Hugging Face's logo

furproxy
/
9b-75

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
llama-factory
full
Generated from Trainer
conversational
Model card Files
xet
 Community
furproxy commited on
Commit
85dfa4b
·
verified ·
1 Parent(s): 652116c

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. .ipynb_checkpoints/README-checkpoint.md +63 -0
  3. README.md +63 -0
  4. all_results.json +9 -0
  5. chat_template.jinja +154 -0
  6. config.json +113 -0
  7. generation_config.json +10 -0
  8. model.safetensors +3 -0
  9. processor_config.json +60 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +33 -0
  12. train_results.json +9 -0
  13. trainer_log.jsonl +0 -0
  14. trainer_state.json +3557 -0
  15. training_args.bin +3 -0
  16. training_loss.png +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.ipynb_checkpoints/README-checkpoint.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen3.5-9B
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: qwen35_caption_galore
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # qwen35_caption_galore
18
+
19
+ This model is a fine-tuned version of [/workspace/models/Qwen3.5-9B](https://huggingface.co//workspace/models/Qwen3.5-9B) on the my_caption dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - family_to_adamw_lr = {
39
+ "language": _fallback(getattr(training_args, "language_adamw_lr", 1e-5), language_lr),
40
+ "vision": _fallback(getattr(training_args, "vision_adamw_lr", 5e-6), vision_lr),
41
+ "merger": _fallback(getattr(training_args, "merger_adamw_lr", 5e-6), merger_lr),
42
+ }
43
+ - train_batch_size: 1
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - gradient_accumulation_steps: 60
48
+ - total_train_batch_size: 60
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine_with_min_lr
51
+ - lr_scheduler_warmup_steps: 0.05
52
+ - num_epochs: 4
53
+
54
+ ### Training results
55
+
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 5.5.3
61
+ - Pytorch 2.11.0+cu128
62
+ - Datasets 4.0.0
63
+ - Tokenizers 0.22.2
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen3.5-9B
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: qwen35_caption_galore
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # qwen35_caption_galore
18
+
19
+ This model is a fine-tuned version of [/workspace/models/Qwen3.5-9B](https://huggingface.co//workspace/models/Qwen3.5-9B) on the my_caption dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - family_to_adamw_lr = {
39
+ "language": _fallback(getattr(training_args, "language_adamw_lr", 1e-5), language_lr),
40
+ "vision": _fallback(getattr(training_args, "vision_adamw_lr", 5e-6), vision_lr),
41
+ "merger": _fallback(getattr(training_args, "merger_adamw_lr", 5e-6), merger_lr),
42
+ }
43
+ - train_batch_size: 1
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - gradient_accumulation_steps: 60
48
+ - total_train_batch_size: 60
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine_with_min_lr
51
+ - lr_scheduler_warmup_steps: 0.05
52
+ - num_epochs: 4
53
+
54
+ ### Training results
55
+
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 5.5.3
61
+ - Pytorch 2.11.0+cu128
62
+ - Datasets 4.0.0
63
+ - Tokenizers 0.22.2
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "effective_tokens_per_sec": 2260.7612660843506,
3
+ "epoch": 4.0,
4
+ "total_flos": 3.954132003103703e+18,
5
+ "train_loss": 0.8403717435273041,
6
+ "train_runtime": 34650.8856,
7
+ "train_samples_per_second": 1.738,
8
+ "train_steps_per_second": 0.029
9
+ }
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if loop.index0 > ns.last_query_index %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "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": "5.5.3",
92
+ "use_cache": false,
93
+ "video_token_id": 248057,
94
+ "vision_config": {
95
+ "deepstack_visual_indexes": [],
96
+ "depth": 27,
97
+ "dtype": "bfloat16",
98
+ "hidden_act": "gelu_pytorch_tanh",
99
+ "hidden_size": 1152,
100
+ "in_channels": 3,
101
+ "initializer_range": 0.02,
102
+ "intermediate_size": 4304,
103
+ "model_type": "qwen3_5",
104
+ "num_heads": 16,
105
+ "num_position_embeddings": 2304,
106
+ "out_hidden_size": 4096,
107
+ "patch_size": 16,
108
+ "spatial_merge_size": 2,
109
+ "temporal_patch_size": 2
110
+ },
111
+ "vision_end_token_id": 248054,
112
+ "vision_start_token_id": 248053
113
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248044
6
+ ],
7
+ "pad_token_id": 248044,
8
+ "transformers_version": "5.5.3",
9
+ "use_cache": true
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd53dc9343ea0a9f7237382ddb70c7a5e21314062e50e5e861dc188072bd4aab
3
+ size 20859273368
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
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "padding_side": "right",
25
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "TokenizersBackend",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>"
33
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "effective_tokens_per_sec": 2260.7612660843506,
3
+ "epoch": 4.0,
4
+ "total_flos": 3.954132003103703e+18,
5
+ "train_loss": 0.8403717435273041,
6
+ "train_runtime": 34650.8856,
7
+ "train_samples_per_second": 1.738,
8
+ "train_steps_per_second": 0.029
9
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,3557 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1004,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00796812749003984,
14
+ "grad_norm": 0.3647017180919647,
15
+ "learning_rate": 1.9607843137254904e-07,
16
+ "loss": 2.1478986740112305,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.01593625498007968,
21
+ "grad_norm": 0.24763226509094238,
22
+ "learning_rate": 5.882352941176471e-07,
23
+ "loss": 2.0969438552856445,
24
+ "step": 4
25
+ },
26
+ {
27
+ "epoch": 0.02390438247011952,
28
+ "grad_norm": 0.9846194982528687,
29
+ "learning_rate": 9.80392156862745e-07,
30
+ "loss": 2.282338857650757,
31
+ "step": 6
32
+ },
33
+ {
34
+ "epoch": 0.03187250996015936,
35
+ "grad_norm": 0.2201109677553177,
36
+ "learning_rate": 1.3725490196078434e-06,
37
+ "loss": 1.9020755290985107,
38
+ "step": 8
39
+ },
40
+ {
41
+ "epoch": 0.0398406374501992,
42
+ "grad_norm": 0.5704253911972046,
43
+ "learning_rate": 1.7647058823529414e-06,
44
+ "loss": 1.4784005880355835,
45
+ "step": 10
46
+ },
47
+ {
48
+ "epoch": 0.04780876494023904,
49
+ "grad_norm": 0.2062346190214157,
50
+ "learning_rate": 2.1568627450980393e-06,
51
+ "loss": 1.731598138809204,
52
+ "step": 12
53
+ },
54
+ {
55
+ "epoch": 0.055776892430278883,
56
+ "grad_norm": 2.076277256011963,
57
+ "learning_rate": 2.549019607843137e-06,
58
+ "loss": 2.348186492919922,
59
+ "step": 14
60
+ },
61
+ {
62
+ "epoch": 0.06374501992031872,
63
+ "grad_norm": 0.8406722545623779,
64
+ "learning_rate": 2.9411764705882355e-06,
65
+ "loss": 2.586444854736328,
66
+ "step": 16
67
+ },
68
+ {
69
+ "epoch": 0.07171314741035857,
70
+ "grad_norm": 0.3690650761127472,
71
+ "learning_rate": 3.3333333333333333e-06,
72
+ "loss": 1.6810544729232788,
73
+ "step": 18
74
+ },
75
+ {
76
+ "epoch": 0.0796812749003984,
77
+ "grad_norm": 0.18414445221424103,
78
+ "learning_rate": 3.7254901960784316e-06,
79
+ "loss": 1.6172391176223755,
80
+ "step": 20
81
+ },
82
+ {
83
+ "epoch": 0.08764940239043825,
84
+ "grad_norm": 0.17469090223312378,
85
+ "learning_rate": 4.11764705882353e-06,
86
+ "loss": 1.25531005859375,
87
+ "step": 22
88
+ },
89
+ {
90
+ "epoch": 0.09561752988047809,
91
+ "grad_norm": 1.353502631187439,
92
+ "learning_rate": 4.509803921568628e-06,
93
+ "loss": 1.4002299308776855,
94
+ "step": 24
95
+ },
96
+ {
97
+ "epoch": 0.10358565737051793,
98
+ "grad_norm": 0.12341447174549103,
99
+ "learning_rate": 4.901960784313726e-06,
100
+ "loss": 1.5042188167572021,
101
+ "step": 26
102
+ },
103
+ {
104
+ "epoch": 0.11155378486055777,
105
+ "grad_norm": 0.3027441203594208,
106
+ "learning_rate": 5.294117647058824e-06,
107
+ "loss": 1.6550602912902832,
108
+ "step": 28
109
+ },
110
+ {
111
+ "epoch": 0.11952191235059761,
112
+ "grad_norm": 0.4921821057796478,
113
+ "learning_rate": 5.686274509803922e-06,
114
+ "loss": 1.3609421253204346,
115
+ "step": 30
116
+ },
117
+ {
118
+ "epoch": 0.12749003984063745,
119
+ "grad_norm": 0.32808157801628113,
120
+ "learning_rate": 6.07843137254902e-06,
121
+ "loss": 1.1800657510757446,
122
+ "step": 32
123
+ },
124
+ {
125
+ "epoch": 0.13545816733067728,
126
+ "grad_norm": 0.4257211983203888,
127
+ "learning_rate": 6.470588235294119e-06,
128
+ "loss": 1.305320143699646,
129
+ "step": 34
130
+ },
131
+ {
132
+ "epoch": 0.14342629482071714,
133
+ "grad_norm": 0.132957324385643,
134
+ "learning_rate": 6.862745098039216e-06,
135
+ "loss": 1.4380031824111938,
136
+ "step": 36
137
+ },
138
+ {
139
+ "epoch": 0.15139442231075698,
140
+ "grad_norm": 0.2522510588169098,
141
+ "learning_rate": 7.2549019607843145e-06,
142
+ "loss": 1.2642239332199097,
143
+ "step": 38
144
+ },
145
+ {
146
+ "epoch": 0.1593625498007968,
147
+ "grad_norm": 0.2946537733078003,
148
+ "learning_rate": 7.647058823529411e-06,
149
+ "loss": 1.3502380847930908,
150
+ "step": 40
151
+ },
152
+ {
153
+ "epoch": 0.16733067729083664,
154
+ "grad_norm": 0.2393134981393814,
155
+ "learning_rate": 8.03921568627451e-06,
156
+ "loss": 0.7276158332824707,
157
+ "step": 42
158
+ },
159
+ {
160
+ "epoch": 0.1752988047808765,
161
+ "grad_norm": 0.16951222717761993,
162
+ "learning_rate": 8.43137254901961e-06,
163
+ "loss": 0.9695879817008972,
164
+ "step": 44
165
+ },
166
+ {
167
+ "epoch": 0.18326693227091634,
168
+ "grad_norm": 0.20765990018844604,
169
+ "learning_rate": 8.823529411764707e-06,
170
+ "loss": 0.9420666098594666,
171
+ "step": 46
172
+ },
173
+ {
174
+ "epoch": 0.19123505976095617,
175
+ "grad_norm": 0.5464557409286499,
176
+ "learning_rate": 9.215686274509804e-06,
177
+ "loss": 1.1855758428573608,
178
+ "step": 48
179
+ },
180
+ {
181
+ "epoch": 0.199203187250996,
182
+ "grad_norm": 0.15976053476333618,
183
+ "learning_rate": 9.607843137254903e-06,
184
+ "loss": 1.3898124694824219,
185
+ "step": 50
186
+ },
187
+ {
188
+ "epoch": 0.20717131474103587,
189
+ "grad_norm": 0.14374567568302155,
190
+ "learning_rate": 1e-05,
191
+ "loss": 1.3371469974517822,
192
+ "step": 52
193
+ },
194
+ {
195
+ "epoch": 0.2151394422310757,
196
+ "grad_norm": 0.3317624032497406,
197
+ "learning_rate": 9.999902196391087e-06,
198
+ "loss": 0.9539063572883606,
199
+ "step": 54
200
+ },
201
+ {
202
+ "epoch": 0.22310756972111553,
203
+ "grad_norm": 0.193589985370636,
204
+ "learning_rate": 9.999608789815699e-06,
205
+ "loss": 1.5122933387756348,
206
+ "step": 56
207
+ },
208
+ {
209
+ "epoch": 0.23107569721115537,
210
+ "grad_norm": 0.20332682132720947,
211
+ "learning_rate": 9.999119793027713e-06,
212
+ "loss": 1.3573031425476074,
213
+ "step": 58
214
+ },
215
+ {
216
+ "epoch": 0.23904382470119523,
217
+ "grad_norm": 0.11816702783107758,
218
+ "learning_rate": 9.998435227282975e-06,
219
+ "loss": 0.7735430598258972,
220
+ "step": 60
221
+ },
222
+ {
223
+ "epoch": 0.24701195219123506,
224
+ "grad_norm": 0.12483549118041992,
225
+ "learning_rate": 9.997555122338372e-06,
226
+ "loss": 1.3591876029968262,
227
+ "step": 62
228
+ },
229
+ {
230
+ "epoch": 0.2549800796812749,
231
+ "grad_norm": 0.4447817802429199,
232
+ "learning_rate": 9.996479516450544e-06,
233
+ "loss": 1.0984009504318237,
234
+ "step": 64
235
+ },
236
+ {
237
+ "epoch": 0.26294820717131473,
238
+ "grad_norm": 0.09938079863786697,
239
+ "learning_rate": 9.99520845637422e-06,
240
+ "loss": 1.285765528678894,
241
+ "step": 66
242
+ },
243
+ {
244
+ "epoch": 0.27091633466135456,
245
+ "grad_norm": 0.12960276007652283,
246
+ "learning_rate": 9.993741997360185e-06,
247
+ "loss": 0.7459665536880493,
248
+ "step": 68
249
+ },
250
+ {
251
+ "epoch": 0.2788844621513944,
252
+ "grad_norm": 0.4153902530670166,
253
+ "learning_rate": 9.992080203152872e-06,
254
+ "loss": 1.610697627067566,
255
+ "step": 70
256
+ },
257
+ {
258
+ "epoch": 0.2868525896414343,
259
+ "grad_norm": 0.19509944319725037,
260
+ "learning_rate": 9.990223145987608e-06,
261
+ "loss": 0.7440732717514038,
262
+ "step": 72
263
+ },
264
+ {
265
+ "epoch": 0.2948207171314741,
266
+ "grad_norm": 0.2681001126766205,
267
+ "learning_rate": 9.98817090658745e-06,
268
+ "loss": 1.1801700592041016,
269
+ "step": 74
270
+ },
271
+ {
272
+ "epoch": 0.30278884462151395,
273
+ "grad_norm": 0.1282671093940735,
274
+ "learning_rate": 9.985923574159696e-06,
275
+ "loss": 1.4409031867980957,
276
+ "step": 76
277
+ },
278
+ {
279
+ "epoch": 0.3107569721115538,
280
+ "grad_norm": 0.4123835563659668,
281
+ "learning_rate": 9.983481246392003e-06,
282
+ "loss": 0.933936357498169,
283
+ "step": 78
284
+ },
285
+ {
286
+ "epoch": 0.3187250996015936,
287
+ "grad_norm": 0.11349471658468246,
288
+ "learning_rate": 9.980844029448135e-06,
289
+ "loss": 0.809579074382782,
290
+ "step": 80
291
+ },
292
+ {
293
+ "epoch": 0.32669322709163345,
294
+ "grad_norm": 0.2041967213153839,
295
+ "learning_rate": 9.97801203796335e-06,
296
+ "loss": 1.3015254735946655,
297
+ "step": 82
298
+ },
299
