Hugging Face's logo

furproxy
/
9b-72

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
llama-factory
full
Generated from Trainer
conversational
Model card Files
xet
 Community
furproxy commited on
Commit
f02eeaa
·
verified ·
1 Parent(s): d5f3cc5

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", 2e-5), language_lr),
40
+ "vision": _fallback(getattr(training_args, "vision_adamw_lr", 1e-5), vision_lr),
41
+ "merger": _fallback(getattr(training_args, "merger_adamw_lr", 5e-6), 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", 2e-5), language_lr),
40
+ "vision": _fallback(getattr(training_args, "vision_adamw_lr", 1e-5), vision_lr),
41
+ "merger": _fallback(getattr(training_args, "merger_adamw_lr", 5e-6), 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": 7862.994109807929,
3
+ "epoch": 4.0,
4
+ "total_flos": 3.519329211045118e+18,
5
+ "train_loss": 0.7596988798197047,
6
+ "train_runtime": 8661.0758,
7
+ "train_samples_per_second": 6.955,
8
+ "train_steps_per_second": 0.116
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 sha256:26233145c233a5cdd5687a889b3214a1079fb15094297bd6e4ef67f1617f79dd
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": 7862.994109807929,
3
+ "epoch": 4.0,
4
+ "total_flos": 3.519329211045118e+18,
5
+ "train_loss": 0.7596988798197047,
6
+ "train_runtime": 8661.0758,
7
+ "train_samples_per_second": 6.955,
8
+ "train_steps_per_second": 0.116
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": 0.9957464337348938,
15
+ "learning_rate": 3.921568627450981e-07,
16
+ "loss": 2.092358350753784,
17
+ "step": 2
18
+ },
19
+ {
20
+ "epoch": 0.01593625498007968,
21
+ "grad_norm": 0.8930569887161255,
22
+ "learning_rate": 1.1764705882352942e-06,
23
+ "loss": 2.0088067054748535,
24
+ "step": 4
25
+ },
26
+ {
27
+ "epoch": 0.02390438247011952,
28
+ "grad_norm": 2.4471495151519775,
29
+ "learning_rate": 1.96078431372549e-06,
30
+ "loss": 2.108173370361328,
31
+ "step": 6
32
+ },
33
+ {
34
+ "epoch": 0.03187250996015936,
35
+ "grad_norm": 0.4212417006492615,
36
+ "learning_rate": 2.7450980392156867e-06,
37
+ "loss": 1.815500020980835,
38
+ "step": 8
39
+ },
40
+ {
41
+ "epoch": 0.0398406374501992,
42
+ "grad_norm": 0.9693068861961365,
43
+ "learning_rate": 3.529411764705883e-06,
44
+ "loss": 1.2837271690368652,
45
+ "step": 10
46
+ },
47
+ {
48
+ "epoch": 0.04780876494023904,
49
+ "grad_norm": 0.7192004919052124,
50
+ "learning_rate": 4.313725490196079e-06,
51
+ "loss": 1.5911014080047607,
52
+ "step": 12
53
+ },
54
+ {
55
+ "epoch": 0.055776892430278883,
56
+ "grad_norm": 0.4175472557544708,
57
+ "learning_rate": 5.098039215686274e-06,
58
+ "loss": 1.6157869100570679,
59
+ "step": 14
60
+ },
61
+ {
62
+ "epoch": 0.06374501992031872,
63
+ "grad_norm": 3.3379127979278564,
64
+ "learning_rate": 5.882352941176471e-06,
65
+ "loss": 1.7002140283584595,
66
+ "step": 16
67
+ },
68
+ {
69
+ "epoch": 0.07171314741035857,
70
+ "grad_norm": 0.7876597046852112,
71
+ "learning_rate": 6.666666666666667e-06,
72
+ "loss": 1.5408495664596558,
73
+ "step": 18
74
+ },
75
+ {
76
+ "epoch": 0.0796812749003984,
77
+ "grad_norm": 0.46036335825920105,
78
+ "learning_rate": 7.450980392156863e-06,
79
+ "loss": 1.4705753326416016,
80
+ "step": 20
81
+ },
82
+ {
83
+ "epoch": 0.08764940239043825,
84
+ "grad_norm": 0.673358678817749,
85
+ "learning_rate": 8.23529411764706e-06,
86
+ "loss": 1.1017413139343262,
87
+ "step": 22
88
+ },
89
+ {
90
+ "epoch": 0.09561752988047809,
91
+ "grad_norm": 0.7209763526916504,
92
+ "learning_rate": 9.019607843137256e-06,
93
+ "loss": 1.294268250465393,
94
+ "step": 24
95
+ },
96
+ {
97
+ "epoch": 0.10358565737051793,
98
+ "grad_norm": 0.4403802752494812,
99
+ "learning_rate": 9.803921568627451e-06,
100
+ "loss": 1.395767331123352,
101
+ "step": 26
102
+ },
103
+ {
104
+ "epoch": 0.11155378486055777,
105
+ "grad_norm": 0.4559030830860138,
106
+ "learning_rate": 1.0588235294117648e-05,
107
+ "loss": 1.6222474575042725,
108
+ "step": 28
109
+ },
110
+ {
111
+ "epoch": 0.11952191235059761,
112
+ "grad_norm": 0.8342038989067078,
113
+ "learning_rate": 1.1372549019607844e-05,
114
+ "loss": 1.3161066770553589,
115
+ "step": 30
116
+ },
117
+ {
118
+ "epoch": 0.12749003984063745,
119
+ "grad_norm": 0.5698347091674805,
120
+ "learning_rate": 1.215686274509804e-05,
121
+ "loss": 1.1639069318771362,
122
+ "step": 32
123
+ },
124
+ {
125
+ "epoch": 0.13545816733067728,
126
+ "grad_norm": 0.6199248433113098,
127
+ "learning_rate": 1.2941176470588238e-05,
128
+ "loss": 1.24606192111969,
129
+ "step": 34
130
+ },
131
+ {
132
+ "epoch": 0.14342629482071714,
133
+ "grad_norm": 0.288705974817276,
134
+ "learning_rate": 1.3725490196078432e-05,
135
+ "loss": 1.3773506879806519,
136
+ "step": 36
137
+ },
138
+ {
139
+ "epoch": 0.15139442231075698,
140
+ "grad_norm": 0.6997499465942383,
141
+ "learning_rate": 1.4509803921568629e-05,
142
+ "loss": 1.175160527229309,
143
+ "step": 38
144
+ },
145
+ {
146
+ "epoch": 0.1593625498007968,
147
+ "grad_norm": 0.5133037567138672,
148
+ "learning_rate": 1.5294117647058822e-05,
149
+ "loss": 1.2939589023590088,
150
+ "step": 40
151
+ },
152
+ {
153
+ "epoch": 0.16733067729083664,
154
+ "grad_norm": 1.701066017150879,
155
+ "learning_rate": 1.607843137254902e-05,
156
+ "loss": 0.8205271363258362,
157
+ "step": 42
158
+ },
159
+ {
160
+ "epoch": 0.1752988047808765,
161
+ "grad_norm": 0.4490733742713928,
162
+ "learning_rate": 1.686274509803922e-05,
163
+ "loss": 0.9646032452583313,
164
+ "step": 44
165
+ },
166
+ {
167
+ "epoch": 0.18326693227091634,
168
+ "grad_norm": 0.7051479816436768,
169
+ "learning_rate": 1.7647058823529414e-05,
170
+ "loss": 0.9549788236618042,
171
+ "step": 46
172
+ },
173
+ {
174
+ "epoch": 0.19123505976095617,
175
+ "grad_norm": 0.8199656009674072,
176
+ "learning_rate": 1.843137254901961e-05,
177
+ "loss": 1.1781502962112427,
178
+ "step": 48
179
+ },
180
+ {
181
+ "epoch": 0.199203187250996,
182
+ "grad_norm": 0.45470499992370605,
183
+ "learning_rate": 1.9215686274509807e-05,
184
+ "loss": 1.3290269374847412,
185
+ "step": 50
186
+ },
187
+ {
188
+ "epoch": 0.20717131474103587,
189
+ "grad_norm": 0.850440502166748,
190
+ "learning_rate": 2e-05,
191
+ "loss": 1.2819088697433472,
192
+ "step": 52
193
+ },
194
+ {
195
+ "epoch": 0.2151394422310757,
196
+ "grad_norm": 2.6981277465820312,
197
+ "learning_rate": 1.9999804392782173e-05,
198
+ "loss": 1.1220871210098267,
199
+ "step": 54
200
+ },
201
+ {
202
+ "epoch": 0.22310756972111553,
203
+ "grad_norm": 0.5424857139587402,
204
+ "learning_rate": 1.9999217579631398e-05,
205
+ "loss": 1.534443974494934,
206
+ "step": 56
207
+ },
208
+ {
209
+ "epoch": 0.23107569721115537,
210
+ "grad_norm": 0.3990076780319214,
211
+ "learning_rate": 1.9998239586055426e-05,
212
+ "loss": 1.3426909446716309,
213
+ "step": 58
214
+ },
215
+ {
216
+ "epoch": 0.23904382470119523,
217
+ "grad_norm": 0.36483845114707947,
218
+ "learning_rate": 1.999687045456595e-05,
219
+ "loss": 0.7846556305885315,
220
+ "step": 60
221
+ },
222
+ {
223
+ "epoch": 0.24701195219123506,
224
+ "grad_norm": 0.3828938603401184,
225
+ "learning_rate": 1.9995110244676744e-05,
226
+ "loss": 1.3494534492492676,
227
+ "step": 62
228
+ },
229
+ {
230
+ "epoch": 0.2549800796812749,
231
+ "grad_norm": 1.3368655443191528,
232
+ "learning_rate": 1.999295903290109e-05,
233
+ "loss": 1.1254225969314575,
234
+ "step": 64
235
+ },
236
+ {
237
+ "epoch": 0.26294820717131473,
238
+ "grad_norm": 0.5956477522850037,
239
+ "learning_rate": 1.999041691274844e-05,
240
+ "loss": 1.283703327178955,
241
+ "step": 66
242
+ },
243
+ {
244
+ "epoch": 0.27091633466135456,
245
+ "grad_norm": 1.2891621589660645,
246
+ "learning_rate": 1.998748399472037e-05,
247
+ "loss": 0.9298644661903381,
248
+ "step": 68
249
+ },
250
+ {
251
+ "epoch": 0.2788844621513944,
252
+ "grad_norm": 0.5659030675888062,
253
+ "learning_rate": 1.9984160406305745e-05,
254
+ "loss": 1.5809705257415771,
255
+ "step": 70
256
+ },
257
+ {
258
+ "epoch": 0.2868525896414343,
259
+ "grad_norm": 0.6271833181381226,
260
+ "learning_rate": 1.9980446291975217e-05,
261
+ "loss": 0.895917534828186,
