Hugging Face's logo

furproxy
/
9b-65

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
llama-factory
full
Generated from Trainer
conversational
Model card Files
xet
 Community
furproxy commited on
Commit
9b4ff2d
·
verified ·
1 Parent(s): 67c34f3

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", 1.5e-5), language_lr),
40
+ "vision": _fallback(getattr(training_args, "vision_adamw_lr", 4e-6), vision_lr),
41
+ "merger": _fallback(getattr(training_args, "merger_adamw_lr", 2e-5), merger_lr),
42
+ }
43
+ - train_batch_size: 3
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - gradient_accumulation_steps: 20
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", 1.5e-5), language_lr),
40
+ "vision": _fallback(getattr(training_args, "vision_adamw_lr", 4e-6), vision_lr),
41
+ "merger": _fallback(getattr(training_args, "merger_adamw_lr", 2e-5), merger_lr),
42
+ }
43
+ - train_batch_size: 3
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - gradient_accumulation_steps: 20
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": 7162.660003920485,
3
+ "epoch": 4.0,
4
+ "total_flos": 4.038502240003031e+18,
5
+ "train_loss": 0.7418717171225059,
6
+ "train_runtime": 10936.9117,
7
+ "train_samples_per_second": 5.508,
8
+ "train_steps_per_second": 0.092
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 sha256:663fd994e00efcfcb30f4b59fb9549da282648c7bfe44231ea05c1d6e3d74a56
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": 7162.660003920485,
3
+ "epoch": 4.0,
4
+ "total_flos": 4.038502240003031e+18,
5
+ "train_loss": 0.7418717171225059,
6
+ "train_runtime": 10936.9117,
7
+ "train_samples_per_second": 5.508,
8
+ "train_steps_per_second": 0.092
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": 0.8701496124267578,
15
+ "learning_rate": 2.9411764705882356e-07,
16
+ "loss": 2.091559410095215,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.01593625498007968,
21
+ "grad_norm": 0.9730402231216431,
22
+ "learning_rate": 8.823529411764706e-07,
23
+ "loss": 2.0084309577941895,
24
+ "step": 4
25
+ },
26
+ {
27
+ "epoch": 0.02390438247011952,
28
+ "grad_norm": 23.87286949157715,
29
+ "learning_rate": 1.4705882352941177e-06,
30
+ "loss": 2.1494643688201904,
31
+ "step": 6
32
+ },
33
+ {
34
+ "epoch": 0.03187250996015936,
35
+ "grad_norm": 0.5717560052871704,
36
+ "learning_rate": 2.058823529411765e-06,
37
+ "loss": 1.8582701683044434,
38
+ "step": 8
39
+ },
40
+ {
41
+ "epoch": 0.0398406374501992,
42
+ "grad_norm": 1.2766757011413574,
43
+ "learning_rate": 2.647058823529412e-06,
44
+ "loss": 1.387536644935608,
45
+ "step": 10
46
+ },
47
+ {
48
+ "epoch": 0.04780876494023904,
49
+ "grad_norm": 0.6310649514198303,
50
+ "learning_rate": 3.235294117647059e-06,
51
+ "loss": 1.6384257078170776,
52
+ "step": 12
53
+ },
54
+ {
55
+ "epoch": 0.055776892430278883,
56
+ "grad_norm": 0.5051367282867432,
57
+ "learning_rate": 3.8235294117647055e-06,
58
+ "loss": 1.8997098207473755,
59
+ "step": 14
60
+ },
61
+ {
62
+ "epoch": 0.06374501992031872,
63
+ "grad_norm": 3.0508971214294434,
64
+ "learning_rate": 4.411764705882353e-06,
65
+ "loss": 1.5508460998535156,
66
+ "step": 16
67
+ },
68
+ {
69
+ "epoch": 0.07171314741035857,
70
+ "grad_norm": 0.6429860591888428,
71
+ "learning_rate": 4.9999999999999996e-06,
72
+ "loss": 1.544956922531128,
73
+ "step": 18
74
+ },
75
+ {
76
+ "epoch": 0.0796812749003984,
77
+ "grad_norm": 0.5023921132087708,
78
+ "learning_rate": 5.588235294117647e-06,
79
+ "loss": 1.4685248136520386,
80
+ "step": 20
81
+ },
82
+ {
83
+ "epoch": 0.08764940239043825,
84
+ "grad_norm": 0.4997398853302002,
85
+ "learning_rate": 6.176470588235294e-06,
86
+ "loss": 1.1129087209701538,
87
+ "step": 22
88
+ },
89
+ {
90
+ "epoch": 0.09561752988047809,
91
+ "grad_norm": 1.2241058349609375,
92
+ "learning_rate": 6.7647058823529414e-06,
93
+ "loss": 1.2971528768539429,
94
+ "step": 24
95
+ },
96
+ {
97
+ "epoch": 0.10358565737051793,
98
+ "grad_norm": 0.583693265914917,
99
+ "learning_rate": 7.3529411764705884e-06,
100
+ "loss": 1.399789810180664,
101
+ "step": 26
102
+ },
103
+ {
104
+ "epoch": 0.11155378486055777,
105
+ "grad_norm": 0.41760727763175964,
106
+ "learning_rate": 7.941176470588236e-06,
107
+ "loss": 1.6126567125320435,
108
+ "step": 28
109
+ },
110
+ {
111
+ "epoch": 0.11952191235059761,
112
+ "grad_norm": 0.6942929625511169,
113
+ "learning_rate": 8.529411764705882e-06,
114
+ "loss": 1.3107324838638306,
115
+ "step": 30
116
+ },
117
+ {
118
+ "epoch": 0.12749003984063745,
119
+ "grad_norm": 2.4918148517608643,
120
+ "learning_rate": 9.117647058823529e-06,
121
+ "loss": 1.1656028032302856,
122
+ "step": 32
123
+ },
124
+ {
125
+ "epoch": 0.13545816733067728,
126
+ "grad_norm": 0.6997283101081848,
127
+ "learning_rate": 9.705882352941177e-06,
128
+ "loss": 1.2270398139953613,
129
+ "step": 34
130
+ },
131
+ {
132
+ "epoch": 0.14342629482071714,
133
+ "grad_norm": 0.41730615496635437,
134
+ "learning_rate": 1.0294117647058824e-05,
135
+ "loss": 1.3723477125167847,
136
+ "step": 36
137
+ },
138
+ {
139
+ "epoch": 0.15139442231075698,
140
+ "grad_norm": 0.5808508992195129,
141
+ "learning_rate": 1.0882352941176471e-05,
142
+ "loss": 1.166778802871704,
143
+ "step": 38
144
+ },
145
+ {
146
+ "epoch": 0.1593625498007968,
147
+ "grad_norm": 0.29741156101226807,
148
+ "learning_rate": 1.1470588235294117e-05,
149
+ "loss": 1.2935056686401367,
150
+ "step": 40
151
+ },
152
+ {
153
+ "epoch": 0.16733067729083664,
154
+ "grad_norm": 1.2481650114059448,
155
+ "learning_rate": 1.2058823529411765e-05,
156
+ "loss": 0.765558123588562,
157
+ "step": 42
158
+ },
159
+ {
160
+ "epoch": 0.1752988047808765,
161
+ "grad_norm": 0.4549512267112732,
162
+ "learning_rate": 1.2647058823529412e-05,
163
+ "loss": 0.9544646739959717,
164
+ "step": 44
165
+ },
166
+ {
167
+ "epoch": 0.18326693227091634,
168
+ "grad_norm": 2.7968297004699707,
169
+ "learning_rate": 1.323529411764706e-05,
170
+ "loss": 0.9361187815666199,
171
+ "step": 46
172
+ },
173
+ {
174
+ "epoch": 0.19123505976095617,
175
+ "grad_norm": 0.6919461488723755,
176
+ "learning_rate": 1.3823529411764705e-05,
177
+ "loss": 1.17107093334198,
178
+ "step": 48
179
+ },
180
+ {
181
+ "epoch": 0.199203187250996,
182
+ "grad_norm": 0.5921279191970825,
183
+ "learning_rate": 1.4411764705882353e-05,
184
+ "loss": 1.3282028436660767,
185
+ "step": 50
186
+ },
187
+ {
188
+ "epoch": 0.20717131474103587,
189
+ "grad_norm": 0.5274451971054077,
190
+ "learning_rate": 1.5e-05,
191
+ "loss": 1.2876099348068237,
192
+ "step": 52
193
+ },
194
+ {
195
+ "epoch": 0.2151394422310757,
196
+ "grad_norm": 1.5639928579330444,
197
+ "learning_rate": 1.4999853294586629e-05,
198
+ "loss": 1.109473466873169,
199
+ "step": 54
200
+ },
201
+ {
202
+ "epoch": 0.22310756972111553,
203
+ "grad_norm": 0.6973602771759033,
204
+ "learning_rate": 1.4999413184723549e-05,
205
+ "loss": 1.5242366790771484,
206
+ "step": 56
207
+ },
208
+ {
209
+ "epoch": 0.23107569721115537,
210
+ "grad_norm": 0.5269781351089478,
211
+ "learning_rate": 1.4998679689541569e-05,
212
+ "loss": 1.3331416845321655,
213
+ "step": 58
214
+ },
215
+ {
216
+ "epoch": 0.23904382470119523,
217
+ "grad_norm": 0.4338107109069824,
218
+ "learning_rate": 1.499765284092446e-05,
219
+ "loss": 0.9126222729682922,
220
+ "step": 60
221
+ },
222
+ {
223
+ "epoch": 0.24701195219123506,
224
+ "grad_norm": 0.3536894917488098,
225
+ "learning_rate": 1.4996332683507557e-05,
226
+ "loss": 1.3404982089996338,
227
+ "step": 62
228
+ },
229
+ {
230
+ "epoch": 0.2549800796812749,
231
+ "grad_norm": 0.7808045148849487,
232
+ "learning_rate": 1.4994719274675816e-05,
233
+ "loss": 1.1124142408370972,
234
+ "step": 64
235
+ },
236
+ {
237
+ "epoch": 0.26294820717131473,
238
+ "grad_norm": 0.3446694314479828,
239
+ "learning_rate": 1.4992812684561331e-05,
240
+ "loss": 1.2747009992599487,
241
+ "step": 66
242
+ },
243
+ {
244
+ "epoch": 0.27091633466135456,
245
+ "grad_norm": 13.088342666625977,
246
+ "learning_rate": 1.4990612996040276e-05,
247
+ "loss": 1.282449722290039,
248
+ "step": 68
249
+ },
250
+ {
251
+ "epoch": 0.2788844621513944,
252
+ "grad_norm": 2.078386068344116,
253
+ "learning_rate": 1.498812030472931e-05,
254
+ "loss": 1.5724037885665894,
255
+ "step": 70
256
+ },
257
+ {
258
+ "epoch": 0.2868525896414343,
259
+ "grad_norm": 0.6237571239471436,
260
+ "learning_rate": 1.498533471898141e-05,
261
+ "loss": 0.8898400068283081,
262
+ "step": 72
263
+ },
264
+ {
265
+ "epoch": 0.2948207171314741,
266
+ "grad_norm": 1.2999846935272217,
267
+ "learning_rate": 1.4982256359881172e-05,
268
+ "loss": 1.1757071018218994,
269
+ "step": 74
270
+ },
271
+ {
272
+ "epoch": 0.30278884462151395,
273
+ "grad_norm": 0.5385910868644714,
274
+ "learning_rate": 1.4978885361239544e-05,
275
+ "loss": 1.4709817171096802,
276
+ "step": 76
277
+ },
278
+ {
279
+ "epoch": 0.3107569721115538,
280
+ "grad_norm": 1.2187010049819946,
281
+ "learning_rate": 1.4975221869588004e-05,
282
+ "loss": 0.9453757405281067,
283
+ "step": 78
284
+ },
285
+ {
286
+ "epoch": 0.3187250996015936,
287
+ "grad_norm": 0.3541651964187622,
288
+ "learning_rate": 1.4971266044172201e-05,
289
+ "loss": 0.8519526720046997,
290
+ "step": 80
291
+ },
292
+ {
293
+ "epoch": 0.32669322709163345,
294
+ "grad_norm": 0.4355093836784363,
295
+ "learning_rate": 1.4967018056945026e-05,
296
+ "loss": 1.3587875366210938,
297
+ "step": 82
298
+ },
299
+ {
300
+ "epoch": 0.3346613545816733,
301
+ "grad_norm": 0.6306200623512268,
302
+ "learning_rate": 1.4962478092559135e-05,
303
+ "loss": 0.9281608462333679,
304
+ "step": 84
305
+ },
306
+ {
307
+ "epoch": 0.3426294820717131,
308
+ "grad_norm": 0.4139735698699951,
309
+ "learning_rate": 1.495764634835893e-05,
310
+ "loss": 1.3322420120239258,
311
+ "step": 86
312
+ },
313
+ {
314
+ "epoch": 0.350597609561753,
315
+ "grad_norm": 0.9012618660926819,
316
+ "learning_rate": 1.4952523034371973e-05,
317
+ "loss": 0.9445306658744812,
318
+ "step": 88
319
+ },
320
+ {
321
+ "epoch": 0.35856573705179284,
322
+ "grad_norm": 0.46748796105384827,
323
+ "learning_rate": 1.4947108373299864e-05,
324
+ "loss": 1.3331313133239746,
325
+ "step": 90
326
+ },
327
+ {
328
+ "epoch": 0.3665338645418327,
329
+ "grad_norm": 1.0903550386428833,
330
+ "learning_rate": 1.4941402600508558e-05,
331
+ "loss": 1.128015398979187,
332
+ "step": 92
333
+ },
334
+ {
335
+ "epoch": 0.3745019920318725,
336
+ "grad_norm": 0.4805486798286438,
337
+ "learning_rate": 1.4935405964018128e-05,
338
+ "loss": 1.2455147504806519,
339
+ "step": 94
340
+ },
341
+ {
342
+ "epoch": 0.38247011952191234,
343
+ "grad_norm": 0.7429084181785583,
344
+ "learning_rate": 1.4929118724491996e-05,
345
+ "loss": 1.1041914224624634,
346
+ "step": 96
347
+ },
348
+ {
349
+ "epoch": 0.3904382470119522,
350
+ "grad_norm": 0.27306675910949707,
351
+ "learning_rate": 1.4922541155225586e-05,
352
+ "loss": 1.2655969858169556,
353
+ "step": 98
354
+ },
355
+ {
356
+ "epoch": 0.398406374501992,
357
+ "grad_norm": 0.41318008303642273,
358
+ "learning_rate": 1.4915673542134462e-05,
359
+ "loss": 0.8851726651191711,
360
+ "step": 100
361
+ },
362
+ {
363
+ "epoch": 0.4063745019920319,
364
+ "grad_norm": 0.4386235773563385,
365
+ "learning_rate": 1.4908516183741889e-05,
366
+ "loss": 1.265491008758545,
367
+ "step": 102
368
+ },
369
+ {
370
+ "epoch": 0.41434262948207173,
371
+ "grad_norm": 0.6781812906265259,
372
+ "learning_rate": 1.4901069391165857e-05,
373
+ "loss": 0.8081492185592651,
374
+ "step": 104
375
+ },
376
+ {
377
+ "epoch": 0.42231075697211157,
378
+ "grad_norm": 1.4451416730880737,
379
+ "learning_rate": 1.4893333488105559e-05,
380
+ "loss": 0.7170528173446655,
381
+ "step": 106
382
+ },
383
+ {
384
+ "epoch": 0.4302788844621514,
385
+ "grad_norm": 0.6063726544380188,
386
+ "learning_rate": 1.4885308810827328e-05,
387
+ "loss": 0.9935809969902039,
388
+ "step": 108
389
+ },
390
+ {
391
+ "epoch": 0.43824701195219123,
392
+ "grad_norm": 0.40737852454185486,
393
+ "learning_rate": 1.4876995708150003e-05,
394
+ "loss": 1.2845995426177979,
395
+ "step": 110
396
+ },
397
+ {
398
+ "epoch": 0.44621513944223107,
399
+ "grad_norm": 0.4796580374240875,
400
+ "learning_rate": 1.4868394541429784e-05,
401
+ "loss": 0.8904252052307129,
402
+ "step": 112
403
+ },
404
+ {
405
+ "epoch": 0.4541832669322709,
406
+ "grad_norm": 3.001218318939209,
407
+ "learning_rate": 1.4859505684544512e-05,
408
+ "loss": 1.1530516147613525,
409
+ "step": 114
410
+ },
411
+ {
412
+ "epoch": 0.46215139442231074,
413
+ "grad_norm": 0.4466836452484131,
414