+ {
300
+ "epoch": 0.3346613545816733,
301
+ "grad_norm": 0.315410852432251,
302
+ "learning_rate": 9.974985395039423e-06,
303
+ "loss": 0.8379510641098022,
304
+ "step": 84
305
+ },
306
+ {
307
+ "epoch": 0.3426294820717131,
308
+ "grad_norm": 0.29619190096855164,
309
+ "learning_rate": 9.971764232239287e-06,
310
+ "loss": 1.319396734237671,
311
+ "step": 86
312
+ },
313
+ {
314
+ "epoch": 0.350597609561753,
315
+ "grad_norm": 0.5492198467254639,
316
+ "learning_rate": 9.968348689581315e-06,
317
+ "loss": 0.8692243695259094,
318
+ "step": 88
319
+ },
320
+ {
321
+ "epoch": 0.35856573705179284,
322
+ "grad_norm": 0.14868339896202087,
323
+ "learning_rate": 9.964738915533242e-06,
324
+ "loss": 1.327016830444336,
325
+ "step": 90
326
+ },
327
+ {
328
+ "epoch": 0.3665338645418327,
329
+ "grad_norm": 0.24090534448623657,
330
+ "learning_rate": 9.960935067005706e-06,
331
+ "loss": 1.1243009567260742,
332
+ "step": 92
333
+ },
334
+ {
335
+ "epoch": 0.3745019920318725,
336
+ "grad_norm": 0.12350978702306747,
337
+ "learning_rate": 9.956937309345418e-06,
338
+ "loss": 1.2415589094161987,
339
+ "step": 94
340
+ },
341
+ {
342
+ "epoch": 0.38247011952191234,
343
+ "grad_norm": 0.26156526803970337,
344
+ "learning_rate": 9.952745816327998e-06,
345
+ "loss": 1.1342397928237915,
346
+ "step": 96
347
+ },
348
+ {
349
+ "epoch": 0.3904382470119522,
350
+ "grad_norm": 0.12600702047348022,
351
+ "learning_rate": 9.94836077015039e-06,
352
+ "loss": 1.2638773918151855,
353
+ "step": 98
354
+ },
355
+ {
356
+ "epoch": 0.398406374501992,
357
+ "grad_norm": 0.17442956566810608,
358
+ "learning_rate": 9.943782361422975e-06,
359
+ "loss": 0.8380853533744812,
360
+ "step": 100
361
+ },
362
+ {
363
+ "epoch": 0.4063745019920319,
364
+ "grad_norm": 0.19549265503883362,
365
+ "learning_rate": 9.939010789161259e-06,
366
+ "loss": 1.274878978729248,
367
+ "step": 102
368
+ },
369
+ {
370
+ "epoch": 0.41434262948207173,
371
+ "grad_norm": 0.14597226679325104,
372
+ "learning_rate": 9.934046260777239e-06,
373
+ "loss": 0.7483026385307312,
374
+ "step": 104
375
+ },
376
+ {
377
+ "epoch": 0.42231075697211157,
378
+ "grad_norm": 0.24794237315654755,
379
+ "learning_rate": 9.928888992070373e-06,
380
+ "loss": 0.7552729845046997,
381
+ "step": 106
382
+ },
383
+ {
384
+ "epoch": 0.4302788844621514,
385
+ "grad_norm": 0.1744687557220459,
386
+ "learning_rate": 9.923539207218219e-06,
387
+ "loss": 1.018141746520996,
388
+ "step": 108
389
+ },
390
+ {
391
+ "epoch": 0.43824701195219123,
392
+ "grad_norm": 0.11073736101388931,
393
+ "learning_rate": 9.91799713876667e-06,
394
+ "loss": 1.285387635231018,
395
+ "step": 110
396
+ },
397
+ {
398
+ "epoch": 0.44621513944223107,
399
+ "grad_norm": 0.35274383425712585,
400
+ "learning_rate": 9.912263027619856e-06,
401
+ "loss": 0.8079631328582764,
402
+ "step": 112
403
+ },
404
+ {
405
+ "epoch": 0.4541832669322709,
406
+ "grad_norm": 0.22966524958610535,
407
+ "learning_rate": 9.906337123029675e-06,
408
+ "loss": 1.1002734899520874,
409
+ "step": 114
410
+ },
411
+ {
412
+ "epoch": 0.46215139442231074,
413
+ "grad_norm": 0.1442008912563324,
414
+ "learning_rate": 9.90021968258495e-06,
415
+ "loss": 1.2883250713348389,
416
+ "step": 116
417
+ },
418
+ {
419
+ "epoch": 0.4701195219123506,
420
+ "grad_norm": 0.11145839095115662,
421
+ "learning_rate": 9.893910972200238e-06,
422
+ "loss": 1.35982084274292,
423
+ "step": 118
424
+ },
425
+ {
426
+ "epoch": 0.47808764940239046,
427
+ "grad_norm": 0.2911342680454254,
428
+ "learning_rate": 9.887411266104268e-06,
429
+ "loss": 1.2249188423156738,
430
+ "step": 120
431
+ },
432
+ {
433
+ "epoch": 0.4860557768924303,
434
+ "grad_norm": 0.13076253235340118,
435
+ "learning_rate": 9.880720846828026e-06,
436
+ "loss": 0.9469150304794312,
437
+ "step": 122
438
+ },
439
+ {
440
+ "epoch": 0.4940239043824701,
441
+ "grad_norm": 0.3520956039428711,
442
+ "learning_rate": 9.873840005192466e-06,
443
+ "loss": 1.0702083110809326,
444
+ "step": 124
445
+ },
446
+ {
447
+ "epoch": 0.50199203187251,
448
+ "grad_norm": 0.8981730937957764,
449
+ "learning_rate": 9.866769040295875e-06,
450
+ "loss": 0.9181742668151855,
451
+ "step": 126
452
+ },
453
+ {
454
+ "epoch": 0.5099601593625498,
455
+ "grad_norm": 0.15165890753269196,
456
+ "learning_rate": 9.859508259500869e-06,
457
+ "loss": 1.3017489910125732,
458
+ "step": 128
459
+ },
460
+ {
461
+ "epoch": 0.5179282868525896,
462
+ "grad_norm": 0.14621900022029877,
463
+ "learning_rate": 9.852057978421033e-06,
464
+ "loss": 0.9123371243476868,
465
+ "step": 130
466
+ },
467
+ {
468
+ "epoch": 0.5258964143426295,
469
+ "grad_norm": 0.2252267450094223,
470
+ "learning_rate": 9.844418520907198e-06,
471
+ "loss": 0.8035184741020203,
472
+ "step": 132
473
+ },
474
+ {
475
+ "epoch": 0.5338645418326693,
476
+ "grad_norm": 0.14569298923015594,
477
+ "learning_rate": 9.836590219033375e-06,
478
+ "loss": 0.868083119392395,
479
+ "step": 134
480
+ },
481
+ {
482
+ "epoch": 0.5418326693227091,
483
+ "grad_norm": 0.15642385184764862,
484
+ "learning_rate": 9.828573413082306e-06,
485
+ "loss": 1.2870720624923706,
486
+ "step": 136
487
+ },
488
+ {
489
+ "epoch": 0.549800796812749,
490
+ "grad_norm": 0.1265447586774826,
491
+ "learning_rate": 9.820368451530681e-06,
492
+ "loss": 0.9235859513282776,
493
+ "step": 138
494
+ },
495
+ {
496
+ "epoch": 0.5577689243027888,
497
+ "grad_norm": 0.27114516496658325,
498
+ "learning_rate": 9.811975691033992e-06,
499
+ "loss": 1.0814189910888672,
500
+ "step": 140
501
+ },
502
+ {
503
+ "epoch": 0.5657370517928287,
504
+ "grad_norm": 0.20777811110019684,
505
+ "learning_rate": 9.80339549641102e-06,
506
+ "loss": 1.0009130239486694,
507
+ "step": 142
508
+ },
509
+ {
510
+ "epoch": 0.5737051792828686,
511
+ "grad_norm": 0.08995456993579865,
512
+ "learning_rate": 9.794628240627992e-06,
513
+ "loss": 1.2293169498443604,
514
+ "step": 144
515
+ },
516
+ {
517
+ "epoch": 0.5816733067729084,
518
+ "grad_norm": 0.2387453019618988,
519
+ "learning_rate": 9.785674304782349e-06,
520
+ "loss": 1.2766615152359009,
521
+ "step": 146
522
+ },
523
+ {
524
+ "epoch": 0.5896414342629482,
525
+ "grad_norm": 0.18870815634727478,
526
+ "learning_rate": 9.776534078086202e-06,
527
+ "loss": 0.9375801086425781,
528
+ "step": 148
529
+ },
530
+ {
531
+ "epoch": 0.5976095617529881,
532
+ "grad_norm": 0.32719048857688904,
533
+ "learning_rate": 9.767207957849396e-06,
534
+ "loss": 0.9444013833999634,
535
+ "step": 150
536
+ },
537
+ {
538
+ "epoch": 0.6055776892430279,
539
+ "grad_norm": 0.4171900451183319,
540
+ "learning_rate": 9.757696349462252e-06,
541
+ "loss": 0.9264601469039917,
542
+ "step": 152
543
+ },
544
+ {
545
+ "epoch": 0.6135458167330677,
546
+ "grad_norm": 0.32865679264068604,
547
+ "learning_rate": 9.747999666377934e-06,
548
+ "loss": 1.121659755706787,
549
+ "step": 154
550
+ },
551
+ {
552
+ "epoch": 0.6215139442231076,
553
+ "grad_norm": 0.7469711899757385,
554
+ "learning_rate": 9.738118330094491e-06,
555
+ "loss": 0.9346869587898254,
556
+ "step": 156
557
+ },
558
+ {
559
+ "epoch": 0.6294820717131474,
560
+ "grad_norm": 0.1958705335855484,
561
+ "learning_rate": 9.728052770136518e-06,
562
+ "loss": 1.1452645063400269,
563
+ "step": 158
564
+ },
565
+ {
566
+ "epoch": 0.6374501992031872,
567
+ "grad_norm": 0.10420547425746918,
568
+ "learning_rate": 9.717803424036501e-06,
569
+ "loss": 0.9993031024932861,
570
+ "step": 160
571
+ },
572
+ {
573
+ "epoch": 0.6454183266932271,
574
+ "grad_norm": 0.07185376435518265,
575
+ "learning_rate": 9.707370737315793e-06,
576
+ "loss": 0.7395276427268982,
577
+ "step": 162
578
+ },
579
+ {
580
+ "epoch": 0.6533864541832669,
581
+ "grad_norm": 0.1622873842716217,
582
+ "learning_rate": 9.69675516346524e-06,
583
+ "loss": 1.1817888021469116,
584
+ "step": 164
585
+ },
586
+ {
587
+ "epoch": 0.6613545816733067,
588
+ "grad_norm": 0.22871525585651398,
589
+ "learning_rate": 9.685957163925479e-06,
590
+ "loss": 0.8039273619651794,
591
+ "step": 166
592
+ },
593
+ {
594
+ "epoch": 0.6693227091633466,
595
+ "grad_norm": 0.11571378260850906,
596
+ "learning_rate": 9.67497720806688e-06,
597
+ "loss": 1.2390202283859253,
598
+ "step": 168
599
+ },
600
+ {
601
+ "epoch": 0.6772908366533864,
602
+ "grad_norm": 1.3822053670883179,
603
+ "learning_rate": 9.663815773169131e-06,
604
+ "loss": 0.9708461761474609,
605
+ "step": 170
606
+ },
607
+ {
608
+ "epoch": 0.6852589641434262,
609
+ "grad_norm": 0.23121927678585052,
610
+ "learning_rate": 9.652473344400507e-06,
611
+ "loss": 0.9113867878913879,
612
+ "step": 172
613
+ },
614
+ {
615
+ "epoch": 0.6932270916334662,
616
+ "grad_norm": 0.11104010790586472,
617
+ "learning_rate": 9.640950414796772e-06,
618
+ "loss": 1.2310372591018677,
619
+ "step": 174
620
+ },
621
+ {
622
+ "epoch": 0.701195219123506,
623
+ "grad_norm": 1.821785807609558,
624
+ "learning_rate": 9.629247485239747e-06,
625
+ "loss": 0.7442381381988525,
626
+ "step": 176
627
+ },
628
+ {
629
+ "epoch": 0.7091633466135459,
630
+ "grad_norm": 0.36091160774230957,
631
+ "learning_rate": 9.617365064435544e-06,
632
+ "loss": 0.9631052017211914,
633
+ "step": 178
634
+ },
635
+ {
636
+ "epoch": 0.7171314741035857,
637
+ "grad_norm": 0.29177799820899963,
638
+ "learning_rate": 9.605303668892443e-06,
639
+ "loss": 1.0962485074996948,
640
+ "step": 180
641
+ },
642
+ {
643
+ "epoch": 0.7250996015936255,
644
+ "grad_norm": 0.08216815441846848,
645
+ "learning_rate": 9.593063822898451e-06,
646
+ "loss": 0.4498317837715149,
647
+ "step": 182
648
+ },
649
+ {
650
+ "epoch": 0.7330677290836654,
651
+ "grad_norm": 0.09393391013145447,
652
+ "learning_rate": 9.580646058498505e-06,
653
+ "loss": 1.3047553300857544,
654
+ "step": 184
655
+ },
656
+ {
657
+ "epoch": 0.7410358565737052,
658
+ "grad_norm": 0.10853663086891174,
659
+ "learning_rate": 9.56805091547135e-06,
660
+ "loss": 1.2840948104858398,
661
+ "step": 186
662
+ },
663
+ {
664
+ "epoch": 0.749003984063745,
665
+ "grad_norm": 0.09809323400259018,
666
+ "learning_rate": 9.55527894130607e-06,
667
+ "loss": 1.0851843357086182,
668
+ "step": 188
669
+ },
670
+ {
671
+ "epoch": 0.7569721115537849,
672
+ "grad_norm": 0.17349843680858612,
673
+ "learning_rate": 9.542330691178296e-06,
674
+ "loss": 0.8616277575492859,
675
+ "step": 190
676
+ },
677
+ {
678
+ "epoch": 0.7649402390438247,
679
+ "grad_norm": 0.19055721163749695,
680
+ "learning_rate": 9.529206727926071e-06,
681
+ "loss": 1.2394646406173706,
682
+ "step": 192
683
+ },
684
+ {
685
+ "epoch": 0.7729083665338645,
686
+ "grad_norm": 0.16671667993068695,
687
+ "learning_rate": 9.515907622025376e-06,
688
+ "loss": 0.8858673572540283,
689
+ "step": 194
690
+ },
691
+ {
692
+ "epoch": 0.7808764940239044,
693
+ "grad_norm": 0.3057395815849304,
694
+ "learning_rate": 9.502433951565347e-06,
695
+ "loss": 0.5642332434654236,
696
+ "step": 196
697
+ },
698
+ {
699
+ "epoch": 0.7888446215139442,
700
+ "grad_norm": 0.49418577551841736,
701
+ "learning_rate": 9.48878630222314e-06,
702
+ "loss": 0.7914112210273743,
703
+ "step": 198
704
+ },
705
+ {
706
+ "epoch": 0.796812749003984,
707
+ "grad_norm": 0.16775543987751007,
708
+ "learning_rate": 9.474965267238469e-06,
709
+ "loss": 1.0121368169784546,
710
+ "step": 200
711
+ },
712
+ {
713
+ "epoch": 0.8047808764940239,
714
+ "grad_norm": 0.10699599981307983,
715
+ "learning_rate": 9.460971447387824e-06,
716
+ "loss": 0.9411302804946899,
717
+ "step": 202
718
+ },
719
+ {
720
+ "epoch": 0.8127490039840638,
721
+ "grad_norm": 0.19434906542301178,
722
+ "learning_rate": 9.446805450958353e-06,
723
+ "loss": 1.5670157670974731,
724
+ "step": 204
725
+ },
726
+ {
727
+ "epoch": 0.8207171314741036,
728
+ "grad_norm": 0.3301284909248352,
729
+ "learning_rate": 9.43246789372142e-06,
730
+ "loss": 1.2477513551712036,
731
+ "step": 206
732
+ },
733
+ {
734
+ "epoch": 0.8286852589641435,
735
+ "grad_norm": 0.32433968782424927,
736
+ "learning_rate": 9.417959398905846e-06,
737
+ "loss": 0.6038308143615723,
738
+ "step": 208
739
+ },
740
+ {
741
+ "epoch": 0.8366533864541833,
742
+ "grad_norm": 0.13645341992378235,
743
+ "learning_rate": 9.40328059717081e-06,
744
+ "loss": 1.2748695611953735,
745
+ "step": 210
746
+ },
747
+ {
748
+ "epoch": 0.8446215139442231,
749
+ "grad_norm": 0.1219300627708435,
750
+ "learning_rate": 9.388432126578438e-06,
751
+ "loss": 1.22676682472229,
752
+ "step": 212
753
+ },
754
+ {
755
+ "epoch": 0.852589641434263,
756
+ "grad_norm": 0.09014702588319778,
757
+ "learning_rate": 9.373414632566066e-06,
758
+ "loss": 0.9495640397071838,
759
+ "step": 214
760
+ },
761
+ {
762
+ "epoch": 0.8605577689243028,
763
+ "grad_norm": 0.2150721698999405,
764
+ "learning_rate": 9.35822876791819e-06,
765
+ "loss": 1.4344321489334106,
766
+ "step": 216
767
+ },
768
+ {
769
+ "epoch": 0.8685258964143426,
770
+ "grad_norm": 0.4374437928199768,
771
+ "learning_rate": 9.342875192738083e-06,
772
+ "loss": 0.8705391883850098,
773
+ "step": 218
774
+ },
775
+ {
776
+ "epoch": 0.8764940239043825,
777
+ "grad_norm": 0.10829262435436249,
778
+ "learning_rate": 9.327354574419109e-06,