262
+ "step": 72
263
+ },
264
+ {
265
+ "epoch": 0.2948207171314741,
266
+ "grad_norm": 1.1333332061767578,
267
+ "learning_rate": 1.99763418131749e-05,
268
+ "loss": 1.1716889142990112,
269
+ "step": 74
270
+ },
271
+ {
272
+ "epoch": 0.30278884462151395,
273
+ "grad_norm": 0.9091482758522034,
274
+ "learning_rate": 1.9971847148319392e-05,
275
+ "loss": 1.4918345212936401,
276
+ "step": 76
277
+ },
278
+ {
279
+ "epoch": 0.3107569721115538,
280
+ "grad_norm": 1.295212745666504,
281
+ "learning_rate": 1.9966962492784006e-05,
282
+ "loss": 1.0331875085830688,
283
+ "step": 78
284
+ },
285
+ {
286
+ "epoch": 0.3187250996015936,
287
+ "grad_norm": 0.2440294772386551,
288
+ "learning_rate": 1.996168805889627e-05,
289
+ "loss": 0.924660861492157,
290
+ "step": 80
291
+ },
292
+ {
293
+ "epoch": 0.32669322709163345,
294
+ "grad_norm": 0.28573158383369446,
295
+ "learning_rate": 1.99560240759267e-05,
296
+ "loss": 1.375991702079773,
297
+ "step": 82
298
+ },
299
+ {
300
+ "epoch": 0.3346613545816733,
301
+ "grad_norm": 0.45677199959754944,
302
+ "learning_rate": 1.9949970790078847e-05,
303
+ "loss": 0.9936637878417969,
304
+ "step": 84
305
+ },
306
+ {
307
+ "epoch": 0.3426294820717131,
308
+ "grad_norm": 0.3065952956676483,
309
+ "learning_rate": 1.9943528464478573e-05,
310
+ "loss": 1.3540968894958496,
311
+ "step": 86
312
+ },
313
+ {
314
+ "epoch": 0.350597609561753,
315
+ "grad_norm": 1.1819368600845337,
316
+ "learning_rate": 1.993669737916263e-05,
317
+ "loss": 1.0978449583053589,
318
+ "step": 88
319
+ },
320
+ {
321
+ "epoch": 0.35856573705179284,
322
+ "grad_norm": 0.39413952827453613,
323
+ "learning_rate": 1.9929477831066485e-05,
324
+ "loss": 1.3455610275268555,
325
+ "step": 90
326
+ },
327
+ {
328
+ "epoch": 0.3665338645418327,
329
+ "grad_norm": 0.586239755153656,
330
+ "learning_rate": 1.992187013401141e-05,
331
+ "loss": 1.158692717552185,
332
+ "step": 92
333
+ },
334
+ {
335
+ "epoch": 0.3745019920318725,
336
+ "grad_norm": 0.2929425537586212,
337
+ "learning_rate": 1.9913874618690837e-05,
338
+ "loss": 1.2582529783248901,
339
+ "step": 94
340
+ },
341
+ {
342
+ "epoch": 0.38247011952191234,
343
+ "grad_norm": 0.4790647327899933,
344
+ "learning_rate": 1.9905491632655996e-05,
345
+ "loss": 1.1448304653167725,
346
+ "step": 96
347
+ },
348
+ {
349
+ "epoch": 0.3904382470119522,
350
+ "grad_norm": 0.31453412771224976,
351
+ "learning_rate": 1.989672154030078e-05,
352
+ "loss": 1.277166485786438,
353
+ "step": 98
354
+ },
355
+ {
356
+ "epoch": 0.398406374501992,
357
+ "grad_norm": 0.27740514278411865,
358
+ "learning_rate": 1.988756472284595e-05,
359
+ "loss": 0.9082943201065063,
360
+ "step": 100
361
+ },
362
+ {
363
+ "epoch": 0.4063745019920319,
364
+ "grad_norm": 0.516435444355011,
365
+ "learning_rate": 1.9878021578322518e-05,
366
+ "loss": 1.2856113910675049,
367
+ "step": 102
368
+ },
369
+ {
370
+ "epoch": 0.41434262948207173,
371
+ "grad_norm": 0.38994523882865906,
372
+ "learning_rate": 1.9868092521554478e-05,
373
+ "loss": 0.8686521053314209,
374
+ "step": 104
375
+ },
376
+ {
377
+ "epoch": 0.42231075697211157,
378
+ "grad_norm": 1.3962106704711914,
379
+ "learning_rate": 1.9857777984140746e-05,
380
+ "loss": 0.766525387763977,
381
+ "step": 106
382
+ },
383
+ {
384
+ "epoch": 0.4302788844621514,
385
+ "grad_norm": 0.48875540494918823,
386
+ "learning_rate": 1.9847078414436438e-05,
387
+ "loss": 1.0129103660583496,
388
+ "step": 108
389
+ },
390
+ {
391
+ "epoch": 0.43824701195219123,
392
+ "grad_norm": 0.679126501083374,
393
+ "learning_rate": 1.983599427753334e-05,
394
+ "loss": 1.319523572921753,
395
+ "step": 110
396
+ },
397
+ {
398
+ "epoch": 0.44621513944223107,
399
+ "grad_norm": 0.6783590912818909,
400
+ "learning_rate": 1.9824526055239712e-05,
401
+ "loss": 0.8960539698600769,
402
+ "step": 112
403
+ },
404
+ {
405
+ "epoch": 0.4541832669322709,
406
+ "grad_norm": 0.6845623254776001,
407
+ "learning_rate": 1.981267424605935e-05,
408
+ "loss": 1.1875278949737549,
409
+ "step": 114
410
+ },
411
+ {
412
+ "epoch": 0.46215139442231074,
413
+ "grad_norm": 0.3849475085735321,
414
+ "learning_rate": 1.98004393651699e-05,
415
+ "loss": 1.332448959350586,
416
+ "step": 116
417
+ },
418
+ {
419
+ "epoch": 0.4701195219123506,
420
+ "grad_norm": 0.3897473216056824,
421
+ "learning_rate": 1.9787821944400477e-05,
422
+ "loss": 1.3839960098266602,
423
+ "step": 118
424
+ },
425
+ {
426
+ "epoch": 0.47808764940239046,
427
+ "grad_norm": 0.3927645981311798,
428
+ "learning_rate": 1.9774822532208537e-05,
429
+ "loss": 1.2699512243270874,
430
+ "step": 120
431
+ },
432
+ {
433
+ "epoch": 0.4860557768924303,
434
+ "grad_norm": 0.4918311834335327,
435
+ "learning_rate": 1.9761441693656052e-05,
436
+ "loss": 1.0304157733917236,
437
+ "step": 122
438
+ },
439
+ {
440
+ "epoch": 0.4940239043824701,
441
+ "grad_norm": 1.8012769222259521,
442
+ "learning_rate": 1.974768001038493e-05,
443
+ "loss": 1.088665246963501,
444
+ "step": 124
445
+ },
446
+ {
447
+ "epoch": 0.50199203187251,
448
+ "grad_norm": 0.7356415390968323,
449
+ "learning_rate": 1.973353808059175e-05,
450
+ "loss": 0.9787855744361877,
451
+ "step": 126
452
+ },
453
+ {
454
+ "epoch": 0.5099601593625498,
455
+ "grad_norm": 0.4110127091407776,
456
+ "learning_rate": 1.9719016519001738e-05,
457
+ "loss": 1.3301374912261963,
458
+ "step": 128
459
+ },
460
+ {
461
+ "epoch": 0.5179282868525896,
462
+ "grad_norm": 0.3917061984539032,
463
+ "learning_rate": 1.9704115956842066e-05,
464
+ "loss": 0.9724149703979492,
465
+ "step": 130
466
+ },
467
+ {
468
+ "epoch": 0.5258964143426295,
469
+ "grad_norm": 0.41339319944381714,
470
+ "learning_rate": 1.9688837041814396e-05,
471
+ "loss": 0.9403734803199768,
472
+ "step": 132
473
+ },
474
+ {
475
+ "epoch": 0.5338645418326693,
476
+ "grad_norm": 0.4448390603065491,
477
+ "learning_rate": 1.967318043806675e-05,
478
+ "loss": 0.9430965781211853,
479
+ "step": 134
480
+ },
481
+ {
482
+ "epoch": 0.5418326693227091,
483
+ "grad_norm": 1.0087687969207764,
484
+ "learning_rate": 1.965714682616461e-05,
485
+ "loss": 1.3703218698501587,
486
+ "step": 136
487
+ },
488
+ {
489
+ "epoch": 0.549800796812749,
490
+ "grad_norm": 0.2762286067008972,
491
+ "learning_rate": 1.9640736903061363e-05,
492
+ "loss": 1.0063937902450562,
493
+ "step": 138
494
+ },
495
+ {
496
+ "epoch": 0.5577689243027888,
497
+ "grad_norm": 0.6342159509658813,
498
+ "learning_rate": 1.9623951382067983e-05,
499
+ "loss": 1.1634577512741089,
500
+ "step": 140
501
+ },
502
+ {
503
+ "epoch": 0.5657370517928287,
504
+ "grad_norm": 0.4940018951892853,
505
+ "learning_rate": 1.960679099282204e-05,
506
+ "loss": 1.080363392829895,
507
+ "step": 142
508
+ },
509
+ {
510
+ "epoch": 0.5737051792828686,
511
+ "grad_norm": 0.361111044883728,
512
+ "learning_rate": 1.9589256481255984e-05,
513
+ "loss": 1.2627440690994263,
514
+ "step": 144
515
+ },
516
+ {
517
+ "epoch": 0.5816733067729084,
518
+ "grad_norm": 0.6875961422920227,
519
+ "learning_rate": 1.9571348609564697e-05,
520
+ "loss": 1.2056587934494019,
521
+ "step": 146
522
+ },
523
+ {
524
+ "epoch": 0.5896414342629482,
525
+ "grad_norm": 0.543710470199585,
526
+ "learning_rate": 1.9553068156172404e-05,
527
+ "loss": 1.059579849243164,
528
+ "step": 148
529
+ },
530
+ {
531
+ "epoch": 0.5976095617529881,
532
+ "grad_norm": 0.5071445107460022,
533
+ "learning_rate": 1.9534415915698793e-05,
534
+ "loss": 1.0381158590316772,
535
+ "step": 150
536
+ },
537
+ {
538
+ "epoch": 0.6055776892430279,
539
+ "grad_norm": 0.36371827125549316,
540
+ "learning_rate": 1.9515392698924504e-05,
541
+ "loss": 1.0027271509170532,
542
+ "step": 152
543
+ },
544
+ {
545
+ "epoch": 0.6135458167330677,
546
+ "grad_norm": 0.6223253011703491,
547
+ "learning_rate": 1.949599933275587e-05,
548
+ "loss": 1.1761221885681152,
549
+ "step": 154
550
+ },
551
+ {
552
+ "epoch": 0.6215139442231076,
553
+ "grad_norm": 2.302541494369507,
554
+ "learning_rate": 1.9476236660188982e-05,
555
+ "loss": 1.217422366142273,
556
+ "step": 156
557
+ },
558
+ {
559
+ "epoch": 0.6294820717131474,
560
+ "grad_norm": 0.9959671497344971,
561