+ "learning_rate": 1.4850329523877425e-05,
415
+ "loss": 1.2753629684448242,
416
+ "step": 116
417
+ },
418
+ {
419
+ "epoch": 0.4701195219123506,
420
+ "grad_norm": 0.28066951036453247,
421
+ "learning_rate": 1.4840866458300357e-05,
422
+ "loss": 1.3401973247528076,
423
+ "step": 118
424
+ },
425
+ {
426
+ "epoch": 0.47808764940239046,
427
+ "grad_norm": 0.2835182249546051,
428
+ "learning_rate": 1.4831116899156402e-05,
429
+ "loss": 1.2199780941009521,
430
+ "step": 120
431
+ },
432
+ {
433
+ "epoch": 0.4860557768924303,
434
+ "grad_norm": 0.36116963624954224,
435
+ "learning_rate": 1.4821081270242039e-05,
436
+ "loss": 0.9814391136169434,
437
+ "step": 122
438
+ },
439
+ {
440
+ "epoch": 0.4940239043824701,
441
+ "grad_norm": 0.6912099123001099,
442
+ "learning_rate": 1.48107600077887e-05,
443
+ "loss": 1.0494424104690552,
444
+ "step": 124
445
+ },
446
+ {
447
+ "epoch": 0.50199203187251,
448
+ "grad_norm": 0.8504573702812195,
449
+ "learning_rate": 1.480015356044381e-05,
450
+ "loss": 0.9379956126213074,
451
+ "step": 126
452
+ },
453
+ {
454
+ "epoch": 0.5099601593625498,
455
+ "grad_norm": 0.5862733125686646,
456
+ "learning_rate": 1.4789262389251301e-05,
457
+ "loss": 1.2821743488311768,
458
+ "step": 128
459
+ },
460
+ {
461
+ "epoch": 0.5179282868525896,
462
+ "grad_norm": 0.5818023681640625,
463
+ "learning_rate": 1.4778086967631548e-05,
464
+ "loss": 0.9355220198631287,
465
+ "step": 130
466
+ },
467
+ {
468
+ "epoch": 0.5258964143426295,
469
+ "grad_norm": 0.31655120849609375,
470
+ "learning_rate": 1.4766627781360796e-05,
471
+ "loss": 0.826532244682312,
472
+ "step": 132
473
+ },
474
+ {
475
+ "epoch": 0.5338645418326693,
476
+ "grad_norm": 0.5141142010688782,
477
+ "learning_rate": 1.4754885328550062e-05,
478
+ "loss": 0.9170287251472473,
479
+ "step": 134
480
+ },
481
+ {
482
+ "epoch": 0.5418326693227091,
483
+ "grad_norm": 0.47723662853240967,
484
+ "learning_rate": 1.4742860119623458e-05,
485
+ "loss": 1.3180201053619385,
486
+ "step": 136
487
+ },
488
+ {
489
+ "epoch": 0.549800796812749,
490
+ "grad_norm": 0.32824379205703735,
491
+ "learning_rate": 1.473055267729602e-05,
492
+ "loss": 0.9599122405052185,
493
+ "step": 138
494
+ },
495
+ {
496
+ "epoch": 0.5577689243027888,
497
+ "grad_norm": 1.1303349733352661,
498
+ "learning_rate": 1.4717963536550988e-05,
499
+ "loss": 1.0953630208969116,
500
+ "step": 140
501
+ },
502
+ {
503
+ "epoch": 0.5657370517928287,
504
+ "grad_norm": 0.49718862771987915,
505
+ "learning_rate": 1.470509324461653e-05,
506
+ "loss": 1.0326279401779175,
507
+ "step": 142
508
+ },
509
+ {
510
+ "epoch": 0.5737051792828686,
511
+ "grad_norm": 0.2485317885875702,
512
+ "learning_rate": 1.4691942360941986e-05,
513
+ "loss": 1.2258632183074951,
514
+ "step": 144
515
+ },
516
+ {
517
+ "epoch": 0.5816733067729084,
518
+ "grad_norm": 3.5433390140533447,
519
+ "learning_rate": 1.4678511457173523e-05,
520
+ "loss": 1.202100396156311,
521
+ "step": 146
522
+ },
523
+ {
524
+ "epoch": 0.5896414342629482,
525
+ "grad_norm": 0.3908817172050476,
526
+ "learning_rate": 1.4664801117129303e-05,
527
+ "loss": 0.9758645296096802,
528
+ "step": 148
529
+ },
530
+ {
531
+ "epoch": 0.5976095617529881,
532
+ "grad_norm": 0.5502234697341919,
533
+ "learning_rate": 1.4650811936774093e-05,
534
+ "loss": 0.9454991817474365,
535
+ "step": 150
536
+ },
537
+ {
538
+ "epoch": 0.6055776892430279,
539
+ "grad_norm": 4.790173530578613,
540
+ "learning_rate": 1.4636544524193378e-05,
541
+ "loss": 0.9398374557495117,
542
+ "step": 152
543
+ },
544
+ {
545
+ "epoch": 0.6135458167330677,
546
+ "grad_norm": 0.638011634349823,
547
+ "learning_rate": 1.46219994995669e-05,
548
+ "loss": 1.090728998184204,
549
+ "step": 154
550
+ },
551
+ {
552
+ "epoch": 0.6215139442231076,
553
+ "grad_norm": 2.4593403339385986,
554
+ "learning_rate": 1.4607177495141734e-05,
555
+ "loss": 1.1246390342712402,
556
+ "step": 156
557
+ },
558
+ {
559
+ "epoch": 0.6294820717131474,
560
+ "grad_norm": 0.8616807460784912,
561
+ "learning_rate": 1.4592079155204776e-05,
562
+ "loss": 1.1782993078231812,
563
+ "step": 158
564
+ },
565
+ {
566
+ "epoch": 0.6374501992031872,
567
+ "grad_norm": 0.2915763854980469,
568
+ "learning_rate": 1.457670513605475e-05,
569
+ "loss": 1.0174801349639893,
570
+ "step": 160
571
+ },
572
+ {
573
+ "epoch": 0.6454183266932271,
574
+ "grad_norm": 0.27435067296028137,
575
+ "learning_rate": 1.4561056105973688e-05,
576
+ "loss": 0.8091227412223816,
577
+ "step": 162
578
+ },
579
+ {
580
+ "epoch": 0.6533864541832669,
581
+ "grad_norm": 0.2575240731239319,
582
+ "learning_rate": 1.4545132745197857e-05,
583
+ "loss": 1.1529077291488647,
584
+ "step": 164
585
+ },
586
+ {
587
+ "epoch": 0.6613545816733067,
588
+ "grad_norm": 0.777723491191864,
589
+ "learning_rate": 1.4528935745888218e-05,
590
+ "loss": 0.8908942937850952,
591
+ "step": 166
592
+ },
593
+ {
594
+ "epoch": 0.6693227091633466,
595
+ "grad_norm": 0.2517397105693817,
596
+ "learning_rate": 1.4512465812100317e-05,
597
+ "loss": 1.2097852230072021,
598
+ "step": 168
599
+ },
600
+ {
601
+ "epoch": 0.6772908366533864,
602
+ "grad_norm": 3.4033937454223633,
603
+ "learning_rate": 1.4495723659753695e-05,
604
+ "loss": 1.2028913497924805,
605
+ "step": 170
606
+ },
607
+ {
608
+ "epoch": 0.6852589641434262,
609
+ "grad_norm": 0.3606719374656677,
610
+ "learning_rate": 1.447871001660076e-05,
611
+ "loss": 0.8955773115158081,
612
+ "step": 172
613
+ },
614
+ {
615
+ "epoch": 0.6932270916334662,
616
+ "grad_norm": 0.2552003860473633,
617
+ "learning_rate": 1.4461425622195157e-05,
618
+ "loss": 1.2185531854629517,
619
+ "step": 174
620
+ },
621
+ {
622
+ "epoch": 0.701195219123506,
623
+ "grad_norm": 1.0111852884292603,
624
+ "learning_rate": 1.4443871227859621e-05,
625
+ "loss": 0.7776660919189453,
626
+ "step": 176
627
+ },
628
+ {
629
+ "epoch": 0.7091633466135459,
630
+ "grad_norm": 0.7659691572189331,
631
+ "learning_rate": 1.4426047596653316e-05,
632
+ "loss": 0.9216206669807434,
633
+ "step": 178
634
+ },
635
+ {
636
+ "epoch": 0.7171314741035857,
637
+ "grad_norm": 1.132752776145935,
638
+ "learning_rate": 1.4407955503338663e-05,
639
+ "loss": 1.0899910926818848,
640
+ "step": 180
641
+ },
642
+ {
643
+ "epoch": 0.7250996015936255,
644
+ "grad_norm": 0.16658742725849152,
645
+ "learning_rate": 1.4389595734347675e-05,
646
+ "loss": 0.5195258855819702,
647
+ "step": 182
648
+ },
649
+ {
650
+ "epoch": 0.7330677290836654,
651
+ "grad_norm": 0.6180145144462585,
652
+ "learning_rate": 1.4370969087747755e-05,
653
+ "loss": 1.3304177522659302,
654
+ "step": 184
655
+ },
656
+ {
657
+ "epoch": 0.7410358565737052,
658
+ "grad_norm": 0.35436052083969116,
659
+ "learning_rate": 1.4352076373207023e-05,
660
+ "loss": 1.2653801441192627,
661
+ "step": 186
662
+ },
663
+ {
664
+ "epoch": 0.749003984063745,
665
+ "grad_norm": 0.2843472361564636,
666
+ "learning_rate": 1.4332918411959106e-05,
667
+ "loss": 1.1138914823532104,
668
+ "step": 188
669
+ },
670
+ {
671
+ "epoch": 0.7569721115537849,
672
+ "grad_norm": 1.0151716470718384,
673
+ "learning_rate": 1.4313496036767444e-05,
674
+ "loss": 0.8904833197593689,
675
+ "step": 190
676
+ },
677
+ {
678
+ "epoch": 0.7649402390438247,
679
+ "grad_norm": 0.7267096042633057,
680
+ "learning_rate": 1.4293810091889105e-05,
681
+ "loss": 1.2340463399887085,
682
+ "step": 192
683
+ },
684
+ {
685
+ "epoch": 0.7729083665338645,
686
+ "grad_norm": 0.47353217005729675,
687
+ "learning_rate": 1.4273861433038063e-05,
688
+ "loss": 0.9082501530647278,
689
+ "step": 194
690
+ },
691
+ {
692
+ "epoch": 0.7808764940239044,
693
+ "grad_norm": 0.9817029237747192,
694
+ "learning_rate": 1.425365092734802e-05,
695
+ "loss": 0.663750946521759,
696
+ "step": 196
697
+ },
698
+ {
699
+ "epoch": 0.7888446215139442,
700
+ "grad_norm": 0.7875825762748718,
701
+ "learning_rate": 1.423317945333471e-05,
702
+ "loss": 0.7919776439666748,
703
+ "step": 198
704
+ },
705
+ {
706
+ "epoch": 0.796812749003984,
707
+ "grad_norm": 0.5649994015693665,
708
+ "learning_rate": 1.4212447900857703e-05,
709
+ "loss": 1.0543051958084106,
710
+ "step": 200
711
+ },
712
+ {
713
+ "epoch": 0.8047808764940239,
714
+ "grad_norm": 0.1523721069097519,
715
+ "learning_rate": 1.4191457171081736e-05,
716
+ "loss": 1.0212864875793457,
717
+ "step": 202
718
+ },
719
+ {
720
+ "epoch": 0.8127490039840638,
721
+ "grad_norm": 0.28413787484169006,
722
+ "learning_rate": 1.417020817643753e-05,
723
+ "loss": 1.5364233255386353,
724
+ "step": 204
725
+ },
726
+ {
727
+ "epoch": 0.8207171314741036,
728
+ "grad_norm": 0.2831563651561737,
729
+ "learning_rate": 1.4148701840582129e-05,
730
+ "loss": 1.2227693796157837,
731
+ "step": 206
732
+ },
733
+ {
734
+ "epoch": 0.8286852589641435,
735
+ "grad_norm": 2.0232136249542236,
736
+ "learning_rate": 1.412693909835877e-05,
737
+ "loss": 0.7362918853759766,
738
+ "step": 208
739
+ },
740
+ {
741
+ "epoch": 0.8366533864541833,
742
+ "grad_norm": 0.6372008323669434,
743
+ "learning_rate": 1.4104920895756216e-05,
744
+ "loss": 1.265373945236206,
745
+ "step": 210
746
+ },
747
+ {
748
+ "epoch": 0.8446215139442231,
749
+ "grad_norm": 0.22620588541030884,
750
+ "learning_rate": 1.4082648189867656e-05,
751
+ "loss": 1.2132854461669922,
752
+ "step": 212
753
+ },
754
+ {
755
+ "epoch": 0.852589641434263,
756
+ "grad_norm": 0.287081241607666,
757
+ "learning_rate": 1.4060121948849098e-05,
758
+ "loss": 0.9602269530296326,
759
+ "step": 214
760
+ },
761
+ {
762
+ "epoch": 0.8605577689243028,
763
+ "grad_norm": 0.8160057067871094,
764
+ "learning_rate": 1.4037343151877285e-05,
765
+ "loss": 1.452444076538086,
766
+ "step": 216
767
+ },
768
+ {
769
+ "epoch": 0.8685258964143426,
770
+ "grad_norm": 1.8605669736862183,
771
+ "learning_rate": 1.4014312789107124e-05,
772
+ "loss": 1.3142669200897217,
773
+ "step": 218
774
+ },
775
+ {
776
+ "epoch": 0.8764940239043825,
777
+ "grad_norm": 0.28666868805885315,
778
+ "learning_rate": 1.3991031861628662e-05,
779
+ "loss": 1.2287095785140991,
780
+ "step": 220
781
+ },
782
+ {
783
+ "epoch": 0.8844621513944223,
784
+ "grad_norm": 0.29921239614486694,
785
+ "learning_rate": 1.3967501381423552e-05,
786
+ "loss": 1.48736572265625,
787
+ "step": 222
788
+ },
789
+ {
790
+ "epoch": 0.8924302788844621,
791
+ "grad_norm": 1.2563499212265015,
792
+ "learning_rate": 1.3943722371321075e-05,
793
+ "loss": 0.9397075176239014,
794
+ "step": 224
795
+ },
796
+ {
797
+ "epoch": 0.900398406374502,
798
+ "grad_norm": 0.39466801285743713,
799
+ "learning_rate": 1.3919695864953679e-05,
800
+ "loss": 1.0238375663757324,
801
+ "step": 226
802
+ },
803
+ {
804
+ "epoch": 0.9083665338645418,
805
+ "grad_norm": 2.8415801525115967,
806
+ "learning_rate": 1.3895422906712042e-05,
807
+ "loss": 1.1098148822784424,
808
+ "step": 228
809
+ },
810
+ {
811
+ "epoch": 0.9163346613545816,
812
+ "grad_norm": 0.6246854662895203,
813
+ "learning_rate": 1.3870904551699686e-05,
814
+ "loss": 1.1869398355484009,
815
+ "step": 230
816
+ },
817
+ {
818
+ "epoch": 0.9243027888446215,
819
+ "grad_norm": 0.308601975440979,
820
+ "learning_rate": 1.38461418656871e-05,
821
+ "loss": 1.3266777992248535,
822
+ "step": 232
823
+ },
824
+ {
825
+ "epoch": 0.9322709163346613,
826
+ "grad_norm": 0.3320607841014862,
827
+ "learning_rate": 1.3821135925065423e-05,
828
+ "loss": 0.8920221924781799,
829
+ "step": 234
830
+ },
831
+ {
832
+ "epoch": 0.9402390438247012,
833
+ "grad_norm": 0.2533508837223053,
834
+ "learning_rate": 1.3795887816799647e-05,
835
+ "loss": 0.8552533984184265,
836
+ "step": 236
837
+ },
838
+ {
839
+ "epoch": 0.9482071713147411,
840
+ "grad_norm": 0.37766775488853455,
841
+ "learning_rate": 1.3770398638381374e-05,
842
+ "loss": 0.5838753581047058,
843
+ "step": 238
844
+ },
845
+ {
846
+ "epoch": 0.9561752988047809,
847
+ "grad_norm": 0.5343811511993408,
848
+ "learning_rate": 1.3744669497781111e-05,
849
+ "loss": 0.8912972807884216,
850
+ "step": 240
851
+ },
852
+ {
853
+ "epoch": 0.9641434262948207,
854
+ "grad_norm": 0.5110613107681274,
855
+ "learning_rate": 1.3718701513400104e-05,
856
+ "loss": 1.1340361833572388,
857
+ "step": 242
858
+ },
859
+ {
860
+ "epoch": 0.9721115537848606,
861
+ "grad_norm": 0.34986478090286255,
862
+ "learning_rate": 1.369249581402173e-05,
863
+ "loss": 1.2093524932861328,
864
+ "step": 244
865
+ },
866
+ {
867
+ "epoch": 0.9800796812749004,
868
+ "grad_norm": 0.6902351975440979,
869
+ "learning_rate": 1.3666053538762414e-05,
870
+ "loss": 0.973604142665863,
871
+ "step": 246
872
+ },
873
+ {
874