779
+ "loss": 1.2422717809677124,
780
+ "step": 220
781
+ },
782
+ {
783
+ "epoch": 0.8844621513944223,
784
+ "grad_norm": 0.19894227385520935,
785
+ "learning_rate": 9.311667587615701e-06,
786
+ "loss": 1.4882192611694336,
787
+ "step": 222
788
+ },
789
+ {
790
+ "epoch": 0.8924302788844621,
791
+ "grad_norm": 0.42940643429756165,
792
+ "learning_rate": 9.29581491421405e-06,
793
+ "loss": 0.716874897480011,
794
+ "step": 224
795
+ },
796
+ {
797
+ "epoch": 0.900398406374502,
798
+ "grad_norm": 0.12247120589017868,
799
+ "learning_rate": 9.279797243302453e-06,
800
+ "loss": 0.9885092377662659,
801
+ "step": 226
802
+ },
803
+ {
804
+ "epoch": 0.9083665338645418,
805
+ "grad_norm": 0.4069404900074005,
806
+ "learning_rate": 9.263615271141362e-06,
807
+ "loss": 1.0850290060043335,
808
+ "step": 228
809
+ },
810
+ {
811
+ "epoch": 0.9163346613545816,
812
+ "grad_norm": 0.20781095325946808,
813
+ "learning_rate": 9.247269701133125e-06,
814
+ "loss": 1.1709660291671753,
815
+ "step": 230
816
+ },
817
+ {
818
+ "epoch": 0.9243027888446215,
819
+ "grad_norm": 0.12009521573781967,
820
+ "learning_rate": 9.230761243791401e-06,
821
+ "loss": 1.3472001552581787,
822
+ "step": 232
823
+ },
824
+ {
825
+ "epoch": 0.9322709163346613,
826
+ "grad_norm": 0.11444836854934692,
827
+ "learning_rate": 9.214090616710282e-06,
828
+ "loss": 0.7829840779304504,
829
+ "step": 234
830
+ },
831
+ {
832
+ "epoch": 0.9402390438247012,
833
+ "grad_norm": 0.11701781302690506,
834
+ "learning_rate": 9.197258544533098e-06,
835
+ "loss": 0.7907887101173401,
836
+ "step": 236
837
+ },
838
+ {
839
+ "epoch": 0.9482071713147411,
840
+ "grad_norm": 0.21362987160682678,
841
+ "learning_rate": 9.180265758920916e-06,
842
+ "loss": 0.44280657172203064,
843
+ "step": 238
844
+ },
845
+ {
846
+ "epoch": 0.9561752988047809,
847
+ "grad_norm": 0.20342251658439636,
848
+ "learning_rate": 9.163112998520741e-06,
849
+ "loss": 0.8508027195930481,
850
+ "step": 240
851
+ },
852
+ {
853
+ "epoch": 0.9641434262948207,
854
+ "grad_norm": 0.20921140909194946,
855
+ "learning_rate": 9.145801008933403e-06,
856
+ "loss": 1.1112576723098755,
857
+ "step": 242
858
+ },
859
+ {
860
+ "epoch": 0.9721115537848606,
861
+ "grad_norm": 0.13130858540534973,
862
+ "learning_rate": 9.128330542681154e-06,
863
+ "loss": 1.215651273727417,
864
+ "step": 244
865
+ },
866
+ {
867
+ "epoch": 0.9800796812749004,
868
+ "grad_norm": 0.2843606770038605,
869
+ "learning_rate": 9.110702359174944e-06,
870
+ "loss": 0.9460815787315369,
871
+ "step": 246
872
+ },
873
+ {
874
+ "epoch": 0.9880478087649402,
875
+ "grad_norm": 0.12077733874320984,
876
+ "learning_rate": 9.092917224681427e-06,
877
+ "loss": 0.9816232919692993,
878
+ "step": 248
879
+ },
880
+ {
881
+ "epoch": 0.9960159362549801,
882
+ "grad_norm": 0.1792304813861847,
883
+ "learning_rate": 9.074975912289641e-06,
884
+ "loss": 0.9759309887886047,
885
+ "step": 250
886
+ },
887
+ {
888
+ "epoch": 1.00398406374502,
889
+ "grad_norm": 0.13639993965625763,
890
+ "learning_rate": 9.056879201877412e-06,
891
+ "loss": 0.8936959505081177,
892
+ "step": 252
893
+ },
894
+ {
895
+ "epoch": 1.0119521912350598,
896
+ "grad_norm": 0.1269155740737915,
897
+ "learning_rate": 9.038627880077441e-06,
898
+ "loss": 0.6980884671211243,
899
+ "step": 254
900
+ },
901
+ {
902
+ "epoch": 1.0199203187250996,
903
+ "grad_norm": 0.09299927204847336,
904
+ "learning_rate": 9.020222740243127e-06,
905
+ "loss": 1.15306556224823,
906
+ "step": 256
907
+ },
908
+ {
909
+ "epoch": 1.0278884462151394,
910
+ "grad_norm": 0.14957579970359802,
911
+ "learning_rate": 9.001664582414066e-06,
912
+ "loss": 1.1301281452178955,
913
+ "step": 258
914
+ },
915
+ {
916
+ "epoch": 1.0358565737051793,
917
+ "grad_norm": 0.27969855070114136,
918
+ "learning_rate": 8.982954213281291e-06,
919
+ "loss": 1.0512151718139648,
920
+ "step": 260
921
+ },
922
+ {
923
+ "epoch": 1.043824701195219,
924
+ "grad_norm": 0.15900252759456635,
925
+ "learning_rate": 8.964092446152183e-06,
926
+ "loss": 0.9678531885147095,
927
+ "step": 262
928
+ },
929
+ {
930
+ "epoch": 1.051792828685259,
931
+ "grad_norm": 0.27932503819465637,
932
+ "learning_rate": 8.945080100915145e-06,
933
+ "loss": 1.046820044517517,
934
+ "step": 264
935
+ },
936
+ {
937
+ "epoch": 1.0597609561752988,
938
+ "grad_norm": 0.23315030336380005,
939
+ "learning_rate": 8.925918004003941e-06,
940
+ "loss": 0.6050488352775574,
941
+ "step": 266
942
+ },
943
+ {
944
+ "epoch": 1.0677290836653386,
945
+ "grad_norm": 0.09495838731527328,
946
+ "learning_rate": 8.90660698836179e-06,
947
+ "loss": 0.9008283019065857,
948
+ "step": 268
949
+ },
950
+ {
951
+ "epoch": 1.0756972111553784,
952
+ "grad_norm": 0.35869407653808594,
953
+ "learning_rate": 8.887147893405145e-06,
954
+ "loss": 0.5234286785125732,
955
+ "step": 270
956
+ },
957
+ {
958
+ "epoch": 1.0836653386454183,
959
+ "grad_norm": 0.15390193462371826,
960
+ "learning_rate": 8.867541564987212e-06,
961
+ "loss": 1.230911135673523,
962
+ "step": 272
963
+ },
964
+ {
965
+ "epoch": 1.091633466135458,
966
+ "grad_norm": 0.25453439354896545,
967
+ "learning_rate": 8.84778885536118e-06,
968
+ "loss": 0.5974389910697937,
969
+ "step": 274
970
+ },
971
+ {
972
+ "epoch": 1.099601593625498,
973
+ "grad_norm": 0.13244271278381348,
974
+ "learning_rate": 8.827890623143172e-06,
975
+ "loss": 0.890313446521759,
976
+ "step": 276
977
+ },
978
+ {
979
+ "epoch": 1.1075697211155378,
980
+ "grad_norm": 0.10025046765804291,
981
+ "learning_rate": 8.80784773327494e-06,
982
+ "loss": 0.7988033890724182,
983
+ "step": 278
984
+ },
985
+ {
986
+ "epoch": 1.1155378486055776,
987
+ "grad_norm": 0.1597757637500763,
988
+ "learning_rate": 8.787661056986236e-06,
989
+ "loss": 0.9830846786499023,
990
+ "step": 280
991
+ },
992
+ {
993
+ "epoch": 1.1235059760956174,
994
+ "grad_norm": 0.1170232743024826,
995
+ "learning_rate": 8.767331471756975e-06,
996
+ "loss": 1.138309359550476,
997
+ "step": 282
998
+ },
999
+ {
1000
+ "epoch": 1.1314741035856573,
1001
+ "grad_norm": 0.22332733869552612,
1002
+ "learning_rate": 8.746859861279068e-06,
1003
+ "loss": 1.1853747367858887,
1004
+ "step": 284
1005
+ },
1006
+ {
1007
+ "epoch": 1.139442231075697,
1008
+ "grad_norm": 0.06254544109106064,
1009
+ "learning_rate": 8.726247115418017e-06,
1010
+ "loss": 0.2661963999271393,
1011
+ "step": 286
1012
+ },
1013
+ {
1014
+ "epoch": 1.1474103585657371,
1015
+ "grad_norm": 0.09349869191646576,
1016
+ "learning_rate": 8.70549413017424e-06,
1017
+ "loss": 0.6934034824371338,
1018
+ "step": 288
1019
+ },
1020
+ {
1021
+ "epoch": 1.155378486055777,
1022
+ "grad_norm": 0.6584972143173218,
1023
+ "learning_rate": 8.684601807644114e-06,
1024
+ "loss": 0.9061666131019592,
1025
+ "step": 290
1026
+ },
1027
+ {
1028
+ "epoch": 1.1633466135458168,
1029
+ "grad_norm": 0.2169235199689865,
1030
+ "learning_rate": 8.663571055980769e-06,
1031
+ "loss": 0.497935026884079,
1032
+ "step": 292
1033
+ },
1034
+ {
1035
+ "epoch": 1.1713147410358566,
1036
+ "grad_norm": 0.08594366908073425,
1037
+ "learning_rate": 8.642402789354609e-06,
1038
+ "loss": 1.1939326524734497,
1039
+ "step": 294
1040
+ },
1041
+ {
1042
+ "epoch": 1.1792828685258965,
1043
+ "grad_norm": 0.08441396057605743,
1044
+ "learning_rate": 8.62109792791358e-06,
1045
+ "loss": 1.254359245300293,
1046
+ "step": 296
1047
+ },
1048
+ {
1049
+ "epoch": 1.1872509960159363,
1050
+ "grad_norm": 0.08592527359724045,
1051
+ "learning_rate": 8.599657397743163e-06,
1052
+ "loss": 1.3354953527450562,
1053
+ "step": 298
1054
+ },
1055
+ {
1056
+ "epoch": 1.1952191235059761,
1057
+ "grad_norm": 0.9391301274299622,
1058
+ "learning_rate": 8.578082130826123e-06,
1059
+ "loss": 0.5832847952842712,
1060
+ "step": 300
1061
+ },
1062
+ {
1063
+ "epoch": 1.203187250996016,
1064
+ "grad_norm": 0.14405034482479095,
1065
+ "learning_rate": 8.556373065002006e-06,
1066
+ "loss": 0.8736499547958374,
1067
+ "step": 302
1068
+ },
1069
+ {
1070
+ "epoch": 1.2111553784860558,
1071
+ "grad_norm": 0.12587150931358337,
1072
+ "learning_rate": 8.534531143926359e-06,
1073
+ "loss": 0.4843589961528778,
1074
+ "step": 304
1075
+ },
1076
+ {
1077
+ "epoch": 1.2191235059760956,
1078
+ "grad_norm": 0.09853191673755646,
1079
+ "learning_rate": 8.512557317029715e-06,
1080
+ "loss": 1.1760183572769165,
1081
+ "step": 306
1082
+ },
1083
+ {
1084
+ "epoch": 1.2270916334661355,
1085
+ "grad_norm": 0.3153192102909088,
1086
+ "learning_rate": 8.49045253947633e-06,
1087
+ "loss": 0.984307050704956,
1088
+ "step": 308
1089
+ },
1090
+ {
1091
+ "epoch": 1.2350597609561753,
1092
+ "grad_norm": 0.1911332905292511,
1093
+ "learning_rate": 8.46821777212266e-06,
1094
+ "loss": 1.1619549989700317,
1095
+ "step": 310
1096
+ },
1097
+ {
1098
+ "epoch": 1.2430278884462151,
1099
+ "grad_norm": 0.4250432252883911,
1100
+ "learning_rate": 8.445853981475587e-06,
1101
+ "loss": 1.0535634756088257,
1102
+ "step": 312
1103
+ },
1104
+ {
1105
+ "epoch": 1.250996015936255,
1106
+ "grad_norm": 0.2402748465538025,
1107
+ "learning_rate": 8.423362139650414e-06,
1108
+ "loss": 0.8381243348121643,
1109
+ "step": 314
1110
+ },
1111
+ {
1112
+ "epoch": 1.2589641434262948,
1113
+ "grad_norm": 0.573125422000885,
1114
+ "learning_rate": 8.40074322432861e-06,
1115
+ "loss": 0.719307541847229,
1116
+ "step": 316
1117
+ },
1118
+ {
1119
+ "epoch": 1.2669322709163346,
1120
+ "grad_norm": 0.19297780096530914,
1121
+ "learning_rate": 8.377998218715311e-06,
1122
+ "loss": 0.5993711948394775,
1123
+ "step": 318
1124
+ },
1125
+ {
1126
+ "epoch": 1.2749003984063745,
1127
+ "grad_norm": 0.1421806365251541,
1128
+ "learning_rate": 8.355128111496569e-06,
1129
+ "loss": 0.46684369444847107,
1130
+ "step": 320
1131
+ },
1132
+ {
1133
+ "epoch": 1.2828685258964143,
1134
+ "grad_norm": 0.4090231955051422,
1135
+ "learning_rate": 8.332133896796399e-06,
1136
+ "loss": 0.9673095345497131,
1137
+ "step": 322
1138
+ },
1139
+ {
1140
+ "epoch": 1.2908366533864541,
1141
+ "grad_norm": 0.12756745517253876,
1142
+ "learning_rate": 8.309016574133545e-06,
1143
+ "loss": 0.9027948975563049,
1144
+ "step": 324
1145
+ },
1146
+ {
1147
+ "epoch": 1.298804780876494,
1148
+ "grad_norm": 0.20138461887836456,
1149
+ "learning_rate": 8.28577714837805e-06,
1150
+ "loss": 1.2605825662612915,
1151
+ "step": 326
1152
+ },
1153
+ {
1154
+ "epoch": 1.3067729083665338,
1155
+ "grad_norm": 0.09830658882856369,
1156
+ "learning_rate": 8.262416629707555e-06,
1157
+ "loss": 0.6810956001281738,
1158
+ "step": 328
1159
+ },
1160
+ {
1161
+ "epoch": 1.3147410358565736,
1162
+ "grad_norm": 0.12664003670215607,
1163
+ "learning_rate": 8.238936033563415e-06,
1164
+ "loss": 0.8375826478004456,
1165
+ "step": 330
1166
+ },
1167
+ {
1168
+ "epoch": 1.3227091633466135,
1169
+ "grad_norm": 0.5658034682273865,
1170
+ "learning_rate": 8.215336380606533e-06,
1171
+ "loss": 0.9011093974113464,
1172
+ "step": 332
1173
+ },
1174
+ {
1175
+ "epoch": 1.3306772908366533,
1176
+ "grad_norm": 0.1833939105272293,
1177
+ "learning_rate": 8.191618696673012e-06,
1178
+ "loss": 0.6151177883148193,
1179
+ "step": 334
1180
+ },
1181
+ {
1182
+ "epoch": 1.3386454183266931,
1183
+ "grad_norm": 3.7321767807006836,
1184
+ "learning_rate": 8.167784012729555e-06,
1185
+ "loss": 0.8623945713043213,
1186
+ "step": 336
1187
+ },
1188
+ {
1189
+ "epoch": 1.3466135458167332,
1190
+ "grad_norm": 0.10215169191360474,
1191
+ "learning_rate": 8.143833364828654e-06,
1192
+ "loss": 1.1351113319396973,
1193
+ "step": 338
1194
+ },
1195
+ {
1196
+ "epoch": 1.354581673306773,
1197
+ "grad_norm": 0.06890127807855606,
1198
+ "learning_rate": 8.119767794063553e-06,
1199
+ "loss": 1.1333948373794556,
1200
+ "step": 340
1201
+ },
1202
+ {
1203
+ "epoch": 1.3625498007968129,
1204
+ "grad_norm": 0.09315377473831177,
1205
+ "learning_rate": 8.095588346523e-06,
1206
+ "loss": 1.1782711744308472,
1207
+ "step": 342
1208
+ },
1209
+ {
1210
+ "epoch": 1.3705179282868527,
1211
+ "grad_norm": 0.11636896431446075,
1212
+ "learning_rate": 8.071296073245759e-06,
1213
+ "loss": 1.1379573345184326,
1214
+ "step": 344
1215
+ },
1216
+ {
1217
+ "epoch": 1.3784860557768925,
1218
+ "grad_norm": 0.12263190001249313,
1219
+ "learning_rate": 8.046892030174938e-06,
1220
+ "loss": 0.6890803575515747,
1221
+ "step": 346
1222
+ },
1223
+ {
1224
+ "epoch": 1.3864541832669324,
1225
+ "grad_norm": 0.09175064414739609,
1226
+ "learning_rate": 8.022377278112089e-06,
1227
+ "loss": 1.159577488899231,
1228
+ "step": 348
1229
+ },
1230
+ {
1231
+ "epoch": 1.3944223107569722,
1232
+ "grad_norm": 0.14179781079292297,
1233
+ "learning_rate": 7.997752882671088e-06,
1234
+ "loss": 0.6742680668830872,
1235
+ "step": 350
1236
+ },
1237
+ {
1238
+ "epoch": 1.402390438247012,
1239
+ "grad_norm": 0.09603075683116913,
1240
+ "learning_rate": 7.97301991423182e-06,
1241
+ "loss": 1.183809757232666,
1242
+ "step": 352
1243
+ },
1244
+ {
1245
+ "epoch": 1.4103585657370519,
1246
+ "grad_norm": 0.23190699517726898,
1247
+ "learning_rate": 7.948179447893652e-06,
1248
+ "loss": 1.1228028535842896,
1249
+ "step": 354