+ "learning_rate": 1.9456105540273035e-05,
562
+ "loss": 1.2247614860534668,
563
+ "step": 158
564
+ },
565
+ {
566
+ "epoch": 0.6374501992031872,
567
+ "grad_norm": 0.4775502681732178,
568
+ "learning_rate": 1.9435606848073003e-05,
569
+ "loss": 1.0775845050811768,
570
+ "step": 160
571
+ },
572
+ {
573
+ "epoch": 0.6454183266932271,
574
+ "grad_norm": 0.26653873920440674,
575
+ "learning_rate": 1.9414741474631586e-05,
576
+ "loss": 0.8565905690193176,
577
+ "step": 162
578
+ },
579
+ {
580
+ "epoch": 0.6533864541832669,
581
+ "grad_norm": 0.22560259699821472,
582
+ "learning_rate": 1.939351032693048e-05,
583
+ "loss": 1.2054938077926636,
584
+ "step": 164
585
+ },
586
+ {
587
+ "epoch": 0.6613545816733067,
588
+ "grad_norm": 1.6585121154785156,
589
+ "learning_rate": 1.9371914327850958e-05,
590
+ "loss": 0.9322201013565063,
591
+ "step": 166
592
+ },
593
+ {
594
+ "epoch": 0.6693227091633466,
595
+ "grad_norm": 0.2651222050189972,
596
+ "learning_rate": 1.934995441613376e-05,
597
+ "loss": 1.2844748497009277,
598
+ "step": 168
599
+ },
600
+ {
601
+ "epoch": 0.6772908366533864,
602
+ "grad_norm": 1.817061185836792,
603
+ "learning_rate": 1.9327631546338263e-05,
604
+ "loss": 1.0478943586349487,
605
+ "step": 170
606
+ },
607
+ {
608
+ "epoch": 0.6852589641434262,
609
+ "grad_norm": 0.36144477128982544,
610
+ "learning_rate": 1.9304946688801014e-05,
611
+ "loss": 0.9816558957099915,
612
+ "step": 172
613
+ },
614
+ {
615
+ "epoch": 0.6932270916334662,
616
+ "grad_norm": 0.4334961771965027,
617
+ "learning_rate": 1.9281900829593544e-05,
618
+ "loss": 1.272782564163208,
619
+ "step": 174
620
+ },
621
+ {
622
+ "epoch": 0.701195219123506,
623
+ "grad_norm": 1.2739726305007935,
624
+ "learning_rate": 1.9258494970479494e-05,
625
+ "loss": 0.8628472089767456,
626
+ "step": 176
627
+ },
628
+ {
629
+ "epoch": 0.7091633466135459,
630
+ "grad_norm": 0.8010619878768921,
631
+ "learning_rate": 1.923473012887109e-05,
632
+ "loss": 0.9980822205543518,
633
+ "step": 178
634
+ },
635
+ {
636
+ "epoch": 0.7171314741035857,
637
+ "grad_norm": 0.6696943640708923,
638
+ "learning_rate": 1.9210607337784885e-05,
639
+ "loss": 1.1843255758285522,
640
+ "step": 180
641
+ },
642
+ {
643
+ "epoch": 0.7250996015936255,
644
+ "grad_norm": 0.20754286646842957,
645
+ "learning_rate": 1.9186127645796902e-05,
646
+ "loss": 0.5432711839675903,
647
+ "step": 182
648
+ },
649
+ {
650
+ "epoch": 0.7330677290836654,
651
+ "grad_norm": 0.3109559714794159,
652
+ "learning_rate": 1.916129211699701e-05,
653
+ "loss": 1.4254323244094849,
654
+ "step": 184
655
+ },
656
+ {
657
+ "epoch": 0.7410358565737052,
658
+ "grad_norm": 0.27430951595306396,
659
+ "learning_rate": 1.91361018309427e-05,
660
+ "loss": 1.3617608547210693,
661
+ "step": 186
662
+ },
663
+ {
664
+ "epoch": 0.749003984063745,
665
+ "grad_norm": 0.2770460247993469,
666
+ "learning_rate": 1.911055788261214e-05,
667
+ "loss": 1.1949325799942017,
668
+ "step": 188
669
+ },
670
+ {
671
+ "epoch": 0.7569721115537849,
672
+ "grad_norm": 0.5085469484329224,
673
+ "learning_rate": 1.9084661382356592e-05,
674
+ "loss": 0.9465351104736328,
675
+ "step": 190
676
+ },
677
+ {
678
+ "epoch": 0.7649402390438247,
679
+ "grad_norm": 0.6416473984718323,
680
+ "learning_rate": 1.9058413455852142e-05,
681
+ "loss": 1.2965277433395386,
682
+ "step": 192
683
+ },
684
+ {
685
+ "epoch": 0.7729083665338645,
686
+ "grad_norm": 0.3408448398113251,
687
+ "learning_rate": 1.9031815244050752e-05,
688
+ "loss": 0.9588617086410522,
689
+ "step": 194
690
+ },
691
+ {
692
+ "epoch": 0.7808764940239044,
693
+ "grad_norm": 0.5440645217895508,
694
+ "learning_rate": 1.9004867903130694e-05,
695
+ "loss": 0.7339329719543457,
696
+ "step": 196
697
+ },
698
+ {
699
+ "epoch": 0.7888446215139442,
700
+ "grad_norm": 1.9453508853912354,
701
+ "learning_rate": 1.897757260444628e-05,
702
+ "loss": 0.825846254825592,
703
+ "step": 198
704
+ },
705
+ {
706
+ "epoch": 0.796812749003984,
707
+ "grad_norm": 0.4652504026889801,
708
+ "learning_rate": 1.8949930534476938e-05,
709
+ "loss": 1.123836636543274,
710
+ "step": 200
711
+ },
712
+ {
713
+ "epoch": 0.8047808764940239,
714
+ "grad_norm": 0.2496296465396881,
715
+ "learning_rate": 1.892194289477565e-05,
716
+ "loss": 1.1040383577346802,
717
+ "step": 202
718
+ },
719
+ {
720
+ "epoch": 0.8127490039840638,
721
+ "grad_norm": 0.4298226237297058,
722
+ "learning_rate": 1.8893610901916707e-05,
723
+ "loss": 1.6137018203735352,
724
+ "step": 204
725
+ },
726
+ {
727
+ "epoch": 0.8207171314741036,
728
+ "grad_norm": 0.4001586437225342,
729
+ "learning_rate": 1.886493578744284e-05,
730
+ "loss": 1.3078550100326538,
731
+ "step": 206
732
+ },
733
+ {
734
+ "epoch": 0.8286852589641435,
735
+ "grad_norm": 0.8008004426956177,
736
+ "learning_rate": 1.8835918797811693e-05,
737
+ "loss": 0.6984291672706604,
738
+ "step": 208
739
+ },
740
+ {
741
+ "epoch": 0.8366533864541833,
742
+ "grad_norm": 0.42881664633750916,
743
+ "learning_rate": 1.880656119434162e-05,
744
+ "loss": 1.335817813873291,
745
+ "step": 210
746
+ },
747
+ {
748
+ "epoch": 0.8446215139442231,
749
+ "grad_norm": 1.1458430290222168,
750
+ "learning_rate": 1.8776864253156875e-05,
751
+ "loss": 1.2731460332870483,
752
+ "step": 212
753
+ },
754
+ {
755
+ "epoch": 0.852589641434263,
756
+ "grad_norm": 0.5224696397781372,
757
+ "learning_rate": 1.874682926513213e-05,
758
+ "loss": 0.9890910387039185,
759
+ "step": 214
760
+ },
761
+ {
762
+ "epoch": 0.8605577689243028,
763
+ "grad_norm": 0.8723546862602234,
764
+ "learning_rate": 1.871645753583638e-05,
765
+ "loss": 1.504272222518921,
766
+ "step": 216
767
+ },
768
+ {
769
+ "epoch": 0.8685258964143426,
770
+ "grad_norm": 0.5456506609916687,
771
+ "learning_rate": 1.8685750385476166e-05,
772
+ "loss": 1.0292469263076782,
773
+ "step": 218
774
+ },
775
+ {
776
+ "epoch": 0.8764940239043825,
777
+ "grad_norm": 0.30583837628364563,
778
+ "learning_rate": 1.8654709148838218e-05,
779
+ "loss": 1.2776914834976196,
780
+ "step": 220
781
+ },
782
+ {
783
+ "epoch": 0.8844621513944223,
784
+ "grad_norm": 0.5236691236495972,
785
+ "learning_rate": 1.8623335175231402e-05,
786
+ "loss": 1.5422356128692627,
787
+ "step": 222
788
+ },
789
+ {
790
+ "epoch": 0.8924302788844621,
791
+ "grad_norm": 0.6241909861564636,
792
+ "learning_rate": 1.85916298284281e-05,
793
+ "loss": 0.7620981335639954,
794
+ "step": 224
795
+ },
796
+ {
797
+ "epoch": 0.900398406374502,
798
+ "grad_norm": 0.48723360896110535,
799
+ "learning_rate": 1.8559594486604905e-05,
800
+ "loss": 1.0757262706756592,
801
+ "step": 226
802
+ },
803
+ {
804
+ "epoch": 0.9083665338645418,
805
+ "grad_norm": 1.2864985466003418,
806
+ "learning_rate": 1.8527230542282724e-05,
807
+ "loss": 1.1468511819839478,
808
+ "step": 228
809
+ },
810
+ {
811
+ "epoch": 0.9163346613545816,
812
+ "grad_norm": 1.7492055892944336,
813
+ "learning_rate": 1.849453940226625e-05,
814
+ "loss": 1.213545799255371,
815
+ "step": 230
816
+ },
817
+ {
818
+ "epoch": 0.9243027888446215,
819
+ "grad_norm": 0.40618953108787537,
820
+ "learning_rate": 1.8461522487582803e-05,
821
+ "loss": 1.3688737154006958,
822
+ "step": 232
823
+ },
824
+ {
825
+ "epoch": 0.9322709163346613,
826
+ "grad_norm": 0.36780276894569397,
827
+ "learning_rate": 1.8428181233420565e-05,
828
+ "loss": 0.8684775233268738,
829
+ "step": 234
830
+ },
831
+ {
832
+ "epoch": 0.9402390438247012,
833
+ "grad_norm": 0.3596510589122772,
834
+ "learning_rate": 1.8394517089066197e-05,
835
+ "loss": 0.8614349365234375,
836
+ "step": 236
837
+ },
838
+ {
839
+ "epoch": 0.9482071713147411,
840
+ "grad_norm": 1.7488377094268799,
841
+ "learning_rate": 1.8360531517841832e-05,
842
+ "loss": 0.5599083304405212,
843
+ "step": 238
844
+ },
845
+ {
846
+ "epoch": 0.9561752988047809,
847
+ "grad_norm": 0.9555627703666687,
848
+ "learning_rate": 1.8326225997041482e-05,
849
+ "loss": 0.9110929369926453,
850
+ "step": 240
851
+ },
852
+ {
853
+ "epoch": 0.9641434262948207,
854
+ "grad_norm": 0.3523239493370056,
855
+ "learning_rate": 1.8291602017866806e-05,
856
+ "loss": 1.1641830205917358,
857
+ "step": 242
858
+ },
859
+ {
860
