 708 |
+
"learning_rate": 9.213251524254418e-06,
|
| 709 |
+
"loss": 0.331815242767334,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.531578947368421,
|
| 714 |
+
"grad_norm": 0.65234375,
|
| 715 |
+
"learning_rate": 9.188342742344459e-06,
|
| 716 |
+
"loss": 0.3242619037628174,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.5368421052631579,
|
| 721 |
+
"grad_norm": 0.6640625,
|
| 722 |
+
"learning_rate": 9.163080544038953e-06,
|
| 723 |
+
"loss": 0.32434511184692383,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.5421052631578948,
|
| 728 |
+
"grad_norm": 0.6328125,
|
| 729 |
+
"learning_rate": 9.137467060986531e-06,
|
| 730 |
+
"loss": 0.32496211528778074,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.5473684210526316,
|
| 735 |
+
"grad_norm": 0.67578125,
|
| 736 |
+
"learning_rate": 9.111504454477571e-06,
|
| 737 |
+
"loss": 0.32212533950805666,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.5526315789473685,
|
| 742 |
+
"grad_norm": 0.6953125,
|
| 743 |
+
"learning_rate": 9.08519491526182e-06,
|
| 744 |
+
"loss": 0.31923248767852785,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.5578947368421052,
|
| 749 |
+
"grad_norm": 0.64453125,
|
| 750 |
+
"learning_rate": 9.05854066336354e-06,
|
| 751 |
+
"loss": 0.31866576671600344,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.5631578947368421,
|
| 756 |
+
"grad_norm": 0.66796875,
|
| 757 |
+
"learning_rate": 9.03154394789419e-06,
|
| 758 |
+
"loss": 0.31672356128692625,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.5684210526315789,
|
| 763 |
+
"grad_norm": 0.6796875,
|
| 764 |
+
"learning_rate": 9.004207046862625e-06,
|
| 765 |
+
"loss": 0.32541964054107664,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.5736842105263158,
|
| 770 |
+
"grad_norm": 0.6484375,
|
| 771 |
+
"learning_rate": 8.976532266982893e-06,
|
| 772 |
+
"loss": 0.3155732870101929,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.5789473684210527,
|
| 777 |
+
"grad_norm": 0.609375,
|
| 778 |
+
"learning_rate": 8.94852194347958e-06,
|
| 779 |
+
"loss": 0.32347979545593264,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.5842105263157895,
|
| 784 |
+
"grad_norm": 0.6796875,
|
| 785 |
+
"learning_rate": 8.920178439890765e-06,
|
| 786 |
+
"loss": 0.3177721261978149,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.5894736842105263,
|
| 791 |
+
"grad_norm": 0.609375,
|
| 792 |
+
"learning_rate": 8.891504147868592e-06,
|
| 793 |
+
"loss": 0.3194961309432983,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.5947368421052631,
|
| 798 |
+
"grad_norm": 0.63671875,
|
| 799 |
+
"learning_rate": 8.862501486977439e-06,
|
| 800 |
+
"loss": 0.31951587200164794,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.6,
|
| 805 |
+
"grad_norm": 0.625,
|
| 806 |
+
"learning_rate": 8.83317290448978e-06,
|
| 807 |
+
"loss": 0.32182841300964354,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.6052631578947368,
|
| 812 |
+
"grad_norm": 0.65625,
|
| 813 |
+
"learning_rate": 8.803520875179653e-06,
|
| 814 |
+
"loss": 0.3282808542251587,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.6105263157894737,
|
| 819 |
+
"grad_norm": 0.72265625,
|
| 820 |
+
"learning_rate": 8.773547901113862e-06,
|
| 821 |
+
"loss": 0.31565380096435547,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.6157894736842106,
|
| 826 |
+
"grad_norm": 0.640625,
|
| 827 |
+
"learning_rate": 8.743256511440829e-06,
|
| 828 |
+
"loss": 0.31986217498779296,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.6210526315789474,
|
| 833 |
+
"grad_norm": 0.61328125,
|
| 834 |
+
"learning_rate": 8.712649262177201e-06,
|
| 835 |
+
"loss": 0.31707024574279785,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.6263157894736842,
|
| 840 |
+
"grad_norm": 0.66796875,
|
| 841 |
+
"learning_rate": 8.681728735992156e-06,
|
| 842 |
+
"loss": 0.3156208276748657,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.631578947368421,
|
| 847 |
+
"grad_norm": 0.640625,
|
| 848 |
+
"learning_rate": 8.650497541989483e-06,
|
| 849 |
+
"loss": 0.320496940612793,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.6368421052631579,
|
| 854 |
+
"grad_norm": 0.70703125,
|
| 855 |
+
"learning_rate": 8.618958315487415e-06,
|
| 856 |
+
"loss": 0.3214350700378418,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.6421052631578947,
|
| 861 |
+
"grad_norm": 0.640625,
|
| 862 |
+
"learning_rate": 8.587113717796272e-06,
|
| 863 |
+
"loss": 0.31240484714508054,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.6473684210526316,
|
| 868 |
+
"grad_norm": 0.6640625,
|
| 869 |
+
"learning_rate": 8.554966435993883e-06,
|
| 870 |
+
"loss": 0.3247716426849365,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.6526315789473685,
|
| 875 |
+
"grad_norm": 0.625,
|
| 876 |
+
"learning_rate": 8.522519182698858e-06,
|
| 877 |
+
"loss": 0.31765995025634763,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.6578947368421053,
|
| 882 |
+
"grad_norm": 0.68359375,
|
| 883 |
+
"learning_rate": 8.48977469584169e-06,
|
| 884 |
+
"loss": 0.31092309951782227,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.6631578947368421,
|
| 889 |
+
"grad_norm": 1.015625,
|
| 890 |
+
"learning_rate": 8.456735738433724e-06,
|
| 891 |
+
"loss": 0.31570873260498045,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.6684210526315789,
|
| 896 |
+
"grad_norm": 0.67578125,
|
| 897 |
+
"learning_rate": 8.423405098334015e-06,
|
| 898 |
+
"loss": 0.31320650577545167,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.6736842105263158,
|
| 903 |
+
"grad_norm": 0.6796875,
|
| 904 |
+
"learning_rate": 8.389785588014081e-06,
|
| 905 |
+
"loss": 0.32011613845825193,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.6789473684210526,
|
| 910 |
+
"grad_norm": 0.68359375,
|
| 911 |
+
"learning_rate": 8.355880044320599e-06,
|
| 912 |
+
"loss": 0.3172569274902344,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.6842105263157895,
|
| 917 |
+
"grad_norm": 0.6640625,
|
| 918 |
+
"learning_rate": 8.321691328236003e-06,
|
| 919 |
+
"loss": 0.31363720893859864,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.6894736842105263,
|
| 924 |
+
"grad_norm": 0.640625,
|
| 925 |
+
"learning_rate": 8.287222324637094e-06,
|
| 926 |
+
"loss": 0.3125040531158447,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.6947368421052632,
|
| 931 |
+
"grad_norm": 0.66015625,
|
| 932 |
+
"learning_rate": 8.252475942051605e-06,
|
| 933 |
+
"loss": 0.3284018039703369,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.7,
|
| 938 |
+
"grad_norm": 0.6484375,
|
| 939 |
+
"learning_rate": 8.21745511241277e-06,
|
| 940 |
+
"loss": 0.3152493953704834,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.7052631578947368,
|
| 945 |
+
"grad_norm": 0.62890625,
|
| 946 |
+
"learning_rate": 8.182162790811932e-06,
|
| 947 |
+
"loss": 0.3171976327896118,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.7105263157894737,
|
| 952 |
+
"grad_norm": 0.62890625,
|
| 953 |
+
"learning_rate": 8.146601955249187e-06,
|
| 954 |
+
"loss": 0.3094895362854004,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.7157894736842105,
|
| 959 |
+
"grad_norm": 0.65625,
|
| 960 |
+
"learning_rate": 8.110775606382102e-06,
|
| 961 |
+
"loss": 0.3186656951904297,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.7210526315789474,
|
| 966 |
+
"grad_norm": 0.66796875,
|
| 967 |
+
"learning_rate": 8.074686767272504e-06,
|
| 968 |
+
"loss": 0.3225880146026611,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.7263157894736842,
|
| 973 |
+