1250
+ },
1251
+ {
1252
+ "epoch": 1.4183266932270917,
1253
+ "grad_norm": 0.41616132855415344,
1254
+ "learning_rate": 7.923232563428693e-06,
1255
+ "loss": 0.8794443011283875,
1256
+ "step": 356
1257
+ },
1258
+ {
1259
+ "epoch": 1.4262948207171315,
1260
+ "grad_norm": 0.27986449003219604,
1261
+ "learning_rate": 7.898180345234875e-06,
1262
+ "loss": 1.1482864618301392,
1263
+ "step": 358
1264
+ },
1265
+ {
1266
+ "epoch": 1.4342629482071714,
1267
+ "grad_norm": 0.12306718528270721,
1268
+ "learning_rate": 7.873023882288793e-06,
1269
+ "loss": 0.5888344049453735,
1270
+ "step": 360
1271
+ },
1272
+ {
1273
+ "epoch": 1.4422310756972112,
1274
+ "grad_norm": 0.10971551388502121,
1275
+ "learning_rate": 7.847764268098387e-06,
1276
+ "loss": 0.6951230764389038,
1277
+ "step": 362
1278
+ },
1279
+ {
1280
+ "epoch": 1.450199203187251,
1281
+ "grad_norm": 0.15229885280132294,
1282
+ "learning_rate": 7.822402600655405e-06,
1283
+ "loss": 1.0400999784469604,
1284
+ "step": 364
1285
+ },
1286
+ {
1287
+ "epoch": 1.4581673306772909,
1288
+ "grad_norm": 0.0946863442659378,
1289
+ "learning_rate": 7.79693998238767e-06,
1290
+ "loss": 1.1122182607650757,
1291
+ "step": 366
1292
+ },
1293
+ {
1294
+ "epoch": 1.4661354581673307,
1295
+ "grad_norm": 0.08339293301105499,
1296
+ "learning_rate": 7.771377520111163e-06,
1297
+ "loss": 0.604324460029602,
1298
+ "step": 368
1299
+ },
1300
+ {
1301
+ "epoch": 1.4741035856573705,
1302
+ "grad_norm": 0.16374002397060394,
1303
+ "learning_rate": 7.745716324981912e-06,
1304
+ "loss": 0.684520423412323,
1305
+ "step": 370
1306
+ },
1307
+ {
1308
+ "epoch": 1.4820717131474104,
1309
+ "grad_norm": 0.22385168075561523,
1310
+ "learning_rate": 7.71995751244769e-06,
1311
+ "loss": 1.2398829460144043,
1312
+ "step": 372
1313
+ },
1314
+ {
1315
+ "epoch": 1.4900398406374502,
1316
+ "grad_norm": 0.09120070189237595,
1317
+ "learning_rate": 7.694102202199536e-06,
1318
+ "loss": 1.1202857494354248,
1319
+ "step": 374
1320
+ },
1321
+ {
1322
+ "epoch": 1.49800796812749,
1323
+ "grad_norm": 0.15905345976352692,
1324
+ "learning_rate": 7.66815151812307e-06,
1325
+ "loss": 1.1247127056121826,
1326
+ "step": 376
1327
+ },
1328
+ {
1329
+ "epoch": 1.5059760956175299,
1330
+ "grad_norm": 0.24509046971797943,
1331
+ "learning_rate": 7.642106588249651e-06,
1332
+ "loss": 0.8915665745735168,
1333
+ "step": 378
1334
+ },
1335
+ {
1336
+ "epoch": 1.5139442231075697,
1337
+ "grad_norm": 0.11813104152679443,
1338
+ "learning_rate": 7.6159685447073376e-06,
1339
+ "loss": 1.1169109344482422,
1340
+ "step": 380
1341
+ },
1342
+ {
1343
+ "epoch": 1.5219123505976095,
1344
+ "grad_norm": 0.10362762212753296,
1345
+ "learning_rate": 7.589738523671685e-06,
1346
+ "loss": 0.7195178866386414,
1347
+ "step": 382
1348
+ },
1349
+ {
1350
+ "epoch": 1.5298804780876494,
1351
+ "grad_norm": 0.13230100274085999,
1352
+ "learning_rate": 7.563417665316338e-06,
1353
+ "loss": 0.7218353152275085,
1354
+ "step": 384
1355
+ },
1356
+ {
1357
+ "epoch": 1.5378486055776892,
1358
+ "grad_norm": 0.4582996964454651,
1359
+ "learning_rate": 7.5370071137634984e-06,
1360
+ "loss": 1.0153872966766357,
1361
+ "step": 386
1362
+ },
1363
+ {
1364
+ "epoch": 1.545816733067729,
1365
+ "grad_norm": 0.17963430285453796,
1366
+ "learning_rate": 7.510508017034165e-06,
1367
+ "loss": 1.1490799188613892,
1368
+ "step": 388
1369
+ },
1370
+ {
1371
+ "epoch": 1.5537848605577689,
1372
+ "grad_norm": 0.17351095378398895,
1373
+ "learning_rate": 7.483921526998247e-06,
1374
+ "loss": 0.5256304740905762,
1375
+ "step": 390
1376
+ },
1377
+ {
1378
+ "epoch": 1.5617529880478087,
1379
+ "grad_norm": 0.15164697170257568,
1380
+ "learning_rate": 7.4572487993244865e-06,
1381
+ "loss": 0.5711215138435364,
1382
+ "step": 392
1383
+ },
1384
+ {
1385
+ "epoch": 1.5697211155378485,
1386
+ "grad_norm": 0.9964547753334045,
1387
+ "learning_rate": 7.430490993430232e-06,
1388
+ "loss": 1.0898221731185913,
1389
+ "step": 394
1390
+ },
1391
+ {
1392
+ "epoch": 1.5776892430278884,
1393
+ "grad_norm": 0.19943900406360626,
1394
+ "learning_rate": 7.403649272431027e-06,
1395
+ "loss": 1.0307166576385498,
1396
+ "step": 396
1397
+ },
1398
+ {
1399
+ "epoch": 1.5856573705179282,
1400
+ "grad_norm": 0.0867285281419754,
1401
+ "learning_rate": 7.376724803090069e-06,
1402
+ "loss": 1.1423487663269043,
1403
+ "step": 398
1404
+ },
1405
+ {
1406
+ "epoch": 1.593625498007968,
1407
+ "grad_norm": 1.1143836975097656,
1408
+ "learning_rate": 7.349718755767473e-06,
1409
+ "loss": 0.5850595235824585,
1410
+ "step": 400
1411
+ },
1412
+ {
1413
+ "epoch": 1.6015936254980079,
1414
+ "grad_norm": 0.3400084972381592,
1415
+ "learning_rate": 7.322632304369416e-06,
1416
+ "loss": 1.1260920763015747,
1417
+ "step": 402
1418
+ },
1419
+ {
1420
+ "epoch": 1.6095617529880477,
1421
+ "grad_norm": 0.11252368986606598,
1422
+ "learning_rate": 7.2954666262970965e-06,
1423
+ "loss": 1.2705897092819214,
1424
+ "step": 404
1425
+ },
1426
+ {
1427
+ "epoch": 1.6175298804780875,
1428
+ "grad_norm": 0.1879090517759323,
1429
+ "learning_rate": 7.268222902395562e-06,
1430
+ "loss": 0.7150183320045471,
1431
+ "step": 406
1432
+ },
1433
+ {
1434
+ "epoch": 1.6254980079681274,
1435
+ "grad_norm": 0.07393921166658401,
1436
+ "learning_rate": 7.240902316902373e-06,
1437
+ "loss": 0.5556809306144714,
1438
+ "step": 408
1439
+ },
1440
+ {
1441
+ "epoch": 1.6334661354581672,
1442
+ "grad_norm": 0.2739734649658203,
1443
+ "learning_rate": 7.213506057396134e-06,
1444
+ "loss": 0.767079770565033,
1445
+ "step": 410
1446
+ },
1447
+ {
1448
+ "epoch": 1.641434262948207,
1449
+ "grad_norm": 0.12828262150287628,
1450
+ "learning_rate": 7.186035314744872e-06,
1451
+ "loss": 0.4897518754005432,
1452
+ "step": 412
1453
+ },
1454
+ {
1455
+ "epoch": 1.6494023904382469,
1456
+ "grad_norm": 0.0791148766875267,
1457
+ "learning_rate": 7.1584912830542575e-06,
1458
+ "loss": 0.8231608271598816,
1459
+ "step": 414
1460
+ },
1461
+ {
1462
+ "epoch": 1.6573705179282867,
1463
+ "grad_norm": 0.19900332391262054,
1464
+ "learning_rate": 7.130875159615716e-06,
1465
+ "loss": 0.7192663550376892,
1466
+ "step": 416
1467
+ },
1468
+ {
1469
+ "epoch": 1.6653386454183265,
1470
+ "grad_norm": 0.21691080927848816,
1471
+ "learning_rate": 7.103188144854376e-06,
1472
+ "loss": 0.9949262738227844,
1473
+ "step": 418
1474
+ },
1475
+ {
1476
+ "epoch": 1.6733067729083664,
1477
+ "grad_norm": 0.08056575804948807,
1478
+ "learning_rate": 7.075431442276888e-06,
1479
+ "loss": 1.1483328342437744,
1480
+ "step": 420
1481
+ },
1482
+ {
1483
+ "epoch": 1.6812749003984062,
1484
+ "grad_norm": 0.11413298547267914,
1485
+ "learning_rate": 7.047606258419108e-06,
1486
+ "loss": 1.019271731376648,
1487
+ "step": 422
1488
+ },
1489
+ {
1490
+ "epoch": 1.6892430278884463,
1491
+ "grad_norm": 0.13839687407016754,
1492
+ "learning_rate": 7.019713802793663e-06,
1493
+ "loss": 0.5812303423881531,
1494
+ "step": 424
1495
+ },
1496
+ {
1497
+ "epoch": 1.697211155378486,
1498
+ "grad_norm": 0.0764610543847084,
1499
+ "learning_rate": 6.99175528783736e-06,
1500
+ "loss": 1.199522614479065,
1501
+ "step": 426
1502
+ },
1503
+ {
1504
+ "epoch": 1.705179282868526,
1505
+ "grad_norm": 0.07787472009658813,
1506
+ "learning_rate": 6.963731928858495e-06,
1507
+ "loss": 1.1365389823913574,
1508
+ "step": 428
1509
+ },
1510
+ {
1511
+ "epoch": 1.7131474103585658,
1512
+ "grad_norm": 0.17501701414585114,
1513
+ "learning_rate": 6.935644943984017e-06,
1514
+ "loss": 0.7606980204582214,
1515
+ "step": 430
1516
+ },
1517
+ {
1518
+ "epoch": 1.7211155378486056,
1519
+ "grad_norm": 0.5705646276473999,
1520
+ "learning_rate": 6.9074955541065865e-06,
1521
+ "loss": 0.902596116065979,
1522
+ "step": 432
1523
+ },
1524
+ {
1525
+ "epoch": 1.7290836653386454,
1526
+ "grad_norm": 1.084190011024475,
1527
+ "learning_rate": 6.8792849828315054e-06,
1528
+ "loss": 0.6085677742958069,
1529
+ "step": 434
1530
+ },
1531
+ {
1532
+ "epoch": 1.7370517928286853,
1533
+ "grad_norm": 0.434283047914505,
1534
+ "learning_rate": 6.851014456423515e-06,
1535
+ "loss": 0.3681115508079529,
1536
+ "step": 436
1537
+ },
1538
+ {
1539
+ "epoch": 1.745019920318725,
1540
+ "grad_norm": 0.1507345736026764,
1541
+ "learning_rate": 6.822685203753508e-06,
1542
+ "loss": 0.7172828316688538,
1543
+ "step": 438
1544
+ },
1545
+ {
1546
+ "epoch": 1.752988047808765,
1547
+ "grad_norm": 0.33439791202545166,
1548
+ "learning_rate": 6.794298456245111e-06,
1549
+ "loss": 0.6734229326248169,
1550
+ "step": 440
1551
+ },
1552
+ {
1553
+ "epoch": 1.7609561752988048,
1554
+ "grad_norm": 0.2586667835712433,
1555
+ "learning_rate": 6.765855447821144e-06,
1556
+ "loss": 1.4859187602996826,
1557
+ "step": 442
1558
+ },
1559
+ {
1560
+ "epoch": 1.7689243027888446,
1561
+ "grad_norm": 0.16227927803993225,
1562
+ "learning_rate": 6.737357414849993e-06,
1563
+ "loss": 0.7400438785552979,
1564
+ "step": 444
1565
+ },
1566
+ {
1567
+ "epoch": 1.7768924302788844,
1568
+ "grad_norm": 0.11800998449325562,
1569
+ "learning_rate": 6.70880559609187e-06,
1570
+ "loss": 1.030636191368103,
1571
+ "step": 446
1572
+ },
1573
+ {
1574
+ "epoch": 1.7848605577689243,
1575
+ "grad_norm": 0.6456466317176819,
1576
+ "learning_rate": 6.680201232644958e-06,
1577
+ "loss": 1.1084392070770264,
1578
+ "step": 448
1579
+ },
1580
+ {
1581
+ "epoch": 1.792828685258964,
1582
+ "grad_norm": 0.14494922757148743,
1583
+ "learning_rate": 6.651545567891471e-06,
1584
+ "loss": 0.8555322885513306,
1585
+ "step": 450
1586
+ },
1587
+ {
1588
+ "epoch": 1.800796812749004,
1589
+ "grad_norm": 0.05881403386592865,
1590
+ "learning_rate": 6.622839847443596e-06,
1591
+ "loss": 0.493237167596817,
1592
+ "step": 452
1593
+ },
1594
+ {
1595
+ "epoch": 1.8087649402390438,
1596
+ "grad_norm": 0.2267322540283203,
1597
+ "learning_rate": 6.59408531908936e-06,
1598
+ "loss": 0.982709527015686,
1599
+ "step": 454
1600
+ },
1601
+ {
1602
+ "epoch": 1.8167330677290838,
1603
+ "grad_norm": 3.470564126968384,
1604
+ "learning_rate": 6.565283232738386e-06,
1605
+ "loss": 0.6639694571495056,
1606
+ "step": 456
1607
+ },
1608
+ {
1609
+ "epoch": 1.8247011952191237,
1610
+ "grad_norm": 0.12834540009498596,
1611
+ "learning_rate": 6.536434840367555e-06,
1612
+ "loss": 1.0367791652679443,
1613
+ "step": 458
1614
+ },
1615
+ {
1616
+ "epoch": 1.8326693227091635,
1617
+ "grad_norm": 0.18368105590343475,
1618
+ "learning_rate": 6.507541395966591e-06,
1619
+ "loss": 0.7434819340705872,
1620
+ "step": 460
1621
+ },
1622
+ {
1623
+ "epoch": 1.8406374501992033,
1624
+ "grad_norm": 0.08568334579467773,
1625
+ "learning_rate": 6.47860415548356e-06,
1626
+ "loss": 0.8052833676338196,
1627
+ "step": 462
1628
+ },
1629
+ {
1630
+ "epoch": 1.8486055776892432,
1631
+ "grad_norm": 0.11108598113059998,
1632
+ "learning_rate": 6.449624376770259e-06,
1633
+ "loss": 0.12546391785144806,
1634
+ "step": 464
1635
+ },
1636
+ {
1637
+ "epoch": 1.856573705179283,
1638
+ "grad_norm": 0.20673945546150208,
1639
+ "learning_rate": 6.420603319527554e-06,
1640
+ "loss": 1.1594171524047852,
1641
+ "step": 466
1642
+ },
1643
+ {
1644
+ "epoch": 1.8645418326693228,
1645
+ "grad_norm": 0.1927093267440796,
1646
+ "learning_rate": 6.3915422452506146e-06,
1647
+ "loss": 0.5444157719612122,
1648
+ "step": 468
1649
+ },
1650
+ {
1651
+ "epoch": 1.8725099601593627,
1652
+ "grad_norm": 0.21195177733898163,
1653
+ "learning_rate": 6.362442417174082e-06,
1654
+ "loss": 1.1595547199249268,
1655
+ "step": 470
1656
+ },
1657
+ {
1658
+ "epoch": 1.8804780876494025,
1659
+ "grad_norm": 0.34100231528282166,
1660
+ "learning_rate": 6.33330510021716e-06,
1661
+ "loss": 1.0272108316421509,
1662
+ "step": 472
1663
+ },
1664
+ {
1665
+ "epoch": 1.8884462151394423,
1666
+ "grad_norm": 0.3166549503803253,
1667
+ "learning_rate": 6.304131560928622e-06,
1668
+ "loss": 1.1524168252944946,
1669
+ "step": 474
1670
+ },
1671
+ {
1672
+ "epoch": 1.8964143426294822,
1673
+ "grad_norm": 0.07201140373945236,
1674
+ "learning_rate": 6.274923067431775e-06,
1675
+ "loss": 0.949006974697113,
1676
+ "step": 476
1677
+ },
1678
+ {
1679
+ "epoch": 1.904382470119522,
1680
+ "grad_norm": 0.07126747071743011,
1681
+ "learning_rate": 6.2456808893693155e-06,
1682
+ "loss": 0.8311147093772888,
1683
+ "step": 478
1684
+ },
1685
+ {
1686
+ "epoch": 1.9123505976095618,
1687
+ "grad_norm": 0.9960137605667114,
1688
+ "learning_rate": 6.216406297848155e-06,
1689
+ "loss": 0.5735684633255005,
1690
+ "step": 480
1691
+ },
1692
+ {
1693
+ "epoch": 1.9203187250996017,
1694
+ "grad_norm": 0.3506461977958679,
1695
+ "learning_rate": 6.187100565384162e-06,
1696
+ "loss": 0.7413168549537659,
1697
+ "step": 482
1698
+ },
1699
+ {
1700
+ "epoch": 1.9282868525896415,
1701
+ "grad_norm": 0.07256942987442017,
1702
+ "learning_rate": 6.157764965846841e-06,
1703
+ "loss": 1.1099603176116943,
1704
+ "step": 484
1705
+ },
1706
+ {
1707
+ "epoch": 1.9362549800796813,
1708
+ "grad_norm": 0.13000288605690002,
1709
+ "learning_rate": 6.128400774403974e-06,
1710
+ "loss": 1.0959395170211792,
1711
+ "step": 486
1712
+ },
1713
+ {