+ "epoch": 0.9721115537848606,
861
+ "grad_norm": 0.43567129969596863,
862
+ "learning_rate": 1.8256661085362308e-05,
863
+ "loss": 1.2559393644332886,
864
+ "step": 244
865
+ },
866
+ {
867
+ "epoch": 0.9800796812749004,
868
+ "grad_norm": 0.40791869163513184,
869
+ "learning_rate": 1.8221404718349888e-05,
870
+ "loss": 1.0120309591293335,
871
+ "step": 246
872
+ },
873
+ {
874
+ "epoch": 0.9880478087649402,
875
+ "grad_norm": 0.24796508252620697,
876
+ "learning_rate": 1.8185834449362855e-05,
877
+ "loss": 1.0682169198989868,
878
+ "step": 248
879
+ },
880
+ {
881
+ "epoch": 0.9960159362549801,
882
+ "grad_norm": 0.41540786623954773,
883
+ "learning_rate": 1.8149951824579283e-05,
884
+ "loss": 1.0582711696624756,
885
+ "step": 250
886
+ },
887
+ {
888
+ "epoch": 1.00398406374502,
889
+ "grad_norm": 1.0092355012893677,
890
+ "learning_rate": 1.8113758403754823e-05,
891
+ "loss": 0.979528546333313,
892
+ "step": 252
893
+ },
894
+ {
895
+ "epoch": 1.0119521912350598,
896
+ "grad_norm": 0.6038091778755188,
897
+ "learning_rate": 1.8077255760154883e-05,
898
+ "loss": 0.7742294073104858,
899
+ "step": 254
900
+ },
901
+ {
902
+ "epoch": 1.0199203187250996,
903
+ "grad_norm": 0.3472102880477905,
904
+ "learning_rate": 1.8040445480486254e-05,
905
+ "loss": 1.1254103183746338,
906
+ "step": 256
907
+ },
908
+ {
909
+ "epoch": 1.0278884462151394,
910
+ "grad_norm": 0.38630589842796326,
911
+ "learning_rate": 1.8003329164828133e-05,
912
+ "loss": 1.1129672527313232,
913
+ "step": 258
914
+ },
915
+ {
916
+ "epoch": 1.0358565737051793,
917
+ "grad_norm": 0.4505392014980316,
918
+ "learning_rate": 1.7965908426562582e-05,
919
+ "loss": 1.004437804222107,
920
+ "step": 260
921
+ },
922
+ {
923
+ "epoch": 1.043824701195219,
924
+ "grad_norm": 0.3152492046356201,
925
+ "learning_rate": 1.7928184892304366e-05,
926
+ "loss": 0.9400702118873596,
927
+ "step": 262
928
+ },
929
+ {
930
+ "epoch": 1.051792828685259,
931
+ "grad_norm": 0.6728148460388184,
932
+ "learning_rate": 1.789016020183029e-05,
933
+ "loss": 1.0473450422286987,
934
+ "step": 264
935
+ },
936
+ {
937
+ "epoch": 1.0597609561752988,
938
+ "grad_norm": 0.7942842245101929,
939
+ "learning_rate": 1.7851836008007883e-05,
940
+ "loss": 0.7050523161888123,
941
+ "step": 266
942
+ },
943
+ {
944
+ "epoch": 1.0677290836653386,
945
+ "grad_norm": 0.24827615916728973,
946
+ "learning_rate": 1.781321397672358e-05,
947
+ "loss": 0.8870258927345276,
948
+ "step": 268
949
+ },
950
+ {
951
+ "epoch": 1.0756972111553784,
952
+ "grad_norm": 0.3862256109714508,
953
+ "learning_rate": 1.777429578681029e-05,
954
+ "loss": 0.5399430394172668,
955
+ "step": 270
956
+ },
957
+ {
958
+ "epoch": 1.0836653386454183,
959
+ "grad_norm": 0.3700801134109497,
960
+ "learning_rate": 1.7735083129974423e-05,
961
+ "loss": 1.2206511497497559,
962
+ "step": 272
963
+ },
964
+ {
965
+ "epoch": 1.091633466135458,
966
+ "grad_norm": 0.7308570742607117,
967
+ "learning_rate": 1.769557771072236e-05,
968
+ "loss": 0.680720865726471,
969
+ "step": 274
970
+ },
971
+ {
972
+ "epoch": 1.099601593625498,
973
+ "grad_norm": 0.2208869606256485,
974
+ "learning_rate": 1.7655781246286345e-05,
975
+ "loss": 0.8195149302482605,
976
+ "step": 276
977
+ },
978
+ {
979
+ "epoch": 1.1075697211155378,
980
+ "grad_norm": 0.31552159786224365,
981
+ "learning_rate": 1.761569546654988e-05,
982
+ "loss": 0.7425749897956848,
983
+ "step": 278
984
+ },
985
+ {
986
+ "epoch": 1.1155378486055776,
987
+ "grad_norm": 0.5200814008712769,
988
+ "learning_rate": 1.7575322113972472e-05,
989
+ "loss": 0.9490090608596802,
990
+ "step": 280
991
+ },
992
+ {
993
+ "epoch": 1.1235059760956174,
994
+ "grad_norm": 0.3083236813545227,
995
+ "learning_rate": 1.753466294351395e-05,
996
+ "loss": 1.076003074645996,
997
+ "step": 282
998
+ },
999
+ {
1000
+ "epoch": 1.1314741035856573,
1001
+ "grad_norm": 0.36041611433029175,
1002
+ "learning_rate": 1.7493719722558135e-05,
1003
+ "loss": 1.1486386060714722,
1004
+ "step": 284
1005
+ },
1006
+ {
1007
+ "epoch": 1.139442231075697,
1008
+ "grad_norm": 1.6613099575042725,
1009
+ "learning_rate": 1.7452494230836034e-05,
1010
+ "loss": 0.3132348954677582,
1011
+ "step": 286
1012
+ },
1013
+ {
1014
+ "epoch": 1.1474103585657371,
1015
+ "grad_norm": 0.2219257354736328,
1016
+ "learning_rate": 1.741098826034848e-05,
1017
+ "loss": 0.6475589275360107,
1018
+ "step": 288
1019
+ },
1020
+ {
1021
+ "epoch": 1.155378486055777,
1022
+ "grad_norm": 0.9050571918487549,
1023
+ "learning_rate": 1.7369203615288227e-05,
1024
+ "loss": 0.9298643469810486,
1025
+ "step": 290
1026
+ },
1027
+ {
1028
+ "epoch": 1.1633466135458168,
1029
+ "grad_norm": 0.651750922203064,
1030
+ "learning_rate": 1.7327142111961537e-05,
1031
+ "loss": 0.6063528656959534,
1032
+ "step": 292
1033
+ },
1034
+ {
1035
+ "epoch": 1.1713147410358566,
1036
+ "grad_norm": 0.19915056228637695,
1037
+ "learning_rate": 1.7284805578709218e-05,
1038
+ "loss": 1.1846861839294434,
1039
+ "step": 294
1040
+ },
1041
+ {
1042
+ "epoch": 1.1792828685258965,
1043
+ "grad_norm": 0.21233604848384857,
1044
+ "learning_rate": 1.724219585582716e-05,
1045
+ "loss": 1.264991044998169,
1046
+ "step": 296
1047
+ },
1048
+ {
1049
+ "epoch": 1.1872509960159363,
1050
+ "grad_norm": 0.27689361572265625,
1051
+ "learning_rate": 1.7199314795486325e-05,
1052
+ "loss": 1.2833882570266724,
1053
+ "step": 298
1054
+ },
1055
+ {
1056
+ "epoch": 1.1952191235059761,
1057
+ "grad_norm": 0.454823762178421,
1058
+ "learning_rate": 1.7156164261652247e-05,
1059
+ "loss": 0.58225017786026,
1060
+ "step": 300
1061
+ },
1062
+ {
1063
+ "epoch": 1.203187250996016,
1064
+ "grad_norm": 0.2573089003562927,
1065
+ "learning_rate": 1.711274613000401e-05,
1066
+ "loss": 0.9149743318557739,
1067
+ "step": 302
1068
+ },
1069
+ {
1070
+ "epoch": 1.2111553784860558,
1071
+ "grad_norm": 0.26930296421051025,
1072
+ "learning_rate": 1.7069062287852717e-05,
1073
+ "loss": 0.5347046852111816,
1074
+ "step": 304
1075
+ },
1076
+ {
1077
+ "epoch": 1.2191235059760956,
1078
+ "grad_norm": 0.22766169905662537,
1079
+ "learning_rate": 1.702511463405943e-05,
1080
+ "loss": 1.1858634948730469,
1081
+ "step": 306
1082
+ },
1083
+ {
1084
+ "epoch": 1.2270916334661355,
1085
+ "grad_norm": 1.8281174898147583,
1086
+ "learning_rate": 1.698090507895266e-05,
1087
+ "loss": 0.923149824142456,
1088
+ "step": 308
1089
+ },
1090
+ {
1091
+ "epoch": 1.2350597609561753,
1092
+ "grad_norm": 0.3246043622493744,
1093
+ "learning_rate": 1.693643554424532e-05,
1094
+ "loss": 1.1471027135849,
1095
+ "step": 310
1096
+ },
1097
+ {
1098
+ "epoch": 1.2430278884462151,
1099
+ "grad_norm": 0.5812107920646667,
1100
+ "learning_rate": 1.6891707962951173e-05,
1101
+ "loss": 1.0638307332992554,
1102
+ "step": 312
1103
+ },
1104
+ {
1105
+ "epoch": 1.250996015936255,
1106
+ "grad_norm": 0.2739630341529846,
1107
+ "learning_rate": 1.684672427930083e-05,
1108
+ "loss": 0.8980826735496521,
1109
+ "step": 314
1110
+ },
1111
+ {
1112
+ "epoch": 1.2589641434262948,
1113
+ "grad_norm": 0.31895291805267334,
1114
+ "learning_rate": 1.680148644865722e-05,
1115
+ "loss": 0.7298654317855835,
1116
+ "step": 316
1117
+ },
1118
+ {
1119
+ "epoch": 1.2669322709163346,
1120
+ "grad_norm": 0.2569485604763031,
1121
+ "learning_rate": 1.6755996437430622e-05,
1122
+ "loss": 0.6580713987350464,
1123
+ "step": 318
1124
+ },
1125
+ {
1126
+ "epoch": 1.2749003984063745,
1127
+ "grad_norm": 0.3961490988731384,
1128
+ "learning_rate": 1.6710256222993137e-05,
1129
+ "loss": 0.489969938993454,
1130
+ "step": 320
1131
+ },
1132
+ {
1133
+ "epoch": 1.2828685258964143,
1134
+ "grad_norm": 0.30034857988357544,
1135
+ "learning_rate": 1.6664267793592797e-05,
1136
+ "loss": 0.9578895568847656,
1137
+ "step": 322
1138
+ },
1139
+ {
1140
+ "epoch": 1.2908366533864541,
1141
+ "grad_norm": 0.36320650577545166,
1142
+ "learning_rate": 1.661803314826709e-05,
1143
+ "loss": 0.9098944067955017,
1144
+ "step": 324
1145
+ },
1146
+ {
1147
+ "epoch": 1.298804780876494,
1148
+ "grad_norm": 0.37193965911865234,
1149
+ "learning_rate": 1.65715542967561e-05,
1150
+ "loss": 1.2378405332565308,
1151
+ "step": 326