"grad_norm": 0.66015625,
|
| 974 |
+
"learning_rate": 8.038338483131408e-06,
|
| 975 |
+
"loss": 0.31708440780639646,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.7315789473684211,
|
| 980 |
+
"grad_norm": 0.703125,
|
| 981 |
+
"learning_rate": 8.001733821062043e-06,
|
| 982 |
+
"loss": 0.3101796627044678,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.7368421052631579,
|
| 987 |
+
"grad_norm": 0.67578125,
|
| 988 |
+
"learning_rate": 7.96487586980106e-06,
|
| 989 |
+
"loss": 0.3201738357543945,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.7421052631578947,
|
| 994 |
+
"grad_norm": 0.68359375,
|
| 995 |
+
"learning_rate": 7.927767739457896e-06,
|
| 996 |
+
"loss": 0.3103344917297363,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.7473684210526316,
|
| 1001 |
+
"grad_norm": 0.64453125,
|
| 1002 |
+
"learning_rate": 7.890412561252336e-06,
|
| 1003 |
+
"loss": 0.306152868270874,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.7526315789473684,
|
| 1008 |
+
"grad_norm": 0.73046875,
|
| 1009 |
+
"learning_rate": 7.852813487250307e-06,
|
| 1010 |
+
"loss": 0.3118812084197998,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.7578947368421053,
|
| 1015 |
+
"grad_norm": 0.640625,
|
| 1016 |
+
"learning_rate": 7.814973690097893e-06,
|
| 1017 |
+
"loss": 0.3072047710418701,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.7631578947368421,
|
| 1022 |
+
"grad_norm": 0.66015625,
|
| 1023 |
+
"learning_rate": 7.776896362753632e-06,
|
| 1024 |
+
"loss": 0.3056161880493164,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.7684210526315789,
|
| 1029 |
+
"grad_norm": 0.671875,
|
| 1030 |
+
"learning_rate": 7.738584718219089e-06,
|
| 1031 |
+
"loss": 0.3092217445373535,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.7736842105263158,
|
| 1036 |
+
"grad_norm": 0.69140625,
|
| 1037 |
+
"learning_rate": 7.700041989267738e-06,
|
| 1038 |
+
"loss": 0.30931863784790037,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.7789473684210526,
|
| 1043 |
+
"grad_norm": 0.67578125,
|
| 1044 |
+
"learning_rate": 7.661271428172175e-06,
|
| 1045 |
+
"loss": 0.31501796245574953,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.7842105263157895,
|
| 1050 |
+
"grad_norm": 0.609375,
|
| 1051 |
+
"learning_rate": 7.622276306429703e-06,
|
| 1052 |
+
"loss": 0.315232515335083,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.7894736842105263,
|
| 1057 |
+
"grad_norm": 0.65234375,
|
| 1058 |
+
"learning_rate": 7.583059914486257e-06,
|
| 1059 |
+
"loss": 0.31932260990142824,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.7947368421052632,
|
| 1064 |
+
"grad_norm": 0.66796875,
|
| 1065 |
+
"learning_rate": 7.543625561458772e-06,
|
| 1066 |
+
"loss": 0.313411021232605,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.8,
|
| 1071 |
+
"grad_norm": 0.65625,
|
| 1072 |
+
"learning_rate": 7.5039765748559425e-06,
|
| 1073 |
+
"loss": 0.3128029823303223,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.8052631578947368,
|
| 1078 |
+
"grad_norm": 0.6171875,
|
| 1079 |
+
"learning_rate": 7.464116300297458e-06,
|
| 1080 |
+
"loss": 0.3082960367202759,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.8105263157894737,
|
| 1085 |
+
"grad_norm": 0.68359375,
|
| 1086 |
+
"learning_rate": 7.424048101231687e-06,
|
| 1087 |
+
"loss": 0.321931791305542,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.8157894736842105,
|
| 1092 |
+
"grad_norm": 0.6484375,
|
| 1093 |
+
"learning_rate": 7.383775358651863e-06,
|
| 1094 |
+
"loss": 0.305802583694458,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.8210526315789474,
|
| 1099 |
+
"grad_norm": 0.6953125,
|
| 1100 |
+
"learning_rate": 7.343301470810809e-06,
|
| 1101 |
+
"loss": 0.31627817153930665,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.8263157894736842,
|
| 1106 |
+
"grad_norm": 0.65234375,
|
| 1107 |
+
"learning_rate": 7.302629852934167e-06,
|
| 1108 |
+
"loss": 0.30953359603881836,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.8315789473684211,
|
| 1113 |
+
"grad_norm": 0.67578125,
|
| 1114 |
+
"learning_rate": 7.261763936932237e-06,
|
| 1115 |
+
"loss": 0.3176161527633667,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.8368421052631579,
|
| 1120 |
+
"grad_norm": 0.65234375,
|
| 1121 |
+
"learning_rate": 7.220707171110381e-06,
|
| 1122 |
+
"loss": 0.30671143531799316,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.8421052631578947,
|
| 1127 |
+
"grad_norm": 0.6875,
|
| 1128 |
+
"learning_rate": 7.179463019878053e-06,
|
| 1129 |
+
"loss": 0.30997092723846437,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.8473684210526315,
|
| 1134 |
+
"grad_norm": 0.67578125,
|
| 1135 |
+
"learning_rate": 7.138034963456467e-06,
|
| 1136 |
+
"loss": 0.3097463846206665,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.8526315789473684,
|
| 1141 |
+
"grad_norm": 0.6796875,
|
| 1142 |
+
"learning_rate": 7.096426497584934e-06,
|
| 1143 |
+
"loss": 0.316087007522583,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.8578947368421053,
|
| 1148 |
+
"grad_norm": 0.65625,
|
| 1149 |
+
"learning_rate": 7.054641133225889e-06,
|
| 1150 |
+
"loss": 0.3100144386291504,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.8631578947368421,
|
| 1155 |
+
"grad_norm": 0.65625,
|
| 1156 |
+
"learning_rate": 7.012682396268632e-06,
|
| 1157 |
+
"loss": 0.3151434898376465,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.868421052631579,
|
| 1162 |
+
"grad_norm": 0.6484375,
|
| 1163 |
+
"learning_rate": 6.970553827231809e-06,
|
| 1164 |
+
"loss": 0.3087049722671509,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.8736842105263158,
|
| 1169 |
+
"grad_norm": 0.64453125,
|
| 1170 |
+
"learning_rate": 6.928258980964661e-06,
|
| 1171 |
+
"loss": 0.30957005023956297,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.8789473684210526,
|
| 1176 |
+
"grad_norm": 0.65625,
|
| 1177 |
+
"learning_rate": 6.885801426347063e-06,
|
| 1178 |
+
"loss": 0.30764572620391845,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.8842105263157894,
|
| 1183 |
+
"grad_norm": 0.64453125,
|
| 1184 |
+
"learning_rate": 6.843184745988374e-06,
|
| 1185 |
+
"loss": 0.3205082893371582,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.8894736842105263,
|
| 1190 |
+
"grad_norm": 0.63671875,
|
| 1191 |
+
"learning_rate": 6.800412535925141e-06,
|
| 1192 |
+
"loss": 0.3043262481689453,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.8947368421052632,
|
| 1197 |
+
"grad_norm": 0.6875,
|
| 1198 |
+
"learning_rate": 6.757488405317651e-06,
|
| 1199 |
+
"loss": 0.31385753154754636,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.9,
|
| 1204 |
+
"grad_norm": 0.63671875,
|
| 1205 |
+
"learning_rate": 6.714415976145402e-06,
|
| 1206 |
+
"loss": 0.3092473030090332,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.9052631578947369,
|
| 1211 |
+
"grad_norm": 0.64453125,
|
| 1212 |
+
"learning_rate": 6.671198882901459e-06,
|
| 1213 |
+
"loss": 0.315170955657959,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.9105263157894737,
|
| 1218 |
+
"grad_norm": 0.63671875,
|
| 1219 |
+
"learning_rate": 6.627840772285784e-06,
|
| 1220 |
+
"loss": 0.31401405334472654,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.9157894736842105,
|
| 1225 |
+
"grad_norm": 0.62890625,
|
| 1226 |
+
"learning_rate": 6.584345302897522e-06,
|
| 1227 |
+
"loss": 0.31677677631378176,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.9210526315789473,
|
| 1232 |
+
"grad_norm": 0.66015625,
|
| 1233 |
+
"learning_rate": 6.540716144926283e-06,