1714
+ "epoch": 1.9442231075697212,
1715
+ "grad_norm": 0.06632355600595474,
1716
+ "learning_rate": 6.0990092674661834e-06,
1717
+ "loss": 1.102731704711914,
1718
+ "step": 488
1719
+ },
1720
+ {
1721
+ "epoch": 1.952191235059761,
1722
+ "grad_norm": 0.0742376446723938,
1723
+ "learning_rate": 6.069591722631446e-06,
1724
+ "loss": 1.1146429777145386,
1725
+ "step": 490
1726
+ },
1727
+ {
1728
+ "epoch": 1.9601593625498008,
1729
+ "grad_norm": 0.09307283163070679,
1730
+ "learning_rate": 6.040149418629562e-06,
1731
+ "loss": 0.7695032358169556,
1732
+ "step": 492
1733
+ },
1734
+ {
1735
+ "epoch": 1.9681274900398407,
1736
+ "grad_norm": 1.1231991052627563,
1737
+ "learning_rate": 6.010683635266569e-06,
1738
+ "loss": 0.705299973487854,
1739
+ "step": 494
1740
+ },
1741
+ {
1742
+ "epoch": 1.9760956175298805,
1743
+ "grad_norm": 0.11147436499595642,
1744
+ "learning_rate": 5.981195653369113e-06,
1745
+ "loss": 1.0949732065200806,
1746
+ "step": 496
1747
+ },
1748
+ {
1749
+ "epoch": 1.9840637450199203,
1750
+ "grad_norm": 0.5126568078994751,
1751
+ "learning_rate": 5.95168675472877e-06,
1752
+ "loss": 0.8323699235916138,
1753
+ "step": 498
1754
+ },
1755
+ {
1756
+ "epoch": 1.9920318725099602,
1757
+ "grad_norm": 0.12495867908000946,
1758
+ "learning_rate": 5.922158222046334e-06,
1759
+ "loss": 1.1727375984191895,
1760
+ "step": 500
1761
+ },
1762
+ {
1763
+ "epoch": 2.0,
1764
+ "grad_norm": 0.17220130562782288,
1765
+ "learning_rate": 5.892611338876053e-06,
1766
+ "loss": 0.6304442286491394,
1767
+ "step": 502
1768
+ },
1769
+ {
1770
+ "epoch": 2.00796812749004,
1771
+ "grad_norm": 0.10112476348876953,
1772
+ "learning_rate": 5.8630473895698426e-06,
1773
+ "loss": 0.6072199940681458,
1774
+ "step": 504
1775
+ },
1776
+ {
1777
+ "epoch": 2.0159362549800797,
1778
+ "grad_norm": 0.23855921626091003,
1779
+ "learning_rate": 5.833467659221452e-06,
1780
+ "loss": 0.5671996474266052,
1781
+ "step": 506
1782
+ },
1783
+ {
1784
+ "epoch": 2.0239043824701195,
1785
+ "grad_norm": 0.028424056246876717,
1786
+ "learning_rate": 5.803873433610604e-06,
1787
+ "loss": 0.5381027460098267,
1788
+ "step": 508
1789
+ },
1790
+ {
1791
+ "epoch": 2.0318725099601593,
1792
+ "grad_norm": 0.19135037064552307,
1793
+ "learning_rate": 5.774265999147108e-06,
1794
+ "loss": 0.8364197611808777,
1795
+ "step": 510
1796
+ },
1797
+ {
1798
+ "epoch": 2.039840637450199,
1799
+ "grad_norm": 0.10862982273101807,
1800
+ "learning_rate": 5.744646642814935e-06,
1801
+ "loss": 0.7114787101745605,
1802
+ "step": 512
1803
+ },
1804
+ {
1805
+ "epoch": 2.047808764940239,
1806
+ "grad_norm": 0.23314134776592255,
1807
+ "learning_rate": 5.715016652116284e-06,
1808
+ "loss": 0.31099826097488403,
1809
+ "step": 514
1810
+ },
1811
+ {
1812
+ "epoch": 2.055776892430279,
1813
+ "grad_norm": 0.08411658555269241,
1814
+ "learning_rate": 5.68537731501561e-06,
1815
+ "loss": 0.8799335956573486,
1816
+ "step": 516
1817
+ },
1818
+ {
1819
+ "epoch": 2.0637450199203187,
1820
+ "grad_norm": 0.5435796976089478,
1821
+ "learning_rate": 5.655729919883639e-06,
1822
+ "loss": 0.5037041902542114,
1823
+ "step": 518
1824
+ },
1825
+ {
1826
+ "epoch": 2.0717131474103585,
1827
+ "grad_norm": 0.33835330605506897,
1828
+ "learning_rate": 5.626075755441366e-06,
1829
+ "loss": 0.7988424897193909,
1830
+ "step": 520
1831
+ },
1832
+ {
1833
+ "epoch": 2.0796812749003983,
1834
+ "grad_norm": 0.1254897266626358,
1835
+ "learning_rate": 5.596416110704034e-06,
1836
+ "loss": 0.9907560348510742,
1837
+ "step": 522
1838
+ },
1839
+ {
1840
+ "epoch": 2.087649402390438,
1841
+ "grad_norm": 0.2384515255689621,
1842
+ "learning_rate": 5.566752274925109e-06,
1843
+ "loss": 0.8815075755119324,
1844
+ "step": 524
1845
+ },
1846
+ {
1847
+ "epoch": 2.095617529880478,
1848
+ "grad_norm": 0.26632511615753174,
1849
+ "learning_rate": 5.5370855375402345e-06,
1850
+ "loss": 0.4096245765686035,
1851
+ "step": 526
1852
+ },
1853
+ {
1854
+ "epoch": 2.103585657370518,
1855
+ "grad_norm": 0.14012040197849274,
1856
+ "learning_rate": 5.507417188111176e-06,
1857
+ "loss": 0.7404940724372864,
1858
+ "step": 528
1859
+ },
1860
+ {
1861
+ "epoch": 2.1115537848605577,
1862
+ "grad_norm": 0.08850028365850449,
1863
+ "learning_rate": 5.477748516269779e-06,
1864
+ "loss": 0.6362339854240417,
1865
+ "step": 530
1866
+ },
1867
+ {
1868
+ "epoch": 2.1195219123505975,
1869
+ "grad_norm": 0.14766618609428406,
1870
+ "learning_rate": 5.448080811661897e-06,
1871
+ "loss": 0.20267254114151,
1872
+ "step": 532
1873
+ },
1874
+ {
1875
+ "epoch": 2.1274900398406373,
1876
+ "grad_norm": 0.17179229855537415,
1877
+ "learning_rate": 5.418415363891346e-06,
1878
+ "loss": 0.7317008376121521,
1879
+ "step": 534
1880
+ },
1881
+ {
1882
+ "epoch": 2.135458167330677,
1883
+ "grad_norm": 0.3195139765739441,
1884
+ "learning_rate": 5.3887534624638335e-06,
1885
+ "loss": 0.640765368938446,
1886
+ "step": 536
1887
+ },
1888
+ {
1889
+ "epoch": 2.143426294820717,
1890
+ "grad_norm": 0.3261059820652008,
1891
+ "learning_rate": 5.359096396730924e-06,
1892
+ "loss": 0.684579074382782,
1893
+ "step": 538
1894
+ },
1895
+ {
1896
+ "epoch": 2.151394422310757,
1897
+ "grad_norm": 0.115351602435112,
1898
+ "learning_rate": 5.329445455833975e-06,
1899
+ "loss": 0.9158648252487183,
1900
+ "step": 540
1901
+ },
1902
+ {
1903
+ "epoch": 2.1593625498007967,
1904
+ "grad_norm": 0.34780338406562805,
1905
+ "learning_rate": 5.299801928648105e-06,
1906
+ "loss": 0.8859466910362244,
1907
+ "step": 542
1908
+ },
1909
+ {
1910
+ "epoch": 2.1673306772908365,
1911
+ "grad_norm": 0.08513224869966507,
1912
+ "learning_rate": 5.270167103726181e-06,
1913
+ "loss": 0.7413093447685242,
1914
+ "step": 544
1915
+ },
1916
+ {
1917
+ "epoch": 2.1752988047808763,
1918
+ "grad_norm": 0.12682124972343445,
1919
+ "learning_rate": 5.240542269242794e-06,
1920
+ "loss": 0.6223682165145874,
1921
+ "step": 546
1922
+ },
1923
+ {
1924
+ "epoch": 2.183266932270916,
1925
+ "grad_norm": 0.12175296247005463,
1926
+ "learning_rate": 5.210928712938262e-06,
1927
+ "loss": 0.9578088521957397,
1928
+ "step": 548
1929
+ },
1930
+ {
1931
+ "epoch": 2.191235059760956,
1932
+ "grad_norm": 0.1025998443365097,
1933
+ "learning_rate": 5.181327722062667e-06,
1934
+ "loss": 1.019105076789856,
1935
+ "step": 550
1936
+ },
1937
+ {
1938
+ "epoch": 2.199203187250996,
1939
+ "grad_norm": 1.0863326787948608,
1940
+ "learning_rate": 5.151740583319892e-06,
1941
+ "loss": 0.6743606925010681,
1942
+ "step": 552
1943
+ },
1944
+ {
1945
+ "epoch": 2.2071713147410357,
1946
+ "grad_norm": 0.5417909026145935,
1947
+ "learning_rate": 5.122168582811689e-06,
1948
+ "loss": 0.42565545439720154,
1949
+ "step": 554
1950
+ },
1951
+ {
1952
+ "epoch": 2.2151394422310755,
1953
+ "grad_norm": 0.266326904296875,
1954
+ "learning_rate": 5.092613005981781e-06,
1955
+ "loss": 0.6403976082801819,
1956
+ "step": 556
1957
+ },
1958
+ {
1959
+ "epoch": 2.2231075697211153,
1960
+ "grad_norm": 0.16834671795368195,
1961
+ "learning_rate": 5.063075137559979e-06,
1962
+ "loss": 0.8421195149421692,
1963
+ "step": 558
1964
+ },
1965
+ {
1966
+ "epoch": 2.231075697211155,
1967
+ "grad_norm": 0.13817018270492554,
1968
+ "learning_rate": 5.033556261506343e-06,
1969
+ "loss": 0.8897129893302917,
1970
+ "step": 560
1971
+ },
1972
+ {
1973
+ "epoch": 2.239043824701195,
1974
+ "grad_norm": 0.14422644674777985,
1975
+ "learning_rate": 5.0040576609553645e-06,
1976
+ "loss": 1.0258100032806396,
1977
+ "step": 562
1978
+ },
1979
+ {
1980
+ "epoch": 2.247011952191235,
1981
+ "grad_norm": 0.24181491136550903,
1982
+ "learning_rate": 4.974580618160194e-06,
1983
+ "loss": 0.7488424181938171,
1984
+ "step": 564
1985
+ },
1986
+ {
1987
+ "epoch": 2.2549800796812747,
1988
+ "grad_norm": 0.1938558667898178,
1989
+ "learning_rate": 4.945126414436908e-06,
1990
+ "loss": 0.6393429040908813,
1991
+ "step": 566
1992
+ },
1993
+ {
1994
+ "epoch": 2.2629482071713145,
1995
+ "grad_norm": 0.08594364672899246,
1996
+ "learning_rate": 4.915696330108804e-06,
1997
+ "loss": 0.7282727360725403,
1998
+ "step": 568
1999
+ },
2000
+ {
2001
+ "epoch": 2.2709163346613543,
2002
+ "grad_norm": 0.1412476748228073,
2003
+ "learning_rate": 4.886291644450751e-06,
2004
+ "loss": 0.996859610080719,
2005
+ "step": 570
2006
+ },
2007
+ {
2008
+ "epoch": 2.278884462151394,
2009
+ "grad_norm": 0.35477742552757263,
2010
+ "learning_rate": 4.8569136356335845e-06,
2011
+ "loss": 0.5815088152885437,
2012
+ "step": 572
2013
+ },
2014
+ {
2015
+ "epoch": 2.2868525896414345,
2016
+ "grad_norm": 0.14603076875209808,
2017
+ "learning_rate": 4.827563580668544e-06,
2018
+ "loss": 0.6880822777748108,
2019
+ "step": 574
2020
+ },
2021
+ {
2022
+ "epoch": 2.2948207171314743,
2023
+ "grad_norm": 0.10120602697134018,
2024
+ "learning_rate": 4.798242755351755e-06,
2025
+ "loss": 0.2764871418476105,
2026
+ "step": 576
2027
+ },
2028
+ {
2029
+ "epoch": 2.302788844621514,
2030
+ "grad_norm": 0.15307286381721497,
2031
+ "learning_rate": 4.768952434208795e-06,
2032
+ "loss": 0.6583220362663269,
2033
+ "step": 578
2034
+ },
2035
+ {
2036
+ "epoch": 2.310756972111554,
2037
+ "grad_norm": 0.14034956693649292,
2038
+ "learning_rate": 4.7396938904392656e-06,
2039
+ "loss": 0.6165253520011902,
2040
+ "step": 580
2041
+ },
2042
+ {
2043
+ "epoch": 2.318725099601594,
2044
+ "grad_norm": 0.25004416704177856,
2045
+ "learning_rate": 4.71046839586147e-06,
2046
+ "loss": 0.5720459818840027,
2047
+ "step": 582
2048
+ },
2049
+ {
2050
+ "epoch": 2.3266932270916336,
2051
+ "grad_norm": 0.09810896217823029,
2052
+ "learning_rate": 4.681277220857108e-06,
2053
+ "loss": 0.7465008497238159,
2054
+ "step": 584
2055
+ },
2056
+ {
2057
+ "epoch": 2.3346613545816735,
2058
+ "grad_norm": 0.08897019922733307,
2059
+ "learning_rate": 4.6521216343160824e-06,
2060
+ "loss": 0.6230015158653259,
2061
+ "step": 586
2062
+ },
2063
+ {
2064
+ "epoch": 2.3426294820717133,
2065
+ "grad_norm": 0.38632476329803467,
2066
+ "learning_rate": 4.623002903581316e-06,
2067
+ "loss": 0.8418217897415161,
2068
+ "step": 588
2069
+ },
2070
+ {
2071
+ "epoch": 2.350597609561753,
2072
+ "grad_norm": 0.13882328569889069,
2073
+ "learning_rate": 4.593922294393677e-06,
2074
+ "loss": 0.9831987619400024,
2075
+ "step": 590
2076
+ },
2077
+ {
2078
+ "epoch": 2.358565737051793,
2079
+ "grad_norm": 0.14402514696121216,
2080
+ "learning_rate": 4.564881070836955e-06,
2081
+ "loss": 1.0264031887054443,
2082
+ "step": 592
2083
+ },
2084
+ {
2085
+ "epoch": 2.366533864541833,
2086
+ "grad_norm": 0.12101496756076813,
2087
+ "learning_rate": 4.535880495282916e-06,
2088
+ "loss": 0.6720498204231262,
2089
+ "step": 594
2090
+ },
2091
+ {
2092
+ "epoch": 2.3745019920318726,
2093
+ "grad_norm": 0.0773487314581871,
2094
+ "learning_rate": 4.506921828336427e-06,
2095
+ "loss": 0.9208852052688599,
2096
+ "step": 596
2097
+ },
2098
+ {
2099
+ "epoch": 2.3824701195219125,
2100
+ "grad_norm": 0.07198522239923477,
2101
+ "learning_rate": 4.478006328780657e-06,
2102
+ "loss": 0.6842321753501892,
2103
+ "step": 598
2104
+ },
2105
+ {
2106
+ "epoch": 2.3904382470119523,
2107
+ "grad_norm": 0.804380476474762,
2108
+ "learning_rate": 4.44913525352237e-06,
2109
+ "loss": 0.8522815704345703,
2110
+ "step": 600
2111
+ },
2112
+ {
2113
+ "epoch": 2.398406374501992,
2114
+ "grad_norm": 0.08560741692781448,
2115
+ "learning_rate": 4.420309857537277e-06,
2116
+ "loss": 1.0049006938934326,
2117
+ "step": 602
2118
+ },
2119
+ {
2120
+ "epoch": 2.406374501992032,
2121
+ "grad_norm": 0.14616362750530243,
2122
+ "learning_rate": 4.39153139381549e-06,
2123
+ "loss": 0.5706896781921387,
2124
+ "step": 604
2125
+ },
2126
+ {
2127
+ "epoch": 2.414342629482072,
2128
+ "grad_norm": 0.1779346466064453,
2129
+ "learning_rate": 4.3628011133070605e-06,
2130
+ "loss": 0.2019987553358078,
2131
+ "step": 606
2132
+ },
2133
+ {
2134
+ "epoch": 2.4223107569721116,
2135
+ "grad_norm": 0.049101900309324265,
2136
+ "learning_rate": 4.334120264867596e-06,
2137
+ "loss": 0.4708358347415924,
2138
+ "step": 608
2139
+ },
2140
+ {
2141
+ "epoch": 2.4302788844621515,
2142
+ "grad_norm": 0.07417161762714386,
2143
+ "learning_rate": 4.305490095203979e-06,
2144
+ "loss": 0.8848264217376709,
2145
+ "step": 610
2146
+ },
2147
+ {
2148
+ "epoch": 2.4382470119521913,
2149
+ "grad_norm": 0.08338167518377304,
2150
+ "learning_rate": 4.27691184882017e-06,
2151
+ "loss": 0.6636566519737244,
2152
+ "step": 612
2153
+ },
2154
+ {
2155
+ "epoch": 2.446215139442231,
2156
+ "grad_norm": 0.2790423631668091,
2157
+ "learning_rate": 4.248386767963121e-06,
2158
+ "loss": 0.5570278167724609,
2159
+ "step": 614
2160
+ },
2161
+ {
2162
+ "epoch": 2.454183266932271,
2163
+ "grad_norm": 0.11870516836643219,
2164
+ "learning_rate": 4.219916092568764e-06,
2165
+ "loss": 0.8892803192138672,
2166
+ "step": 616
2167
+ },
2168
+ {
2169
+ "epoch": 2.462151394422311,
2170
+ "grad_norm": 0.20905977487564087,
2171
+ "learning_rate": 4.191501060208121e-06,
2172
+ "loss": 0.679407000541687,
2173
+ "step": 618
2174
+ },
2175
+ {
2176
+ "epoch": 2.4701195219123506,
2177