1152
+ },
1153
+ {
1154
+ "epoch": 1.3067729083665338,
1155
+ "grad_norm": 0.24212397634983063,
1156
+ "learning_rate": 1.652483325941511e-05,
1157
+ "loss": 0.6748937368392944,
1158
+ "step": 328
1159
+ },
1160
+ {
1161
+ "epoch": 1.3147410358565736,
1162
+ "grad_norm": 0.23975537717342377,
1163
+ "learning_rate": 1.647787206712683e-05,
1164
+ "loss": 0.7632936239242554,
1165
+ "step": 330
1166
+ },
1167
+ {
1168
+ "epoch": 1.3227091633466135,
1169
+ "grad_norm": 0.5843632221221924,
1170
+ "learning_rate": 1.6430672761213065e-05,
1171
+ "loss": 0.9058688282966614,
1172
+ "step": 332
1173
+ },
1174
+ {
1175
+ "epoch": 1.3306772908366533,
1176
+ "grad_norm": 1.3426114320755005,
1177
+ "learning_rate": 1.6383237393346025e-05,
1178
+ "loss": 0.6352471113204956,
1179
+ "step": 334
1180
+ },
1181
+ {
1182
+ "epoch": 1.3386454183266931,
1183
+ "grad_norm": 0.40683165192604065,
1184
+ "learning_rate": 1.633556802545911e-05,
1185
+ "loss": 0.8502663373947144,
1186
+ "step": 336
1187
+ },
1188
+ {
1189
+ "epoch": 1.3466135458167332,
1190
+ "grad_norm": 0.37066444754600525,
1191
+ "learning_rate": 1.628766672965731e-05,
1192
+ "loss": 1.084623098373413,
1193
+ "step": 338
1194
+ },
1195
+ {
1196
+ "epoch": 1.354581673306773,
1197
+ "grad_norm": 0.19215187430381775,
1198
+ "learning_rate": 1.6239535588127107e-05,
1199
+ "loss": 1.0811511278152466,
1200
+ "step": 340
1201
+ },
1202
+ {
1203
+ "epoch": 1.3625498007968129,
1204
+ "grad_norm": 0.20627997815608978,
1205
+ "learning_rate": 1.6191176693046e-05,
1206
+ "loss": 1.156653642654419,
1207
+ "step": 342
1208
+ },
1209
+ {
1210
+ "epoch": 1.3705179282868527,
1211
+ "grad_norm": 0.24132803082466125,
1212
+ "learning_rate": 1.6142592146491517e-05,
1213
+ "loss": 1.0989466905593872,
1214
+ "step": 344
1215
+ },
1216
+ {
1217
+ "epoch": 1.3784860557768925,
1218
+ "grad_norm": 1.311899185180664,
1219
+ "learning_rate": 1.6093784060349876e-05,
1220
+ "loss": 0.7021924257278442,
1221
+ "step": 346
1222
+ },
1223
+ {
1224
+ "epoch": 1.3864541832669324,
1225
+ "grad_norm": 0.2994781732559204,
1226
+ "learning_rate": 1.6044754556224178e-05,
1227
+ "loss": 1.1349058151245117,
1228
+ "step": 348
1229
+ },
1230
+ {
1231
+ "epoch": 1.3944223107569722,
1232
+ "grad_norm": 0.7709036469459534,
1233
+ "learning_rate": 1.5995505765342176e-05,
1234
+ "loss": 0.6554039716720581,
1235
+ "step": 350
1236
+ },
1237
+ {
1238
+ "epoch": 1.402390438247012,
1239
+ "grad_norm": 0.2403658926486969,
1240
+ "learning_rate": 1.594603982846364e-05,
1241
+ "loss": 1.129141926765442,
1242
+ "step": 352
1243
+ },
1244
+ {
1245
+ "epoch": 1.4103585657370519,
1246
+ "grad_norm": 0.38826340436935425,
1247
+ "learning_rate": 1.5896358895787304e-05,
1248
+ "loss": 1.1050136089324951,
1249
+ "step": 354
1250
+ },
1251
+ {
1252
+ "epoch": 1.4183266932270917,
1253
+ "grad_norm": 0.3303016722202301,
1254
+ "learning_rate": 1.5846465126857386e-05,
1255
+ "loss": 0.8948855400085449,
1256
+ "step": 356
1257
+ },
1258
+ {
1259
+ "epoch": 1.4262948207171315,
1260
+ "grad_norm": 0.25158822536468506,
1261
+ "learning_rate": 1.579636069046975e-05,
1262
+ "loss": 1.1352990865707397,
1263
+ "step": 358
1264
+ },
1265
+ {
1266
+ "epoch": 1.4342629482071714,
1267
+ "grad_norm": 0.3274855613708496,
1268
+ "learning_rate": 1.5746047764577586e-05,
1269
+ "loss": 0.5751365423202515,
1270
+ "step": 360
1271
+ },
1272
+ {
1273
+ "epoch": 1.4422310756972112,
1274
+ "grad_norm": 0.1873192936182022,
1275
+ "learning_rate": 1.5695528536196774e-05,
1276
+ "loss": 0.654511034488678,
1277
+ "step": 362
1278
+ },
1279
+ {
1280
+ "epoch": 1.450199203187251,
1281
+ "grad_norm": 0.2384817749261856,
1282
+ "learning_rate": 1.564480520131081e-05,
1283
+ "loss": 1.0301330089569092,
1284
+ "step": 364
1285
+ },
1286
+ {
1287
+ "epoch": 1.4581673306772909,
1288
+ "grad_norm": 0.18577991425991058,
1289
+ "learning_rate": 1.559387996477534e-05,
1290
+ "loss": 1.0699549913406372,
1291
+ "step": 366
1292
+ },
1293
+ {
1294
+ "epoch": 1.4661354581673307,
1295
+ "grad_norm": 0.20976194739341736,
1296
+ "learning_rate": 1.5542755040222325e-05,
1297
+ "loss": 0.5935020446777344,
1298
+ "step": 368
1299
+ },
1300
+ {
1301
+ "epoch": 1.4741035856573705,
1302
+ "grad_norm": 0.6415178179740906,
1303
+ "learning_rate": 1.5491432649963823e-05,
1304
+ "loss": 0.6804059147834778,
1305
+ "step": 370
1306
+ },
1307
+ {
1308
+ "epoch": 1.4820717131474104,
1309
+ "grad_norm": 0.6343056559562683,
1310
+ "learning_rate": 1.543991502489538e-05,
1311
+ "loss": 1.2095876932144165,
1312
+ "step": 372
1313
+ },
1314
+ {
1315
+ "epoch": 1.4900398406374502,
1316
+ "grad_norm": 0.19021844863891602,
1317
+ "learning_rate": 1.5388204404399073e-05,
1318
+ "loss": 1.059179663658142,
1319
+ "step": 374
1320
+ },
1321
+ {
1322
+ "epoch": 1.49800796812749,
1323
+ "grad_norm": 0.1728297770023346,
1324
+ "learning_rate": 1.533630303624614e-05,
1325
+ "loss": 1.0693382024765015,
1326
+ "step": 376
1327
+ },
1328
+ {
1329
+ "epoch": 1.5059760956175299,
1330
+ "grad_norm": 0.376954585313797,
1331
+ "learning_rate": 1.5284213176499302e-05,
1332
+ "loss": 0.8699037432670593,
1333
+ "step": 378
1334
+ },
1335
+ {
1336
+ "epoch": 1.5139442231075697,
1337
+ "grad_norm": 0.22751152515411377,
1338
+ "learning_rate": 1.5231937089414675e-05,
1339
+ "loss": 1.1054149866104126,
1340
+ "step": 380
1341
+ },
1342
+ {
1343
+ "epoch": 1.5219123505976095,
1344
+ "grad_norm": 0.23990006744861603,
1345
+ "learning_rate": 1.517947704734337e-05,
1346
+ "loss": 0.6814401745796204,
1347
+ "step": 382
1348
+ },
1349
+ {
1350
+ "epoch": 1.5298804780876494,
1351
+ "grad_norm": 0.4457078278064728,
1352
+ "learning_rate": 1.5126835330632677e-05,
1353
+ "loss": 0.7228714227676392,
1354
+ "step": 384
1355
+ },
1356
+ {
1357
+ "epoch": 1.5378486055776892,
1358
+ "grad_norm": 0.40967053174972534,
1359
+ "learning_rate": 1.5074014227526997e-05,
1360
+ "loss": 0.9597483277320862,
1361
+ "step": 386
1362
+ },
1363
+ {
1364
+ "epoch": 1.545816733067729,
1365
+ "grad_norm": 0.31324154138565063,
1366
+ "learning_rate": 1.502101603406833e-05,
1367
+ "loss": 1.1154417991638184,
1368
+ "step": 388
1369
+ },
1370
+ {
1371
+ "epoch": 1.5537848605577689,
1372
+ "grad_norm": 0.9542575478553772,
1373
+ "learning_rate": 1.4967843053996494e-05,
1374
+ "loss": 0.5699301362037659,
1375
+ "step": 390
1376
+ },
1377
+ {
1378
+ "epoch": 1.5617529880478087,
1379
+ "grad_norm": 0.31226351857185364,
1380
+ "learning_rate": 1.4914497598648973e-05,
1381
+ "loss": 0.6108444333076477,
1382
+ "step": 392
1383
+ },
1384
+ {
1385
+ "epoch": 1.5697211155378485,
1386
+ "grad_norm": 6.123598098754883,
1387
+ "learning_rate": 1.4860981986860464e-05,
1388
+ "loss": 1.0147069692611694,
1389
+ "step": 394
1390
+ },
1391
+ {
1392
+ "epoch": 1.5776892430278884,
1393
+ "grad_norm": 0.5377170443534851,
1394
+ "learning_rate": 1.4807298544862054e-05,
1395
+ "loss": 1.0180771350860596,
1396
+ "step": 396
1397
+ },
1398
+ {
1399
+ "epoch": 1.5856573705179282,
1400
+ "grad_norm": 0.20692817866802216,
1401
+ "learning_rate": 1.4753449606180137e-05,
1402
+ "loss": 1.1011747121810913,
1403
+ "step": 398
1404
+ },
1405
+ {
1406
+ "epoch": 1.593625498007968,
1407
+ "grad_norm": 0.4750509560108185,
1408
+ "learning_rate": 1.4699437511534947e-05,
1409
+ "loss": 0.5985136032104492,
1410
+ "step": 400
1411
+ },
1412
+ {
1413
+ "epoch": 1.6015936254980079,
1414
+ "grad_norm": 0.3046919107437134,
1415
+ "learning_rate": 1.4645264608738832e-05,
1416
+ "loss": 1.0762031078338623,
1417
+ "step": 402
1418
+ },
1419
+ {
1420
+ "epoch": 1.6095617529880477,
1421
+ "grad_norm": 0.22464171051979065,
1422
+ "learning_rate": 1.4590933252594193e-05,
1423
+ "loss": 1.2067527770996094,
1424
+ "step": 404
1425
+ },
1426
+ {
1427
+ "epoch": 1.6175298804780875,
1428
+ "grad_norm": 2.2710113525390625,
1429
+ "learning_rate": 1.4536445804791125e-05,
1430
+ "loss": 0.7306970357894897,
1431
+ "step": 406
1432
+ },
1433
+ {
1434
+ "epoch": 1.6254980079681274,
1435
+ "grad_norm": 0.1687576174736023,
1436
+ "learning_rate": 1.4481804633804746e-05,
1437
+ "loss": 0.5554207563400269,
1438
+ "step": 408