+ "epoch": 0.9880478087649402,
875
+ "grad_norm": 0.364798903465271,
876
+ "learning_rate": 1.363937583702214e-05,
877
+ "loss": 1.004298448562622,
878
+ "step": 248
879
+ },
880
+ {
881
+ "epoch": 0.9960159362549801,
882
+ "grad_norm": 0.594591498374939,
883
+ "learning_rate": 1.3612463868434462e-05,
884
+ "loss": 1.005676031112671,
885
+ "step": 250
886
+ },
887
+ {
888
+ "epoch": 1.00398406374502,
889
+ "grad_norm": 0.9396325349807739,
890
+ "learning_rate": 1.3585318802816118e-05,
891
+ "loss": 0.9656413197517395,
892
+ "step": 252
893
+ },
894
+ {
895
+ "epoch": 1.0119521912350598,
896
+ "grad_norm": 0.5345960855484009,
897
+ "learning_rate": 1.3557941820116163e-05,
898
+ "loss": 0.7036761045455933,
899
+ "step": 254
900
+ },
901
+ {
902
+ "epoch": 1.0199203187250996,
903
+ "grad_norm": 0.8415208458900452,
904
+ "learning_rate": 1.3530334110364691e-05,
905
+ "loss": 1.0861495733261108,
906
+ "step": 256
907
+ },
908
+ {
909
+ "epoch": 1.0278884462151394,
910
+ "grad_norm": 0.4500897228717804,
911
+ "learning_rate": 1.35024968736211e-05,
912
+ "loss": 1.0180453062057495,
913
+ "step": 258
914
+ },
915
+ {
916
+ "epoch": 1.0358565737051793,
917
+ "grad_norm": 0.3588436245918274,
918
+ "learning_rate": 1.3474431319921936e-05,
919
+ "loss": 0.9354724884033203,
920
+ "step": 260
921
+ },
922
+ {
923
+ "epoch": 1.043824701195219,
924
+ "grad_norm": 0.3891165852546692,
925
+ "learning_rate": 1.3446138669228274e-05,
926
+ "loss": 0.9144407510757446,
927
+ "step": 262
928
+ },
929
+ {
930
+ "epoch": 1.051792828685259,
931
+ "grad_norm": 1.5371865034103394,
932
+ "learning_rate": 1.3417620151372716e-05,
933
+ "loss": 0.9848403930664062,
934
+ "step": 264
935
+ },
936
+ {
937
+ "epoch": 1.0597609561752988,
938
+ "grad_norm": 0.6903578639030457,
939
+ "learning_rate": 1.3388877006005911e-05,
940
+ "loss": 0.6154371500015259,
941
+ "step": 266
942
+ },
943
+ {
944
+ "epoch": 1.0677290836653386,
945
+ "grad_norm": 0.19243323802947998,
946
+ "learning_rate": 1.3359910482542686e-05,
947
+ "loss": 0.8479989171028137,
948
+ "step": 268
949
+ },
950
+ {
951
+ "epoch": 1.0756972111553784,
952
+ "grad_norm": 0.5195255279541016,
953
+ "learning_rate": 1.3330721840107718e-05,
954
+ "loss": 0.5587765574455261,
955
+ "step": 270
956
+ },
957
+ {
958
+ "epoch": 1.0836653386454183,
959
+ "grad_norm": 0.3604806661605835,
960
+ "learning_rate": 1.3301312347480817e-05,
961
+ "loss": 1.1884621381759644,
962
+ "step": 272
963
+ },
964
+ {
965
+ "epoch": 1.091633466135458,
966
+ "grad_norm": 1.2894952297210693,
967
+ "learning_rate": 1.3271683283041767e-05,
968
+ "loss": 0.625873863697052,
969
+ "step": 274
970
+ },
971
+ {
972
+ "epoch": 1.099601593625498,
973
+ "grad_norm": 0.27667495608329773,
974
+ "learning_rate": 1.3241835934714759e-05,
975
+ "loss": 0.7773606181144714,
976
+ "step": 276
977
+ },
978
+ {
979
+ "epoch": 1.1075697211155378,
980
+ "grad_norm": 0.23738747835159302,
981
+ "learning_rate": 1.3211771599912408e-05,
982
+ "loss": 0.7299227714538574,
983
+ "step": 278
984
+ },
985
+ {
986
+ "epoch": 1.1155378486055776,
987
+ "grad_norm": 0.3089618980884552,
988
+ "learning_rate": 1.3181491585479354e-05,
989
+ "loss": 0.8809335231781006,
990
+ "step": 280
991
+ },
992
+ {
993
+ "epoch": 1.1235059760956174,
994
+ "grad_norm": 0.25363025069236755,
995
+ "learning_rate": 1.3150997207635463e-05,
996
+ "loss": 1.0729031562805176,
997
+ "step": 282
998
+ },
999
+ {
1000
+ "epoch": 1.1314741035856573,
1001
+ "grad_norm": 0.47339093685150146,
1002
+ "learning_rate": 1.31202897919186e-05,
1003
+ "loss": 1.0833154916763306,
1004
+ "step": 284
1005
+ },
1006
+ {
1007
+ "epoch": 1.139442231075697,
1008
+ "grad_norm": 0.18187947571277618,
1009
+ "learning_rate": 1.3089370673127026e-05,
1010
+ "loss": 0.3476455509662628,
1011
+ "step": 286
1012
+ },
1013
+ {
1014
+ "epoch": 1.1474103585657371,
1015
+ "grad_norm": 0.226917564868927,
1016
+ "learning_rate": 1.3058241195261357e-05,
1017
+ "loss": 0.6067731976509094,
1018
+ "step": 288
1019
+ },
1020
+ {
1021
+ "epoch": 1.155378486055777,
1022
+ "grad_norm": 1.2993286848068237,
1023
+ "learning_rate": 1.3026902711466169e-05,
1024
+ "loss": 0.8683360815048218,
1025
+ "step": 290
1026
+ },
1027
+ {
1028
+ "epoch": 1.1633466135458168,
1029
+ "grad_norm": 0.4915187954902649,
1030
+ "learning_rate": 1.2995356583971152e-05,
1031
+ "loss": 0.6069297790527344,
1032
+ "step": 292
1033
+ },
1034
+ {
1035
+ "epoch": 1.1713147410358566,
1036
+ "grad_norm": 0.24846410751342773,
1037
+ "learning_rate": 1.2963604184031913e-05,
1038
+ "loss": 1.096907615661621,
1039
+ "step": 294
1040
+ },
1041
+ {
1042
+ "epoch": 1.1792828685258965,
1043
+ "grad_norm": 0.40995633602142334,
1044
+ "learning_rate": 1.2931646891870371e-05,
1045
+ "loss": 1.1847357749938965,
1046
+ "step": 296
1047
+ },
1048
+ {
1049
+ "epoch": 1.1872509960159363,
1050
+ "grad_norm": 0.42281821370124817,
1051
+ "learning_rate": 1.2899486096614742e-05,
1052
+ "loss": 1.1937490701675415,
1053
+ "step": 298
1054
+ },
1055
+ {
1056
+ "epoch": 1.1952191235059761,
1057
+ "grad_norm": 0.5707376003265381,
1058
+ "learning_rate": 1.2867123196239186e-05,
1059
+ "loss": 0.5830255746841431,
1060
+ "step": 300
1061
+ },
1062
+ {
1063
+ "epoch": 1.203187250996016,
1064
+ "grad_norm": 0.5589886903762817,
1065
+ "learning_rate": 1.2834559597503008e-05,
1066
+ "loss": 0.8486528992652893,
1067
+ "step": 302
1068
+ },
1069
+ {
1070
+ "epoch": 1.2111553784860558,
1071
+ "grad_norm": 0.4859887361526489,
1072
+ "learning_rate": 1.2801796715889535e-05,
1073
+ "loss": 0.7010272145271301,
1074
+ "step": 304
1075
+ },
1076
+ {
1077
+ "epoch": 1.2191235059760956,
1078
+ "grad_norm": 0.3184964060783386,
1079
+ "learning_rate": 1.2768835975544572e-05,
1080
+ "loss": 1.087632179260254,
1081
+ "step": 306
1082
+ },
1083
+ {
1084
+ "epoch": 1.2270916334661355,
1085
+ "grad_norm": 0.6567210555076599,
1086
+ "learning_rate": 1.2735678809214497e-05,
1087
+ "loss": 0.8818908333778381,
1088
+ "step": 308
1089
+ },
1090
+ {
1091
+ "epoch": 1.2350597609561753,
1092
+ "grad_norm": 0.8336063027381897,
1093
+ "learning_rate": 1.270232665818399e-05,
1094
+ "loss": 1.1307973861694336,
1095
+ "step": 310
1096
+ },
1097
+ {
1098
+ "epoch": 1.2430278884462151,
1099
+ "grad_norm": 0.46054601669311523,
1100
+ "learning_rate": 1.266878097221338e-05,
1101
+ "loss": 1.0041382312774658,
1102
+ "step": 312
1103
+ },
1104
+ {
1105
+ "epoch": 1.250996015936255,
1106
+ "grad_norm": 1.004090666770935,
1107
+ "learning_rate": 1.263504320947562e-05,
1108
+ "loss": 0.8790667057037354,
1109
+ "step": 314
1110
+ },
1111
+ {
1112
+ "epoch": 1.2589641434262948,
1113
+ "grad_norm": 0.6220927834510803,
1114
+ "learning_rate": 1.2601114836492917e-05,
1115
+ "loss": 0.7389086484909058,
1116
+ "step": 316
1117
+ },
1118
+ {
1119
+ "epoch": 1.2669322709163346,
1120
+ "grad_norm": 1.0630143880844116,
1121
+ "learning_rate": 1.2566997328072966e-05,
1122
+ "loss": 0.6448332667350769,
1123
+ "step": 318
1124
+ },
1125
+ {
1126
+ "epoch": 1.2749003984063745,
1127
+ "grad_norm": 0.4616350829601288,
1128
+ "learning_rate": 1.2532692167244852e-05,
1129
+ "loss": 0.5268493890762329,
1130
+ "step": 320
1131
+ },
1132
+ {
1133
+ "epoch": 1.2828685258964143,
1134
+ "grad_norm": 3.0412392616271973,
1135
+ "learning_rate": 1.2498200845194596e-05,
1136
+ "loss": 0.9104723930358887,
1137
+ "step": 322
1138
+ },
1139
+ {
1140
+ "epoch": 1.2908366533864541,
1141
+ "grad_norm": 0.4327695369720459,
1142
+ "learning_rate": 1.2463524861200316e-05,
1143
+ "loss": 0.8771180510520935,
1144
+ "step": 324
1145
+ },
1146
+ {
1147
+ "epoch": 1.298804780876494,
1148
+ "grad_norm": 0.6371755599975586,
1149
+ "learning_rate": 1.2428665722567073e-05,
1150
+ "loss": 1.1892993450164795,
1151
+ "step": 326
1152
+ },
1153
+ {
1154
+ "epoch": 1.3067729083665338,
1155
+ "grad_norm": 0.503496527671814,
1156
+ "learning_rate": 1.2393624944561334e-05,
1157
+ "loss": 0.7128881216049194,
1158
+ "step": 328
1159
+ },
1160
+ {
1161
+ "epoch": 1.3147410358565736,
1162
+ "grad_norm": 0.43169552087783813,
1163
+ "learning_rate": 1.2358404050345122e-05,
1164
+ "loss": 0.7095832824707031,
1165
+ "step": 330
1166
+ },
1167
+ {
1168
+ "epoch": 1.3227091633466135,
1169
+ "grad_norm": 0.5526296496391296,
1170
+ "learning_rate": 1.2323004570909798e-05,
1171
+ "loss": 0.8684831261634827,
1172
+ "step": 332
1173
+ },
1174
+ {
1175
+ "epoch": 1.3306772908366533,
1176
+ "grad_norm": 1.0183297395706177,
1177
+ "learning_rate": 1.2287428045009517e-05,
1178
+ "loss": 0.665216863155365,
1179
+ "step": 334
1180
+ },
1181
+ {
1182
+ "epoch": 1.3386454183266931,
1183
+ "grad_norm": 0.7202191352844238,
1184
+ "learning_rate": 1.2251676019094331e-05,
1185
+ "loss": 0.8956350684165955,
1186
+ "step": 336
1187
+ },
1188
+ {
1189
+ "epoch": 1.3466135458167332,
1190
+ "grad_norm": 0.38658207654953003,
1191
+ "learning_rate": 1.2215750047242982e-05,
1192
+ "loss": 1.0827162265777588,
1193
+ "step": 338
1194
+ },
1195
+ {
1196
+ "epoch": 1.354581673306773,
1197
+ "grad_norm": 0.2367570847272873,
1198
+ "learning_rate": 1.2179651691095329e-05,
1199
+ "loss": 1.0241369009017944,
1200
+ "step": 340
1201
+ },
1202
+ {
1203
+ "epoch": 1.3625498007968129,
1204
+ "grad_norm": 0.3254954218864441,
1205
+ "learning_rate": 1.2143382519784498e-05,
1206
+ "loss": 1.1053788661956787,
1207
+ "step": 342
1208
+ },
1209
+ {
1210
+ "epoch": 1.3705179282868527,
1211
+ "grad_norm": 0.25897926092147827,
1212
+ "learning_rate": 1.2106944109868636e-05,
1213
+ "loss": 1.037227988243103,
1214
+ "step": 344
1215
+ },
1216
+ {
1217
+ "epoch": 1.3784860557768925,
1218
+ "grad_norm": 0.4815937876701355,
1219
+ "learning_rate": 1.2070338045262406e-05,
1220
+ "loss": 0.7165056467056274,
1221
+ "step": 346
1222
+ },
1223
+ {
1224
+ "epoch": 1.3864541832669324,
1225
+ "grad_norm": 0.2625236213207245,
1226
+ "learning_rate": 1.2033565917168133e-05,
1227
+ "loss": 1.0718673467636108,
1228
+ "step": 348
1229
+ },
1230
+ {
1231
+ "epoch": 1.3944223107569722,
1232
+ "grad_norm": 0.4188198447227478,
1233
+ "learning_rate": 1.1996629324006632e-05,
1234
+ "loss": 0.6164529323577881,
1235
+ "step": 350
1236
+ },
1237
+ {
1238
+ "epoch": 1.402390438247012,
1239
+ "grad_norm": 0.25191178917884827,
1240
+ "learning_rate": 1.195952987134773e-05,
1241
+ "loss": 1.0730476379394531,
1242
+ "step": 352
1243
+ },
1244
+ {
1245
+ "epoch": 1.4103585657370519,
1246
+ "grad_norm": 0.5282136797904968,
1247
+ "learning_rate": 1.1922269171840477e-05,
1248
+ "loss": 1.1133763790130615,
1249
+ "step": 354
1250
+ },
1251
+ {
1252
+ "epoch": 1.4183266932270917,
1253
+ "grad_norm": 0.39372941851615906,
1254
+ "learning_rate": 1.1884848845143039e-05,
1255
+ "loss": 0.9437786936759949,
1256
+ "step": 356
1257
+ },
1258
+ {
1259
+ "epoch": 1.4262948207171315,
1260
+ "grad_norm": 0.27430135011672974,
1261
+ "learning_rate": 1.1847270517852312e-05,
1262
+ "loss": 1.101191759109497,
1263
+ "step": 358
1264
+ },
1265
+ {
1266
+ "epoch": 1.4342629482071714,
1267
+ "grad_norm": 0.4338213801383972,
1268
+ "learning_rate": 1.180953582343319e-05,
1269
+ "loss": 0.5615993738174438,
1270
+ "step": 360
1271
+ },
1272
+ {
1273
+ "epoch": 1.4422310756972112,
1274
+ "grad_norm": 0.20297643542289734,
1275
+ "learning_rate": 1.177164640214758e-05,
1276
+ "loss": 0.648676335811615,
1277
+ "step": 362
1278
+ },
1279
+ {
1280
+ "epoch": 1.450199203187251,
1281
+ "grad_norm": 0.43412458896636963,
1282
+ "learning_rate": 1.1733603900983107e-05,
1283
+ "loss": 0.9797654747962952,
1284
+ "step": 364
1285
+ },
1286
+ {
1287
+ "epoch": 1.4581673306772909,
1288
+ "grad_norm": 0.27069559693336487,
1289
+ "learning_rate": 1.1695409973581504e-05,
1290
+ "loss": 1.0201314687728882,
1291
+ "step": 366
1292
+ },
1293
+ {
1294
+ "epoch": 1.4661354581673307,
1295
+ "grad_norm": 0.21320168673992157,
1296
+ "learning_rate": 1.1657066280166745e-05,
1297
+ "loss": 0.5693846940994263,
1298
+ "step": 368
1299
+ },
1300
+ {
1301
+ "epoch": 1.4741035856573705,
1302
+ "grad_norm": 0.609273374080658,
1303
+ "learning_rate": 1.1618574487472867e-05,
1304
+ "loss": 0.6598872542381287,
1305
+ "step": 370
1306
+ },
1307
+ {
1308
+ "epoch": 1.4820717131474104,
1309
+ "grad_norm": 1.0151580572128296,
1310
+ "learning_rate": 1.1579936268671537e-05,
1311
+ "loss": 1.1873997449874878,
1312
+ "step": 372
1313
+ },
1314
+ {
1315
+ "epoch": 1.4900398406374502,
1316
+ "grad_norm": 0.5126774907112122,
1317
+ "learning_rate": 1.1541153303299305e-05,
1318
+ "loss": 1.0114318132400513,
1319
+ "step": 374
1320
+ },
1321
+ {
1322