+ "grad_norm": 0.6341357827186584,
2178
+ "learning_rate": 4.163142906033512e-06,
2179
+ "loss": 0.7536314129829407,
2180
+ "step": 620
2181
+ },
2182
+ {
2183
+ "epoch": 2.4780876494023905,
2184
+ "grad_norm": 2.335040807723999,
2185
+ "learning_rate": 4.134842862724854e-06,
2186
+ "loss": 0.8042733669281006,
2187
+ "step": 622
2188
+ },
2189
+ {
2190
+ "epoch": 2.4860557768924303,
2191
+ "grad_norm": 0.4020189642906189,
2192
+ "learning_rate": 4.106602160436088e-06,
2193
+ "loss": 0.7613189220428467,
2194
+ "step": 624
2195
+ },
2196
+ {
2197
+ "epoch": 2.49402390438247,
2198
+ "grad_norm": 0.24192647635936737,
2199
+ "learning_rate": 4.078422026741706e-06,
2200
+ "loss": 0.5949269533157349,
2201
+ "step": 626
2202
+ },
2203
+ {
2204
+ "epoch": 2.50199203187251,
2205
+ "grad_norm": 0.26743894815444946,
2206
+ "learning_rate": 4.050303686583386e-06,
2207
+ "loss": 0.9827489852905273,
2208
+ "step": 628
2209
+ },
2210
+ {
2211
+ "epoch": 2.50996015936255,
2212
+ "grad_norm": 0.11117087304592133,
2213
+ "learning_rate": 4.0222483622167465e-06,
2214
+ "loss": 0.440542995929718,
2215
+ "step": 630
2216
+ },
2217
+ {
2218
+ "epoch": 2.5179282868525896,
2219
+ "grad_norm": 0.29913899302482605,
2220
+ "learning_rate": 3.9942572731582185e-06,
2221
+ "loss": 0.4106953740119934,
2222
+ "step": 632
2223
+ },
2224
+ {
2225
+ "epoch": 2.5258964143426295,
2226
+ "grad_norm": 0.10013361275196075,
2227
+ "learning_rate": 3.966331636132039e-06,
2228
+ "loss": 1.0027564764022827,
2229
+ "step": 634
2230
+ },
2231
+ {
2232
+ "epoch": 2.5338645418326693,
2233
+ "grad_norm": 0.21742190420627594,
2234
+ "learning_rate": 3.938472665017355e-06,
2235
+ "loss": 0.9385004639625549,
2236
+ "step": 636
2237
+ },
2238
+ {
2239
+ "epoch": 2.541832669322709,
2240
+ "grad_norm": 0.25196295976638794,
2241
+ "learning_rate": 3.91068157079546e-06,
2242
+ "loss": 0.9623706936836243,
2243
+ "step": 638
2244
+ },
2245
+ {
2246
+ "epoch": 2.549800796812749,
2247
+ "grad_norm": 0.04752785339951515,
2248
+ "learning_rate": 3.882959561497159e-06,
2249
+ "loss": 0.5855326652526855,
2250
+ "step": 640
2251
+ },
2252
+ {
2253
+ "epoch": 2.557768924302789,
2254
+ "grad_norm": 0.14722587168216705,
2255
+ "learning_rate": 3.855307842150259e-06,
2256
+ "loss": 0.9499075412750244,
2257
+ "step": 642
2258
+ },
2259
+ {
2260
+ "epoch": 2.5657370517928286,
2261
+ "grad_norm": 0.09414464980363846,
2262
+ "learning_rate": 3.827727614727177e-06,
2263
+ "loss": 1.0164247751235962,
2264
+ "step": 644
2265
+ },
2266
+ {
2267
+ "epoch": 2.5737051792828685,
2268
+ "grad_norm": 0.1502121239900589,
2269
+ "learning_rate": 3.8002200780927e-06,
2270
+ "loss": 0.5638771057128906,
2271
+ "step": 646
2272
+ },
2273
+ {
2274
+ "epoch": 2.5816733067729083,
2275
+ "grad_norm": 0.15606221556663513,
2276
+ "learning_rate": 3.772786427951878e-06,
2277
+ "loss": 0.9924614429473877,
2278
+ "step": 648
2279
+ },
2280
+ {
2281
+ "epoch": 2.589641434262948,
2282
+ "grad_norm": 0.10345933586359024,
2283
+ "learning_rate": 3.7454278567980406e-06,
2284
+ "loss": 0.7498367428779602,
2285
+ "step": 650
2286
+ },
2287
+ {
2288
+ "epoch": 2.597609561752988,
2289
+ "grad_norm": 0.16408374905586243,
2290
+ "learning_rate": 3.7181455538609577e-06,
2291
+ "loss": 0.7573265433311462,
2292
+ "step": 652
2293
+ },
2294
+ {
2295
+ "epoch": 2.605577689243028,
2296
+ "grad_norm": 0.10498823970556259,
2297
+ "learning_rate": 3.690940705055163e-06,
2298
+ "loss": 0.6695098280906677,
2299
+ "step": 654
2300
+ },
2301
+ {
2302
+ "epoch": 2.6135458167330676,
2303
+ "grad_norm": 0.14632731676101685,
2304
+ "learning_rate": 3.6638144929283824e-06,
2305
+ "loss": 0.29860806465148926,
2306
+ "step": 656
2307
+ },
2308
+ {
2309
+ "epoch": 2.6215139442231075,
2310
+ "grad_norm": 0.10948789119720459,
2311
+ "learning_rate": 3.6367680966101483e-06,
2312
+ "loss": 0.5482282042503357,
2313
+ "step": 658
2314
+ },
2315
+ {
2316
+ "epoch": 2.6294820717131473,
2317
+ "grad_norm": 0.07876993715763092,
2318
+ "learning_rate": 3.6098026917605334e-06,
2319
+ "loss": 0.8400536775588989,
2320
+ "step": 660
2321
+ },
2322
+ {
2323
+ "epoch": 2.637450199203187,
2324
+ "grad_norm": 0.25182756781578064,
2325
+ "learning_rate": 3.5829194505190534e-06,
2326
+ "loss": 0.9076658487319946,
2327
+ "step": 662
2328
+ },
2329
+ {
2330
+ "epoch": 2.645418326693227,
2331
+ "grad_norm": 0.2158064991235733,
2332
+ "learning_rate": 3.5561195414537164e-06,
2333
+ "loss": 0.5271828174591064,
2334
+ "step": 664
2335
+ },
2336
+ {
2337
+ "epoch": 2.653386454183267,
2338
+ "grad_norm": 0.18953320384025574,
2339
+ "learning_rate": 3.529404129510221e-06,
2340
+ "loss": 0.9022460579872131,
2341
+ "step": 666
2342
+ },
2343
+ {
2344
+ "epoch": 2.6613545816733066,
2345
+ "grad_norm": 0.03914133086800575,
2346
+ "learning_rate": 3.502774375961321e-06,
2347
+ "loss": 0.5820519328117371,
2348
+ "step": 668
2349
+ },
2350
+ {
2351
+ "epoch": 2.6693227091633465,
2352
+ "grad_norm": 0.3090229332447052,
2353
+ "learning_rate": 3.4762314383563533e-06,
2354
+ "loss": 0.7122098207473755,
2355
+ "step": 670
2356
+ },
2357
+ {
2358
+ "epoch": 2.6772908366533863,
2359
+ "grad_norm": 0.0372186154127121,
2360
+ "learning_rate": 3.4497764704709143e-06,
2361
+ "loss": 0.32675519585609436,
2362
+ "step": 672
2363
+ },
2364
+ {
2365
+ "epoch": 2.685258964143426,
2366
+ "grad_norm": 0.07880748063325882,
2367
+ "learning_rate": 3.4234106222567055e-06,
2368
+ "loss": 0.999765932559967,
2369
+ "step": 674
2370
+ },
2371
+ {
2372
+ "epoch": 2.6932270916334664,
2373
+ "grad_norm": 0.5355376601219177,
2374
+ "learning_rate": 3.3971350397915504e-06,
2375
+ "loss": 0.6687252521514893,
2376
+ "step": 676
2377
+ },
2378
+ {
2379
+ "epoch": 2.7011952191235062,
2380
+ "grad_norm": 0.23132771253585815,
2381
+ "learning_rate": 3.370950865229583e-06,
2382
+ "loss": 0.5730953812599182,
2383
+ "step": 678
2384
+ },
2385
+ {
2386
+ "epoch": 2.709163346613546,
2387
+ "grad_norm": 0.12966091930866241,
2388
+ "learning_rate": 3.344859236751585e-06,
2389
+ "loss": 0.9984683394432068,
2390
+ "step": 680
2391
+ },
2392
+ {
2393
+ "epoch": 2.717131474103586,
2394
+ "grad_norm": 0.1126488447189331,
2395
+ "learning_rate": 3.3188612885155257e-06,
2396
+ "loss": 1.0314698219299316,
2397
+ "step": 682
2398
+ },
2399
+ {
2400
+ "epoch": 2.7250996015936257,
2401
+ "grad_norm": 0.09455672651529312,
2402
+ "learning_rate": 3.2929581506072596e-06,
2403
+ "loss": 0.6806710958480835,
2404
+ "step": 684
2405
+ },
2406
+ {
2407
+ "epoch": 2.7330677290836656,
2408
+ "grad_norm": 0.3752633333206177,
2409
+ "learning_rate": 3.267150948991387e-06,
2410
+ "loss": 0.4101208448410034,
2411
+ "step": 686
2412
+ },
2413
+ {
2414
+ "epoch": 2.7410358565737054,
2415
+ "grad_norm": 0.10289090871810913,
2416
+ "learning_rate": 3.241440805462337e-06,
2417
+ "loss": 1.0035781860351562,
2418
+ "step": 688
2419
+ },
2420
+ {
2421
+ "epoch": 2.7490039840637452,
2422
+ "grad_norm": 0.17575260996818542,
2423
+ "learning_rate": 3.215828837595585e-06,
2424
+ "loss": 0.4762260913848877,
2425
+ "step": 690
2426
+ },
2427
+ {
2428
+ "epoch": 2.756972111553785,
2429
+ "grad_norm": 0.09884456545114517,
2430
+ "learning_rate": 3.190316158699084e-06,
2431
+ "loss": 1.0761598348617554,
2432
+ "step": 692
2433
+ },
2434
+ {
2435
+ "epoch": 2.764940239043825,
2436
+ "grad_norm": 0.27310195565223694,
2437
+ "learning_rate": 3.1649038777648622e-06,
2438
+ "loss": 0.8205622434616089,
2439
+ "step": 694
2440
+ },
2441
+ {
2442
+ "epoch": 2.7729083665338647,
2443
+ "grad_norm": 0.21241426467895508,
2444
+ "learning_rate": 3.1395930994208234e-06,
2445
+ "loss": 0.6146988868713379,
2446
+ "step": 696
2447
+ },
2448
+ {
2449
+ "epoch": 2.7808764940239046,
2450
+ "grad_norm": 0.09035513550043106,
2451
+ "learning_rate": 3.114384923882734e-06,
2452
+ "loss": 0.8542025089263916,
2453
+ "step": 698
2454
+ },
2455
+ {
2456
+ "epoch": 2.7888446215139444,
2457
+ "grad_norm": 0.07631594687700272,
2458
+ "learning_rate": 3.089280446906387e-06,
2459
+ "loss": 1.030548334121704,
2460
+ "step": 700
2461
+ },
2462
+ {
2463
+ "epoch": 2.7968127490039842,
2464
+ "grad_norm": 0.5440763831138611,
2465
+ "learning_rate": 3.0642807597399847e-06,
2466
+ "loss": 0.637408435344696,
2467
+ "step": 702
2468
+ },
2469
+ {
2470
+ "epoch": 2.804780876494024,
2471
+ "grad_norm": 0.16706421971321106,
2472
+ "learning_rate": 3.0393869490766913e-06,
2473
+ "loss": 1.169363021850586,
2474
+ "step": 704
2475
+ },
2476
+ {
2477
+ "epoch": 2.812749003984064,
2478
+ "grad_norm": 0.10243828594684601,
2479
+ "learning_rate": 3.0146000970074087e-06,
2480
+ "loss": 1.1671249866485596,
2481
+ "step": 706
2482
+ },
2483
+ {
2484
+ "epoch": 2.8207171314741037,
2485
+ "grad_norm": 0.1540513038635254,
2486
+ "learning_rate": 2.9899212809737275e-06,
2487
+ "loss": 1.0633411407470703,
2488
+ "step": 708
2489
+ },
2490
+ {
2491
+ "epoch": 2.8286852589641436,
2492
+ "grad_norm": 0.7056778073310852,
2493
+ "learning_rate": 2.9653515737211037e-06,
2494
+ "loss": 0.520878255367279,
2495
+ "step": 710
2496
+ },
2497
+ {
2498
+ "epoch": 2.8366533864541834,
2499
+ "grad_norm": 0.11693540215492249,
2500
+ "learning_rate": 2.940892043252225e-06,
2501
+ "loss": 1.0443507432937622,
2502
+ "step": 712
2503
+ },
2504
+ {
2505
+ "epoch": 2.8446215139442232,
2506
+ "grad_norm": 0.12096396833658218,
2507
+ "learning_rate": 2.916543752780574e-06,
2508
+ "loss": 0.5934324860572815,
2509
+ "step": 714
2510
+ },
2511
+ {
2512
+ "epoch": 2.852589641434263,
2513
+ "grad_norm": 0.09405473619699478,
2514
+ "learning_rate": 2.892307760684234e-06,
2515
+ "loss": 1.0029265880584717,
2516
+ "step": 716
2517
+ },
2518
+ {
2519
+ "epoch": 2.860557768924303,
2520
+ "grad_norm": 0.511938214302063,
2521
+ "learning_rate": 2.8681851204598675e-06,
2522
+ "loss": 0.5955791473388672,
2523
+ "step": 718
2524
+ },
2525
+ {
2526
+ "epoch": 2.8685258964143427,
2527
+ "grad_norm": 0.10217857360839844,
2528
+ "learning_rate": 2.844176880676931e-06,
2529
+ "loss": 0.5846378207206726,
2530
+ "step": 720
2531
+ },
2532
+ {
2533
+ "epoch": 2.8764940239043826,
2534
+ "grad_norm": 0.31432026624679565,
2535
+ "learning_rate": 2.8202840849320867e-06,
2536
+ "loss": 0.6362673044204712,
2537
+ "step": 722
2538
+ },
2539
+ {
2540
+ "epoch": 2.8844621513944224,
2541
+ "grad_norm": 0.09505125880241394,
2542
+ "learning_rate": 2.7965077718038437e-06,
2543
+ "loss": 0.6044365763664246,
2544
+ "step": 724
2545
+ },
2546
+ {
2547
+ "epoch": 2.8924302788844622,
2548
+ "grad_norm": 0.09395304322242737,
2549
+ "learning_rate": 2.7728489748074193e-06,
2550
+ "loss": 0.9599644541740417,
2551
+ "step": 726
2552
+ },
2553
+ {
2554
+ "epoch": 2.900398406374502,
2555
+ "grad_norm": 0.36247771978378296,
2556
+ "learning_rate": 2.7493087223498015e-06,
2557
+ "loss": 0.5444557666778564,
2558
+ "step": 728
2559
+ },
2560
+ {
2561
+ "epoch": 2.908366533864542,
2562
+ "grad_norm": 0.5664392113685608,
2563
+ "learning_rate": 2.725888037685057e-06,
2564
+ "loss": 0.9327759742736816,
2565
+ "step": 730
2566
+ },
2567
+ {
2568
+ "epoch": 2.9163346613545817,
2569
+ "grad_norm": 0.8039626479148865,
2570
+ "learning_rate": 2.702587938869842e-06,
2571
+ "loss": 0.3262653648853302,
2572
+ "step": 732
2573
+ },
2574
+ {
2575
+ "epoch": 2.9243027888446216,
2576
+ "grad_norm": 0.08595606684684753,
2577
+ "learning_rate": 2.6794094387191617e-06,
2578
+ "loss": 1.0276615619659424,
2579
+ "step": 734
2580
+ },
2581
+ {
2582
+ "epoch": 2.9322709163346614,
2583
+ "grad_norm": 0.35183244943618774,
2584
+ "learning_rate": 2.6563535447623302e-06,
2585
+ "loss": 0.40339601039886475,
2586
+ "step": 736
2587
+ },
2588
+ {
2589
+ "epoch": 2.9402390438247012,
2590
+ "grad_norm": 0.23763059079647064,
2591
+ "learning_rate": 2.6334212591991847e-06,
2592
+ "loss": 0.7936598062515259,
2593
+ "step": 738
2594
+ },
2595
+ {
2596
+ "epoch": 2.948207171314741,
2597
+ "grad_norm": 0.08670516312122345,
2598
+ "learning_rate": 2.6106135788565248e-06,
2599
+ "loss": 1.1121079921722412,
2600
+ "step": 740
2601
+ },
2602
+ {
2603
+ "epoch": 2.956175298804781,
2604
+ "grad_norm": 0.3945688009262085,
2605
+ "learning_rate": 2.5879314951447688e-06,
2606
+ "loss": 0.3207225799560547,
2607
+ "step": 742
2608
+ },
2609
+ {
2610
+ "epoch": 2.9641434262948207,
2611
+ "grad_norm": 0.10507278144359589,
2612
+ "learning_rate": 2.5653759940148692e-06,
2613
+ "loss": 0.8529314398765564,
2614
+ "step": 744
2615
+ },
2616
+ {
2617
+ "epoch": 2.9721115537848606,
2618
+ "grad_norm": 0.18137764930725098,
2619
+ "learning_rate": 2.542948055915454e-06,
2620
+ "loss": 0.8667153716087341,
2621
+ "step": 746
2622
+ },
2623
+ {
2624
+ "epoch": 2.9800796812749004,
2625
+ "grad_norm": 0.1851310282945633,
2626
+ "learning_rate": 2.5206486557502087e-06,
2627
+ "loss": 0.5118793249130249,
2628
+ "step": 748
2629
+ },
2630
+ {
2631
+ "epoch": 2.9880478087649402,
2632
+ "grad_norm": 0.11910346150398254,
2633
+ "learning_rate": 2.498478762835492e-06,
2634
+ "loss": 0.13238655030727386,
2635
+ "step": 750
2636
+ },
2637
+ {
2638
+ "epoch": 2.99601593625498,
2639