1439
+ },
1440
+ {
1441
+ "epoch": 1.6334661354581672,
1442
+ "grad_norm": 0.39087173342704773,
1443
+ "learning_rate": 1.4427012114792269e-05,
1444
+ "loss": 0.7205751538276672,
1445
+ "step": 410
1446
+ },
1447
+ {
1448
+ "epoch": 1.641434262948207,
1449
+ "grad_norm": 0.2729649841785431,
1450
+ "learning_rate": 1.4372070629489744e-05,
1451
+ "loss": 0.4776345193386078,
1452
+ "step": 412
1453
+ },
1454
+ {
1455
+ "epoch": 1.6494023904382469,
1456
+ "grad_norm": 0.3640289306640625,
1457
+ "learning_rate": 1.4316982566108515e-05,
1458
+ "loss": 0.7648314237594604,
1459
+ "step": 414
1460
+ },
1461
+ {
1462
+ "epoch": 1.6573705179282867,
1463
+ "grad_norm": 0.6474630832672119,
1464
+ "learning_rate": 1.4261750319231432e-05,
1465
+ "loss": 0.7392333745956421,
1466
+ "step": 416
1467
+ },
1468
+ {
1469
+ "epoch": 1.6653386454183265,
1470
+ "grad_norm": 0.34522193670272827,
1471
+ "learning_rate": 1.4206376289708752e-05,
1472
+ "loss": 0.883467435836792,
1473
+ "step": 418
1474
+ },
1475
+ {
1476
+ "epoch": 1.6733067729083664,
1477
+ "grad_norm": 0.277730256319046,
1478
+ "learning_rate": 1.4150862884553776e-05,
1479
+ "loss": 1.131731390953064,
1480
+ "step": 420
1481
+ },
1482
+ {
1483
+ "epoch": 1.6812749003984062,
1484
+ "grad_norm": 0.3468133807182312,
1485
+ "learning_rate": 1.4095212516838216e-05,
1486
+ "loss": 0.9705685377120972,
1487
+ "step": 422
1488
+ },
1489
+ {
1490
+ "epoch": 1.6892430278884463,
1491
+ "grad_norm": 0.9739753603935242,
1492
+ "learning_rate": 1.4039427605587326e-05,
1493
+ "loss": 0.5433371663093567,
1494
+ "step": 424
1495
+ },
1496
+ {
1497
+ "epoch": 1.697211155378486,
1498
+ "grad_norm": 0.45867398381233215,
1499
+ "learning_rate": 1.398351057567472e-05,
1500
+ "loss": 1.1449828147888184,
1501
+ "step": 426
1502
+ },
1503
+ {
1504
+ "epoch": 1.705179282868526,
1505
+ "grad_norm": 0.25316959619522095,
1506
+ "learning_rate": 1.392746385771699e-05,
1507
+ "loss": 1.084163784980774,
1508
+ "step": 428
1509
+ },
1510
+ {
1511
+ "epoch": 1.7131474103585658,
1512
+ "grad_norm": 0.25396499037742615,
1513
+ "learning_rate": 1.3871289887968034e-05,
1514
+ "loss": 0.7046893239021301,
1515
+ "step": 430
1516
+ },
1517
+ {
1518
+ "epoch": 1.7211155378486056,
1519
+ "grad_norm": 0.6979869604110718,
1520
+ "learning_rate": 1.3814991108213173e-05,
1521
+ "loss": 0.8699672222137451,
1522
+ "step": 432
1523
+ },
1524
+ {
1525
+ "epoch": 1.7290836653386454,
1526
+ "grad_norm": 0.632816731929779,
1527
+ "learning_rate": 1.3758569965663011e-05,
1528
+ "loss": 0.6414164304733276,
1529
+ "step": 434
1530
+ },
1531
+ {
1532
+ "epoch": 1.7370517928286853,
1533
+ "grad_norm": 0.5996594429016113,
1534
+ "learning_rate": 1.370202891284703e-05,
1535
+ "loss": 0.4016932547092438,
1536
+ "step": 436
1537
+ },
1538
+ {
1539
+ "epoch": 1.745019920318725,
1540
+ "grad_norm": 0.374830037355423,
1541
+ "learning_rate": 1.3645370407507017e-05,
1542
+ "loss": 0.7375532388687134,
1543
+ "step": 438
1544
+ },
1545
+ {
1546
+ "epoch": 1.752988047808765,
1547
+ "grad_norm": 1.5595433712005615,
1548
+ "learning_rate": 1.3588596912490222e-05,
1549
+ "loss": 0.7329553365707397,
1550
+ "step": 440
1551
+ },
1552
+ {
1553
+ "epoch": 1.7609561752988048,
1554
+ "grad_norm": 0.526985228061676,
1555
+ "learning_rate": 1.3531710895642288e-05,
1556
+ "loss": 1.329801321029663,
1557
+ "step": 442
1558
+ },
1559
+ {
1560
+ "epoch": 1.7689243027888446,
1561
+ "grad_norm": 0.2958177328109741,
1562
+ "learning_rate": 1.3474714829699987e-05,
1563
+ "loss": 0.7087810039520264,
1564
+ "step": 444
1565
+ },
1566
+ {
1567
+ "epoch": 1.7768924302788844,
1568
+ "grad_norm": 0.5098376274108887,
1569
+ "learning_rate": 1.341761119218374e-05,
1570
+ "loss": 1.0286879539489746,
1571
+ "step": 446
1572
+ },
1573
+ {
1574
+ "epoch": 1.7848605577689243,
1575
+ "grad_norm": 0.7928891777992249,
1576
+ "learning_rate": 1.3360402465289916e-05,
1577
+ "loss": 1.0772615671157837,
1578
+ "step": 448
1579
+ },
1580
+ {
1581
+ "epoch": 1.792828685258964,
1582
+ "grad_norm": 0.26385796070098877,
1583
+ "learning_rate": 1.3303091135782942e-05,
1584
+ "loss": 0.8347827196121216,
1585
+ "step": 450
1586
+ },
1587
+ {
1588
+ "epoch": 1.800796812749004,
1589
+ "grad_norm": 0.28425443172454834,
1590
+ "learning_rate": 1.3245679694887192e-05,
1591
+ "loss": 0.44587215781211853,
1592
+ "step": 452
1593
+ },
1594
+ {
1595
+ "epoch": 1.8087649402390438,
1596
+ "grad_norm": 0.5673894882202148,
1597
+ "learning_rate": 1.318817063817872e-05,
1598
+ "loss": 0.9081963896751404,
1599
+ "step": 454
1600
+ },
1601
+ {
1602
+ "epoch": 1.8167330677290838,
1603
+ "grad_norm": 0.3212035298347473,
1604
+ "learning_rate": 1.3130566465476773e-05,
1605
+ "loss": 0.6184219717979431,
1606
+ "step": 456
1607
+ },
1608
+ {
1609
+ "epoch": 1.8247011952191237,
1610
+ "grad_norm": 0.30924293398857117,
1611
+ "learning_rate": 1.307286968073511e-05,
1612
+ "loss": 1.0215346813201904,
1613
+ "step": 458
1614
+ },
1615
+ {
1616
+ "epoch": 1.8326693227091635,
1617
+ "grad_norm": 0.28430241346359253,
1618
+ "learning_rate": 1.3015082791933182e-05,
1619
+ "loss": 0.7581181526184082,
1620
+ "step": 460
1621
+ },
1622
+ {
1623
+ "epoch": 1.8406374501992033,
1624
+ "grad_norm": 3.09944748878479,
1625
+ "learning_rate": 1.295720831096712e-05,
1626
+ "loss": 0.8157633543014526,
1627
+ "step": 462
1628
+ },
1629
+ {
1630
+ "epoch": 1.8486055776892432,
1631
+ "grad_norm": 0.1777675449848175,
1632
+ "learning_rate": 1.2899248753540518e-05,
1633
+ "loss": 0.13458193838596344,
1634
+ "step": 464
1635
+ },
1636
+ {
1637
+ "epoch": 1.856573705179283,
1638
+ "grad_norm": 0.6683889627456665,
1639
+ "learning_rate": 1.2841206639055108e-05,
1640
+ "loss": 1.1309783458709717,
1641
+ "step": 466
1642
+ },
1643
+ {
1644
+ "epoch": 1.8645418326693228,
1645
+ "grad_norm": 0.7414482831954956,
1646
+ "learning_rate": 1.2783084490501229e-05,
1647
+ "loss": 0.5139486193656921,
1648
+ "step": 468
1649
+ },
1650
+ {
1651
+ "epoch": 1.8725099601593627,
1652
+ "grad_norm": 0.4845532774925232,
1653
+ "learning_rate": 1.2724884834348163e-05,
1654
+ "loss": 1.1115937232971191,
1655
+ "step": 470
1656
+ },
1657
+ {
1658
+ "epoch": 1.8804780876494025,
1659
+ "grad_norm": 0.42305639386177063,
1660
+ "learning_rate": 1.266661020043432e-05,
1661
+ "loss": 0.9607354402542114,
1662
+ "step": 472
1663
+ },
1664
+ {
1665
+ "epoch": 1.8884462151394423,
1666
+ "grad_norm": 0.9543145895004272,
1667
+ "learning_rate": 1.2608263121857244e-05,
1668
+ "loss": 0.9997490048408508,
1669
+ "step": 474
1670
+ },
1671
+ {
1672
+ "epoch": 1.8964143426294822,
1673
+ "grad_norm": 0.227760910987854,
1674
+ "learning_rate": 1.254984613486355e-05,
1675
+ "loss": 0.958122730255127,
1676
+ "step": 476
1677
+ },
1678
+ {
1679
+ "epoch": 1.904382470119522,
1680
+ "grad_norm": 0.20254026353359222,
1681
+ "learning_rate": 1.2491361778738631e-05,
1682
+ "loss": 0.8319299817085266,
1683
+ "step": 478
1684
+ },
1685
+ {
1686
+ "epoch": 1.9123505976095618,
1687
+ "grad_norm": 1.022902250289917,
1688
+ "learning_rate": 1.243281259569631e-05,
1689
+ "loss": 0.5840953588485718,
1690
+ "step": 480
1691
+ },
1692
+ {
1693
+ "epoch": 1.9203187250996017,
1694
+ "grad_norm": 0.37438637018203735,
1695
+ "learning_rate": 1.2374201130768325e-05,
1696
+ "loss": 0.771386444568634,
1697
+ "step": 482
1698
+ },
1699
+ {
1700
+ "epoch": 1.9282868525896415,
1701
+ "grad_norm": 0.2661597728729248,
1702
+ "learning_rate": 1.2315529931693682e-05,
1703
+ "loss": 1.074930191040039,
1704
+ "step": 484
1705
+ },
1706
+ {
1707
+ "epoch": 1.9362549800796813,
1708
+ "grad_norm": 0.5989009141921997,
1709
+ "learning_rate": 1.2256801548807948e-05,
1710
+ "loss": 1.0152567625045776,
1711
+ "step": 486
1712
+ },
1713
+ {
1714
+ "epoch": 1.9442231075697212,
1715
+ "grad_norm": 0.23072665929794312,
1716
+ "learning_rate": 1.2198018534932367e-05,
1717
+ "loss": 1.0628975629806519,
1718
+ "step": 488
1719
+ },
1720
+ {
1721
+ "epoch": 1.952191235059761,
1722
+ "grad_norm": 0.281194806098938,
1723
+ "learning_rate": 1.2139183445262892e-05,
1724
+ "loss": 1.063922643661499,
1725
+ "step": 490
1726
+ },
1727
+ {