|
| 1234 |
+
"loss": 0.3068485498428345,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.9263157894736842,
|
| 1239 |
+
"grad_norm": 0.6328125,
|
| 1240 |
+
"learning_rate": 6.4969569798424485e-06,
|
| 1241 |
+
"loss": 0.3036781311035156,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.9315789473684211,
|
| 1246 |
+
"grad_norm": 0.65625,
|
| 1247 |
+
"learning_rate": 6.453071500086521e-06,
|
| 1248 |
+
"loss": 0.31591813564300536,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.9368421052631579,
|
| 1253 |
+
"grad_norm": 0.69921875,
|
| 1254 |
+
"learning_rate": 6.409063408757563e-06,
|
| 1255 |
+
"loss": 0.30909504890441897,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.9421052631578948,
|
| 1260 |
+
"grad_norm": 0.66015625,
|
| 1261 |
+
"learning_rate": 6.364936419300718e-06,
|
| 1262 |
+
"loss": 0.30489392280578614,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.9473684210526315,
|
| 1267 |
+
"grad_norm": 0.6328125,
|
| 1268 |
+
"learning_rate": 6.320694255193867e-06,
|
| 1269 |
+
"loss": 0.31351609230041505,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.9526315789473684,
|
| 1274 |
+
"grad_norm": 0.65234375,
|
| 1275 |
+
"learning_rate": 6.2763406496334366e-06,
|
| 1276 |
+
"loss": 0.3008957624435425,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.9578947368421052,
|
| 1281 |
+
"grad_norm": 0.6875,
|
| 1282 |
+
"learning_rate": 6.231879345219396e-06,
|
| 1283 |
+
"loss": 0.30812935829162597,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.9631578947368421,
|
| 1288 |
+
"grad_norm": 0.62890625,
|
| 1289 |
+
"learning_rate": 6.187314093639444e-06,
|
| 1290 |
+
"loss": 0.3064786195755005,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.968421052631579,
|
| 1295 |
+
"grad_norm": 0.6953125,
|
| 1296 |
+
"learning_rate": 6.142648655352441e-06,
|
| 1297 |
+
"loss": 0.3132913112640381,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.9736842105263158,
|
| 1302 |
+
"grad_norm": 0.6484375,
|
| 1303 |
+
"learning_rate": 6.0978867992711e-06,
|
| 1304 |
+
"loss": 0.3124531745910645,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.9789473684210527,
|
| 1309 |
+
"grad_norm": 0.62890625,
|
| 1310 |
+
"learning_rate": 6.05303230244396e-06,
|
| 1311 |
+
"loss": 0.3071515321731567,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.9842105263157894,
|
| 1316 |
+
"grad_norm": 0.65625,
|
| 1317 |
+
"learning_rate": 6.008088949736672e-06,
|
| 1318 |
+
"loss": 0.30440750122070315,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.9894736842105263,
|
| 1323 |
+
"grad_norm": 0.6171875,
|
| 1324 |
+
"learning_rate": 5.963060533512639e-06,
|
| 1325 |
+
"loss": 0.3114898443222046,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.9947368421052631,
|
| 1330 |
+
"grad_norm": 0.60546875,
|
| 1331 |
+
"learning_rate": 5.917950853313e-06,
|
| 1332 |
+
"loss": 0.2996272087097168,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.0,
|
| 1337 |
+
"grad_norm": 0.72265625,
|
| 1338 |
+
"learning_rate": 5.872763715536026e-06,
|
| 1339 |
+
"loss": 0.3033472537994385,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.0052631578947369,
|
| 1344 |
+
"grad_norm": 0.68359375,
|
| 1345 |
+
"learning_rate": 5.827502933115937e-06,
|
| 1346 |
+
"loss": 0.30527944564819337,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.0105263157894737,
|
| 1351 |
+
"grad_norm": 0.65234375,
|
| 1352 |
+
"learning_rate": 5.782172325201155e-06,
|
| 1353 |
+
"loss": 0.30853846073150637,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.0157894736842106,
|
| 1358 |
+
"grad_norm": 0.65234375,
|
| 1359 |
+
"learning_rate": 5.736775716832047e-06,
|
| 1360 |
+
"loss": 0.30219359397888185,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.0210526315789474,
|
| 1365 |
+
"grad_norm": 0.671875,
|
| 1366 |
+
"learning_rate": 5.691316938618161e-06,
|
| 1367 |
+
"loss": 0.3018205642700195,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.0263157894736843,
|
| 1372 |
+
"grad_norm": 0.67578125,
|
| 1373 |
+
"learning_rate": 5.645799826414997e-06,
|
| 1374 |
+
"loss": 0.3029512405395508,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.0315789473684212,
|
| 1379 |
+
"grad_norm": 0.6484375,
|
| 1380 |
+
"learning_rate": 5.600228221000334e-06,
|
| 1381 |
+
"loss": 0.30471067428588866,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.0368421052631578,
|
| 1386 |
+
"grad_norm": 0.6484375,
|
| 1387 |
+
"learning_rate": 5.554605967750135e-06,
|
| 1388 |
+
"loss": 0.30075364112854003,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.0421052631578946,
|
| 1393 |
+
"grad_norm": 0.625,
|
| 1394 |
+
"learning_rate": 5.508936916314086e-06,
|
| 1395 |
+
"loss": 0.30173373222351074,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.0473684210526315,
|
| 1400 |
+
"grad_norm": 0.65234375,
|
| 1401 |
+
"learning_rate": 5.463224920290739e-06,
|
| 1402 |
+
"loss": 0.3010159254074097,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.0526315789473684,
|
| 1407 |
+
"grad_norm": 0.62890625,
|
| 1408 |
+
"learning_rate": 5.417473836902361e-06,
|
| 1409 |
+
"loss": 0.30011806488037107,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.0578947368421052,
|
| 1414 |
+
"grad_norm": 0.69140625,
|
| 1415 |
+
"learning_rate": 5.371687526669439e-06,
|
| 1416 |
+
"loss": 0.2978121042251587,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.063157894736842,
|
| 1421 |
+
"grad_norm": 0.6171875,
|
| 1422 |
+
"learning_rate": 5.325869853084942e-06,
|
| 1423 |
+
"loss": 0.29638888835906985,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.068421052631579,
|
| 1428 |
+
"grad_norm": 0.65625,
|
| 1429 |
+
"learning_rate": 5.280024682288307e-06,
|
| 1430 |
+
"loss": 0.30433881282806396,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.0736842105263158,
|
| 1435 |
+
"grad_norm": 0.6328125,
|
| 1436 |
+
"learning_rate": 5.234155882739213e-06,
|
| 1437 |
+
"loss": 0.2943264484405518,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.0789473684210527,
|
| 1442 |
+
"grad_norm": 0.63671875,
|
| 1443 |
+
"learning_rate": 5.188267324891152e-06,
|
| 1444 |
+
"loss": 0.3040822982788086,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.0842105263157895,
|
| 1449 |
+
"grad_norm": 0.6484375,
|
| 1450 |
+
"learning_rate": 5.142362880864845e-06,
|
| 1451 |
+
"loss": 0.3013319492340088,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.0894736842105264,
|
| 1456 |
+
"grad_norm": 0.66796875,
|
| 1457 |
+
"learning_rate": 5.096446424121502e-06,
|
| 1458 |
+
"loss": 0.29690141677856446,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.0947368421052632,
|
| 1463 |
+
"grad_norm": 0.671875,
|
| 1464 |
+
"learning_rate": 5.050521829135977e-06,
|
| 1465 |
+
"loss": 0.2941089153289795,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.1,
|
| 1470 |
+
"grad_norm": 0.62109375,
|
| 1471 |
+
"learning_rate": 5.004592971069838e-06,
|
| 1472 |
+
"loss": 0.30376276969909666,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.1052631578947367,
|
| 1477 |
+
"grad_norm": 0.671875,
|
| 1478 |
+
"learning_rate": 4.958663725444376e-06,
|
| 1479 |
+
"loss": 0.30148308277130126,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.1105263157894736,
|
| 1484 |
+
"grad_norm": 0.68359375,
|
| 1485 |
+
"learning_rate": 4.9127379678135825e-06,
|
| 1486 |
+
"loss": 0.29861633777618407,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.1157894736842104,
|
| 1491 |
+
"grad_norm": 0.65625,
|
| 1492 |
+
"learning_rate": 4.866819573437133e-06,
|
| 1493 |
+