+ "grad_norm": 0.1383173167705536,
2640
+ "learning_rate": 2.476439340858208e-06,
2641
+ "loss": 0.9977914094924927,
2642
+ "step": 752
2643
+ },
2644
+ {
2645
+ "epoch": 3.00398406374502,
2646
+ "grad_norm": 0.08733584731817245,
2647
+ "learning_rate": 2.4545313478339178e-06,
2648
+ "loss": 0.5296513438224792,
2649
+ "step": 754
2650
+ },
2651
+ {
2652
+ "epoch": 3.0119521912350598,
2653
+ "grad_norm": 0.103951096534729,
2654
+ "learning_rate": 2.4327557360651895e-06,
2655
+ "loss": 0.5676113367080688,
2656
+ "step": 756
2657
+ },
2658
+ {
2659
+ "epoch": 3.0199203187250996,
2660
+ "grad_norm": 0.07021525502204895,
2661
+ "learning_rate": 2.411113452100211e-06,
2662
+ "loss": 0.2701667249202728,
2663
+ "step": 758
2664
+ },
2665
+ {
2666
+ "epoch": 3.0278884462151394,
2667
+ "grad_norm": 0.37724074721336365,
2668
+ "learning_rate": 2.3896054366916365e-06,
2669
+ "loss": 0.6014183759689331,
2670
+ "step": 760
2671
+ },
2672
+ {
2673
+ "epoch": 3.0358565737051793,
2674
+ "grad_norm": 0.2236529439687729,
2675
+ "learning_rate": 2.3682326247557e-06,
2676
+ "loss": 0.39284777641296387,
2677
+ "step": 762
2678
+ },
2679
+ {
2680
+ "epoch": 3.043824701195219,
2681
+ "grad_norm": 0.0903429388999939,
2682
+ "learning_rate": 2.346995945331576e-06,
2683
+ "loss": 0.9162108302116394,
2684
+ "step": 764
2685
+ },
2686
+ {
2687
+ "epoch": 3.051792828685259,
2688
+ "grad_norm": 0.19768160581588745,
2689
+ "learning_rate": 2.325896321540993e-06,
2690
+ "loss": 0.1558755487203598,
2691
+ "step": 766
2692
+ },
2693
+ {
2694
+ "epoch": 3.0597609561752988,
2695
+ "grad_norm": 0.10917969048023224,
2696
+ "learning_rate": 2.3049346705481086e-06,
2697
+ "loss": 0.5417059063911438,
2698
+ "step": 768
2699
+ },
2700
+ {
2701
+ "epoch": 3.0677290836653386,
2702
+ "grad_norm": 0.18912799656391144,
2703
+ "learning_rate": 2.284111903519641e-06,
2704
+ "loss": 0.7214385867118835,
2705
+ "step": 770
2706
+ },
2707
+ {
2708
+ "epoch": 3.0756972111553784,
2709
+ "grad_norm": 0.20590689778327942,
2710
+ "learning_rate": 2.26342892558526e-06,
2711
+ "loss": 0.9078834652900696,
2712
+ "step": 772
2713
+ },
2714
+ {
2715
+ "epoch": 3.0836653386454183,
2716
+ "grad_norm": 0.8302822709083557,
2717
+ "learning_rate": 2.2428866357982515e-06,
2718
+ "loss": 0.7995004057884216,
2719
+ "step": 774
2720
+ },
2721
+ {
2722
+ "epoch": 3.091633466135458,
2723
+ "grad_norm": 0.020072488114237785,
2724
+ "learning_rate": 2.222485927096424e-06,
2725
+ "loss": 0.5199475288391113,
2726
+ "step": 776
2727
+ },
2728
+ {
2729
+ "epoch": 3.099601593625498,
2730
+ "grad_norm": 0.16181273758411407,
2731
+ "learning_rate": 2.2022276862633075e-06,
2732
+ "loss": 0.5194544196128845,
2733
+ "step": 778
2734
+ },
2735
+ {
2736
+ "epoch": 3.1075697211155378,
2737
+ "grad_norm": 0.09146042913198471,
2738
+ "learning_rate": 2.1821127938895938e-06,
2739
+ "loss": 0.8923799395561218,
2740
+ "step": 780
2741
+ },
2742
+ {
2743
+ "epoch": 3.1155378486055776,
2744
+ "grad_norm": 0.05091450363397598,
2745
+ "learning_rate": 2.162142124334871e-06,
2746
+ "loss": 0.2357436567544937,
2747
+ "step": 782
2748
+ },
2749
+ {
2750
+ "epoch": 3.1235059760956174,
2751
+ "grad_norm": 0.1348317712545395,
2752
+ "learning_rate": 2.1423165456896068e-06,
2753
+ "loss": 0.9547862410545349,
2754
+ "step": 784
2755
+ },
2756
+ {
2757
+ "epoch": 3.1314741035856573,
2758
+ "grad_norm": 0.10621712356805801,
2759
+ "learning_rate": 2.1226369197374176e-06,
2760
+ "loss": 0.6909422278404236,
2761
+ "step": 786
2762
+ },
2763
+ {
2764
+ "epoch": 3.139442231075697,
2765
+ "grad_norm": 0.2938082814216614,
2766
+ "learning_rate": 2.103104101917615e-06,
2767
+ "loss": 0.5021622180938721,
2768
+ "step": 788
2769
+ },
2770
+ {
2771
+ "epoch": 3.147410358565737,
2772
+ "grad_norm": 0.07215439528226852,
2773
+ "learning_rate": 2.0837189412880044e-06,
2774
+ "loss": 0.48427554965019226,
2775
+ "step": 790
2776
+ },
2777
+ {
2778
+ "epoch": 3.1553784860557768,
2779
+ "grad_norm": 0.37235894799232483,
2780
+ "learning_rate": 2.0644822804879964e-06,
2781
+ "loss": 0.6456067562103271,
2782
+ "step": 792
2783
+ },
2784
+ {
2785
+ "epoch": 3.1633466135458166,
2786
+ "grad_norm": 0.023045551031827927,
2787
+ "learning_rate": 2.045394955701969e-06,
2788
+ "loss": 0.16015684604644775,
2789
+ "step": 794
2790
+ },
2791
+ {
2792
+ "epoch": 3.1713147410358564,
2793
+ "grad_norm": 0.291789710521698,
2794
+ "learning_rate": 2.0264577966229222e-06,
2795
+ "loss": 0.5443094372749329,
2796
+ "step": 796
2797
+ },
2798
+ {
2799
+ "epoch": 3.1792828685258963,
2800
+ "grad_norm": 0.16915495693683624,
2801
+ "learning_rate": 2.007671626416412e-06,
2802
+ "loss": 0.505410373210907,
2803
+ "step": 798
2804
+ },
2805
+ {
2806
+ "epoch": 3.187250996015936,
2807
+ "grad_norm": 0.23237206041812897,
2808
+ "learning_rate": 1.9890372616847663e-06,
2809
+ "loss": 0.7769385576248169,
2810
+ "step": 800
2811
+ },
2812
+ {
2813
+ "epoch": 3.195219123505976,
2814
+ "grad_norm": 0.09916416555643082,
2815
+ "learning_rate": 1.9705555124315965e-06,
2816
+ "loss": 0.655504584312439,
2817
+ "step": 802
2818
+ },
2819
+ {
2820
+ "epoch": 3.2031872509960158,
2821
+ "grad_norm": 0.3141724169254303,
2822
+ "learning_rate": 1.95222718202658e-06,
2823
+ "loss": 0.5474756360054016,
2824
+ "step": 804
2825
+ },
2826
+ {
2827
+ "epoch": 3.2111553784860556,
2828
+ "grad_norm": 0.2176314890384674,
2829
+ "learning_rate": 1.934053067170545e-06,
2830
+ "loss": 0.9463359713554382,
2831
+ "step": 806
2832
+ },
2833
+ {
2834
+ "epoch": 3.2191235059760954,
2835
+ "grad_norm": 0.3539562523365021,
2836
+ "learning_rate": 1.9160339578608305e-06,
2837
+ "loss": 0.2166862040758133,
2838
+ "step": 808
2839
+ },
2840
+ {
2841
+ "epoch": 3.2270916334661353,
2842
+ "grad_norm": 0.11151967942714691,
2843
+ "learning_rate": 1.8981706373569602e-06,
2844
+ "loss": 0.6182011961936951,
2845
+ "step": 810
2846
+ },
2847
+ {
2848
+ "epoch": 3.235059760956175,
2849
+ "grad_norm": 0.18874166905879974,
2850
+ "learning_rate": 1.8804638821465821e-06,
2851
+ "loss": 0.31370559334754944,
2852
+ "step": 812
2853
+ },
2854
+ {
2855
+ "epoch": 3.243027888446215,
2856
+ "grad_norm": 0.08038028329610825,
2857
+ "learning_rate": 1.8629144619117234e-06,
2858
+ "loss": 0.7675144076347351,
2859
+ "step": 814
2860
+ },
2861
+ {
2862
+ "epoch": 3.2509960159362548,
2863
+ "grad_norm": 0.3184245824813843,
2864
+ "learning_rate": 1.8455231394953348e-06,
2865
+ "loss": 0.22720375657081604,
2866
+ "step": 816
2867
+ },
2868
+ {
2869
+ "epoch": 3.2589641434262946,
2870
+ "grad_norm": 0.10131336003541946,
2871
+ "learning_rate": 1.8282906708681238e-06,
2872
+ "loss": 0.9015382528305054,
2873
+ "step": 818
2874
+ },
2875
+ {
2876
+ "epoch": 3.2669322709163344,
2877
+ "grad_norm": 0.39507946372032166,
2878
+ "learning_rate": 1.811217805095699e-06,
2879
+ "loss": 0.43418973684310913,
2880
+ "step": 820
2881
+ },
2882
+ {
2883
+ "epoch": 3.2749003984063743,
2884
+ "grad_norm": 0.29091838002204895,
2885
+ "learning_rate": 1.7943052843060133e-06,
2886
+ "loss": 0.6147860884666443,
2887
+ "step": 822
2888
+ },
2889
+ {
2890
+ "epoch": 3.2828685258964145,
2891
+ "grad_norm": 0.33153676986694336,
2892
+ "learning_rate": 1.7775538436570937e-06,
2893
+ "loss": 0.5188818573951721,
2894
+ "step": 824
2895
+ },
2896
+ {
2897
+ "epoch": 3.2908366533864544,
2898
+ "grad_norm": 0.09359156340360641,
2899
+ "learning_rate": 1.7609642113050996e-06,
2900
+ "loss": 0.8976441025733948,
2901
+ "step": 826
2902
+ },
2903
+ {
2904
+ "epoch": 3.298804780876494,
2905
+ "grad_norm": 0.16510267555713654,
2906
+ "learning_rate": 1.7445371083726567e-06,
2907
+ "loss": 0.8939739465713501,
2908
+ "step": 828
2909
+ },
2910
+ {
2911
+ "epoch": 3.306772908366534,
2912
+ "grad_norm": 0.1346827745437622,
2913
+ "learning_rate": 1.7282732489175224e-06,
2914
+ "loss": 0.8164635896682739,
2915
+ "step": 830
2916
+ },
2917
+ {
2918
+ "epoch": 3.314741035856574,
2919
+ "grad_norm": 0.2717640995979309,
2920
+ "learning_rate": 1.7121733399015406e-06,
2921
+ "loss": 0.37919336557388306,
2922
+ "step": 832
2923
+ },
2924
+ {
2925
+ "epoch": 3.3227091633466137,
2926
+ "grad_norm": 0.637654185295105,
2927
+ "learning_rate": 1.6962380811599138e-06,
2928
+ "loss": 0.24662509560585022,
2929
+ "step": 834
2930
+ },
2931
+ {
2932
+ "epoch": 3.3306772908366535,
2933
+ "grad_norm": 0.39412349462509155,
2934
+ "learning_rate": 1.6804681653707816e-06,
2935
+ "loss": 0.46995463967323303,
2936
+ "step": 836
2937
+ },
2938
+ {
2939
+ "epoch": 3.3386454183266934,
2940
+ "grad_norm": 0.1424451619386673,
2941
+ "learning_rate": 1.6648642780251096e-06,
2942
+ "loss": 0.7019530534744263,
2943
+ "step": 838
2944
+ },
2945
+ {
2946
+ "epoch": 3.346613545816733,
2947
+ "grad_norm": 0.29868650436401367,
2948
+ "learning_rate": 1.6494270973968974e-06,
2949
+ "loss": 0.1480187326669693,
2950
+ "step": 840
2951
+ },
2952
+ {
2953
+ "epoch": 3.354581673306773,
2954
+ "grad_norm": 0.30046868324279785,
2955
+ "learning_rate": 1.6341572945136902e-06,
2956
+ "loss": 0.580310583114624,
2957
+ "step": 842
2958
+ },
2959
+ {
2960
+ "epoch": 3.362549800796813,
2961
+ "grad_norm": 0.08614935725927353,
2962
+ "learning_rate": 1.6190555331274122e-06,
2963
+ "loss": 0.5572804808616638,
2964
+ "step": 844
2965
+ },
2966
+ {
2967
+ "epoch": 3.3705179282868527,
2968
+ "grad_norm": 0.13543984293937683,
2969
+ "learning_rate": 1.6041224696855145e-06,
2970
+ "loss": 0.9477728009223938,
2971
+ "step": 846
2972
+ },
2973
+ {
2974
+ "epoch": 3.3784860557768925,
2975
+ "grad_norm": 0.11601915210485458,
2976
+ "learning_rate": 1.589358753302439e-06,
2977
+ "loss": 0.8788732886314392,
2978
+ "step": 848
2979
+ },
2980
+ {
2981
+ "epoch": 3.3864541832669324,
2982
+ "grad_norm": 0.2447684109210968,
2983
+ "learning_rate": 1.5747650257314068e-06,
2984
+ "loss": 0.8367201685905457,
2985
+ "step": 850
2986
+ },
2987
+ {
2988
+ "epoch": 3.394422310756972,
2989
+ "grad_norm": 0.3203533887863159,
2990
+ "learning_rate": 1.5603419213365146e-06,
2991
+ "loss": 0.8870067596435547,
2992
+ "step": 852
2993
+ },
2994
+ {
2995
+ "epoch": 3.402390438247012,
2996
+ "grad_norm": 0.2368336319923401,
2997
+ "learning_rate": 1.5460900670651705e-06,
2998
+ "loss": 0.5136474967002869,
2999
+ "step": 854
3000
+ },
3001
+ {
3002
+ "epoch": 3.410358565737052,
3003
+ "grad_norm": 0.15598580241203308,
3004
+ "learning_rate": 1.5320100824208306e-06,
3005
+ "loss": 0.8361679315567017,
3006
+ "step": 856
3007
+ },
3008
+ {
3009
+ "epoch": 3.4183266932270917,
3010
+ "grad_norm": 0.12319839000701904,
3011
+ "learning_rate": 1.51810257943608e-06,
3012
+ "loss": 0.9815875887870789,
3013
+ "step": 858
3014
+ },
3015
+ {
3016
+ "epoch": 3.4262948207171315,
3017
+ "grad_norm": 0.16267569363117218,
3018
+ "learning_rate": 1.5043681626460196e-06,
3019
+ "loss": 0.9458333849906921,
3020
+ "step": 860
3021
+ },
3022
+ {
3023
+ "epoch": 3.4342629482071714,
3024
+ "grad_norm": 0.08212095499038696,
3025
+ "learning_rate": 1.4908074290619972e-06,
3026
+ "loss": 0.6067045331001282,
3027
+ "step": 862
3028
+ },
3029
+ {
3030
+ "epoch": 3.442231075697211,
3031
+ "grad_norm": 0.2448061853647232,
3032
+ "learning_rate": 1.477420968145652e-06,
3033
+ "loss": 0.44623082876205444,
3034
+ "step": 864
3035
+ },
3036
+ {
3037
+ "epoch": 3.450199203187251,
3038
+ "grad_norm": 0.1172880157828331,
3039
+ "learning_rate": 1.4642093617832853e-06,
3040
+ "loss": 0.7335717678070068,
3041
+ "step": 866
3042
+ },
3043
+ {
3044
+ "epoch": 3.458167330677291,
3045
+ "grad_norm": 0.11858659982681274,
3046
+ "learning_rate": 1.4511731842605805e-06,
3047
+ "loss": 0.64848393201828,
3048
+ "step": 868
3049
+ },
3050
+ {
3051
+ "epoch": 3.4661354581673307,
3052
+ "grad_norm": 0.32108765840530396,
3053
+ "learning_rate": 1.4383130022376298e-06,
3054
+ "loss": 0.48904505372047424,
3055
+ "step": 870
3056
+ },
3057
+ {
3058
+ "epoch": 3.4741035856573705,
3059
+ "grad_norm": 0.03352862969040871,
3060
+ "learning_rate": 1.4256293747243065e-06,
3061
+ "loss": 0.5316774845123291,
3062
+ "step": 872
3063
+ },
3064
+ {
3065
+ "epoch": 3.4820717131474104,
3066
+ "grad_norm": 0.20545020699501038,
3067
+ "learning_rate": 1.4131228530559637e-06,
3068
+ "loss": 0.6059108376502991,
3069
+ "step": 874
3070
+ },
3071
+ {
3072
+ "epoch": 3.49003984063745,
3073
+ "grad_norm": 0.11125019192695618,
3074
+ "learning_rate": 1.400793980869468e-06,
3075
+ "loss": 0.48970475792884827,
3076
+ "step": 876
3077
+ },
3078
+ {
3079
+ "epoch": 3.49800796812749,
3080
+ "grad_norm": 0.15669061243534088,
3081
+ "learning_rate": 1.3886432940795744e-06,
3082
+ "loss": 0.49637895822525024,
3083
+ "step": 878
3084
+ },
3085
+ {
3086
+ "epoch": 3.50597609561753,
3087
+ "grad_norm": 0.04867348074913025,
3088
+ "learning_rate": 1.3766713208556232e-06,
3089
+ "loss": 0.32917848229408264,
3090
+ "step": 880
3091
+ },
3092
+ {
3093
+ "epoch": 3.5139442231075697,
3094
+ "grad_norm": 0.19297191500663757,
3095
+ "learning_rate": 1.3648785815985876e-06,
3096
+ "loss": 0.5148631930351257,
3097
+ "step": 882
3098
+ },
3099
+ {
3100
+ "epoch": 3.5219123505976095,