+ "epoch": 1.49800796812749,
1323
+ "grad_norm": 0.4790279269218445,
1324
+ "learning_rate": 1.1502227277184605e-05,
1325
+ "loss": 1.0180116891860962,
1326
+ "step": 376
1327
+ },
1328
+ {
1329
+ "epoch": 1.5059760956175299,
1330
+ "grad_norm": 3.794914722442627,
1331
+ "learning_rate": 1.1463159882374477e-05,
1332
+ "loss": 0.8887977004051208,
1333
+ "step": 378
1334
+ },
1335
+ {
1336
+ "epoch": 1.5139442231075697,
1337
+ "grad_norm": 0.2821894884109497,
1338
+ "learning_rate": 1.1423952817061005e-05,
1339
+ "loss": 1.0826634168624878,
1340
+ "step": 380
1341
+ },
1342
+ {
1343
+ "epoch": 1.5219123505976095,
1344
+ "grad_norm": 0.26013344526290894,
1345
+ "learning_rate": 1.1384607785507527e-05,
1346
+ "loss": 0.6501424312591553,
1347
+ "step": 382
1348
+ },
1349
+ {
1350
+ "epoch": 1.5298804780876494,
1351
+ "grad_norm": 0.21201461553573608,
1352
+ "learning_rate": 1.1345126497974507e-05,
1353
+ "loss": 0.6929817795753479,
1354
+ "step": 384
1355
+ },
1356
+ {
1357
+ "epoch": 1.5378486055776892,
1358
+ "grad_norm": 0.603386402130127,
1359
+ "learning_rate": 1.1305510670645247e-05,
1360
+ "loss": 0.9329879879951477,
1361
+ "step": 386
1362
+ },
1363
+ {
1364
+ "epoch": 1.545816733067729,
1365
+ "grad_norm": 0.3552367389202118,
1366
+ "learning_rate": 1.1265762025551246e-05,
1367
+ "loss": 1.1002554893493652,
1368
+ "step": 388
1369
+ },
1370
+ {
1371
+ "epoch": 1.5537848605577689,
1372
+ "grad_norm": 0.8357146382331848,
1373
+ "learning_rate": 1.122588229049737e-05,
1374
+ "loss": 0.5634505152702332,
1375
+ "step": 390
1376
+ },
1377
+ {
1378
+ "epoch": 1.5617529880478087,
1379
+ "grad_norm": 0.9403584003448486,
1380
+ "learning_rate": 1.118587319898673e-05,
1381
+ "loss": 0.6033604145050049,
1382
+ "step": 392
1383
+ },
1384
+ {
1385
+ "epoch": 1.5697211155378485,
1386
+ "grad_norm": 2.087606430053711,
1387
+ "learning_rate": 1.1145736490145346e-05,
1388
+ "loss": 1.0487326383590698,
1389
+ "step": 394
1390
+ },
1391
+ {
1392
+ "epoch": 1.5776892430278884,
1393
+ "grad_norm": 0.7443987727165222,
1394
+ "learning_rate": 1.110547390864654e-05,
1395
+ "loss": 0.9917337894439697,
1396
+ "step": 396
1397
+ },
1398
+ {
1399
+ "epoch": 1.5856573705179282,
1400
+ "grad_norm": 0.4282863438129425,
1401
+ "learning_rate": 1.1065087204635103e-05,
1402
+ "loss": 1.0512839555740356,
1403
+ "step": 398
1404
+ },
1405
+ {
1406
+ "epoch": 1.593625498007968,
1407
+ "grad_norm": 0.6512730121612549,
1408
+ "learning_rate": 1.1024578133651209e-05,
1409
+ "loss": 0.6531898975372314,
1410
+ "step": 400
1411
+ },
1412
+ {
1413
+ "epoch": 1.6015936254980079,
1414
+ "grad_norm": 0.47180187702178955,
1415
+ "learning_rate": 1.0983948456554123e-05,
1416
+ "loss": 1.0244213342666626,
1417
+ "step": 402
1418
+ },
1419
+ {
1420
+ "epoch": 1.6095617529880477,
1421
+ "grad_norm": 0.41504454612731934,
1422
+ "learning_rate": 1.0943199939445644e-05,
1423
+ "loss": 1.141480803489685,
1424
+ "step": 404
1425
+ },
1426
+ {
1427
+ "epoch": 1.6175298804780875,
1428
+ "grad_norm": 0.7667415142059326,
1429
+ "learning_rate": 1.0902334353593342e-05,
1430
+ "loss": 0.6996335387229919,
1431
+ "step": 406
1432
+ },
1433
+ {
1434
+ "epoch": 1.6254980079681274,
1435
+ "grad_norm": 0.23972085118293762,
1436
+ "learning_rate": 1.0861353475353559e-05,
1437
+ "loss": 0.5143875479698181,
1438
+ "step": 408
1439
+ },
1440
+ {
1441
+ "epoch": 1.6334661354581672,
1442
+ "grad_norm": 0.1878281980752945,
1443
+ "learning_rate": 1.08202590860942e-05,
1444
+ "loss": 0.6930667757987976,
1445
+ "step": 410
1446
+ },
1447
+ {
1448
+ "epoch": 1.641434262948207,
1449
+ "grad_norm": 0.3578081429004669,
1450
+ "learning_rate": 1.0779052972117306e-05,
1451
+ "loss": 0.4972156882286072,
1452
+ "step": 412
1453
+ },
1454
+ {
1455
+ "epoch": 1.6494023904382469,
1456
+ "grad_norm": 0.26842987537384033,
1457
+ "learning_rate": 1.0737736924581386e-05,
1458
+ "loss": 0.7380754351615906,
1459
+ "step": 414
1460
+ },
1461
+ {
1462
+ "epoch": 1.6573705179282867,
1463
+ "grad_norm": 0.31403297185897827,
1464
+ "learning_rate": 1.0696312739423573e-05,
1465
+ "loss": 0.7590941190719604,
1466
+ "step": 416
1467
+ },
1468
+ {
1469
+ "epoch": 1.6653386454183265,
1470
+ "grad_norm": 0.5314321517944336,
1471
+ "learning_rate": 1.0654782217281563e-05,
1472
+ "loss": 0.8922839760780334,
1473
+ "step": 418
1474
+ },
1475
+ {
1476
+ "epoch": 1.6733067729083664,
1477
+ "grad_norm": 0.2761631906032562,
1478
+ "learning_rate": 1.0613147163415331e-05,
1479
+ "loss": 1.112337350845337,
1480
+ "step": 420
1481
+ },
1482
+ {
1483
+ "epoch": 1.6812749003984062,
1484
+ "grad_norm": 0.3739781081676483,
1485
+ "learning_rate": 1.0571409387628661e-05,
1486
+ "loss": 0.9243249893188477,
1487
+ "step": 422
1488
+ },
1489
+ {
1490
+ "epoch": 1.6892430278884463,
1491
+ "grad_norm": 0.8964663147926331,
1492
+ "learning_rate": 1.0529570704190493e-05,
1493
+ "loss": 0.5647684335708618,
1494
+ "step": 424
1495
+ },
1496
+ {
1497
+ "epoch": 1.697211155378486,
1498
+ "grad_norm": 0.333854079246521,
1499
+ "learning_rate": 1.0487632931756039e-05,
1500
+ "loss": 1.0856620073318481,
1501
+ "step": 426
1502
+ },
1503
+ {
1504
+ "epoch": 1.705179282868526,
1505
+ "grad_norm": 0.26213064789772034,
1506
+ "learning_rate": 1.0445597893287742e-05,
1507
+ "loss": 1.0230387449264526,
1508
+ "step": 428
1509
+ },
1510
+ {
1511
+ "epoch": 1.7131474103585658,
1512
+ "grad_norm": 0.4736036956310272,
1513
+ "learning_rate": 1.0403467415976025e-05,
1514
+ "loss": 0.6771261692047119,
1515
+ "step": 430
1516
+ },
1517
+ {
1518
+ "epoch": 1.7211155378486056,
1519
+ "grad_norm": 0.8969900608062744,
1520
+ "learning_rate": 1.036124333115988e-05,
1521
+ "loss": 0.8703440427780151,
1522
+ "step": 432
1523
+ },
1524
+ {
1525
+ "epoch": 1.7290836653386454,
1526
+ "grad_norm": 0.9138644337654114,
1527
+ "learning_rate": 1.0318927474247258e-05,
1528
+ "loss": 0.6527059674263,
1529
+ "step": 434
1530
+ },
1531
+ {
1532
+ "epoch": 1.7370517928286853,
1533
+ "grad_norm": 1.2199382781982422,
1534
+ "learning_rate": 1.0276521684635272e-05,
1535
+ "loss": 0.42034152150154114,
1536
+ "step": 436
1537
+ },
1538
+ {
1539
+ "epoch": 1.745019920318725,
1540
+ "grad_norm": 0.753322422504425,
1541
+ "learning_rate": 1.0234027805630263e-05,
1542
+ "loss": 0.8424271941184998,
1543
+ "step": 438
1544
+ },
1545
+ {
1546
+ "epoch": 1.752988047808765,
1547
+ "grad_norm": 0.6605293154716492,
1548
+ "learning_rate": 1.0191447684367665e-05,
1549
+ "loss": 0.6778283715248108,
1550
+ "step": 440
1551
+ },
1552
+ {
1553
+ "epoch": 1.7609561752988048,
1554
+ "grad_norm": 0.8106198310852051,
1555
+ "learning_rate": 1.0148783171731716e-05,
1556
+ "loss": 1.4355847835540771,
1557
+ "step": 442
1558
+ },
1559
+ {
1560
+ "epoch": 1.7689243027888446,
1561
+ "grad_norm": 0.3683789074420929,
1562
+ "learning_rate": 1.0106036122274989e-05,
1563
+ "loss": 0.6579235196113586,
1564
+ "step": 444
1565
+ },
1566
+ {
1567
+ "epoch": 1.7768924302788844,
1568
+ "grad_norm": 0.2205553501844406,
1569
+ "learning_rate": 1.0063208394137804e-05,
1570
+ "loss": 0.9973717927932739,
1571
+ "step": 446
1572
+ },
1573
+ {
1574
+ "epoch": 1.7848605577689243,
1575
+ "grad_norm": 0.8739639520645142,
1576
+ "learning_rate": 1.0020301848967437e-05,
1577
+ "loss": 1.029483437538147,
1578
+ "step": 448
1579
+ },
1580
+ {
1581
+ "epoch": 1.792828685258964,
1582
+ "grad_norm": 0.2899617552757263,
1583
+ "learning_rate": 9.977318351837206e-06,
1584
+ "loss": 0.7871066331863403,
1585
+ "step": 450
1586
+ },
1587
+ {
1588
+ "epoch": 1.800796812749004,
1589
+ "grad_norm": 0.42468908429145813,
1590
+ "learning_rate": 9.934259771165394e-06,
1591
+ "loss": 0.3967509865760803,
1592
+ "step": 452
1593
+ },
1594
+ {
1595
+ "epoch": 1.8087649402390438,
1596
+ "grad_norm": 0.8459072113037109,
1597
+ "learning_rate": 9.89112797863404e-06,
1598
+ "loss": 0.9443418383598328,
1599
+ "step": 454
1600
+ },
1601
+ {
1602
+ "epoch": 1.8167330677290838,
1603
+ "grad_norm": 0.7007260322570801,
1604
+ "learning_rate": 9.847924849107578e-06,
1605
+ "loss": 0.7411941289901733,
1606
+ "step": 456
1607
+ },
1608
+ {
1609
+ "epoch": 1.8247011952191237,
1610
+ "grad_norm": 1.2606959342956543,
1611
+ "learning_rate": 9.804652260551332e-06,
1612
+ "loss": 0.9570497274398804,
1613
+ "step": 458
1614
+ },
1615
+ {
1616
+ "epoch": 1.8326693227091635,
1617
+ "grad_norm": 1.1064777374267578,
1618
+ "learning_rate": 9.761312093949886e-06,
1619
+ "loss": 0.7529144883155823,
1620
+ "step": 460
1621
+ },
1622
+ {
1623
+ "epoch": 1.8406374501992033,
1624
+ "grad_norm": 0.7540960907936096,
1625
+ "learning_rate": 9.717906233225339e-06,
1626
+ "loss": 0.7726236581802368,
1627
+ "step": 462
1628
+ },
1629
+ {
1630
+ "epoch": 1.8486055776892432,
1631
+ "grad_norm": 0.4733653962612152,
1632
+ "learning_rate": 9.674436565155389e-06,
1633
+ "loss": 0.15728430449962616,
1634
+ "step": 464
1635
+ },
1636
+ {
1637
+ "epoch": 1.856573705179283,
1638
+ "grad_norm": 0.2718278169631958,
1639
+ "learning_rate": 9.63090497929133e-06,
1640
+ "loss": 1.0682100057601929,
1641
+ "step": 466
1642
+ },
1643
+ {
1644
+ "epoch": 1.8645418326693228,
1645
+ "grad_norm": 1.8510208129882812,
1646
+ "learning_rate": 9.587313367875922e-06,
1647
+ "loss": 0.4695431590080261,
1648
+ "step": 468
1649
+ },
1650
+ {
1651
+ "epoch": 1.8725099601593627,
1652
+ "grad_norm": 0.4119950234889984,
1653
+ "learning_rate": 9.543663625761121e-06,
1654
+ "loss": 1.0789568424224854,
1655
+ "step": 470
1656
+ },
1657
+ {
1658
+ "epoch": 1.8804780876494025,
1659
+ "grad_norm": 0.7990518808364868,
1660
+ "learning_rate": 9.499957650325738e-06,
1661
+ "loss": 1.02091383934021,
1662
+ "step": 472
1663
+ },
1664
+ {
1665
+ "epoch": 1.8884462151394423,
1666
+ "grad_norm": 0.7012404799461365,
1667
+ "learning_rate": 9.456197341392932e-06,
1668
+ "loss": 0.9402192831039429,
1669
+ "step": 474
1670
+ },
1671
+ {
1672
+ "epoch": 1.8964143426294822,
1673
+ "grad_norm": 0.3745291531085968,
1674
+ "learning_rate": 9.412384601147663e-06,
1675
+ "loss": 0.9166637063026428,
1676
+ "step": 476
1677
+ },
1678
+ {
1679
+ "epoch": 1.904382470119522,
1680
+ "grad_norm": 0.30497679114341736,
1681
+ "learning_rate": 9.368521334053973e-06,
1682
+ "loss": 0.812641978263855,
1683
+ "step": 478
1684
+ },
1685
+ {
1686
+ "epoch": 1.9123505976095618,
1687
+ "grad_norm": 1.237668514251709,
1688
+ "learning_rate": 9.324609446772233e-06,
1689
+ "loss": 0.5746023058891296,
1690
+ "step": 480
1691
+ },
1692
+ {
1693
+ "epoch": 1.9203187250996017,
1694
+ "grad_norm": 0.6451582908630371,
1695
+ "learning_rate": 9.280650848076242e-06,
1696
+ "loss": 0.760349690914154,
1697
+ "step": 482
1698
+ },
1699
+ {
1700
+ "epoch": 1.9282868525896415,
1701
+ "grad_norm": 0.288142591714859,
1702
+ "learning_rate": 9.23664744877026e-06,
1703
+ "loss": 1.0170018672943115,
1704
+ "step": 484
1705
+ },
1706
+ {
1707
+ "epoch": 1.9362549800796813,
1708
+ "grad_norm": 0.407728374004364,
1709
+ "learning_rate": 9.19260116160596e-06,
1710
+ "loss": 0.9356874227523804,
1711
+ "step": 486
1712
+ },
1713
+ {
1714
+ "epoch": 1.9442231075697212,
1715
+ "grad_norm": 0.23040206730365753,
1716
+ "learning_rate": 9.148513901199276e-06,
1717
+ "loss": 1.0043561458587646,
1718
+ "step": 488
1719
+ },
1720
+ {
1721
+ "epoch": 1.952191235059761,
1722
+ "grad_norm": 0.2875385880470276,
1723
+ "learning_rate": 9.104387583947168e-06,
1724
+ "loss": 1.023063063621521,
1725
+ "step": 490
1726
+ },
1727
+ {
1728
+ "epoch": 1.9601593625498008,
1729
+ "grad_norm": 0.3855358362197876,
1730
+ "learning_rate": 9.060224127944343e-06,
1731
+ "loss": 0.6780633330345154,
1732
+ "step": 492
1733
+ },
1734
+ {
1735
+ "epoch": 1.9681274900398407,
1736
+ "grad_norm": 2.7685351371765137,
1737
+ "learning_rate": 9.016025452899853e-06,
1738
+ "loss": 0.7522924542427063,
1739
+ "step": 494
1740
+ },
1741
+ {
1742
+ "epoch": 1.9760956175298805,
1743
+ "grad_norm": 0.37701013684272766,
1744
+ "learning_rate": 8.971793480053668e-06,
1745
+ "loss": 0.9699747562408447,
1746
+ "step": 496
1747
+ },
1748
+ {
1749
+ "epoch": 1.9840637450199203,
1750
+ "grad_norm": 5.959843635559082,
1751
+ "learning_rate": 8.927530132093156e-06,
1752
+ "loss": 0.8083460927009583,
1753
+ "step": 498
1754
+ },
1755
+ {
1756
+ "epoch": 1.9920318725099602,
1757
+ "grad_norm": 0.27620622515678406,
1758
+ "learning_rate": 8.8832373330695e-06,
1759
+ "loss": 1.1264008283615112,
1760
+ "step": 500
1761
+ },
1762
+ {
1763
+ "epoch": 2.0,
1764
+ "grad_norm": 0.4609326422214508,
1765
+ "learning_rate": 8.83891700831408e-06,
1766