"loss": 0.29627511501312254,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.1210526315789473,
|
| 1498 |
+
"grad_norm": 0.6796875,
|
| 1499 |
+
"learning_rate": 4.820912416953377e-06,
|
| 1500 |
+
"loss": 0.29882948398590087,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.1263157894736842,
|
| 1505 |
+
"grad_norm": 0.69140625,
|
| 1506 |
+
"learning_rate": 4.775020372052408e-06,
|
| 1507 |
+
"loss": 0.2994240283966064,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.131578947368421,
|
| 1512 |
+
"grad_norm": 0.6875,
|
| 1513 |
+
"learning_rate": 4.729147311149186e-06,
|
| 1514 |
+
"loss": 0.30175774097442626,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.1368421052631579,
|
| 1519 |
+
"grad_norm": 0.66015625,
|
| 1520 |
+
"learning_rate": 4.683297105056782e-06,
|
| 1521 |
+
"loss": 0.2977766513824463,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.1421052631578947,
|
| 1526 |
+
"grad_norm": 0.65234375,
|
| 1527 |
+
"learning_rate": 4.637473622659755e-06,
|
| 1528 |
+
"loss": 0.29984431266784667,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.1473684210526316,
|
| 1533 |
+
"grad_norm": 0.6640625,
|
| 1534 |
+
"learning_rate": 4.591680730587698e-06,
|
| 1535 |
+
"loss": 0.3037722110748291,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.1526315789473685,
|
| 1540 |
+
"grad_norm": 0.671875,
|
| 1541 |
+
"learning_rate": 4.545922292888959e-06,
|
| 1542 |
+
"loss": 0.30381975173950193,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.1578947368421053,
|
| 1547 |
+
"grad_norm": 0.640625,
|
| 1548 |
+
"learning_rate": 4.500202170704595e-06,
|
| 1549 |
+
"loss": 0.29502048492431643,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.1631578947368422,
|
| 1554 |
+
"grad_norm": 0.6484375,
|
| 1555 |
+
"learning_rate": 4.454524221942557e-06,
|
| 1556 |
+
"loss": 0.29793238639831543,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.168421052631579,
|
| 1561 |
+
"grad_norm": 0.6796875,
|
| 1562 |
+
"learning_rate": 4.408892300952171e-06,
|
| 1563 |
+
"loss": 0.3094764709472656,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.1736842105263159,
|
| 1568 |
+
"grad_norm": 0.66015625,
|
| 1569 |
+
"learning_rate": 4.363310258198888e-06,
|
| 1570 |
+
"loss": 0.3042739391326904,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.1789473684210527,
|
| 1575 |
+
"grad_norm": 0.8359375,
|
| 1576 |
+
"learning_rate": 4.317781939939392e-06,
|
| 1577 |
+
"loss": 0.3023380279541016,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.1842105263157894,
|
| 1582 |
+
"grad_norm": 0.7109375,
|
| 1583 |
+
"learning_rate": 4.272311187897032e-06,
|
| 1584 |
+
"loss": 0.29675605297088625,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.1894736842105262,
|
| 1589 |
+
"grad_norm": 0.68359375,
|
| 1590 |
+
"learning_rate": 4.2269018389376776e-06,
|
| 1591 |
+
"loss": 0.29840383529663084,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.194736842105263,
|
| 1596 |
+
"grad_norm": 0.6796875,
|
| 1597 |
+
"learning_rate": 4.181557724745937e-06,
|
| 1598 |
+
"loss": 0.29515602588653567,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.2,
|
| 1603 |
+
"grad_norm": 0.703125,
|
| 1604 |
+
"learning_rate": 4.13628267150185e-06,
|
| 1605 |
+
"loss": 0.30409936904907225,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.2052631578947368,
|
| 1610 |
+
"grad_norm": 0.65625,
|
| 1611 |
+
"learning_rate": 4.091080499558023e-06,
|
| 1612 |
+
"loss": 0.2933309078216553,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.2105263157894737,
|
| 1617 |
+
"grad_norm": 0.65234375,
|
| 1618 |
+
"learning_rate": 4.045955023117276e-06,
|
| 1619 |
+
"loss": 0.3037595510482788,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.2157894736842105,
|
| 1624 |
+
"grad_norm": 0.71875,
|
| 1625 |
+
"learning_rate": 4.000910049910783e-06,
|
| 1626 |
+
"loss": 0.29630026817321775,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.2210526315789474,
|
| 1631 |
+
"grad_norm": 0.6796875,
|
| 1632 |
+
"learning_rate": 3.955949380876775e-06,
|
| 1633 |
+
"loss": 0.2985749959945679,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.2263157894736842,
|
| 1638 |
+
"grad_norm": 0.71875,
|
| 1639 |
+
"learning_rate": 3.911076809839822e-06,
|
| 1640 |
+
"loss": 0.3097393989562988,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.231578947368421,
|
| 1645 |
+
"grad_norm": 0.6484375,
|
| 1646 |
+
"learning_rate": 3.866296123190696e-06,
|
| 1647 |
+
"loss": 0.29675517082214353,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 1.236842105263158,
|
| 1652 |
+
"grad_norm": 0.6796875,
|
| 1653 |
+
"learning_rate": 3.821611099566879e-06,
|
| 1654 |
+
"loss": 0.2994438409805298,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 1.2421052631578948,
|
| 1659 |
+
"grad_norm": 0.6328125,
|
| 1660 |
+
"learning_rate": 3.7770255095337105e-06,
|
| 1661 |
+
"loss": 0.29492621421813964,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 1.2473684210526317,
|
| 1666 |
+
"grad_norm": 0.69140625,
|
| 1667 |
+
"learning_rate": 3.73254311526623e-06,
|
| 1668 |
+
"loss": 0.30408706665039065,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 1.2526315789473683,
|
| 1673 |
+
"grad_norm": 0.625,
|
| 1674 |
+
"learning_rate": 3.688167670231721e-06,
|
| 1675 |
+
"loss": 0.3012866497039795,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.2578947368421054,
|
| 1680 |
+
"grad_norm": 0.6796875,
|
| 1681 |
+
"learning_rate": 3.6439029188729858e-06,
|
| 1682 |
+
"loss": 0.3001688241958618,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 1.263157894736842,
|
| 1687 |
+
"grad_norm": 0.6875,
|
| 1688 |
+
"learning_rate": 3.599752596292386e-06,
|
| 1689 |
+
"loss": 0.29881649017333983,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.268421052631579,
|
| 1694 |
+
"grad_norm": 0.6953125,
|
| 1695 |
+
"learning_rate": 3.555720427936673e-06,
|
| 1696 |
+
"loss": 0.30099704265594485,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 1.2736842105263158,
|
| 1701 |
+
"grad_norm": 0.6171875,
|
| 1702 |
+
"learning_rate": 3.5118101292826356e-06,
|
| 1703 |
+
"loss": 0.29522502422332764,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 1.2789473684210526,
|
| 1708 |
+
"grad_norm": 0.62890625,
|
| 1709 |
+
"learning_rate": 3.4680254055235763e-06,
|
| 1710 |
+
"loss": 0.29836034774780273,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 1.2842105263157895,
|
| 1715 |
+
"grad_norm": 0.65625,
|
| 1716 |
+
"learning_rate": 3.4243699512566634e-06,
|
| 1717 |
+
"loss": 0.29813971519470217,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.2894736842105263,
|
| 1722 |
+
"grad_norm": 0.69140625,
|
| 1723 |
+
"learning_rate": 3.3808474501711865e-06,
|
| 1724 |
+
"loss": 0.3014229297637939,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 1.2947368421052632,
|
| 1729 |
+
"grad_norm": 0.69140625,
|
| 1730 |
+
"learning_rate": 3.3374615747377165e-06,
|
| 1731 |
+
"loss": 0.3070537090301514,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 1.3,
|
| 1736 |
+
"grad_norm": 0.6796875,
|
| 1737 |
+
"learning_rate": 3.2942159858982196e-06,
|
| 1738 |
+
"loss": 0.30273582935333254,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 1.305263157894737,
|
| 1743 |
+
"grad_norm": 0.7109375,
|
| 1744 |
+
"learning_rate": 3.251114332757142e-06,
|
| 1745 |
+
"loss": 0.30204660892486573,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.3105263157894738,
|
| 1750 |
+
"grad_norm": 0.68359375,
|
| 1751 |
+
"learning_rate": 3.2081602522734987e-06,
|
| 1752 |
+
"loss": 0.2994037628173828,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 1.3157894736842106,