1728
+ "epoch": 1.9601593625498008,
1729
+ "grad_norm": 0.2512539327144623,
1730
+ "learning_rate": 1.2080298837259124e-05,
1731
+ "loss": 0.7215337157249451,
1732
+ "step": 492
1733
+ },
1734
+ {
1735
+ "epoch": 1.9681274900398407,
1736
+ "grad_norm": 1.4636787176132202,
1737
+ "learning_rate": 1.2021367270533138e-05,
1738
+ "loss": 0.753463625907898,
1739
+ "step": 494
1740
+ },
1741
+ {
1742
+ "epoch": 1.9760956175298805,
1743
+ "grad_norm": 0.20480957627296448,
1744
+ "learning_rate": 1.1962391306738226e-05,
1745
+ "loss": 1.0385065078735352,
1746
+ "step": 496
1747
+ },
1748
+ {
1749
+ "epoch": 1.9840637450199203,
1750
+ "grad_norm": 3.6724064350128174,
1751
+ "learning_rate": 1.190337350945754e-05,
1752
+ "loss": 0.8450489044189453,
1753
+ "step": 498
1754
+ },
1755
+ {
1756
+ "epoch": 1.9920318725099602,
1757
+ "grad_norm": 0.24277392029762268,
1758
+ "learning_rate": 1.1844316444092667e-05,
1759
+ "loss": 1.1586743593215942,
1760
+ "step": 500
1761
+ },
1762
+ {
1763
+ "epoch": 2.0,
1764
+ "grad_norm": 0.4689848721027374,
1765
+ "learning_rate": 1.1785222677752105e-05,
1766
+ "loss": 0.6194124221801758,
1767
+ "step": 502
1768
+ },
1769
+ {
1770
+ "epoch": 2.00796812749004,
1771
+ "grad_norm": 0.19164475798606873,
1772
+ "learning_rate": 1.1726094779139685e-05,
1773
+ "loss": 0.5169786810874939,
1774
+ "step": 504
1775
+ },
1776
+ {
1777
+ "epoch": 2.0159362549800797,
1778
+ "grad_norm": 0.3737673759460449,
1779
+ "learning_rate": 1.1666935318442905e-05,
1780
+ "loss": 0.4465612769126892,
1781
+ "step": 506
1782
+ },
1783
+ {
1784
+ "epoch": 2.0239043824701195,
1785
+ "grad_norm": 0.059804949909448624,
1786
+ "learning_rate": 1.1607746867221208e-05,
1787
+ "loss": 0.4815758168697357,
1788
+ "step": 508
1789
+ },
1790
+ {
1791
+ "epoch": 2.0318725099601593,
1792
+ "grad_norm": 0.19923484325408936,
1793
+ "learning_rate": 1.1548531998294217e-05,
1794
+ "loss": 0.7441997528076172,
1795
+ "step": 510
1796
+ },
1797
+ {
1798
+ "epoch": 2.039840637450199,
1799
+ "grad_norm": 0.39438050985336304,
1800
+ "learning_rate": 1.148929328562987e-05,
1801
+ "loss": 0.6462599635124207,
1802
+ "step": 512
1803
+ },
1804
+ {
1805
+ "epoch": 2.047808764940239,
1806
+ "grad_norm": 0.6492677927017212,
1807
+ "learning_rate": 1.1430033304232569e-05,
1808
+ "loss": 0.3487642705440521,
1809
+ "step": 514
1810
+ },
1811
+ {
1812
+ "epoch": 2.055776892430279,
1813
+ "grad_norm": 0.21399064362049103,
1814
+ "learning_rate": 1.137075463003122e-05,
1815
+ "loss": 0.7897251844406128,
1816
+ "step": 516
1817
+ },
1818
+ {
1819
+ "epoch": 2.0637450199203187,
1820
+ "grad_norm": 0.45779934525489807,
1821
+ "learning_rate": 1.1311459839767278e-05,
1822
+ "loss": 0.47086820006370544,
1823
+ "step": 518
1824
+ },
1825
+ {
1826
+ "epoch": 2.0717131474103585,
1827
+ "grad_norm": 0.45006412267684937,
1828
+ "learning_rate": 1.1252151510882731e-05,
1829
+ "loss": 0.6521967053413391,
1830
+ "step": 520
1831
+ },
1832
+ {
1833
+ "epoch": 2.0796812749003983,
1834
+ "grad_norm": 0.5039223432540894,
1835
+ "learning_rate": 1.1192832221408068e-05,
1836
+ "loss": 0.8312692046165466,
1837
+ "step": 522
1838
+ },
1839
+ {
1840
+ "epoch": 2.087649402390438,
1841
+ "grad_norm": 0.5422983765602112,
1842
+ "learning_rate": 1.1133504549850218e-05,
1843
+ "loss": 0.744563639163971,
1844
+ "step": 524
1845
+ },
1846
+ {
1847
+ "epoch": 2.095617529880478,
1848
+ "grad_norm": 0.4640710949897766,
1849
+ "learning_rate": 1.1074171075080469e-05,
1850
+ "loss": 0.3822844624519348,
1851
+ "step": 526
1852
+ },
1853
+ {
1854
+ "epoch": 2.103585657370518,
1855
+ "grad_norm": 0.2076382040977478,
1856
+ "learning_rate": 1.1014834376222351e-05,
1857
+ "loss": 0.6223887205123901,
1858
+ "step": 528
1859
+ },
1860
+ {
1861
+ "epoch": 2.1115537848605577,
1862
+ "grad_norm": 0.12689504027366638,
1863
+ "learning_rate": 1.0955497032539557e-05,
1864
+ "loss": 0.47389209270477295,
1865
+ "step": 530
1866
+ },
1867
+ {
1868
+ "epoch": 2.1195219123505975,
1869
+ "grad_norm": 0.184941366314888,
1870
+ "learning_rate": 1.0896161623323795e-05,
1871
+ "loss": 0.22031724452972412,
1872
+ "step": 532
1873
+ },
1874
+ {
1875
+ "epoch": 2.1274900398406373,
1876
+ "grad_norm": 0.3087546229362488,
1877
+ "learning_rate": 1.0836830727782692e-05,
1878
+ "loss": 0.6414751410484314,
1879
+ "step": 534
1880
+ },
1881
+ {
1882
+ "epoch": 2.135458167330677,
1883
+ "grad_norm": 0.6677108407020569,
1884
+ "learning_rate": 1.0777506924927667e-05,
1885
+ "loss": 0.596595823764801,
1886
+ "step": 536
1887
+ },
1888
+ {
1889
+ "epoch": 2.143426294820717,
1890
+ "grad_norm": 0.6424462795257568,
1891
+ "learning_rate": 1.0718192793461849e-05,
1892
+ "loss": 0.6871726512908936,
1893
+ "step": 538
1894
+ },
1895
+ {
1896
+ "epoch": 2.151394422310757,
1897
+ "grad_norm": 0.19472549855709076,
1898
+ "learning_rate": 1.065889091166795e-05,
1899
+ "loss": 0.7834715247154236,
1900
+ "step": 540
1901
+ },
1902
+ {
1903
+ "epoch": 2.1593625498007967,
1904
+ "grad_norm": 0.26970356702804565,
1905
+ "learning_rate": 1.059960385729621e-05,
1906
+ "loss": 0.7224296927452087,
1907
+ "step": 542
1908
+ },
1909
+ {
1910
+ "epoch": 2.1673306772908365,
1911
+ "grad_norm": 0.19753654301166534,
1912
+ "learning_rate": 1.0540334207452363e-05,
1913
+ "loss": 0.5219651460647583,
1914
+ "step": 544
1915
+ },
1916
+ {
1917
+ "epoch": 2.1752988047808763,
1918
+ "grad_norm": 0.23047387599945068,
1919
+ "learning_rate": 1.0481084538485589e-05,
1920
+ "loss": 0.5418217182159424,
1921
+ "step": 546
1922
+ },
1923
+ {
1924
+ "epoch": 2.183266932270916,
1925
+ "grad_norm": 0.3223879635334015,
1926
+ "learning_rate": 1.0421857425876524e-05,
1927
+ "loss": 0.802264928817749,
1928
+ "step": 548
1929
+ },
1930
+ {
1931
+ "epoch": 2.191235059760956,
1932
+ "grad_norm": 0.27228158712387085,
1933
+ "learning_rate": 1.0362655444125334e-05,
1934
+ "loss": 0.8337580561637878,
1935
+ "step": 550
1936
+ },
1937
+ {
1938
+ "epoch": 2.199203187250996,
1939
+ "grad_norm": 0.37938058376312256,
1940
+ "learning_rate": 1.0303481166639784e-05,
1941
+ "loss": 0.5192627310752869,
1942
+ "step": 552
1943
+ },
1944
+ {
1945
+ "epoch": 2.2071713147410357,
1946
+ "grad_norm": 0.5020936727523804,
1947
+ "learning_rate": 1.0244337165623378e-05,
1948
+ "loss": 0.4618823230266571,
1949
+ "step": 554
1950
+ },
1951
+ {
1952
+ "epoch": 2.2151394422310755,
1953
+ "grad_norm": 0.2157645970582962,
1954
+ "learning_rate": 1.0185226011963563e-05,
1955
+ "loss": 0.6217008233070374,
1956
+ "step": 556
1957
+ },
1958
+ {
1959
+ "epoch": 2.2231075697211153,
1960
+ "grad_norm": 0.4750109612941742,
1961
+ "learning_rate": 1.0126150275119958e-05,
1962
+ "loss": 0.7997477054595947,
1963
+ "step": 558
1964
+ },
1965
+ {
1966
+ "epoch": 2.231075697211155,
1967
+ "grad_norm": 0.24116151034832,
1968
+ "learning_rate": 1.0067112523012686e-05,
1969
+ "loss": 0.7890470027923584,
1970
+ "step": 560
1971
+ },
1972
+ {
1973
+ "epoch": 2.239043824701195,
1974
+ "grad_norm": 0.3130785822868347,
1975
+ "learning_rate": 1.0008115321910729e-05,
1976
+ "loss": 0.9172634482383728,
1977
+ "step": 562
1978
+ },
1979
+ {
1980
+ "epoch": 2.247011952191235,
1981
+ "grad_norm": 0.43472668528556824,
1982
+ "learning_rate": 9.949161236320388e-06,
1983
+ "loss": 0.6723137497901917,
1984
+ "step": 564
1985
+ },
1986
+ {
1987
+ "epoch": 2.2549800796812747,
1988
+ "grad_norm": 0.491053968667984,
1989
+ "learning_rate": 9.890252828873816e-06,
1990
+ "loss": 0.4990261197090149,
1991
+ "step": 566
1992
+ },
1993
+ {
1994
+ "epoch": 2.2629482071713145,
1995
+ "grad_norm": 0.19463039934635162,
1996
+ "learning_rate": 9.831392660217608e-06,
1997
+ "loss": 0.6660031080245972,
1998
+ "step": 568
1999
+ },
2000
+ {
2001
+ "epoch": 2.2709163346613543,
2002
+ "grad_norm": 0.1894519180059433,
2003
+ "learning_rate": 9.772583288901502e-06,
2004
+ "loss": 0.804633617401123,
2005
+ "step": 570
2006
+ },
2007
+ {
2008
+ "epoch": 2.278884462151394,
2009
+ "grad_norm": 0.6049039363861084,
2010
+ "learning_rate": 9.713827271267169e-06,
2011
+ "loss": 0.5522835850715637,
2012
+ "step": 572
2013
+ },
2014
+ {
2015
+ "epoch": 2.2868525896414345,