3101
+ "grad_norm": 0.5676918029785156,
3102
+ "learning_rate": 1.353265588918448e-06,
3103
+ "loss": 0.10626660287380219,
3104
+ "step": 884
3105
+ },
3106
+ {
3107
+ "epoch": 3.5298804780876494,
3108
+ "grad_norm": 0.1393618881702423,
3109
+ "learning_rate": 1.3418328476119136e-06,
3110
+ "loss": 0.7224240303039551,
3111
+ "step": 886
3112
+ },
3113
+ {
3114
+ "epoch": 3.537848605577689,
3115
+ "grad_norm": 0.16956079006195068,
3116
+ "learning_rate": 1.330580854640477e-06,
3117
+ "loss": 0.861225962638855,
3118
+ "step": 888
3119
+ },
3120
+ {
3121
+ "epoch": 3.545816733067729,
3122
+ "grad_norm": 0.15440139174461365,
3123
+ "learning_rate": 1.3195100991088142e-06,
3124
+ "loss": 0.47051650285720825,
3125
+ "step": 890
3126
+ },
3127
+ {
3128
+ "epoch": 3.553784860557769,
3129
+ "grad_norm": 0.3990451395511627,
3130
+ "learning_rate": 1.308621062243524e-06,
3131
+ "loss": 0.8131183385848999,
3132
+ "step": 892
3133
+ },
3134
+ {
3135
+ "epoch": 3.5617529880478087,
3136
+ "grad_norm": 0.893460214138031,
3137
+ "learning_rate": 1.2979142173722054e-06,
3138
+ "loss": 0.9933807253837585,
3139
+ "step": 894
3140
+ },
3141
+ {
3142
+ "epoch": 3.5697211155378485,
3143
+ "grad_norm": 0.0942659005522728,
3144
+ "learning_rate": 1.2873900299028896e-06,
3145
+ "loss": 0.18559087812900543,
3146
+ "step": 896
3147
+ },
3148
+ {
3149
+ "epoch": 3.5776892430278884,
3150
+ "grad_norm": 0.11877981573343277,
3151
+ "learning_rate": 1.2770489573038073e-06,
3152
+ "loss": 0.5669529438018799,
3153
+ "step": 898
3154
+ },
3155
+ {
3156
+ "epoch": 3.585657370517928,
3157
+ "grad_norm": 0.27595198154449463,
3158
+ "learning_rate": 1.2668914490834983e-06,
3159
+ "loss": 0.1947745680809021,
3160
+ "step": 900
3161
+ },
3162
+ {
3163
+ "epoch": 3.593625498007968,
3164
+ "grad_norm": 0.12320013344287872,
3165
+ "learning_rate": 1.2569179467712805e-06,
3166
+ "loss": 0.08118575066328049,
3167
+ "step": 902
3168
+ },
3169
+ {
3170
+ "epoch": 3.601593625498008,
3171
+ "grad_norm": 0.15320217609405518,
3172
+ "learning_rate": 1.2471288838980505e-06,
3173
+ "loss": 0.7362831234931946,
3174
+ "step": 904
3175
+ },
3176
+ {
3177
+ "epoch": 3.6095617529880477,
3178
+ "grad_norm": 0.15283599495887756,
3179
+ "learning_rate": 1.237524685977444e-06,
3180
+ "loss": 0.5521562695503235,
3181
+ "step": 906
3182
+ },
3183
+ {
3184
+ "epoch": 3.6175298804780875,
3185
+ "grad_norm": 0.12375420331954956,
3186
+ "learning_rate": 1.2281057704873331e-06,
3187
+ "loss": 0.8319555521011353,
3188
+ "step": 908
3189
+ },
3190
+ {
3191
+ "epoch": 3.6254980079681274,
3192
+ "grad_norm": 0.2633494734764099,
3193
+ "learning_rate": 1.2188725468516876e-06,
3194
+ "loss": 0.7656584978103638,
3195
+ "step": 910
3196
+ },
3197
+ {
3198
+ "epoch": 3.633466135458167,
3199
+ "grad_norm": 0.048641543835401535,
3200
+ "learning_rate": 1.2098254164227706e-06,
3201
+ "loss": 0.04072123020887375,
3202
+ "step": 912
3203
+ },
3204
+ {
3205
+ "epoch": 3.641434262948207,
3206
+ "grad_norm": 0.14492478966712952,
3207
+ "learning_rate": 1.200964772463695e-06,
3208
+ "loss": 0.7114333510398865,
3209
+ "step": 914
3210
+ },
3211
+ {
3212
+ "epoch": 3.649402390438247,
3213
+ "grad_norm": 0.18942925333976746,
3214
+ "learning_rate": 1.1922910001313312e-06,
3215
+ "loss": 0.7078197002410889,
3216
+ "step": 916
3217
+ },
3218
+ {
3219
+ "epoch": 3.6573705179282867,
3220
+ "grad_norm": 0.3490183651447296,
3221
+ "learning_rate": 1.1838044764595617e-06,
3222
+ "loss": 0.1272016018629074,
3223
+ "step": 918
3224
+ },
3225
+ {
3226
+ "epoch": 3.6653386454183265,
3227
+ "grad_norm": 0.13709823787212372,
3228
+ "learning_rate": 1.1755055703428958e-06,
3229
+ "loss": 0.8840264678001404,
3230
+ "step": 920
3231
+ },
3232
+ {
3233
+ "epoch": 3.6733067729083664,
3234
+ "grad_norm": 0.29470717906951904,
3235
+ "learning_rate": 1.1673946425204288e-06,
3236
+ "loss": 0.12348813563585281,
3237
+ "step": 922
3238
+ },
3239
+ {
3240
+ "epoch": 3.681274900398406,
3241
+ "grad_norm": 0.25545525550842285,
3242
+ "learning_rate": 1.1594720455601664e-06,
3243
+ "loss": 0.8577460050582886,
3244
+ "step": 924
3245
+ },
3246
+ {
3247
+ "epoch": 3.6892430278884465,
3248
+ "grad_norm": 0.10373926907777786,
3249
+ "learning_rate": 1.1517381238436986e-06,
3250
+ "loss": 0.22830277681350708,
3251
+ "step": 926
3252
+ },
3253
+ {
3254
+ "epoch": 3.6972111553784863,
3255
+ "grad_norm": 0.08529862016439438,
3256
+ "learning_rate": 1.1441932135512262e-06,
3257
+ "loss": 0.5053238868713379,
3258
+ "step": 928
3259
+ },
3260
+ {
3261
+ "epoch": 3.705179282868526,
3262
+ "grad_norm": 0.09483988583087921,
3263
+ "learning_rate": 1.1368376426469526e-06,
3264
+ "loss": 0.7587119936943054,
3265
+ "step": 930
3266
+ },
3267
+ {
3268
+ "epoch": 3.713147410358566,
3269
+ "grad_norm": 0.13993456959724426,
3270
+ "learning_rate": 1.1296717308648237e-06,
3271
+ "loss": 0.8940988779067993,
3272
+ "step": 932
3273
+ },
3274
+ {
3275
+ "epoch": 3.721115537848606,
3276
+ "grad_norm": 0.17292512953281403,
3277
+ "learning_rate": 1.1226957896946332e-06,
3278
+ "loss": 0.4452460706233978,
3279
+ "step": 934
3280
+ },
3281
+ {
3282
+ "epoch": 3.7290836653386457,
3283
+ "grad_norm": 0.20580518245697021,
3284
+ "learning_rate": 1.115910122368479e-06,
3285
+ "loss": 0.8040222525596619,
3286
+ "step": 936
3287
+ },
3288
+ {
3289
+ "epoch": 3.7370517928286855,
3290
+ "grad_norm": 0.266689270734787,
3291
+ "learning_rate": 1.1093150238475847e-06,
3292
+ "loss": 0.46449920535087585,
3293
+ "step": 938
3294
+ },
3295
+ {
3296
+ "epoch": 3.7450199203187253,
3297
+ "grad_norm": 0.11229197680950165,
3298
+ "learning_rate": 1.1029107808094789e-06,
3299
+ "loss": 0.7149961590766907,
3300
+ "step": 940
3301
+ },
3302
+ {
3303
+ "epoch": 3.752988047808765,
3304
+ "grad_norm": 0.5672265291213989,
3305
+ "learning_rate": 1.0966976716355294e-06,
3306
+ "loss": 0.5650360584259033,
3307
+ "step": 942
3308
+ },
3309
+ {
3310
+ "epoch": 3.760956175298805,
3311
+ "grad_norm": 0.3948570191860199,
3312
+ "learning_rate": 1.0906759663988475e-06,
3313
+ "loss": 0.4824882447719574,
3314
+ "step": 944
3315
+ },
3316
+ {
3317
+ "epoch": 3.768924302788845,
3318
+ "grad_norm": 0.09813003987073898,
3319
+ "learning_rate": 1.084845926852547e-06,
3320
+ "loss": 0.9347279667854309,
3321
+ "step": 946
3322
+ },
3323
+ {
3324
+ "epoch": 3.7768924302788847,
3325
+ "grad_norm": 0.1827877312898636,
3326
+ "learning_rate": 1.0792078064183652e-06,
3327
+ "loss": 0.5004470348358154,
3328
+ "step": 948
3329
+ },
3330
+ {
3331
+ "epoch": 3.7848605577689245,
3332
+ "grad_norm": 0.08153803646564484,
3333
+ "learning_rate": 1.0737618501756455e-06,
3334
+ "loss": 0.898761510848999,
3335
+ "step": 950
3336
+ },
3337
+ {
3338
+ "epoch": 3.7928286852589643,
3339
+ "grad_norm": 0.13369211554527283,
3340
+ "learning_rate": 1.0685082948506875e-06,
3341
+ "loss": 0.9007242321968079,
3342
+ "step": 952
3343
+ },
3344
+ {
3345
+ "epoch": 3.800796812749004,
3346
+ "grad_norm": 0.11834340542554855,
3347
+ "learning_rate": 1.063447368806457e-06,
3348
+ "loss": 0.5072510838508606,
3349
+ "step": 954
3350
+ },
3351
+ {
3352
+ "epoch": 3.808764940239044,
3353
+ "grad_norm": 0.6668749451637268,
3354
+ "learning_rate": 1.0585792920326565e-06,
3355
+ "loss": 0.6785795092582703,
3356
+ "step": 956
3357
+ },
3358
+ {
3359
+ "epoch": 3.816733067729084,
3360
+ "grad_norm": 1.107836127281189,
3361
+ "learning_rate": 1.0539042761361646e-06,
3362
+ "loss": 0.477740615606308,
3363
+ "step": 958
3364
+ },
3365
+ {
3366
+ "epoch": 3.8247011952191237,
3367
+ "grad_norm": 0.19571809470653534,
3368
+ "learning_rate": 1.0494225243318373e-06,
3369
+ "loss": 0.597763180732727,
3370
+ "step": 960
3371
+ },
3372
+ {
3373
+ "epoch": 3.8326693227091635,
3374
+ "grad_norm": 0.04349878430366516,
3375
+ "learning_rate": 1.0451342314336755e-06,
3376
+ "loss": 0.513166069984436,
3377
+ "step": 962
3378
+ },
3379
+ {
3380
+ "epoch": 3.8406374501992033,
3381
+ "grad_norm": 0.20118169486522675,
3382
+ "learning_rate": 1.0410395838463547e-06,
3383
+ "loss": 0.9219191074371338,
3384
+ "step": 964
3385
+ },
3386
+ {
3387
+ "epoch": 3.848605577689243,
3388
+ "grad_norm": 0.2624046206474304,
3389
+ "learning_rate": 1.0371387595571248e-06,
3390
+ "loss": 0.30333149433135986,
3391
+ "step": 966
3392
+ },
3393
+ {
3394
+ "epoch": 3.856573705179283,
3395
+ "grad_norm": 0.09783243387937546,
3396
+ "learning_rate": 1.0334319281280715e-06,
3397
+ "loss": 0.5276415348052979,
3398
+ "step": 968
3399
+ },
3400
+ {
3401
+ "epoch": 3.864541832669323,
3402
+ "grad_norm": 0.2174321860074997,
3403
+ "learning_rate": 1.0299192506887467e-06,
3404
+ "loss": 0.6463159918785095,
3405
+ "step": 970
3406
+ },
3407
+ {
3408
+ "epoch": 3.8725099601593627,
3409
+ "grad_norm": 0.02547277696430683,
3410
+ "learning_rate": 1.0266008799291635e-06,
3411
+ "loss": 0.4986192584037781,
3412
+ "step": 972
3413
+ },
3414
+ {
3415
+ "epoch": 3.8804780876494025,
3416
+ "grad_norm": 0.041136253625154495,
3417
+ "learning_rate": 1.0234769600931612e-06,
3418
+ "loss": 0.39934349060058594,
3419
+ "step": 974
3420
+ },
3421
+ {
3422
+ "epoch": 3.8884462151394423,
3423
+ "grad_norm": 0.09584596008062363,
3424
+ "learning_rate": 1.0205476269721312e-06,
3425
+ "loss": 0.9003692269325256,
3426
+ "step": 976
3427
+ },
3428
+ {
3429
+ "epoch": 3.896414342629482,
3430
+ "grad_norm": 0.1499820202589035,
3431
+ "learning_rate": 1.0178130078991196e-06,
3432
+ "loss": 0.5276603102684021,
3433
+ "step": 978
3434
+ },
3435
+ {
3436
+ "epoch": 3.904382470119522,
3437
+ "grad_norm": 0.062052126973867416,
3438
+ "learning_rate": 1.0152732217432875e-06,
3439
+ "loss": 0.35644063353538513,
3440
+ "step": 980
3441
+ },
3442
+ {
3443
+ "epoch": 3.912350597609562,
3444
+ "grad_norm": 0.21071912348270416,
3445
+ "learning_rate": 1.0129283789047473e-06,
3446
+ "loss": 0.40043482184410095,
3447
+ "step": 982
3448
+ },
3449
+ {
3450
+ "epoch": 3.9203187250996017,
3451
+ "grad_norm": 0.0894634947180748,
3452
+ "learning_rate": 1.0107785813097621e-06,
3453
+ "loss": 0.8511362671852112,
3454
+ "step": 984
3455
+ },
3456
+ {
3457
+ "epoch": 3.9282868525896415,
3458
+ "grad_norm": 0.23283158242702484,
3459
+ "learning_rate": 1.0088239224063153e-06,
3460
+ "loss": 0.1116846427321434,
3461
+ "step": 986
3462
+ },
3463
+ {
3464
+ "epoch": 3.9362549800796813,
3465
+ "grad_norm": 0.4885595738887787,
3466
+ "learning_rate": 1.0070644871600495e-06,
3467
+ "loss": 0.5695192813873291,
3468
+ "step": 988
3469
+ },
3470
+ {
3471
+ "epoch": 3.944223107569721,
3472
+ "grad_norm": 0.09019921720027924,
3473
+ "learning_rate": 1.0055003520505714e-06,
3474
+ "loss": 0.5186564326286316,
3475
+ "step": 990
3476
+ },
3477
+ {
3478
+ "epoch": 3.952191235059761,
3479
+ "grad_norm": 0.11849397420883179,
3480
+ "learning_rate": 1.00413158506813e-06,
3481
+ "loss": 0.9052659869194031,
3482
+ "step": 992
3483
+ },
3484
+ {
3485
+ "epoch": 3.960159362549801,
3486
+ "grad_norm": 0.07879645377397537,
3487
+ "learning_rate": 1.0029582457106588e-06,
3488
+ "loss": 0.20878446102142334,
3489
+ "step": 994
3490
+ },
3491
+ {
3492
+ "epoch": 3.9681274900398407,
3493
+ "grad_norm": 0.2216099500656128,
3494
+ "learning_rate": 1.00198038498119e-06,
3495
+ "loss": 0.7964245676994324,
3496
+ "step": 996
3497
+ },
3498
+ {
3499
+ "epoch": 3.9760956175298805,
3500
+ "grad_norm": 0.04027597978711128,
3501
+ "learning_rate": 1.0011980453856391e-06,
3502
+ "loss": 0.5180699229240417,
3503
+ "step": 998
3504
+ },
3505
+ {
3506
+ "epoch": 3.9840637450199203,
3507
+ "grad_norm": 0.3593519330024719,
3508
+ "learning_rate": 1.0006112609309548e-06,
3509
+ "loss": 0.37535738945007324,
3510
+ "step": 1000
3511
+ },
3512
+ {
3513
+ "epoch": 3.99203187250996,
3514
+ "grad_norm": 0.12222480773925781,
3515
+ "learning_rate": 1.0002200571236429e-06,
3516
+ "loss": 0.9074435234069824,
3517
+ "step": 1002
3518
+ },
3519
+ {
3520
+ "epoch": 4.0,
3521
+ "grad_norm": 0.051510538905858994,
3522
+ "learning_rate": 1.0000244509686564e-06,
3523
+ "loss": 0.2501225471496582,
3524
+ "step": 1004
3525
+ },
3526
+ {
3527
+ "epoch": 4.0,
3528
+ "step": 1004,
3529
+ "total_flos": 3.954132003103703e+18,
3530
+ "train_loss": 0.8403717435273041,
3531
+ "train_runtime": 34650.8856,
3532
+ "train_samples_per_second": 1.738,
3533
+ "train_steps_per_second": 0.029
3534
+ }
3535
+ ],
3536
+ "logging_steps": 2,
3537
+ "max_steps": 1004,
3538
+ "num_input_tokens_seen": 0,
3539
+ "num_train_epochs": 4,
3540
+ "save_steps": 99999,
3541
+ "stateful_callbacks": {
3542
+ "TrainerControl": {
3543
+ "args": {
3544
+ "should_epoch_stop": false,
3545
+ "should_evaluate": false,
3546
+ "should_log": false,
3547
+ "should_save": false,
3548
+ "should_training_stop": false
3549
+ },
3550
+ "attributes": {}
3551
+ }
3552
+ },
3553
+ "total_flos": 3.954132003103703e+18,
3554
+ "train_batch_size": 1,
3555
+ "trial_name": null,
3556
+ "trial_params": null
3557
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da449856a02039da017acb91972f85a6f2a2d217b7b0f5ff9d1f0cd14011afb
3
+ size 5649
training_loss.png ADDED