|
| 1757 |
+
"grad_norm": 0.67578125,
|
| 1758 |
+
"learning_rate": 3.165357368953984e-06,
|
| 1759 |
+
"loss": 0.3061041355133057,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.3210526315789473,
|
| 1764 |
+
"grad_norm": 0.6953125,
|
| 1765 |
+
"learning_rate": 3.122709294547127e-06,
|
| 1766 |
+
"loss": 0.29471826553344727,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 1.3263157894736843,
|
| 1771 |
+
"grad_norm": 0.6875,
|
| 1772 |
+
"learning_rate": 3.0802196277385317e-06,
|
| 1773 |
+
"loss": 0.2963252544403076,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 1.331578947368421,
|
| 1778 |
+
"grad_norm": 0.65625,
|
| 1779 |
+
"learning_rate": 3.037891953847215e-06,
|
| 1780 |
+
"loss": 0.29909396171569824,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 1.3368421052631578,
|
| 1785 |
+
"grad_norm": 0.69140625,
|
| 1786 |
+
"learning_rate": 2.9957298445230808e-06,
|
| 1787 |
+
"loss": 0.29614212512969973,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 1.3421052631578947,
|
| 1792 |
+
"grad_norm": 0.6875,
|
| 1793 |
+
"learning_rate": 2.9537368574455304e-06,
|
| 1794 |
+
"loss": 0.3006807804107666,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 1.3473684210526315,
|
| 1799 |
+
"grad_norm": 0.6875,
|
| 1800 |
+
"learning_rate": 2.911916536023269e-06,
|
| 1801 |
+
"loss": 0.2975183963775635,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.3526315789473684,
|
| 1806 |
+
"grad_norm": 0.70703125,
|
| 1807 |
+
"learning_rate": 2.8702724090953023e-06,
|
| 1808 |
+
"loss": 0.2994128465652466,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 1.3578947368421053,
|
| 1813 |
+
"grad_norm": 0.6953125,
|
| 1814 |
+
"learning_rate": 2.8288079906331867e-06,
|
| 1815 |
+
"loss": 0.30081496238708494,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 1.3631578947368421,
|
| 1820 |
+
"grad_norm": 0.64453125,
|
| 1821 |
+
"learning_rate": 2.7875267794444948e-06,
|
| 1822 |
+
"loss": 0.3012939691543579,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 1.368421052631579,
|
| 1827 |
+
"grad_norm": 0.6484375,
|
| 1828 |
+
"learning_rate": 2.7464322588775947e-06,
|
| 1829 |
+
"loss": 0.29359281063079834,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 1.3736842105263158,
|
| 1834 |
+
"grad_norm": 0.6484375,
|
| 1835 |
+
"learning_rate": 2.705527896527721e-06,
|
| 1836 |
+
"loss": 0.29863748550415037,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 1.3789473684210527,
|
| 1841 |
+
"grad_norm": 0.6640625,
|
| 1842 |
+
"learning_rate": 2.664817143944376e-06,
|
| 1843 |
+
"loss": 0.297974967956543,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.3842105263157896,
|
| 1848 |
+
"grad_norm": 0.65234375,
|
| 1849 |
+
"learning_rate": 2.6243034363400843e-06,
|
| 1850 |
+
"loss": 0.3142268180847168,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 1.3894736842105262,
|
| 1855 |
+
"grad_norm": 0.640625,
|
| 1856 |
+
"learning_rate": 2.5839901923005207e-06,
|
| 1857 |
+
"loss": 0.2994800567626953,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.3947368421052633,
|
| 1862 |
+
"grad_norm": 0.65234375,
|
| 1863 |
+
"learning_rate": 2.5438808134960556e-06,
|
| 1864 |
+
"loss": 0.2963359832763672,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 1.4,
|
| 1869 |
+
"grad_norm": 0.6875,
|
| 1870 |
+
"learning_rate": 2.5039786843947113e-06,
|
| 1871 |
+
"loss": 0.3018345355987549,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 1.4052631578947368,
|
| 1876 |
+
"grad_norm": 0.6640625,
|
| 1877 |
+
"learning_rate": 2.4642871719765854e-06,
|
| 1878 |
+
"loss": 0.30335607528686526,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 1.4105263157894736,
|
| 1883 |
+
"grad_norm": 0.6796875,
|
| 1884 |
+
"learning_rate": 2.424809625449729e-06,
|
| 1885 |
+
"loss": 0.30669000148773196,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.4157894736842105,
|
| 1890 |
+
"grad_norm": 0.6796875,
|
| 1891 |
+
"learning_rate": 2.3855493759675542e-06,
|
| 1892 |
+
"loss": 0.3048810243606567,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 1.4210526315789473,
|
| 1897 |
+
"grad_norm": 0.72265625,
|
| 1898 |
+
"learning_rate": 2.346509736347731e-06,
|
| 1899 |
+
"loss": 0.29688520431518556,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 1.4263157894736842,
|
| 1904 |
+
"grad_norm": 0.68359375,
|
| 1905 |
+
"learning_rate": 2.307694000792663e-06,
|
| 1906 |
+
"loss": 0.29866323471069334,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 1.431578947368421,
|
| 1911 |
+
"grad_norm": 0.65625,
|
| 1912 |
+
"learning_rate": 2.269105444611508e-06,
|
| 1913 |
+
"loss": 0.29165570735931395,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.436842105263158,
|
| 1918 |
+
"grad_norm": 0.66796875,
|
| 1919 |
+
"learning_rate": 2.2307473239438153e-06,
|
| 1920 |
+
"loss": 0.30020575523376464,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 1.4421052631578948,
|
| 1925 |
+
"grad_norm": 0.70703125,
|
| 1926 |
+
"learning_rate": 2.1926228754847557e-06,
|
| 1927 |
+
"loss": 0.29546422958374025,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.4473684210526316,
|
| 1932 |
+
"grad_norm": 0.67578125,
|
| 1933 |
+
"learning_rate": 2.1547353162120226e-06,
|
| 1934 |
+
"loss": 0.2950193166732788,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 1.4526315789473685,
|
| 1939 |
+
"grad_norm": 0.640625,
|
| 1940 |
+
"learning_rate": 2.117087843114364e-06,
|
| 1941 |
+
"loss": 0.2982841730117798,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 1.4578947368421051,
|
| 1946 |
+
"grad_norm": 0.71484375,
|
| 1947 |
+
"learning_rate": 2.079683632921831e-06,
|
| 1948 |
+
"loss": 0.2915778636932373,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 1.4631578947368422,
|
| 1953 |
+
"grad_norm": 0.7265625,
|
| 1954 |
+
"learning_rate": 2.042525841837712e-06,
|
| 1955 |
+
"loss": 0.2988855838775635,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.4684210526315788,
|
| 1960 |
+
"grad_norm": 0.64453125,
|
| 1961 |
+
"learning_rate": 2.0056176052722175e-06,
|
| 1962 |
+
"loss": 0.2997340202331543,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 1.4736842105263157,
|
| 1967 |
+
"grad_norm": 0.66015625,
|
| 1968 |
+
"learning_rate": 1.9689620375779034e-06,
|
| 1969 |
+
"loss": 0.30264670848846437,
|
| 1970 |
+
"step": 2800
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.4789473684210526,
|
| 1974 |
+
"grad_norm": 0.6640625,
|
| 1975 |
+
"learning_rate": 1.932562231786887e-06,
|
| 1976 |
+
"loss": 0.29979183673858645,
|
| 1977 |
+
"step": 2810
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 1.4842105263157894,
|
| 1981 |
+
"grad_norm": 0.7109375,
|
| 1982 |
+
"learning_rate": 1.8964212593498444e-06,
|
| 1983 |
+
"loss": 0.3019663572311401,
|
| 1984 |
+
"step": 2820
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 1.4894736842105263,
|
| 1988 |
+
"grad_norm": 0.65234375,
|
| 1989 |
+
"learning_rate": 1.860542169876851e-06,
|
| 1990 |
+
"loss": 0.3000542402267456,
|
| 1991 |
+
"step": 2830
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 1.4947368421052631,
|
| 1995 |
+
"grad_norm": 0.671875,
|
| 1996 |
+
"learning_rate": 1.8249279908800382e-06,
|
| 1997 |
+
"loss": 0.3003431558609009,
|
| 1998 |
+
"step": 2840
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 1.5,
|
| 2002 |
+
"grad_norm": 0.6796875,
|
| 2003 |
+
"learning_rate": 1.7895817275181433e-06,
|
| 2004 |
+
"loss": 0.29599614143371583,
|
| 2005 |
+
"step": 2850
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 1.5052631578947369,
|
| 2009 |