+ "loss": 0.5836660265922546,
1767
+ "step": 502
1768
+ },
1769
+ {
1770
+ "epoch": 2.00796812749004,
1771
+ "grad_norm": 0.4023412764072418,
1772
+ "learning_rate": 8.794571084354764e-06,
1773
+ "loss": 0.47467219829559326,
1774
+ "step": 504
1775
+ },
1776
+ {
1777
+ "epoch": 2.0159362549800797,
1778
+ "grad_norm": 1.0555591583251953,
1779
+ "learning_rate": 8.750201488832178e-06,
1780
+ "loss": 0.44583338499069214,
1781
+ "step": 506
1782
+ },
1783
+ {
1784
+ "epoch": 2.0239043824701195,
1785
+ "grad_norm": 0.038634952157735825,
1786
+ "learning_rate": 8.705810150415905e-06,
1787
+ "loss": 0.42819151282310486,
1788
+ "step": 508
1789
+ },
1790
+ {
1791
+ "epoch": 2.0318725099601593,
1792
+ "grad_norm": 0.418973833322525,
1793
+ "learning_rate": 8.661398998720662e-06,
1794
+ "loss": 0.6882845163345337,
1795
+ "step": 510
1796
+ },
1797
+ {
1798
+ "epoch": 2.039840637450199,
1799
+ "grad_norm": 0.32119250297546387,
1800
+ "learning_rate": 8.616969964222403e-06,
1801
+ "loss": 0.5964008569717407,
1802
+ "step": 512
1803
+ },
1804
+ {
1805
+ "epoch": 2.047808764940239,
1806
+ "grad_norm": 0.9128912091255188,
1807
+ "learning_rate": 8.572524978174426e-06,
1808
+ "loss": 0.33640968799591064,
1809
+ "step": 514
1810
+ },
1811
+ {
1812
+ "epoch": 2.055776892430279,
1813
+ "grad_norm": 0.3310595452785492,
1814
+ "learning_rate": 8.528065972523414e-06,
1815
+ "loss": 0.7787442207336426,
1816
+ "step": 516
1817
+ },
1818
+ {
1819
+ "epoch": 2.0637450199203187,
1820
+ "grad_norm": 1.0674067735671997,
1821
+ "learning_rate": 8.483594879825458e-06,
1822
+ "loss": 0.4966733455657959,
1823
+ "step": 518
1824
+ },
1825
+ {
1826
+ "epoch": 2.0717131474103585,
1827
+ "grad_norm": 1.0013618469238281,
1828
+ "learning_rate": 8.439113633162048e-06,
1829
+ "loss": 0.6508659720420837,
1830
+ "step": 520
1831
+ },
1832
+ {
1833
+ "epoch": 2.0796812749003983,
1834
+ "grad_norm": 0.3296944797039032,
1835
+ "learning_rate": 8.39462416605605e-06,
1836
+ "loss": 0.7466489672660828,
1837
+ "step": 522
1838
+ },
1839
+ {
1840
+ "epoch": 2.087649402390438,
1841
+ "grad_norm": 0.7697274684906006,
1842
+ "learning_rate": 8.350128412387663e-06,
1843
+ "loss": 0.754063606262207,
1844
+ "step": 524
1845
+ },
1846
+ {
1847
+ "epoch": 2.095617529880478,
1848
+ "grad_norm": 1.24392831325531,
1849
+ "learning_rate": 8.305628306310352e-06,
1850
+ "loss": 0.3448694050312042,
1851
+ "step": 526
1852
+ },
1853
+ {
1854
+ "epoch": 2.103585657370518,
1855
+ "grad_norm": 0.42689138650894165,
1856
+ "learning_rate": 8.261125782166764e-06,
1857
+ "loss": 0.6862057447433472,
1858
+ "step": 528
1859
+ },
1860
+ {
1861
+ "epoch": 2.1115537848605577,
1862
+ "grad_norm": 0.13302293419837952,
1863
+ "learning_rate": 8.216622774404667e-06,
1864
+ "loss": 0.42651891708374023,
1865
+ "step": 530
1866
+ },
1867
+ {
1868
+ "epoch": 2.1195219123505975,
1869
+ "grad_norm": 1.496959924697876,
1870
+ "learning_rate": 8.172121217492846e-06,
1871
+ "loss": 0.2123342901468277,
1872
+ "step": 532
1873
+ },
1874
+ {
1875
+ "epoch": 2.1274900398406373,
1876
+ "grad_norm": 0.46577370166778564,
1877
+ "learning_rate": 8.127623045837018e-06,
1878
+ "loss": 0.7218248844146729,
1879
+ "step": 534
1880
+ },
1881
+ {
1882
+ "epoch": 2.135458167330677,
1883
+ "grad_norm": 1.5315691232681274,
1884
+ "learning_rate": 8.08313019369575e-06,
1885
+ "loss": 0.610504686832428,
1886
+ "step": 536
1887
+ },
1888
+ {
1889
+ "epoch": 2.143426294820717,
1890
+ "grad_norm": 0.7654959559440613,
1891
+ "learning_rate": 8.038644595096385e-06,
1892
+ "loss": 0.6098729372024536,
1893
+ "step": 538
1894
+ },
1895
+ {
1896
+ "epoch": 2.151394422310757,
1897
+ "grad_norm": 0.5512191653251648,
1898
+ "learning_rate": 7.994168183750962e-06,
1899
+ "loss": 0.7628468871116638,
1900
+ "step": 540
1901
+ },
1902
+ {
1903
+ "epoch": 2.1593625498007967,
1904
+ "grad_norm": 0.3205984830856323,
1905
+ "learning_rate": 7.949702892972157e-06,
1906
+ "loss": 0.6645801067352295,
1907
+ "step": 542
1908
+ },
1909
+ {
1910
+ "epoch": 2.1673306772908365,
1911
+ "grad_norm": 0.1639721542596817,
1912
+ "learning_rate": 7.905250655589271e-06,
1913
+ "loss": 0.5173146724700928,
1914
+ "step": 544
1915
+ },
1916
+ {
1917
+ "epoch": 2.1752988047808763,
1918
+ "grad_norm": 0.9050138592720032,
1919
+ "learning_rate": 7.860813403864191e-06,
1920
+ "loss": 0.6048539876937866,
1921
+ "step": 546
1922
+ },
1923
+ {
1924
+ "epoch": 2.183266932270916,
1925
+ "grad_norm": 0.3164230287075043,
1926
+ "learning_rate": 7.816393069407394e-06,
1927
+ "loss": 0.7414080500602722,
1928
+ "step": 548
1929
+ },
1930
+ {
1931
+ "epoch": 2.191235059760956,
1932
+ "grad_norm": 0.24208378791809082,
1933
+ "learning_rate": 7.771991583094e-06,
1934
+ "loss": 0.7846360206604004,
1935
+ "step": 550
1936
+ },
1937
+ {
1938
+ "epoch": 2.199203187250996,
1939
+ "grad_norm": 0.35901176929473877,
1940
+ "learning_rate": 7.727610874979838e-06,
1941
+ "loss": 0.48403286933898926,
1942
+ "step": 552
1943
+ },
1944
+ {
1945
+ "epoch": 2.2071713147410357,
1946
+ "grad_norm": 0.506497323513031,
1947
+ "learning_rate": 7.683252874217535e-06,
1948
+ "loss": 0.43215182423591614,
1949
+ "step": 554
1950
+ },
1951
+ {
1952
+ "epoch": 2.2151394422310755,
1953
+ "grad_norm": 0.31206437945365906,
1954
+ "learning_rate": 7.638919508972672e-06,
1955
+ "loss": 0.5736108422279358,
1956
+ "step": 556
1957
+ },
1958
+ {
1959
+ "epoch": 2.2231075697211153,
1960
+ "grad_norm": 1.6536140441894531,
1961
+ "learning_rate": 7.594612706339969e-06,
1962
+ "loss": 0.8024041056632996,
1963
+ "step": 558
1964
+ },
1965
+ {
1966
+ "epoch": 2.231075697211155,
1967
+ "grad_norm": 0.21574831008911133,
1968
+ "learning_rate": 7.550334392259514e-06,
1969
+ "loss": 0.8128300905227661,
1970
+ "step": 560
1971
+ },
1972
+ {
1973
+ "epoch": 2.239043824701195,
1974
+ "grad_norm": 0.6206152439117432,
1975
+ "learning_rate": 7.506086491433047e-06,
1976
+ "loss": 0.833297610282898,
1977
+ "step": 562
1978
+ },
1979
+ {
1980
+ "epoch": 2.247011952191235,
1981
+ "grad_norm": 0.8244820237159729,
1982
+ "learning_rate": 7.461870927240291e-06,
1983
+ "loss": 0.7118552327156067,
1984
+ "step": 564
1985
+ },
1986
+ {
1987
+ "epoch": 2.2549800796812747,
1988
+ "grad_norm": 0.2986677587032318,
1989
+ "learning_rate": 7.417689621655362e-06,
1990
+ "loss": 0.5102535486221313,
1991
+ "step": 566
1992
+ },
1993
+ {
1994
+ "epoch": 2.2629482071713145,
1995
+ "grad_norm": 0.2273208200931549,
1996
+ "learning_rate": 7.373544495163206e-06,
1997
+ "loss": 0.6329899430274963,
1998
+ "step": 568
1999
+ },
2000
+ {
2001
+ "epoch": 2.2709163346613543,
2002
+ "grad_norm": 0.23210270702838898,
2003
+ "learning_rate": 7.329437466676127e-06,
2004
+ "loss": 0.7478767037391663,
2005
+ "step": 570
2006
+ },
2007
+ {
2008
+ "epoch": 2.278884462151394,
2009
+ "grad_norm": 0.6402852535247803,
2010
+ "learning_rate": 7.285370453450376e-06,
2011
+ "loss": 0.6049424409866333,
2012
+ "step": 572
2013
+ },
2014
+ {
2015
+ "epoch": 2.2868525896414345,
2016
+ "grad_norm": 0.48132938146591187,
2017
+ "learning_rate": 7.2413453710028155e-06,
2018
+ "loss": 0.5839511156082153,
2019
+ "step": 574
2020
+ },
2021
+ {
2022
+ "epoch": 2.2948207171314743,
2023
+ "grad_norm": 0.29688745737075806,
2024
+ "learning_rate": 7.197364133027632e-06,
2025
+ "loss": 0.25525566935539246,
2026
+ "step": 576
2027
+ },
2028
+ {
2029
+ "epoch": 2.302788844621514,
2030
+ "grad_norm": 0.6722139120101929,
2031
+ "learning_rate": 7.153428651313191e-06,
2032
+ "loss": 0.5150002241134644,
2033
+ "step": 578
2034
+ },
2035
+ {
2036
+ "epoch": 2.310756972111554,
2037
+ "grad_norm": 0.4063420593738556,
2038
+ "learning_rate": 7.109540835658898e-06,
2039
+ "loss": 0.5354428887367249,
2040
+ "step": 580
2041
+ },
2042
+ {
2043
+ "epoch": 2.318725099601594,
2044
+ "grad_norm": 0.9487866163253784,
2045
+ "learning_rate": 7.065702593792204e-06,
2046
+ "loss": 0.5104379653930664,
2047
+ "step": 582
2048
+ },
2049
+ {
2050
+ "epoch": 2.3266932270916336,
2051
+ "grad_norm": 0.2526935040950775,
2052
+ "learning_rate": 7.021915831285661e-06,
2053
+ "loss": 0.6450150609016418,
2054
+ "step": 584
2055
+ },
2056
+ {
2057
+ "epoch": 2.3346613545816735,
2058
+ "grad_norm": 0.3406190276145935,
2059
+ "learning_rate": 6.978182451474124e-06,
2060
+ "loss": 0.5338073968887329,
2061
+ "step": 586
2062
+ },
2063
+ {
2064
+ "epoch": 2.3426294820717133,
2065
+ "grad_norm": 1.3200128078460693,
2066
+ "learning_rate": 6.934504355371974e-06,
2067
+ "loss": 0.7506805062294006,
2068
+ "step": 588
2069
+ },
2070
+ {
2071
+ "epoch": 2.350597609561753,
2072
+ "grad_norm": 0.27950209379196167,
2073
+ "learning_rate": 6.890883441590515e-06,
2074
+ "loss": 0.7645633220672607,
2075
+ "step": 590
2076
+ },
2077
+ {
2078
+ "epoch": 2.358565737051793,
2079
+ "grad_norm": 0.29245108366012573,
2080
+ "learning_rate": 6.847321606255432e-06,
2081
+ "loss": 0.7928623557090759,
2082
+ "step": 592
2083
+ },
2084
+ {
2085
+ "epoch": 2.366533864541833,
2086
+ "grad_norm": 0.4357150197029114,
2087
+ "learning_rate": 6.803820742924374e-06,
2088
+ "loss": 0.5477173924446106,
2089
+ "step": 594
2090
+ },
2091
+ {
2092
+ "epoch": 2.3745019920318726,
2093
+ "grad_norm": 0.3675963878631592,
2094
+ "learning_rate": 6.76038274250464e-06,
2095
+ "loss": 0.8036378622055054,
2096
+ "step": 596
2097
+ },
2098
+ {
2099
+ "epoch": 2.3824701195219125,
2100
+ "grad_norm": 0.5962640047073364,
2101
+ "learning_rate": 6.717009493170986e-06,
2102
+ "loss": 0.5513007044792175,
2103
+ "step": 598
2104
+ },
2105
+ {
2106
+ "epoch": 2.3904382470119523,
2107
+ "grad_norm": 0.8920307159423828,
2108
+ "learning_rate": 6.673702880283554e-06,
2109
+ "loss": 0.8076795935630798,
2110
+ "step": 600
2111
+ },
2112
+ {
2113
+ "epoch": 2.398406374501992,
2114
+ "grad_norm": 0.22857658565044403,
2115
+ "learning_rate": 6.6304647863059155e-06,
2116
+ "loss": 0.7613834142684937,
2117
+ "step": 602
2118
+ },
2119
+ {
2120
+ "epoch": 2.406374501992032,
2121
+ "grad_norm": 0.9126567244529724,
2122
+ "learning_rate": 6.587297090723235e-06,
2123
+ "loss": 0.47278252243995667,
2124
+ "step": 604
2125
+ },
2126
+ {
2127
+ "epoch": 2.414342629482072,
2128
+ "grad_norm": 0.8739012479782104,
2129
+ "learning_rate": 6.54420166996059e-06,
2130
+ "loss": 0.23272567987442017,
2131
+ "step": 606
2132
+ },
2133
+ {
2134
+ "epoch": 2.4223107569721116,
2135
+ "grad_norm": 0.09651335328817368,
2136
+ "learning_rate": 6.501180397301394e-06,
2137
+ "loss": 0.32919982075691223,
2138
+ "step": 608
2139
+ },
2140
+ {
2141
+ "epoch": 2.4302788844621515,
2142
+ "grad_norm": 0.1508469432592392,
2143
+ "learning_rate": 6.458235142805968e-06,
2144
+ "loss": 0.6115418672561646,
2145
+ "step": 610
2146
+ },
2147
+ {
2148
+ "epoch": 2.4382470119521913,
2149
+ "grad_norm": 0.223999485373497,
2150
+ "learning_rate": 6.415367773230254e-06,
2151
+ "loss": 0.656358540058136,
2152
+ "step": 612
2153
+ },
2154
+ {
2155
+ "epoch": 2.446215139442231,
2156
+ "grad_norm": 0.3630542755126953,
2157
+ "learning_rate": 6.372580151944681e-06,
2158
+ "loss": 0.4408586919307709,
2159
+ "step": 614
2160
+ },
2161
+ {
2162
+ "epoch": 2.454183266932271,
2163
+ "grad_norm": 0.5294836163520813,
2164
+ "learning_rate": 6.329874138853146e-06,
2165
+ "loss": 0.7569445371627808,
2166
+ "step": 616
2167
+ },
2168
+ {
2169
+ "epoch": 2.462151394422311,
2170
+ "grad_norm": 0.7806637287139893,
2171
+ "learning_rate": 6.287251590312181e-06,
2172
+ "loss": 0.5635365843772888,
2173
+ "step": 618
2174
+ },
2175
+ {
2176
+ "epoch": 2.4701195219123506,
2177
+ "grad_norm": 0.8465815186500549,
2178
+ "learning_rate": 6.244714359050267e-06,
2179
+ "loss": 0.6494905352592468,
2180
+ "step": 620
2181
+ },
2182
+ {
2183
+ "epoch": 2.4780876494023905,
2184
+ "grad_norm": 0.30154383182525635,
2185
+ "learning_rate": 6.20226429408728e-06,
2186
+ "loss": 0.722070038318634,
2187
+ "step": 622
2188
+ },
2189
+ {
2190
+ "epoch": 2.4860557768924303,
2191
+ "grad_norm": 0.49222832918167114,
2192
+ "learning_rate": 6.159903240654132e-06,
2193
+ "loss": 0.6191802620887756,
2194
+ "step": 624
2195
+ },
2196
+ {
2197
+ "epoch": 2.49402390438247,
2198
+ "grad_norm": 0.4883638322353363,
2199
+ "learning_rate": 6.117633040112559e-06,
2200
+ "loss": 0.3768939673900604,
2201
+ "step": 626
2202
+ },
2203
+ {
2204
+ "epoch": 2.50199203187251,
2205
+ "grad_norm": 0.7983854413032532,
2206
+ "learning_rate": 6.0754555298750795e-06,
2207
+ "loss": 0.7864499688148499,
2208
+ "step": 628
2209
+ },
2210
+ {
2211
+ "epoch": 2.50996015936255,
2212
+ "grad_norm": 0.3459266126155853,
2213
+ "learning_rate": 6.033372543325119e-06,
2214
+ "loss": 0.3463517427444458,
2215
+ "step": 630
2216
+ },
2217
+ {
2218
+ "epoch": 2.5179282868525896,
2219
+ "grad_norm": 1.2402698993682861,
2220
+ "learning_rate": 5.991385909737327e-06,
2221
+ "loss": 0.3873278796672821,
2222
+ "step": 632
2223
+ },
2224
+ {
2225
+ "epoch": 2.5258964143426295,
2226
+ "grad_norm": 0.28206056356430054,
2227
+ "learning_rate": 5.949497454198058e-06,
2228
+ "loss": 0.7801554799079895,
2229
+ "step": 634
2230
+ },
2231
+ {
2232
+ "epoch": 2.5338645418326693,
2233
+ "grad_norm": 0.5089584589004517,
2234
+ "learning_rate": 5.907708997526031e-06,
2235
+ "loss": 0.7173982262611389,
2236
+ "step": 636
2237
+ },
2238
+ {
2239
+ "epoch": 2.541832669322709,
2240
+ "grad_norm": 0.7955684065818787,
2241
+ "learning_rate": 5.86602235619319e-06,
2242
+ "loss": 0.9195908904075623,
2243
+ "step": 638
2244
+ },
2245
+ {
2246
+ "epoch": 2.549800796812749,
2247
+ "grad_norm": 0.17236770689487457,
2248
+ "learning_rate": 5.824439342245739e-06,
2249
+ "loss": 0.40686023235321045,
2250
+ "step": 640
2251
+ },
2252
+ {
2253
+ "epoch": 2.557768924302789,
2254
+ "grad_norm": 0.4617612063884735,
2255
+ "learning_rate": 5.782961763225388e-06,
2256
+ "loss": 0.7664303183555603,
2257
+ "step": 642
2258
+ },
2259
+ {
2260
+ "epoch": 2.5657370517928286,
2261
+ "grad_norm": 0.2930012345314026,
2262
+ "learning_rate": 5.741591422090765e-06,
2263
+ "loss": 0.7867609858512878,
2264
+ "step": 644
2265
+ },
2266
+ {
2267
+ "epoch": 2.5737051792828685,
2268
+ "grad_norm": 0.436357706785202,
2269
+ "learning_rate": 5.70033011713905e-06,
2270
+ "loss": 0.5984311699867249,
2271
+ "step": 646
2272
+ },
2273
+ {
2274
+ "epoch": 2.5816733067729083,
2275
+ "grad_norm": 0.40557265281677246,
2276
+ "learning_rate": 5.659179641927816e-06,
2277
+ "loss": 0.7649792432785034,
2278
+ "step": 648
2279
+ },
2280
+ {
2281
+ "epoch": 2.589641434262948,
2282
+ "grad_norm": 0.17836439609527588,
2283
+ "learning_rate": 5.61814178519706e-06,
2284
+ "loss": 0.5768654346466064,
2285
+ "step": 650
2286
+ },
2287
+ {
2288
+ "epoch": 2.597609561752988,
2289
+ "grad_norm": 0.40341848134994507,
2290
+ "learning_rate": 5.577218330791436e-06,
2291
+ "loss": 0.5763181447982788,
2292
+ "step": 652
2293
+ },
2294
+ {
2295
+ "epoch": 2.605577689243028,
2296
+ "grad_norm": 0.5692223906517029,
2297
+ "learning_rate": 5.536411057582744e-06,
2298
+ "loss": 0.5641070008277893,
2299
+ "step": 654
2300
+ },
2301
+ {
2302
+ "epoch": 2.6135458167330676,
2303
+ "grad_norm": 0.29569053649902344,
2304
+ "learning_rate": 5.4957217393925734e-06,
2305
+ "loss": 0.2429419606924057,
2306
+ "step": 656
2307
+ },
2308
+ {
2309
+ "epoch": 2.6215139442231075,
2310
+ "grad_norm": 0.3552258610725403,
2311
+ "learning_rate": 5.4551521449152216e-06,
2312
+ "loss": 0.42948848009109497,
2313
+ "step": 658
2314
+ },
2315
+ {
2316
+ "epoch": 2.6294820717131473,
2317
+ "grad_norm": 0.41975289583206177,
2318
+ "learning_rate": 5.4147040376408e-06,
2319
+ "loss": 0.7414237260818481,
2320
+ "step": 660
2321
+ },
2322
+ {
2323
+ "epoch": 2.637450199203187,
2324
+ "grad_norm": 0.8263479471206665,
2325
+ "learning_rate": 5.37437917577858e-06,
2326
+ "loss": 0.6220693588256836,
2327
+ "step": 662
2328
+ },
2329
+ {
2330
+ "epoch": 2.645418326693227,
2331
+ "grad_norm": 1.41019868850708,
2332
+ "learning_rate": 5.334179312180574e-06,
2333
+ "loss": 0.4769461154937744,
2334
+ "step": 664
2335
+ },
2336
+ {
2337
+ "epoch": 2.653386454183267,
2338
+ "grad_norm": 9.828413009643555,
2339
+ "learning_rate": 5.2941061942653315e-06,
2340
+ "loss": 0.7357695698738098,
2341
+ "step": 666
2342
+ },
2343
+ {
2344
+ "epoch": 2.6613545816733066,
2345
+ "grad_norm": 0.20442984998226166,
2346
+ "learning_rate": 5.254161563941981e-06,
2347
+ "loss": 0.545133650302887,
2348
+ "step": 668
2349
+ },
2350
+ {
2351
+ "epoch": 2.6693227091633465,
2352
+ "grad_norm": 1.070529818534851,
2353
+ "learning_rate": 5.2143471575345295e-06,
2354
+ "loss": 0.5713125467300415,
2355
+ "step": 670
2356
+ },
2357
+ {
2358
+ "epoch": 2.6772908366533863,
2359
+ "grad_norm": 0.08597006648778915,
2360
+ "learning_rate": 5.174664705706371e-06,
2361
+ "loss": 0.2371898740530014,
2362
+ "step": 672
2363
+ },
2364
+ {
2365
+ "epoch": 2.685258964143426,
2366
+ "grad_norm": 0.2467171996831894,
2367
+ "learning_rate": 5.135115933385058e-06,
2368
+ "loss": 0.7705000638961792,
2369
+ "step": 674
2370
+ },
2371
+ {
2372
+ "epoch": 2.6932270916334664,
2373
+ "grad_norm": 1.5602085590362549,
2374
+ "learning_rate": 5.0957025596873256e-06,
2375
+ "loss": 0.5420997142791748,
2376
+ "step": 676
2377
+ },
2378
+ {
2379
+ "epoch": 2.7011952191235062,
2380
+ "grad_norm": 0.6235253810882568,
2381
+ "learning_rate": 5.0564262978443745e-06,
2382
+ "loss": 0.4899404048919678,
2383
+ "step": 678
2384
+ },
2385
+ {
2386
+ "epoch": 2.709163346613546,
2387
+ "grad_norm": 0.2874850332736969,
2388
+ "learning_rate": 5.017288855127377e-06,
2389
+ "loss": 0.778532862663269,
2390
+ "step": 680
2391
+ },
2392
+ {
2393
+ "epoch": 2.717131474103586,
2394
+ "grad_norm": 0.26746895909309387,
2395
+ "learning_rate": 4.978291932773289e-06,
2396
+ "loss": 0.7769652605056763,
2397
+ "step": 682
2398
+ },
2399
+ {
2400
+ "epoch": 2.7250996015936257,
2401
+ "grad_norm": 0.25973984599113464,
2402
+ "learning_rate": 4.9394372259108886e-06,
2403
+ "loss": 0.5638492107391357,
2404
+ "step": 684
2405
+ },
2406
+ {
2407
+ "epoch": 2.7330677290836656,
2408
+ "grad_norm": 0.8309025168418884,
2409
+ "learning_rate": 4.9007264234870805e-06,
2410
+ "loss": 0.41929128766059875,
2411
+ "step": 686
2412
+ },
2413
+ {
2414
+ "epoch": 2.7410358565737054,
2415
+ "grad_norm": 0.3012772798538208,
2416
+ "learning_rate": 4.862161208193505e-06,
2417
+ "loss": 0.7767641544342041,
2418
+ "step": 688
2419
+ },
2420
+ {
2421
+ "epoch": 2.7490039840637452,
2422
+ "grad_norm": 0.35578370094299316,
2423
+ "learning_rate": 4.823743256393377e-06,
2424
+ "loss": 0.47287169098854065,
2425
+ "step": 690
2426
+ },
2427
+ {
2428
+ "epoch": 2.756972111553785,
2429
+ "grad_norm": 0.49327176809310913,
2430
+ "learning_rate": 4.785474238048626e-06,
2431
+ "loss": 0.8931385278701782,
2432
+ "step": 692
2433
+ },
2434
+ {
2435
+ "epoch": 2.764940239043825,
2436
+ "grad_norm": 1.3697088956832886,
2437
+ "learning_rate": 4.747355816647293e-06,
2438
+ "loss": 0.6319751143455505,
2439
+ "step": 694
2440
+ },
2441
+ {
2442
+ "epoch": 2.7729083665338647,
2443
+ "grad_norm": 1.342233657836914,
2444
+ "learning_rate": 4.709389649131235e-06,
2445
+ "loss": 0.4150761365890503,
2446
+ "step": 696
2447
+ },
2448
+ {
2449
+ "epoch": 2.7808764940239046,
2450
+ "grad_norm": 0.27556970715522766,
2451
+ "learning_rate": 4.6715773858241e-06,
2452
+ "loss": 0.8045108318328857,
2453
+ "step": 698
2454
+ },
2455
+ {
2456
+ "epoch": 2.7888446215139444,
2457
+ "grad_norm": 0.31476858258247375,
2458
+ "learning_rate": 4.63392067035958e-06,
2459
+ "loss": 0.8101509213447571,
2460
+ "step": 700
2461
+ },
2462
+ {
2463
+ "epoch": 2.7968127490039842,
2464
+ "grad_norm": 0.5621429681777954,
2465
+ "learning_rate": 4.596421139609977e-06,
2466
+ "loss": 0.4465515911579132,
2467
+ "step": 702
2468
+ },
2469
+ {
2470
+ "epoch": 2.804780876494024,
2471
+ "grad_norm": 0.8817136287689209,
2472
+ "learning_rate": 4.5590804236150365e-06,
2473
+ "loss": 0.9612689018249512,
2474
+ "step": 704
2475
+ },
2476
+ {
2477
+ "epoch": 2.812749003984064,
2478
+ "grad_norm": 0.19133038818836212,
2479
+ "learning_rate": 4.521900145511112e-06,
2480
+ "loss": 0.8152596950531006,
2481
+ "step": 706
2482
+ },
2483
+ {
2484
+ "epoch": 2.8207171314741037,
2485
+ "grad_norm": 0.4524690508842468,
2486
+ "learning_rate": 4.484881921460591e-06,
2487
+ "loss": 0.8935415744781494,
2488
+ "step": 708
2489
+ },
2490
+ {
2491
+ "epoch": 2.8286852589641436,
2492
+ "grad_norm": 0.24354888498783112,
2493
+ "learning_rate": 4.4480273605816556e-06,
2494
+ "loss": 0.4386708736419678,
2495
+ "step": 710
2496
+ },
2497
+ {
2498
+ "epoch": 2.8366533864541834,
2499
+ "grad_norm": 0.2424662858247757,
2500
+ "learning_rate": 4.411338064878337e-06,
2501
+ "loss": 0.8338403701782227,
2502
+ "step": 712
2503
+ },
2504
+ {
2505
+ "epoch": 2.8446215139442232,
2506
+ "grad_norm": 0.319381445646286,
2507
+ "learning_rate": 4.374815629170861e-06,
2508
+ "loss": 0.5186902284622192,
2509
+ "step": 714
2510
+ },
2511
+ {
2512
+ "epoch": 2.852589641434263,
2513
+ "grad_norm": 0.2536839246749878,
2514
+ "learning_rate": 4.338461641026351e-06,
2515
+ "loss": 0.769604504108429,
2516
+ "step": 716
2517
+ },
2518
+ {
2519
+ "epoch": 2.860557768924303,
2520
+ "grad_norm": 0.8778960108757019,
2521
+ "learning_rate": 4.302277680689801e-06,
2522
+ "loss": 0.6171420216560364,
2523
+ "step": 718
2524
+ },
2525
+ {
2526
+ "epoch": 2.8685258964143427,
2527
+ "grad_norm": 0.39766034483909607,
2528
+ "learning_rate": 4.2662653210153965e-06,
2529
+ "loss": 0.5202685594558716,
2530
+ "step": 720
2531
+ },
2532
+ {
2533
+ "epoch": 2.8764940239043826,
2534
+ "grad_norm": 0.8559178113937378,
2535
+ "learning_rate": 4.23042612739813e-06,
2536
+ "loss": 0.4717506766319275,
2537
+ "step": 722
2538
+ },
2539
+ {
2540
+ "epoch": 2.8844621513944224,
2541
+ "grad_norm": 0.3448426127433777,
2542
+ "learning_rate": 4.194761657705765e-06,
2543
+ "loss": 0.5054087042808533,
2544
+ "step": 724
2545
+ },
2546
+ {
2547
+ "epoch": 2.8924302788844622,
2548
+ "grad_norm": 0.29262322187423706,
2549
+ "learning_rate": 4.159273462211129e-06,
2550
+ "loss": 0.7536461353302002,
2551
+ "step": 726
2552
+ },
2553
+ {
2554
+ "epoch": 2.900398406374502,
2555
+ "grad_norm": 0.4943152964115143,
2556
+ "learning_rate": 4.123963083524702e-06,
2557
+ "loss": 0.43974122405052185,
2558
+ "step": 728
2559
+ },
2560
+ {
2561
+ "epoch": 2.908366533864542,
2562
+ "grad_norm": 0.24242062866687775,
2563
+ "learning_rate": 4.0888320565275854e-06,
2564
+ "loss": 0.7488172650337219,
2565
+ "step": 730
2566
+ },
2567
+ {
2568
+ "epoch": 2.9163346613545817,
2569
+ "grad_norm": 0.6715952754020691,
2570
+ "learning_rate": 4.053881908304764e-06,
2571
+ "loss": 0.2420373111963272,
2572
+ "step": 732
2573
+ },
2574
+ {
2575
+ "epoch": 2.9243027888446216,
2576
+ "grad_norm": 0.2856823205947876,
2577
+ "learning_rate": 4.019114158078742e-06,
2578
+ "loss": 0.8018136620521545,
2579
+ "step": 734
2580
+ },
2581
+ {
2582
+ "epoch": 2.9322709163346614,
2583
+ "grad_norm": 0.7715031504631042,
2584
+ "learning_rate": 3.984530317143495e-06,
2585
+ "loss": 0.41188791394233704,
2586
+ "step": 736
2587
+ },
2588
+ {
2589
+ "epoch": 2.9402390438247012,
2590
+ "grad_norm": 1.3740425109863281,
2591
+ "learning_rate": 3.950131888798777e-06,
2592
+ "loss": 0.6634250283241272,
2593
+ "step": 738
2594
+ },
2595
+ {
2596
+ "epoch": 2.948207171314741,
2597
+ "grad_norm": 0.7085353136062622,
2598
+ "learning_rate": 3.915920368284786e-06,
2599
+ "loss": 0.8047435283660889,
2600
+ "step": 740
2601
+ },
2602
+ {
2603
+ "epoch": 2.956175298804781,
2604
+ "grad_norm": 1.6132349967956543,
2605
+ "learning_rate": 3.881897242717153e-06,
2606
+ "loss": 0.2846962511539459,
2607
+ "step": 742
2608
+ },
2609
+ {
2610
+ "epoch": 2.9641434262948207,
2611
+ "grad_norm": 0.3325771987438202,
2612
+ "learning_rate": 3.848063991022304e-06,
2613
+ "loss": 0.679719865322113,
2614
+ "step": 744
2615
+ },
2616
+ {
2617
+ "epoch": 2.9721115537848606,
2618
+ "grad_norm": 0.3333672881126404,
2619
+ "learning_rate": 3.814422083873181e-06,
2620
+ "loss": 0.716017484664917,
2621
+ "step": 746
2622
+ },
2623
+ {
2624
+ "epoch": 2.9800796812749004,
2625
+ "grad_norm": 0.31956031918525696,
2626
+ "learning_rate": 3.7809729836253126e-06,
2627
+ "loss": 0.44896891713142395,
2628
+ "step": 748
2629
+ },
2630
+ {
2631
+ "epoch": 2.9880478087649402,
2632
+ "grad_norm": 0.14244171977043152,
2633
+ "learning_rate": 3.7477181442532373e-06,
2634
+ "loss": 0.11532896757125854,
2635
+ "step": 750
2636
+ },
2637
+ {
2638
+ "epoch": 2.99601593625498,
2639
+ "grad_norm": 0.196710005402565,
2640
+ "learning_rate": 3.7146590112873117e-06,
2641
+ "loss": 0.7710368633270264,
2642
+ "step": 752
2643
+ },
2644
+ {
2645
+ "epoch": 3.00398406374502,
2646
+ "grad_norm": 0.2597305178642273,
2647
+ "learning_rate": 3.6817970217508766e-06,
2648
+ "loss": 0.37589359283447266,
2649
+ "step": 754
2650
+ },
2651
+ {
2652
+ "epoch": 3.0119521912350598,
2653
+ "grad_norm": 0.36714112758636475,
2654
+ "learning_rate": 3.649133604097784e-06,
2655
+ "loss": 0.34749507904052734,
2656
+ "step": 756