+
"grad_norm": 0.6796875,
|
| 2010 |
+
"learning_rate": 1.7545063623429159e-06,
|
| 2011 |
+
"loss": 0.2995570182800293,
|
| 2012 |
+
"step": 2860
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 1.5105263157894737,
|
| 2016 |
+
"grad_norm": 0.640625,
|
| 2017 |
+
"learning_rate": 1.7197048550474643e-06,
|
| 2018 |
+
"loss": 0.30172271728515626,
|
| 2019 |
+
"step": 2870
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 1.5157894736842106,
|
| 2023 |
+
"grad_norm": 0.75,
|
| 2024 |
+
"learning_rate": 1.6851801422164982e-06,
|
| 2025 |
+
"loss": 0.2962552785873413,
|
| 2026 |
+
"step": 2880
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.5210526315789474,
|
| 2030 |
+
"grad_norm": 0.68359375,
|
| 2031 |
+
"learning_rate": 1.6509351370785488e-06,
|
| 2032 |
+
"loss": 0.2978742361068726,
|
| 2033 |
+
"step": 2890
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 1.526315789473684,
|
| 2037 |
+
"grad_norm": 0.66796875,
|
| 2038 |
+
"learning_rate": 1.6169727292601378e-06,
|
| 2039 |
+
"loss": 0.2929815769195557,
|
| 2040 |
+
"step": 2900
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 1.5315789473684212,
|
| 2044 |
+
"grad_norm": 0.66015625,
|
| 2045 |
+
"learning_rate": 1.5832957845419583e-06,
|
| 2046 |
+
"loss": 0.2996316194534302,
|
| 2047 |
+
"step": 2910
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 1.5368421052631578,
|
| 2051 |
+
"grad_norm": 0.66796875,
|
| 2052 |
+
"learning_rate": 1.5499071446170466e-06,
|
| 2053 |
+
"loss": 0.2979148864746094,
|
| 2054 |
+
"step": 2920
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 1.5421052631578949,
|
| 2058 |
+
"grad_norm": 0.70703125,
|
| 2059 |
+
"learning_rate": 1.5168096268510079e-06,
|
| 2060 |
+
"loss": 0.29439692497253417,
|
| 2061 |
+
"step": 2930
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 1.5473684210526315,
|
| 2065 |
+
"grad_norm": 0.65625,
|
| 2066 |
+
"learning_rate": 1.484006024044274e-06,
|
| 2067 |
+
"loss": 0.2965528964996338,
|
| 2068 |
+
"step": 2940
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 1.5526315789473686,
|
| 2072 |
+
"grad_norm": 0.65625,
|
| 2073 |
+
"learning_rate": 1.4514991041964544e-06,
|
| 2074 |
+
"loss": 0.3051332712173462,
|
| 2075 |
+
"step": 2950
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 1.5578947368421052,
|
| 2079 |
+
"grad_norm": 0.6328125,
|
| 2080 |
+
"learning_rate": 1.41929161027276e-06,
|
| 2081 |
+
"loss": 0.30417981147766116,
|
| 2082 |
+
"step": 2960
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.563157894736842,
|
| 2086 |
+
"grad_norm": 0.6796875,
|
| 2087 |
+
"learning_rate": 1.387386259972558e-06,
|
| 2088 |
+
"loss": 0.2969485282897949,
|
| 2089 |
+
"step": 2970
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 1.568421052631579,
|
| 2093 |
+
"grad_norm": 0.71875,
|
| 2094 |
+
"learning_rate": 1.3557857455000417e-06,
|
| 2095 |
+
"loss": 0.29744491577148435,
|
| 2096 |
+
"step": 2980
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 1.5736842105263158,
|
| 2100 |
+
"grad_norm": 0.70703125,
|
| 2101 |
+
"learning_rate": 1.3244927333370672e-06,
|
| 2102 |
+
"loss": 0.2998826026916504,
|
| 2103 |
+
"step": 2990
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 1.5789473684210527,
|
| 2107 |
+
"grad_norm": 0.6796875,
|
| 2108 |
+
"learning_rate": 1.293509864018146e-06,
|
| 2109 |
+
"loss": 0.3018002510070801,
|
| 2110 |
+
"step": 3000
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 1.5842105263157895,
|
| 2114 |
+
"grad_norm": 0.69921875,
|
| 2115 |
+
"learning_rate": 1.2628397519076412e-06,
|
| 2116 |
+
"loss": 0.29767565727233886,
|
| 2117 |
+
"step": 3010
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 1.5894736842105264,
|
| 2121 |
+
"grad_norm": 0.70703125,
|
| 2122 |
+
"learning_rate": 1.232484984979157e-06,
|
| 2123 |
+
"loss": 0.30785164833068845,
|
| 2124 |
+
"step": 3020
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 1.594736842105263,
|
| 2128 |
+
"grad_norm": 0.65234375,
|
| 2129 |
+
"learning_rate": 1.202448124597173e-06,
|
| 2130 |
+
"loss": 0.3030004739761353,
|
| 2131 |
+
"step": 3030
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 1.6,
|
| 2135 |
+
"grad_norm": 0.67578125,
|
| 2136 |
+
"learning_rate": 1.1727317053009025e-06,
|
| 2137 |
+
"loss": 0.30095791816711426,
|
| 2138 |
+
"step": 3040
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.6052631578947367,
|
| 2142 |
+
"grad_norm": 0.64453125,
|
| 2143 |
+
"learning_rate": 1.1433382345904355e-06,
|
| 2144 |
+
"loss": 0.3002848386764526,
|
| 2145 |
+
"step": 3050
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 1.6105263157894738,
|
| 2149 |
+
"grad_norm": 0.671875,
|
| 2150 |
+
"learning_rate": 1.1142701927151456e-06,
|
| 2151 |
+
"loss": 0.2984454154968262,
|
| 2152 |
+
"step": 3060
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 1.6157894736842104,
|
| 2156 |
+
"grad_norm": 0.7265625,
|
| 2157 |
+
"learning_rate": 1.085530032464412e-06,
|
| 2158 |
+
"loss": 0.3011799335479736,
|
| 2159 |
+
"step": 3070
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 1.6210526315789475,
|
| 2163 |
+
"grad_norm": 0.671875,
|
| 2164 |
+
"learning_rate": 1.0571201789606416e-06,
|
| 2165 |
+
"loss": 0.2953039169311523,
|
| 2166 |
+
"step": 3080
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 1.6263157894736842,
|
| 2170 |
+
"grad_norm": 0.74609375,
|
| 2171 |
+
"learning_rate": 1.0290430294546449e-06,
|
| 2172 |
+
"loss": 0.29342939853668215,
|
| 2173 |
+
"step": 3090
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 1.631578947368421,
|
| 2177 |
+
"grad_norm": 0.6640625,
|
| 2178 |
+
"learning_rate": 1.0013009531233441e-06,
|
| 2179 |
+
"loss": 0.2983479738235474,
|
| 2180 |
+
"step": 3100
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 1.6368421052631579,
|
| 2184 |
+
"grad_norm": 0.6953125,
|
| 2185 |
+
"learning_rate": 9.738962908698679e-07,
|
| 2186 |
+
"loss": 0.2971032619476318,
|
| 2187 |
+
"step": 3110
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 1.6421052631578947,
|
| 2191 |
+
"grad_norm": 0.6796875,
|
| 2192 |
+
"learning_rate": 9.468313551260161e-07,
|
| 2193 |
+
"loss": 0.30310494899749757,
|
| 2194 |
+
"step": 3120
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.6473684210526316,
|
| 2198 |
+
"grad_norm": 0.63671875,
|
| 2199 |
+
"learning_rate": 9.201084296571427e-07,
|
| 2200 |
+
"loss": 0.30494041442871095,
|
| 2201 |
+
"step": 3130
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 1.6526315789473685,
|
| 2205 |
+
"grad_norm": 0.703125,
|
| 2206 |
+
"learning_rate": 8.937297693694407e-07,
|
| 2207 |
+
"loss": 0.3013713836669922,
|
| 2208 |
+
"step": 3140
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 1.6578947368421053,
|
| 2212 |
+
"grad_norm": 0.69921875,
|
| 2213 |
+
"learning_rate": 8.676976001196802e-07,
|
| 2214 |
+
"loss": 0.30413882732391356,
|
| 2215 |
+
"step": 3150
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 1.663157894736842,
|
| 2219 |
+
"grad_norm": 0.71484375,
|
| 2220 |
+
"learning_rate": 8.420141185273784e-07,
|
| 2221 |
+
"loss": 0.29632341861724854,
|
| 2222 |
+
"step": 3160
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 1.668421052631579,
|
| 2226 |
+
"grad_norm": 0.6953125,
|
| 2227 |
+
"learning_rate": 8.166814917894577e-07,
|
| 2228 |
+
"loss": 0.29839210510253905,
|
| 2229 |
+
"step": 3170
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 1.6736842105263157,
|
| 2233 |
+
"grad_norm": 0.72265625,
|
| 2234 |
+
"learning_rate": 7.917018574973646e-07,
|
| 2235 |
+
"loss": 0.2972310304641724,
|
| 2236 |
+
"step": 3180
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 1.6789473684210527,
|
| 2240 |
+
"grad_norm": 0.65625,
|
| 2241 |
+
"learning_rate": 7.67077323456708e-07,
|
| 2242 |
+
"loss": 0.2946524381637573,
|
| 2243 |
+
"step": 3190
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 1.6842105263157894,
|
| 2247 |
+
"grad_norm": 0.6796875,
|
| 2248 |
+
"learning_rate": 7.428099675093903e-07,
|
| 2249 |
+
"loss": 0.2969599008560181,
|
| 2250 |
+
"step": 3200
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.6894736842105265,
|
| 2254 |
+
"grad_norm": 0.6875,
|
| 2255 |
+
"learning_rate": 7.189018373582873e-07,
|
| 2256 |
+
"loss": 0.29296250343322755,
|
| 2257 |
+
"step": 3210
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 1.694736842105263,
|
| 2261 |
+
"grad_norm": 0.6640625,
|
| 2262 |
+
"learning_rate": 6.953549503944512e-07,
|
| 2263 |
+
"loss": 0.30225491523742676,
|
| 2264 |
+
"step": 3220
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 1.7,
|
| 2268 |
+
"grad_norm": 0.6953125,
|
| 2269 |
+
"learning_rate": 6.72171293526891e-07,
|
| 2270 |
+
"loss": 0.30234057903289796,
|
| 2271 |
+
"step": 3230
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 1.7052631578947368,
|
| 2275 |
+
"grad_norm": 0.6796875,
|
| 2276 |
+
"learning_rate": 6.493528230149054e-07,
|
| 2277 |
+
"loss": 0.2982638835906982,
|
| 2278 |
+
"step": 3240
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 1.7105263157894737,
|
| 2282 |
+
"grad_norm": 0.69140625,
|
| 2283 |
+
"learning_rate": 6.269014643030214e-07,
|
| 2284 |
+
"loss": 0.3014231204986572,
|
| 2285 |
+
"step": 3250
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 1.7157894736842105,
|
| 2289 |
+
"grad_norm": 0.65234375,
|
| 2290 |
+
"learning_rate": 6.048191118585139e-07,
|
| 2291 |
+
"loss": 0.2946383237838745,
|
| 2292 |
+
"step": 3260
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 1.7210526315789474,
|
| 2296 |
+
"grad_norm": 0.66796875,
|
| 2297 |
+
"learning_rate": 5.831076290115572e-07,
|
| 2298 |
+
"loss": 0.29816861152648927,
|
| 2299 |
+
"step": 3270
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 1.7263157894736842,
|
| 2303 |
+
"grad_norm": 0.8203125,
|
| 2304 |
+
"learning_rate": 5.617688477979893e-07,
|
| 2305 |
+
"loss": 0.305389404296875,
|
| 2306 |
+
"step": 3280
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.731578947368421,
|
| 2310 |
+
"grad_norm": 0.69921875,
|
| 2311 |
+
"learning_rate": 5.408045688047275e-07,
|
| 2312 |
+
"loss": 0.2932974100112915,
|
| 2313 |
+
"step": 3290
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 1.736842105263158,
|
| 2317 |
+
"grad_norm": 0.66015625,
|
| 2318 |
+
"learning_rate": 5.202165610178284e-07,
|
| 2319 |
+
"loss": 0.2984506607055664,
|
| 2320 |
+
"step": 3300
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 1.7421052631578946,
|
| 2324 |
+
"grad_norm": 0.6875,
|
| 2325 |
+
"learning_rate": 5.000065616732242e-07,
|
| 2326 |
+
"loss": 0.30037047863006594,
|
| 2327 |
+
"step": 3310
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 1.7473684210526317,
|
| 2331 |
+
"grad_norm": 0.671875,
|
| 2332 |
+
"learning_rate": 4.80176276110128e-07,
|
| 2333 |
+
"loss": 0.2955051898956299,
|
| 2334 |
+
"step": 3320
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 1.7526315789473683,
|
| 2338 |
+
"grad_norm": 0.6875,
|
| 2339 |
+
"learning_rate": 4.607273776271415e-07,
|
| 2340 |
+
"loss": 0.2953267812728882,
|
| 2341 |
+
"step": 3330
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 1.7578947368421054,
|
| 2345 |
+
"grad_norm": 0.63671875,
|
| 2346 |
+
"learning_rate": 4.4166150734105296e-07,
|
| 2347 |
+
"loss": 0.3000968933105469,
|
| 2348 |
+
"step": 3340
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 1.763157894736842,
|
| 2352 |
+
"grad_norm": 0.68359375,
|
| 2353 |
+
"learning_rate": 4.229802740483674e-07,
|
| 2354 |
+
"loss": 0.2961698532104492,
|
| 2355 |
+
"step": 3350
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 1.768421052631579,
|
| 2359 |
+
"grad_norm": 0.65625,
|
| 2360 |
+
"learning_rate": 4.046852540895446e-07,
|
| 2361 |
+
"loss": 0.29968795776367185,
|
| 2362 |
+
"step": 3360
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.7736842105263158,
|
| 2366 |
+
"grad_norm": 0.640625,
|
| 2367 |
+
"learning_rate": 3.8677799121599525e-07,
|
| 2368 |
+
"loss": 0.30074248313903806,
|
| 2369 |
+
"step": 3370
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 1.7789473684210526,
|
| 2373 |
+
"grad_norm": 0.6796875,
|
| 2374 |
+
"learning_rate": 3.6925999645981205e-07,
|
| 2375 |
+
"loss": 0.29626715183258057,
|
| 2376 |
+
"step": 3380
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 1.7842105263157895,
|
| 2380 |
+
"grad_norm": 0.66015625,
|
| 2381 |
+
"learning_rate": 3.5213274800626696e-07,
|
| 2382 |
+
"loss": 0.29154119491577146,
|
| 2383 |
+
"step": 3390
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 1.7894736842105263,
|
| 2387 |
+
"grad_norm": 0.68359375,
|
| 2388 |
+
"learning_rate": 3.353976910690865e-07,
|
| 2389 |
+
"loss": 0.30303730964660647,
|
| 2390 |
+
"step": 3400
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 1.7947368421052632,
|
| 2394 |
+
"grad_norm": 0.640625,
|
| 2395 |
+
"learning_rate": 3.190562377684969e-07,
|
| 2396 |
+
"loss": 0.29616270065307615,
|
| 2397 |
+
"step": 3410
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 1.8,
|
| 2401 |
+
"grad_norm": 0.703125,
|
| 2402 |
+
"learning_rate": 3.031097670120703e-07,
|
| 2403 |
+
"loss": 0.30332746505737307,
|
| 2404 |
+
"step": 3420
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 1.805263157894737,
|
| 2408 |
+
"grad_norm": 0.67578125,
|
| 2409 |
+
"learning_rate": 2.875596243783713e-07,
|
| 2410 |
+
"loss": 0.30052239894866944,
|
| 2411 |
+
"step": 3430
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 1.8105263157894735,
|
| 2415 |
+
"grad_norm": 0.67578125,
|
| 2416 |
+
"learning_rate": 2.724071220034158e-07,
|
| 2417 |
+
"loss": 0.2973964214324951,
|
| 2418 |
+
"step": 3440
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 1.8157894736842106,
|
| 2422 |
+
"grad_norm": 0.71484375,
|
| 2423 |
+
"learning_rate": 2.57653538469953e-07,
|
| 2424 |
+
"loss": 0.29910430908203123,
|
| 2425 |
+
"step": 3450
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 1.8210526315789473,
|
| 2429 |
+
"grad_norm": 0.6875,
|
| 2430 |
+
"learning_rate": 2.433001186995737e-07,
|
| 2431 |
+
"loss": 0.3015556812286377,
|
| 2432 |
+
"step": 3460
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 1.8263157894736843,
|
| 2436 |
+
"grad_norm": 0.69140625,
|
| 2437 |
+
"learning_rate": 2.2934807384766555e-07,
|
| 2438 |
+
"loss": 0.3117814064025879,
|
| 2439 |
+
"step": 3470
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 1.831578947368421,
|
| 2443 |
+
"grad_norm": 0.66796875,
|
| 2444 |
+
"learning_rate": 2.1579858120121477e-07,
|
| 2445 |
+
"loss": 0.3009961605072021,
|
| 2446 |
+
"step": 3480
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 1.836842105263158,
|
| 2450 |
+
"grad_norm": 0.71875,
|
| 2451 |
+
"learning_rate": 2.02652784079464e-07,
|
| 2452 |
+
"loss": 0.29814648628234863,
|
| 2453 |
+
"step": 3490
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 1.8421052631578947,
|
| 2457 |
+
"grad_norm": 0.7265625,
|
| 2458 |
+
"learning_rate": 1.8991179173743935e-07,
|
| 2459 |
+
"loss": 0.292824387550354,
|
| 2460 |
+
"step": 3500
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 1.8473684210526315,
|
| 2464 |
+
"grad_norm": 0.69140625,
|
| 2465 |
+