2657
+ },
2658
+ {
2659
+ "epoch": 3.0199203187250996,
2660
+ "grad_norm": 2.629531145095825,
2661
+ "learning_rate": 3.616670178150316e-06,
2662
+ "loss": 0.18874035775661469,
2663
+ "step": 758
2664
+ },
2665
+ {
2666
+ "epoch": 3.0278884462151394,
2667
+ "grad_norm": 0.3082272410392761,
2668
+ "learning_rate": 3.5844081550374545e-06,
2669
+ "loss": 0.37505829334259033,
2670
+ "step": 760
2671
+ },
2672
+ {
2673
+ "epoch": 3.0358565737051793,
2674
+ "grad_norm": 0.6151975989341736,
2675
+ "learning_rate": 3.5523489371335502e-06,
2676
+ "loss": 0.3742624819278717,
2677
+ "step": 762
2678
+ },
2679
+ {
2680
+ "epoch": 3.043824701195219,
2681
+ "grad_norm": 0.3428267538547516,
2682
+ "learning_rate": 3.5204939179973634e-06,
2683
+ "loss": 0.4816422462463379,
2684
+ "step": 764
2685
+ },
2686
+ {
2687
+ "epoch": 3.051792828685259,
2688
+ "grad_norm": 0.6483787894248962,
2689
+ "learning_rate": 3.488844482311489e-06,
2690
+ "loss": 0.16634498536586761,
2691
+ "step": 766
2692
+ },
2693
+ {
2694
+ "epoch": 3.0597609561752988,
2695
+ "grad_norm": 0.5806704163551331,
2696
+ "learning_rate": 3.457402005822163e-06,
2697
+ "loss": 0.31581252813339233,
2698
+ "step": 768
2699
+ },
2700
+ {
2701
+ "epoch": 3.0677290836653386,
2702
+ "grad_norm": 0.3666588068008423,
2703
+ "learning_rate": 3.4261678552794615e-06,
2704
+ "loss": 0.3485649824142456,
2705
+ "step": 770
2706
+ },
2707
+ {
2708
+ "epoch": 3.0756972111553784,
2709
+ "grad_norm": 0.3737334609031677,
2710
+ "learning_rate": 3.39514338837789e-06,
2711
+ "loss": 0.5422434210777283,
2712
+ "step": 772
2713
+ },
2714
+ {
2715
+ "epoch": 3.0836653386454183,
2716
+ "grad_norm": 1.312560796737671,
2717
+ "learning_rate": 3.364329953697377e-06,
2718
+ "loss": 0.5372627973556519,
2719
+ "step": 774
2720
+ },
2721
+ {
2722
+ "epoch": 3.091633466135458,
2723
+ "grad_norm": 0.025555025786161423,
2724
+ "learning_rate": 3.3337288906446356e-06,
2725
+ "loss": 0.30303874611854553,
2726
+ "step": 776
2727
+ },
2728
+ {
2729
+ "epoch": 3.099601593625498,
2730
+ "grad_norm": 0.36579927802085876,
2731
+ "learning_rate": 3.303341529394961e-06,
2732
+ "loss": 0.3074573278427124,
2733
+ "step": 778
2734
+ },
2735
+ {
2736
+ "epoch": 3.1075697211155378,
2737
+ "grad_norm": 0.36329302191734314,
2738
+ "learning_rate": 3.2731691908343907e-06,
2739
+ "loss": 0.4981156885623932,
2740
+ "step": 780
2741
+ },
2742
+ {
2743
+ "epoch": 3.1155378486055776,
2744
+ "grad_norm": 0.08173166960477829,
2745
+ "learning_rate": 3.2432131865023065e-06,
2746
+ "loss": 0.160829097032547,
2747
+ "step": 782
2748
+ },
2749
+ {
2750
+ "epoch": 3.1235059760956174,
2751
+ "grad_norm": 0.3885779082775116,
2752
+ "learning_rate": 3.2134748185344098e-06,
2753
+ "loss": 0.5554381608963013,
2754
+ "step": 784
2755
+ },
2756
+ {
2757
+ "epoch": 3.1314741035856573,
2758
+ "grad_norm": 0.317030668258667,
2759
+ "learning_rate": 3.1839553796061266e-06,
2760
+ "loss": 0.45913565158843994,
2761
+ "step": 786
2762
+ },
2763
+ {
2764
+ "epoch": 3.139442231075697,
2765
+ "grad_norm": 0.6573988795280457,
2766
+ "learning_rate": 3.1546561528764227e-06,
2767
+ "loss": 0.32907965779304504,
2768
+ "step": 788
2769
+ },
2770
+ {
2771
+ "epoch": 3.147410358565737,
2772
+ "grad_norm": 0.35516512393951416,
2773
+ "learning_rate": 3.1255784119320064e-06,
2774
+ "loss": 0.25920620560646057,
2775
+ "step": 790
2776
+ },
2777
+ {
2778
+ "epoch": 3.1553784860557768,
2779
+ "grad_norm": 0.789368748664856,
2780
+ "learning_rate": 3.0967234207319946e-06,
2781
+ "loss": 0.3322998285293579,
2782
+ "step": 792
2783
+ },
2784
+ {
2785
+ "epoch": 3.1633466135458166,
2786
+ "grad_norm": 0.08553847670555115,
2787
+ "learning_rate": 3.0680924335529536e-06,
2788
+ "loss": 0.20808134973049164,
2789
+ "step": 794
2790
+ },
2791
+ {
2792
+ "epoch": 3.1713147410358564,
2793
+ "grad_norm": 1.4314020872116089,
2794
+ "learning_rate": 3.0396866949343833e-06,
2795
+ "loss": 0.33690834045410156,
2796
+ "step": 796
2797
+ },
2798
+ {
2799
+ "epoch": 3.1792828685258963,
2800
+ "grad_norm": 0.279748797416687,
2801
+ "learning_rate": 3.0115074396246176e-06,
2802
+ "loss": 0.36214491724967957,
2803
+ "step": 798
2804
+ },
2805
+ {
2806
+ "epoch": 3.187250996015936,
2807
+ "grad_norm": 0.6961238384246826,
2808
+ "learning_rate": 2.9835558925271495e-06,
2809
+ "loss": 0.501541018486023,
2810
+ "step": 800
2811
+ },
2812
+ {
2813
+ "epoch": 3.195219123505976,
2814
+ "grad_norm": 0.18416091799736023,
2815
+ "learning_rate": 2.955833268647395e-06,
2816
+ "loss": 0.3577136993408203,
2817
+ "step": 802
2818
+ },
2819
+ {
2820
+ "epoch": 3.2031872509960158,
2821
+ "grad_norm": 0.6885810494422913,
2822
+ "learning_rate": 2.9283407730398702e-06,
2823
+ "loss": 0.29195672273635864,
2824
+ "step": 804
2825
+ },
2826
+ {
2827
+ "epoch": 3.2111553784860556,
2828
+ "grad_norm": 1.7156380414962769,
2829
+ "learning_rate": 2.901079600755817e-06,
2830
+ "loss": 0.5778890252113342,
2831
+ "step": 806
2832
+ },
2833
+ {
2834
+ "epoch": 3.2191235059760954,
2835
+ "grad_norm": 0.6983752846717834,
2836
+ "learning_rate": 2.8740509367912457e-06,
2837
+ "loss": 0.18633845448493958,
2838
+ "step": 808
2839
+ },
2840
+ {
2841
+ "epoch": 3.2270916334661353,
2842
+ "grad_norm": 0.6704440712928772,
2843
+ "learning_rate": 2.8472559560354404e-06,
2844
+ "loss": 0.3643829822540283,
2845
+ "step": 810
2846
+ },
2847
+ {
2848
+ "epoch": 3.235059760956175,
2849
+ "grad_norm": 1.632941484451294,
2850
+ "learning_rate": 2.820695823219873e-06,
2851
+ "loss": 0.2959984838962555,
2852
+ "step": 812
2853
+ },
2854
+ {
2855
+ "epoch": 3.243027888446215,
2856
+ "grad_norm": 0.39763104915618896,
2857
+ "learning_rate": 2.794371692867585e-06,
2858
+ "loss": 0.44851499795913696,
2859
+ "step": 814
2860
+ },
2861
+ {
2862
+ "epoch": 3.2509960159362548,
2863
+ "grad_norm": 1.5863844156265259,
2864
+ "learning_rate": 2.768284709243002e-06,
2865
+ "loss": 0.13297411799430847,
2866
+ "step": 816
2867
+ },
2868
+ {
2869
+ "epoch": 3.2589641434262946,
2870
+ "grad_norm": 0.5324887633323669,
2871
+ "learning_rate": 2.7424360063021855e-06,
2872
+ "loss": 0.5013939142227173,
2873
+ "step": 818
2874
+ },
2875
+ {
2876
+ "epoch": 3.2669322709163344,
2877
+ "grad_norm": 2.0388095378875732,
2878
+ "learning_rate": 2.7168267076435485e-06,
2879
+ "loss": 0.2653783857822418,
2880
+ "step": 820
2881
+ },
2882
+ {
2883
+ "epoch": 3.2749003984063743,
2884
+ "grad_norm": 0.6833744049072266,
2885
+ "learning_rate": 2.69145792645902e-06,
2886
+ "loss": 0.41534146666526794,
2887
+ "step": 822
2888
+ },
2889
+ {
2890
+ "epoch": 3.2828685258964145,
2891
+ "grad_norm": 0.8634832501411438,
2892
+ "learning_rate": 2.6663307654856407e-06,
2893
+ "loss": 0.3562511205673218,
2894
+ "step": 824
2895
+ },
2896
+ {
2897
+ "epoch": 3.2908366533864544,
2898
+ "grad_norm": 0.39872676134109497,
2899
+ "learning_rate": 2.6414463169576492e-06,
2900
+ "loss": 0.4844256043434143,
2901
+ "step": 826
2902
+ },
2903
+ {
2904
+ "epoch": 3.298804780876494,
2905
+ "grad_norm": 0.434477299451828,
2906
+ "learning_rate": 2.616805662558985e-06,
2907
+ "loss": 0.6063498854637146,
2908
+ "step": 828
2909
+ },
2910
+ {
2911
+ "epoch": 3.306772908366534,
2912
+ "grad_norm": 2.5125367641448975,
2913
+ "learning_rate": 2.5924098733762835e-06,
2914
+ "loss": 0.4092828035354614,
2915
+ "step": 830
2916
+ },
2917
+ {
2918
+ "epoch": 3.314741035856574,
2919
+ "grad_norm": 0.5066865682601929,
2920
+ "learning_rate": 2.5682600098523105e-06,
2921
+ "loss": 0.28628939390182495,
2922
+ "step": 832
2923
+ },
2924
+ {
2925
+ "epoch": 3.3227091633466137,
2926
+ "grad_norm": 0.6276751160621643,
2927
+ "learning_rate": 2.5443571217398705e-06,
2928
+ "loss": 0.2303668111562729,
2929
+ "step": 834
2930
+ },
2931
+ {
2932
+ "epoch": 3.3306772908366535,
2933
+ "grad_norm": 3.6938159465789795,
2934
+ "learning_rate": 2.5207022480561722e-06,
2935
+ "loss": 0.3531423807144165,
2936
+ "step": 836
2937
+ },
2938
+ {
2939
+ "epoch": 3.3386454183266934,
2940
+ "grad_norm": 0.4289490580558777,
2941
+ "learning_rate": 2.497296417037664e-06,
2942
+ "loss": 0.4265778660774231,
2943
+ "step": 838
2944
+ },
2945
+ {
2946
+ "epoch": 3.346613545816733,
2947
+ "grad_norm": 0.859740674495697,
2948
+ "learning_rate": 2.474140646095346e-06,
2949
+ "loss": 0.11164703965187073,
2950
+ "step": 840
2951
+ },
2952
+ {
2953
+ "epoch": 3.354581673306773,
2954
+ "grad_norm": 0.573935866355896,
2955
+ "learning_rate": 2.451235941770535e-06,
2956
+ "loss": 0.36163708567619324,
2957
+ "step": 842
2958
+ },
2959
+ {
2960
+ "epoch": 3.362549800796813,
2961
+ "grad_norm": 0.38408342003822327,
2962
+ "learning_rate": 2.428583299691118e-06,
2963
+ "loss": 0.4686431884765625,
2964
+ "step": 844
2965
+ },
2966
+ {
2967
+ "epoch": 3.3705179282868527,
2968
+ "grad_norm": 0.3920894265174866,
2969
+ "learning_rate": 2.4061837045282717e-06,
2970
+ "loss": 0.544544517993927,
2971
+ "step": 846
2972
+ },
2973
+ {
2974
+ "epoch": 3.3784860557768925,
2975
+ "grad_norm": 0.2612384259700775,
2976
+ "learning_rate": 2.3840381299536584e-06,
2977
+ "loss": 0.4954265058040619,
2978
+ "step": 848
2979
+ },
2980
+ {
2981
+ "epoch": 3.3864541832669324,
2982
+ "grad_norm": 0.9370325207710266,
2983
+ "learning_rate": 2.36214753859711e-06,
2984
+ "loss": 0.45011717081069946,
2985
+ "step": 850
2986
+ },
2987
+ {
2988
+ "epoch": 3.394422310756972,
2989
+ "grad_norm": 0.42760828137397766,
2990
+ "learning_rate": 2.3405128820047716e-06,
2991
+ "loss": 0.4825401306152344,
2992
+ "step": 852
2993
+ },
2994
+ {
2995
+ "epoch": 3.402390438247012,
2996
+ "grad_norm": 0.4402712285518646,
2997
+ "learning_rate": 2.3191351005977556e-06,
2998
+ "loss": 0.31368541717529297,
2999
+ "step": 854
3000
+ },
3001
+ {
3002
+ "epoch": 3.410358565737052,
3003
+ "grad_norm": 0.4192966818809509,
3004
+ "learning_rate": 2.298015123631246e-06,
3005
+ "loss": 0.4709932208061218,
3006
+ "step": 856
3007
+ },
3008
+ {
3009
+ "epoch": 3.4183266932270917,
3010
+ "grad_norm": 0.5742263197898865,
3011
+ "learning_rate": 2.2771538691541196e-06,
3012
+ "loss": 0.439094603061676,
3013
+ "step": 858
3014
+ },
3015
+ {
3016
+ "epoch": 3.4262948207171315,
3017
+ "grad_norm": 0.41355282068252563,
3018
+ "learning_rate": 2.256552243969029e-06,
3019
+ "loss": 0.5255416035652161,
3020
+ "step": 860
3021
+ },
3022
+ {
3023
+ "epoch": 3.4342629482071714,
3024
+ "grad_norm": 0.2783606946468353,
3025
+ "learning_rate": 2.2362111435929956e-06,
3026
+ "loss": 0.3297284245491028,
3027
+ "step": 862
3028
+ },
3029
+ {
3030
+ "epoch": 3.442231075697211,
3031
+ "grad_norm": 1.933573842048645,
3032
+ "learning_rate": 2.2161314522184778e-06,
3033
+ "loss": 0.4290310740470886,
3034
+ "step": 864
3035
+ },
3036
+ {
3037
+ "epoch": 3.450199203187251,
3038
+ "grad_norm": 0.4777624309062958,
3039
+ "learning_rate": 2.1963140426749277e-06,
3040
+ "loss": 0.5890864729881287,
3041
+ "step": 866
3042
+ },
3043
+ {
3044
+ "epoch": 3.458167330677291,
3045
+ "grad_norm": 0.30510279536247253,
3046
+ "learning_rate": 2.176759776390871e-06,
3047
+ "loss": 0.4166991114616394,
3048
+ "step": 868
3049
+ },
3050
+ {
3051
+ "epoch": 3.4661354581673307,
3052
+ "grad_norm": 0.32527998089790344,
3053
+ "learning_rate": 2.1574695033564447e-06,
3054
+ "loss": 0.343144029378891,
3055
+ "step": 870
3056
+ },
3057
+ {
3058
+ "epoch": 3.4741035856573705,
3059
+ "grad_norm": 0.06616739183664322,
3060
+ "learning_rate": 2.1384440620864597e-06,
3061
+ "loss": 0.32270875573158264,
3062
+ "step": 872
3063
+ },
3064
+ {
3065
+ "epoch": 3.4820717131474104,
3066
+ "grad_norm": 0.08085694909095764,
3067
+ "learning_rate": 2.1196842795839454e-06,
3068
+ "loss": 0.28370317816734314,
3069
+ "step": 874
3070
+ },
3071
+ {
3072
+ "epoch": 3.49003984063745,
3073
+ "grad_norm": 0.543026328086853,
3074
+ "learning_rate": 2.101190971304202e-06,
3075
+ "loss": 0.2624368369579315,
3076
+ "step": 876
3077
+ },
3078
+ {
3079
+ "epoch": 3.49800796812749,
3080
+ "grad_norm": 0.3456118702888489,
3081
+ "learning_rate": 2.0829649411193613e-06,
3082
+ "loss": 0.3216794431209564,
3083
+ "step": 878
3084
+ },
3085
+ {
3086
+ "epoch": 3.50597609561753,
3087
+ "grad_norm": 0.2047196626663208,
3088
+ "learning_rate": 2.0650069812834345e-06,
3089
+ "loss": 0.2091296762228012,
3090
+ "step": 880
3091
+ },
3092
+ {
3093
+ "epoch": 3.5139442231075697,
3094
+ "grad_norm": 0.286630779504776,
3095
+ "learning_rate": 2.0473178723978813e-06,
3096
+ "loss": 0.20823848247528076,
3097
+ "step": 882
3098
+ },
3099
+ {
3100
+ "epoch": 3.5219123505976095,
3101