"learning_rate": 1.7757667927234767e-07,
|
| 2466 |
+
"loss": 0.30036211013793945,
|
| 2467 |
+
"step": 3510
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 1.8526315789473684,
|
| 2471 |
+
"grad_norm": 0.65625,
|
| 2472 |
+
"learning_rate": 1.6564848753286233e-07,
|
| 2473 |
+
"loss": 0.2989194869995117,
|
| 2474 |
+
"step": 3520
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.8578947368421053,
|
| 2478 |
+
"grad_norm": 0.72265625,
|
| 2479 |
+
"learning_rate": 1.5412822303129514e-07,
|
| 2480 |
+
"loss": 0.2997861862182617,
|
| 2481 |
+
"step": 3530
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 1.8631578947368421,
|
| 2485 |
+
"grad_norm": 0.67578125,
|
| 2486 |
+
"learning_rate": 1.4301685785866215e-07,
|
| 2487 |
+
"loss": 0.29810757637023927,
|
| 2488 |
+
"step": 3540
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 1.868421052631579,
|
| 2492 |
+
"grad_norm": 0.66796875,
|
| 2493 |
+
"learning_rate": 1.3231532960266024e-07,
|
| 2494 |
+
"loss": 0.3078226804733276,
|
| 2495 |
+
"step": 3550
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 1.8736842105263158,
|
| 2499 |
+
"grad_norm": 0.6953125,
|
| 2500 |
+
"learning_rate": 1.220245412685539e-07,
|
| 2501 |
+
"loss": 0.30055484771728513,
|
| 2502 |
+
"step": 3560
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 1.8789473684210525,
|
| 2506 |
+
"grad_norm": 0.6796875,
|
| 2507 |
+
"learning_rate": 1.1214536120297714e-07,
|
| 2508 |
+
"loss": 0.2956956386566162,
|
| 2509 |
+
"step": 3570
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 1.8842105263157896,
|
| 2513 |
+
"grad_norm": 0.66015625,
|
| 2514 |
+
"learning_rate": 1.0267862302066112e-07,
|
| 2515 |
+
"loss": 0.29946484565734866,
|
| 2516 |
+
"step": 3580
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 1.8894736842105262,
|
| 2520 |
+
"grad_norm": 0.703125,
|
| 2521 |
+
"learning_rate": 9.362512553409253e-08,
|
| 2522 |
+
"loss": 0.30321674346923827,
|
| 2523 |
+
"step": 3590
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 1.8947368421052633,
|
| 2527 |
+
"grad_norm": 0.609375,
|
| 2528 |
+
"learning_rate": 8.498563268611205e-08,
|
| 2529 |
+
"loss": 0.29636733531951903,
|
| 2530 |
+
"step": 3600
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 1.9,
|
| 2534 |
+
"grad_norm": 0.671875,
|
| 2535 |
+
"learning_rate": 7.67608734854497e-08,
|
| 2536 |
+
"loss": 0.2988576412200928,
|
| 2537 |
+
"step": 3610
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 1.905263157894737,
|
| 2541 |
+
"grad_norm": 0.6875,
|
| 2542 |
+
"learning_rate": 6.895154194521026e-08,
|
| 2543 |
+
"loss": 0.30216183662414553,
|
| 2544 |
+
"step": 3620
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 1.9105263157894736,
|
| 2548 |
+
"grad_norm": 0.6875,
|
| 2549 |
+
"learning_rate": 6.15582970243117e-08,
|
| 2550 |
+
"loss": 0.302366304397583,
|
| 2551 |
+
"step": 3630
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 1.9157894736842105,
|
| 2555 |
+
"grad_norm": 0.6796875,
|
| 2556 |
+
"learning_rate": 5.458176257188308e-08,
|
| 2557 |
+
"loss": 0.3039771556854248,
|
| 2558 |
+
"step": 3640
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 1.9210526315789473,
|
| 2562 |
+
"grad_norm": 0.67578125,
|
| 2563 |
+
"learning_rate": 4.8022527274622644e-08,
|
| 2564 |
+
"loss": 0.30275673866271974,
|
| 2565 |
+
"step": 3650
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 1.9263157894736842,
|
| 2569 |
+
"grad_norm": 0.69140625,
|
| 2570 |
+
"learning_rate": 4.1881144607124334e-08,
|
| 2571 |
+
"loss": 0.292505145072937,
|
| 2572 |
+
"step": 3660
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 1.931578947368421,
|
| 2576 |
+
"grad_norm": 0.67578125,
|
| 2577 |
+
"learning_rate": 3.615813278517344e-08,
|
| 2578 |
+
"loss": 0.3019336938858032,
|
| 2579 |
+
"step": 3670
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 1.936842105263158,
|
| 2583 |
+
"grad_norm": 0.69140625,
|
| 2584 |
+
"learning_rate": 3.085397472202101e-08,
|
| 2585 |
+
"loss": 0.30004544258117677,
|
| 2586 |
+
"step": 3680
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 1.9421052631578948,
|
| 2590 |
+
"grad_norm": 0.6875,
|
| 2591 |
+
"learning_rate": 2.5969117987634795e-08,
|
| 2592 |
+
"loss": 0.30235512256622316,
|
| 2593 |
+
"step": 3690
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 1.9473684210526314,
|
| 2597 |
+
"grad_norm": 0.62109375,
|
| 2598 |
+
"learning_rate": 2.1503974770931137e-08,
|
| 2599 |
+
"loss": 0.29522273540496824,
|
| 2600 |
+
"step": 3700
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 1.9526315789473685,
|
| 2604 |
+
"grad_norm": 0.66015625,
|
| 2605 |
+
"learning_rate": 1.7458921844996646e-08,
|
| 2606 |
+
"loss": 0.2977579593658447,
|
| 2607 |
+
"step": 3710
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 1.9578947368421051,
|
| 2611 |
+
"grad_norm": 0.6796875,
|
| 2612 |
+
"learning_rate": 1.383430053529422e-08,
|
| 2613 |
+
"loss": 0.29578843116760256,
|
| 2614 |
+
"step": 3720
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 1.9631578947368422,
|
| 2618 |
+
"grad_norm": 0.671875,
|
| 2619 |
+
"learning_rate": 1.0630416690862178e-08,
|
| 2620 |
+
"loss": 0.29667110443115235,
|
| 2621 |
+
"step": 3730
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 1.9684210526315788,
|
| 2625 |
+
"grad_norm": 0.68359375,
|
| 2626 |
+
"learning_rate": 7.84754065850546e-09,
|
| 2627 |
+
"loss": 0.2974194049835205,
|
| 2628 |
+
"step": 3740
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 1.973684210526316,
|
| 2632 |
+
"grad_norm": 0.75,
|
| 2633 |
+
"learning_rate": 5.485907259984435e-09,
|
| 2634 |
+
"loss": 0.2973806381225586,
|
| 2635 |
+
"step": 3750
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 1.9789473684210526,
|
| 2639 |
+
"grad_norm": 0.6953125,
|
| 2640 |
+
"learning_rate": 3.545715772200753e-09,
|
| 2641 |
+
"loss": 0.2977163314819336,
|
| 2642 |
+
"step": 3760
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 1.9842105263157894,
|
| 2646 |
+
"grad_norm": 0.6328125,
|
| 2647 |
+
"learning_rate": 2.0271299103813423e-09,
|
| 2648 |
+
"loss": 0.2955323696136475,
|
| 2649 |
+
"step": 3770
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 1.9894736842105263,
|
| 2653 |
+
"grad_norm": 0.71484375,
|
| 2654 |
+
"learning_rate": 9.302778142639135e-10,
|
| 2655 |
+
"loss": 0.3025184392929077,
|
| 2656 |
+
"step": 3780
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 1.9947368421052631,
|
| 2660 |
+
"grad_norm": 0.71484375,
|
| 2661 |
+
"learning_rate": 2.552520372844924e-10,
|
| 2662 |
+
"loss": 0.3038780927658081,
|
| 2663 |
+
"step": 3790
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 2.0,
|
| 2667 |
+
"grad_norm": 0.73046875,
|
| 2668 |
+
"learning_rate": 2.1095387697789293e-12,
|
| 2669 |
+
"loss": 0.29937565326690674,
|
| 2670 |
+
"step": 3800
|
| 2671 |
+
}
|
| 2672 |
+
],
|
| 2673 |
+
"logging_steps": 10,
|
| 2674 |
+
"max_steps": 3800,
|
| 2675 |
+
"num_input_tokens_seen": 0,
|
| 2676 |
+
"num_train_epochs": 2,
|
| 2677 |
+
"save_steps": 400,
|
| 2678 |
+
"stateful_callbacks": {
|
| 2679 |
+
"TrainerControl": {
|
| 2680 |
+
"args": {
|
| 2681 |
+
"should_epoch_stop": false,
|
| 2682 |
+
"should_evaluate": false,
|
| 2683 |
+
"should_log": false,
|
| 2684 |
+
"should_save": true,
|
| 2685 |
+
"should_training_stop": true
|
| 2686 |
+
},
|
| 2687 |
+
"attributes": {}
|
| 2688 |
+
}
|
| 2689 |
+
},
|
| 2690 |
+
"total_flos": 1.005129553083682e+20,
|
| 2691 |
+
"train_batch_size": 1,
|
| 2692 |
+
"trial_name": null,
|
| 2693 |
+
"trial_params": null
|
| 2694 |
+
}
|