+ "grad_norm": 0.5212514400482178,
3102
+ "learning_rate": 2.0298983833776717e-06,
3103
+ "loss": 0.08361003547906876,
3104
+ "step": 884
3105
+ },
3106
+ {
3107
+ "epoch": 3.5298804780876494,
3108
+ "grad_norm": 0.5501599311828613,
3109
+ "learning_rate": 2.01274927141787e-06,
3110
+ "loss": 0.4509070813655853,
3111
+ "step": 886
3112
+ },
3113
+ {
3114
+ "epoch": 3.537848605577689,
3115
+ "grad_norm": 0.39404916763305664,
3116
+ "learning_rate": 1.995871281960715e-06,
3117
+ "loss": 0.44182029366493225,
3118
+ "step": 888
3119
+ },
3120
+ {
3121
+ "epoch": 3.545816733067729,
3122
+ "grad_norm": 0.39789876341819763,
3123
+ "learning_rate": 1.9792651486632213e-06,
3124
+ "loss": 0.27486419677734375,
3125
+ "step": 890
3126
+ },
3127
+ {
3128
+ "epoch": 3.553784860557769,
3129
+ "grad_norm": 1.1401015520095825,
3130
+ "learning_rate": 1.962931593365286e-06,
3131
+ "loss": 0.3863001763820648,
3132
+ "step": 892
3133
+ },
3134
+ {
3135
+ "epoch": 3.5617529880478087,
3136
+ "grad_norm": 0.37662816047668457,
3137
+ "learning_rate": 1.946871326058308e-06,
3138
+ "loss": 0.6621991395950317,
3139
+ "step": 894
3140
+ },
3141
+ {
3142
+ "epoch": 3.5697211155378485,
3143
+ "grad_norm": 0.10905114561319351,
3144
+ "learning_rate": 1.9310850448543344e-06,
3145
+ "loss": 0.10537078976631165,
3146
+ "step": 896
3147
+ },
3148
+ {
3149
+ "epoch": 3.5776892430278884,
3150
+ "grad_norm": 0.3512639105319977,
3151
+ "learning_rate": 1.915573435955711e-06,
3152
+ "loss": 0.2836357057094574,
3153
+ "step": 898
3154
+ },
3155
+ {
3156
+ "epoch": 3.585657370517928,
3157
+ "grad_norm": 0.43090760707855225,
3158
+ "learning_rate": 1.9003371736252472e-06,
3159
+ "loss": 0.15316523611545563,
3160
+ "step": 900
3161
+ },
3162
+ {
3163
+ "epoch": 3.593625498007968,
3164
+ "grad_norm": 0.6001132726669312,
3165
+ "learning_rate": 1.8853769201569208e-06,
3166
+ "loss": 0.09330594539642334,
3167
+ "step": 902
3168
+ },
3169
+ {
3170
+ "epoch": 3.601593625498008,
3171
+ "grad_norm": 0.5064031481742859,
3172
+ "learning_rate": 1.8706933258470757e-06,
3173
+ "loss": 0.4762483835220337,
3174
+ "step": 904
3175
+ },
3176
+ {
3177
+ "epoch": 3.6095617529880477,
3178
+ "grad_norm": 0.3355056643486023,
3179
+ "learning_rate": 1.8562870289661659e-06,
3180
+ "loss": 0.27884015440940857,
3181
+ "step": 906
3182
+ },
3183
+ {
3184
+ "epoch": 3.6175298804780875,
3185
+ "grad_norm": 0.3930132985115051,
3186
+ "learning_rate": 1.8421586557309996e-06,
3187
+ "loss": 0.5141717195510864,
3188
+ "step": 908
3189
+ },
3190
+ {
3191
+ "epoch": 3.6254980079681274,
3192
+ "grad_norm": 0.46708425879478455,
3193
+ "learning_rate": 1.8283088202775314e-06,
3194
+ "loss": 0.4603351652622223,
3195
+ "step": 910
3196
+ },
3197
+ {
3198
+ "epoch": 3.633466135458167,
3199
+ "grad_norm": 0.037517350167036057,
3200
+ "learning_rate": 1.8147381246341558e-06,
3201
+ "loss": 0.02768601104617119,
3202
+ "step": 912
3203
+ },
3204
+ {
3205
+ "epoch": 3.641434262948207,
3206
+ "grad_norm": 0.3065638542175293,
3207
+ "learning_rate": 1.8014471586955424e-06,
3208
+ "loss": 0.3721899390220642,
3209
+ "step": 914
3210
+ },
3211
+ {
3212
+ "epoch": 3.649402390438247,
3213
+ "grad_norm": 0.43989261984825134,
3214
+ "learning_rate": 1.7884365001969967e-06,
3215
+ "loss": 0.43738237023353577,
3216
+ "step": 916
3217
+ },
3218
+ {
3219
+ "epoch": 3.6573705179282867,
3220
+ "grad_norm": 0.6677345633506775,
3221
+ "learning_rate": 1.7757067146893425e-06,
3222
+ "loss": 0.0748777762055397,
3223
+ "step": 918
3224
+ },
3225
+ {
3226
+ "epoch": 3.6653386454183265,
3227
+ "grad_norm": 0.3021090030670166,
3228
+ "learning_rate": 1.7632583555143435e-06,
3229
+ "loss": 0.5561968684196472,
3230
+ "step": 920
3231
+ },
3232
+ {
3233
+ "epoch": 3.6733067729083664,
3234
+ "grad_norm": 0.42820993065834045,
3235
+ "learning_rate": 1.751091963780643e-06,
3236
+ "loss": 0.07096469402313232,
3237
+ "step": 922
3238
+ },
3239
+ {
3240
+ "epoch": 3.681274900398406,
3241
+ "grad_norm": 0.8393615484237671,
3242
+ "learning_rate": 1.7392080683402496e-06,
3243
+ "loss": 0.46100661158561707,
3244
+ "step": 924
3245
+ },
3246
+ {
3247
+ "epoch": 3.6892430278884465,
3248
+ "grad_norm": 0.6544818878173828,
3249
+ "learning_rate": 1.7276071857655479e-06,
3250
+ "loss": 0.1528330296278,
3251
+ "step": 926
3252
+ },
3253
+ {
3254
+ "epoch": 3.6972111553784863,
3255
+ "grad_norm": 0.31229308247566223,
3256
+ "learning_rate": 1.716289820326839e-06,
3257
+ "loss": 0.29350802302360535,
3258
+ "step": 928
3259
+ },
3260
+ {
3261
+ "epoch": 3.705179282868526,
3262
+ "grad_norm": 0.1188875362277031,
3263
+ "learning_rate": 1.7052564639704286e-06,
3264
+ "loss": 0.3660446107387543,
3265
+ "step": 930
3266
+ },
3267
+ {
3268
+ "epoch": 3.713147410358566,
3269
+ "grad_norm": 0.5841293931007385,
3270
+ "learning_rate": 1.6945075962972356e-06,
3271
+ "loss": 0.45137277245521545,
3272
+ "step": 932
3273
+ },
3274
+ {
3275
+ "epoch": 3.721115537848606,
3276
+ "grad_norm": 0.7146270275115967,
3277
+ "learning_rate": 1.6840436845419498e-06,
3278
+ "loss": 0.4348509907722473,
3279
+ "step": 934
3280
+ },
3281
+ {
3282
+ "epoch": 3.7290836653386457,
3283
+ "grad_norm": 0.326523095369339,
3284
+ "learning_rate": 1.6738651835527184e-06,
3285
+ "loss": 0.4922831654548645,
3286
+ "step": 936
3287
+ },
3288
+ {
3289
+ "epoch": 3.7370517928286855,
3290
+ "grad_norm": 0.8038604855537415,
3291
+ "learning_rate": 1.6639725357713769e-06,
3292
+ "loss": 0.21507446467876434,
3293
+ "step": 938
3294
+ },
3295
+ {
3296
+ "epoch": 3.7450199203187253,
3297
+ "grad_norm": 0.36527737975120544,
3298
+ "learning_rate": 1.6543661712142184e-06,
3299
+ "loss": 0.4618900418281555,
3300
+ "step": 940
3301
+ },
3302
+ {
3303
+ "epoch": 3.752988047808765,
3304
+ "grad_norm": 0.6607845425605774,
3305
+ "learning_rate": 1.645046507453294e-06,
3306
+ "loss": 0.36659500002861023,
3307
+ "step": 942
3308
+ },
3309
+ {
3310
+ "epoch": 3.760956175298805,
3311
+ "grad_norm": 0.421165406703949,
3312
+ "learning_rate": 1.6360139495982712e-06,
3313
+ "loss": 0.28992268443107605,
3314
+ "step": 944
3315
+ },
3316
+ {
3317
+ "epoch": 3.768924302788845,
3318
+ "grad_norm": 0.5764026641845703,
3319
+ "learning_rate": 1.6272688902788207e-06,
3320
+ "loss": 0.5770589709281921,
3321
+ "step": 946
3322
+ },
3323
+ {
3324
+ "epoch": 3.7768924302788847,
3325
+ "grad_norm": 0.3415585160255432,
3326
+ "learning_rate": 1.6188117096275477e-06,
3327
+ "loss": 0.3260127305984497,
3328
+ "step": 948
3329
+ },
3330
+ {
3331
+ "epoch": 3.7848605577689245,
3332
+ "grad_norm": 0.2808169424533844,
3333
+ "learning_rate": 1.610642775263468e-06,
3334
+ "loss": 0.5168456435203552,
3335
+ "step": 950
3336
+ },
3337
+ {
3338
+ "epoch": 3.7928286852589643,
3339
+ "grad_norm": 0.3828094005584717,
3340
+ "learning_rate": 1.6027624422760312e-06,
3341
+ "loss": 0.5155588388442993,
3342
+ "step": 952
3343
+ },
3344
+ {
3345
+ "epoch": 3.800796812749004,
3346
+ "grad_norm": 0.616820216178894,
3347
+ "learning_rate": 1.5951710532096857e-06,
3348
+ "loss": 0.2644089460372925,
3349
+ "step": 954
3350
+ },
3351
+ {
3352
+ "epoch": 3.808764940239044,
3353
+ "grad_norm": 0.531527042388916,
3354
+ "learning_rate": 1.5878689380489846e-06,
3355
+ "loss": 0.38867413997650146,
3356
+ "step": 956
3357
+ },
3358
+ {
3359
+ "epoch": 3.816733067729084,
3360
+ "grad_norm": 0.9145589470863342,
3361
+ "learning_rate": 1.580856414204247e-06,
3362
+ "loss": 0.3010810315608978,
3363
+ "step": 958
3364
+ },
3365
+ {
3366
+ "epoch": 3.8247011952191237,
3367
+ "grad_norm": 1.3794469833374023,
3368
+ "learning_rate": 1.5741337864977558e-06,
3369
+ "loss": 0.21975839138031006,
3370
+ "step": 960
3371
+ },
3372
+ {
3373
+ "epoch": 3.8326693227091635,
3374
+ "grad_norm": 0.11370343714952469,
3375
+ "learning_rate": 1.567701347150513e-06,
3376
+ "loss": 0.3248888850212097,
3377
+ "step": 962
3378
+ },
3379
+ {
3380
+ "epoch": 3.8406374501992033,
3381
+ "grad_norm": 0.4226270616054535,
3382
+ "learning_rate": 1.5615593757695319e-06,
3383
+ "loss": 0.6149446964263916,
3384
+ "step": 964
3385
+ },
3386
+ {
3387
+ "epoch": 3.848605577689243,
3388
+ "grad_norm": 0.4638464152812958,
3389
+ "learning_rate": 1.555708139335687e-06,
3390
+ "loss": 0.21839484572410583,
3391
+ "step": 966
3392
+ },
3393
+ {
3394
+ "epoch": 3.856573705179283,
3395
+ "grad_norm": 0.28881698846817017,
3396
+ "learning_rate": 1.5501478921921071e-06,
3397
+ "loss": 0.3512417674064636,
3398
+ "step": 968
3399
+ },
3400
+ {
3401
+ "epoch": 3.864541832669323,
3402
+ "grad_norm": 0.8101674318313599,
3403
+ "learning_rate": 1.54487887603312e-06,
3404
+ "loss": 0.36906710267066956,
3405
+ "step": 970
3406
+ },
3407
+ {
3408
+ "epoch": 3.8725099601593627,
3409
+ "grad_norm": 0.10503221303224564,
3410
+ "learning_rate": 1.5399013198937452e-06,
3411
+ "loss": 0.3287951946258545,
3412
+ "step": 972
3413
+ },
3414
+ {
3415
+ "epoch": 3.8804780876494025,
3416
+ "grad_norm": 0.1844586879014969,
3417
+ "learning_rate": 1.5352154401397418e-06,
3418
+ "loss": 0.32523638010025024,
3419
+ "step": 974
3420
+ },
3421
+ {
3422
+ "epoch": 3.8884462151394423,
3423
+ "grad_norm": 0.38847818970680237,
3424
+ "learning_rate": 1.5308214404581968e-06,
3425
+ "loss": 0.5000988245010376,
3426
+ "step": 976
3427
+ },
3428
+ {
3429
+ "epoch": 3.896414342629482,
3430
+ "grad_norm": 0.4692430794239044,
3431
+ "learning_rate": 1.5267195118486794e-06,
3432
+ "loss": 0.2642746567726135,
3433
+ "step": 978
3434
+ },
3435
+ {
3436
+ "epoch": 3.904382470119522,
3437
+ "grad_norm": 0.2286023050546646,
3438
+ "learning_rate": 1.522909832614931e-06,
3439
+ "loss": 0.2238185554742813,
3440
+ "step": 980
3441
+ },
3442
+ {
3443
+ "epoch": 3.912350597609562,
3444
+ "grad_norm": 0.3902443051338196,
3445
+ "learning_rate": 1.5193925683571211e-06,
3446
+ "loss": 0.19102515280246735,
3447
+ "step": 982
3448
+ },
3449
+ {
3450
+ "epoch": 3.9203187250996017,
3451
+ "grad_norm": 0.4479309320449829,
3452
+ "learning_rate": 1.516167871964643e-06,
3453
+ "loss": 0.5202714800834656,
3454
+ "step": 984
3455
+ },
3456
+ {
3457
+ "epoch": 3.9282868525896415,
3458
+ "grad_norm": 0.5768634080886841,
3459
+ "learning_rate": 1.5132358836094728e-06,
3460
+ "loss": 0.16960352659225464,
3461
+ "step": 986
3462
+ },
3463
+ {
3464
+ "epoch": 3.9362549800796813,
3465
+ "grad_norm": 3.171630620956421,
3466
+ "learning_rate": 1.510596730740074e-06,
3467
+ "loss": 0.4183100461959839,
3468
+ "step": 988
3469
+ },
3470
+ {
3471
+ "epoch": 3.944223107569721,
3472
+ "grad_norm": 0.10318754613399506,
3473
+ "learning_rate": 1.508250528075857e-06,
3474
+ "loss": 0.3005601763725281,
3475
+ "step": 990
3476
+ },
3477
+ {
3478
+ "epoch": 3.952191235059761,
3479
+ "grad_norm": 0.5118750929832458,
3480
+ "learning_rate": 1.5061973776021949e-06,
3481
+ "loss": 0.4696381390094757,
3482
+ "step": 992
3483
+ },
3484
+ {
3485
+ "epoch": 3.960159362549801,
3486
+ "grad_norm": 0.3834742307662964,
3487
+ "learning_rate": 1.504437368565988e-06,
3488
+ "loss": 0.1685551553964615,
3489
+ "step": 994
3490
+ },
3491
+ {
3492
+ "epoch": 3.9681274900398407,
3493
+ "grad_norm": 0.34701693058013916,
3494
+ "learning_rate": 1.502970577471785e-06,
3495
+ "loss": 0.4004333019256592,
3496
+ "step": 996
3497
+ },
3498
+ {
3499
+ "epoch": 3.9760956175298805,
3500
+ "grad_norm": 0.14854289591312408,
3501
+ "learning_rate": 1.5017970680784587e-06,
3502
+ "loss": 0.32395121455192566,
3503
+ "step": 998
3504
+ },
3505
+ {
3506
+ "epoch": 3.9840637450199203,
3507
+ "grad_norm": 0.3810655474662781,
3508
+ "learning_rate": 1.5009168913964322e-06,
3509
+ "loss": 0.23012831807136536,
3510
+ "step": 1000
3511
+ },
3512
+ {
3513
+ "epoch": 3.99203187250996,
3514
+ "grad_norm": 0.3381198048591614,
3515
+ "learning_rate": 1.5003300856854642e-06,
3516
+ "loss": 0.48588454723358154,
3517
+ "step": 1002
3518
+ },
3519
+ {
3520
+ "epoch": 4.0,
3521
+ "grad_norm": 0.07251780480146408,
3522
+ "learning_rate": 1.5000366764529846e-06,
3523
+ "loss": 0.11095666140317917,
3524
+ "step": 1004
3525
+ },
3526
+ {
3527
+ "epoch": 4.0,
3528
+ "step": 1004,
3529
+ "total_flos": 4.038502240003031e+18,
3530
+ "train_loss": 0.7418717171225059,
3531
+ "train_runtime": 10936.9117,
3532
+ "train_samples_per_second": 5.508,
3533
+ "train_steps_per_second": 0.092
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": 4.038502240003031e+18,
3554
+ "train_batch_size": 3,
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 sha256:98ca1a3153d0bb381eded7d815a0d6c846f865dfd739454844594d8ea37ee83d
3
+ size 5649
training_loss.png ADDED