2016
+ "grad_norm": 0.21983656287193298,
2017
+ "learning_rate": 9.655127161337088e-06,
2018
+ "loss": 0.6103823184967041,
2019
+ "step": 574
2020
+ },
2021
+ {
2022
+ "epoch": 2.2948207171314743,
2023
+ "grad_norm": 0.6579908728599548,
2024
+ "learning_rate": 9.59648551070351e-06,
2025
+ "loss": 0.24219289422035217,
2026
+ "step": 576
2027
+ },
2028
+ {
2029
+ "epoch": 2.302788844621514,
2030
+ "grad_norm": 0.5361920595169067,
2031
+ "learning_rate": 9.53790486841759e-06,
2032
+ "loss": 0.5663895010948181,
2033
+ "step": 578
2034
+ },
2035
+ {
2036
+ "epoch": 2.310756972111554,
2037
+ "grad_norm": 0.3519666790962219,
2038
+ "learning_rate": 9.479387780878531e-06,
2039
+ "loss": 0.5547711849212646,
2040
+ "step": 580
2041
+ },
2042
+ {
2043
+ "epoch": 2.318725099601594,
2044
+ "grad_norm": 3.0020523071289062,
2045
+ "learning_rate": 9.42093679172294e-06,
2046
+ "loss": 0.5223433375358582,
2047
+ "step": 582
2048
+ },
2049
+ {
2050
+ "epoch": 2.3266932270916336,
2051
+ "grad_norm": 0.20067761838436127,
2052
+ "learning_rate": 9.362554441714216e-06,
2053
+ "loss": 0.6483029127120972,
2054
+ "step": 584
2055
+ },
2056
+ {
2057
+ "epoch": 2.3346613545816735,
2058
+ "grad_norm": 0.6246410012245178,
2059
+ "learning_rate": 9.304243268632165e-06,
2060
+ "loss": 0.5529161691665649,
2061
+ "step": 586
2062
+ },
2063
+ {
2064
+ "epoch": 2.3426294820717133,
2065
+ "grad_norm": 0.4139845669269562,
2066
+ "learning_rate": 9.246005807162632e-06,
2067
+ "loss": 0.7177547812461853,
2068
+ "step": 588
2069
+ },
2070
+ {
2071
+ "epoch": 2.350597609561753,
2072
+ "grad_norm": 0.4397997260093689,
2073
+ "learning_rate": 9.187844588787354e-06,
2074
+ "loss": 0.8279111981391907,
2075
+ "step": 590
2076
+ },
2077
+ {
2078
+ "epoch": 2.358565737051793,
2079
+ "grad_norm": 0.22359026968479156,
2080
+ "learning_rate": 9.12976214167391e-06,
2081
+ "loss": 0.8503004908561707,
2082
+ "step": 592
2083
+ },
2084
+ {
2085
+ "epoch": 2.366533864541833,
2086
+ "grad_norm": 0.3120749890804291,
2087
+ "learning_rate": 9.071760990565832e-06,
2088
+ "loss": 0.5646694898605347,
2089
+ "step": 594
2090
+ },
2091
+ {
2092
+ "epoch": 2.3745019920318726,
2093
+ "grad_norm": 0.1713973730802536,
2094
+ "learning_rate": 9.013843656672854e-06,
2095
+ "loss": 0.7497953772544861,
2096
+ "step": 596
2097
+ },
2098
+ {
2099
+ "epoch": 2.3824701195219125,
2100
+ "grad_norm": 0.13825774192810059,
2101
+ "learning_rate": 8.956012657561314e-06,
2102
+ "loss": 0.5747182965278625,
2103
+ "step": 598
2104
+ },
2105
+ {
2106
+ "epoch": 2.3904382470119523,
2107
+ "grad_norm": 0.6295970678329468,
2108
+ "learning_rate": 8.89827050704474e-06,
2109
+ "loss": 0.6441735625267029,
2110
+ "step": 600
2111
+ },
2112
+ {
2113
+ "epoch": 2.398406374501992,
2114
+ "grad_norm": 0.3059506416320801,
2115
+ "learning_rate": 8.840619715074553e-06,
2116
+ "loss": 0.8171231746673584,
2117
+ "step": 602
2118
+ },
2119
+ {
2120
+ "epoch": 2.406374501992032,
2121
+ "grad_norm": 0.416616290807724,
2122
+ "learning_rate": 8.78306278763098e-06,
2123
+ "loss": 0.49859338998794556,
2124
+ "step": 604
2125
+ },
2126
+ {
2127
+ "epoch": 2.414342629482072,
2128
+ "grad_norm": 0.6188241243362427,
2129
+ "learning_rate": 8.725602226614121e-06,
2130
+ "loss": 0.23148350417613983,
2131
+ "step": 606
2132
+ },
2133
+ {
2134
+ "epoch": 2.4223107569721116,
2135
+ "grad_norm": 0.17639189958572388,
2136
+ "learning_rate": 8.668240529735192e-06,
2137
+ "loss": 0.3683927357196808,
2138
+ "step": 608
2139
+ },
2140
+ {
2141
+ "epoch": 2.4302788844621515,
2142
+ "grad_norm": 0.14717182517051697,
2143
+ "learning_rate": 8.610980190407958e-06,
2144
+ "loss": 0.6629661321640015,
2145
+ "step": 610
2146
+ },
2147
+ {
2148
+ "epoch": 2.4382470119521913,
2149
+ "grad_norm": 0.472764790058136,
2150
+ "learning_rate": 8.55382369764034e-06,
2151
+ "loss": 0.6623281836509705,
2152
+ "step": 612
2153
+ },
2154
+ {
2155
+ "epoch": 2.446215139442231,
2156
+ "grad_norm": 0.28185757994651794,
2157
+ "learning_rate": 8.496773535926242e-06,
2158
+ "loss": 0.4608023464679718,
2159
+ "step": 614
2160
+ },
2161
+ {
2162
+ "epoch": 2.454183266932271,
2163
+ "grad_norm": 0.246009960770607,
2164
+ "learning_rate": 8.439832185137529e-06,
2165
+ "loss": 0.7289039492607117,
2166
+ "step": 616
2167
+ },
2168
+ {
2169
+ "epoch": 2.462151394422311,
2170
+ "grad_norm": 0.3146935701370239,
2171
+ "learning_rate": 8.383002120416241e-06,
2172
+ "loss": 0.595883309841156,
2173
+ "step": 618
2174
+ },
2175
+ {
2176
+ "epoch": 2.4701195219123506,
2177
+ "grad_norm": 0.46129530668258667,
2178
+ "learning_rate": 8.326285812067023e-06,
2179
+ "loss": 0.6848819851875305,
2180
+ "step": 620
2181
+ },
2182
+ {
2183
+ "epoch": 2.4780876494023905,
2184
+ "grad_norm": 0.39660993218421936,
2185
+ "learning_rate": 8.269685725449708e-06,
2186
+ "loss": 0.6775418519973755,
2187
+ "step": 622
2188
+ },
2189
+ {
2190
+ "epoch": 2.4860557768924303,
2191
+ "grad_norm": 0.4998105764389038,
2192
+ "learning_rate": 8.213204320872176e-06,
2193
+ "loss": 0.668332040309906,
2194
+ "step": 624
2195
+ },
2196
+ {
2197
+ "epoch": 2.49402390438247,
2198
+ "grad_norm": 0.3267073333263397,
2199
+ "learning_rate": 8.156844053483412e-06,
2200
+ "loss": 0.4088161289691925,
2201
+ "step": 626
2202
+ },
2203
+ {
2204
+ "epoch": 2.50199203187251,
2205
+ "grad_norm": 0.6505297422409058,
2206
+ "learning_rate": 8.100607373166773e-06,
2207
+ "loss": 0.8275009393692017,
2208
+ "step": 628
2209
+ },
2210
+ {
2211
+ "epoch": 2.50996015936255,
2212
+ "grad_norm": 0.40992996096611023,
2213
+ "learning_rate": 8.044496724433493e-06,
2214
+ "loss": 0.3234272003173828,
2215
+ "step": 630
2216
+ },
2217
+ {
2218
+ "epoch": 2.5179282868525896,
2219
+ "grad_norm": 0.5893640518188477,
2220
+ "learning_rate": 7.988514546316437e-06,
2221
+ "loss": 0.4355270564556122,
2222
+ "step": 632
2223
+ },
2224
+ {
2225
+ "epoch": 2.5258964143426295,
2226
+ "grad_norm": 0.2000420093536377,
2227
+ "learning_rate": 7.932663272264079e-06,
2228
+ "loss": 0.8469869494438171,
2229
+ "step": 634
2230
+ },
2231
+ {
2232
+ "epoch": 2.5338645418326693,
2233
+ "grad_norm": 2.3752691745758057,
2234
+ "learning_rate": 7.87694533003471e-06,
2235
+ "loss": 0.7660741209983826,
2236
+ "step": 636
2237
+ },
2238
+ {
2239
+ "epoch": 2.541832669322709,
2240
+ "grad_norm": 0.38962018489837646,
2241
+ "learning_rate": 7.82136314159092e-06,
2242
+ "loss": 0.8690819144248962,
2243
+ "step": 638
2244
+ },
2245
+ {
2246
+ "epoch": 2.549800796812749,
2247
+ "grad_norm": 0.12522974610328674,
2248
+ "learning_rate": 7.765919122994319e-06,
2249
+ "loss": 0.30734166502952576,
2250
+ "step": 640
2251
+ },
2252
+ {
2253
+ "epoch": 2.557768924302789,
2254
+ "grad_norm": 0.2867269217967987,
2255
+ "learning_rate": 7.710615684300518e-06,
2256
+ "loss": 0.8029553890228271,
2257
+ "step": 642
2258
+ },
2259
+ {
2260
+ "epoch": 2.5657370517928286,
2261
+ "grad_norm": 0.19536034762859344,
2262
+ "learning_rate": 7.655455229454354e-06,
2263
+ "loss": 0.7299827337265015,
2264
+ "step": 644
2265
+ },
2266
+ {
2267
+ "epoch": 2.5737051792828685,
2268
+ "grad_norm": 0.38802143931388855,
2269
+ "learning_rate": 7.6004401561854e-06,
2270
+ "loss": 0.5647068023681641,
2271
+ "step": 646
2272
+ },
2273
+ {
2274
+ "epoch": 2.5816733067729083,
2275
+ "grad_norm": 0.23780430853366852,
2276
+ "learning_rate": 7.545572855903756e-06,
2277
+ "loss": 0.8187406659126282,
2278
+ "step": 648
2279
+ },
2280
+ {
2281
+ "epoch": 2.589641434262948,
2282
+ "grad_norm": 0.16200827062129974,
2283
+ "learning_rate": 7.490855713596081e-06,
2284
+ "loss": 0.6111049056053162,
2285
+ "step": 650
2286
+ },
2287
+ {
2288
+ "epoch": 2.597609561752988,
2289
+ "grad_norm": 0.3508452773094177,
2290
+ "learning_rate": 7.4362911077219155e-06,
2291
+ "loss": 0.5618999600410461,
2292
+ "step": 652
2293
+ },
2294
+ {
2295
+ "epoch": 2.605577689243028,
2296
+ "grad_norm": 0.632539689540863,
2297
+ "learning_rate": 7.381881410110326e-06,
2298
+ "loss": 0.5881422758102417,
2299
+ "step": 654
2300
+ },
2301
+ {
2302
+ "epoch": 2.6135458167330676,
2303
+ "grad_norm": 0.3363528251647949,
2304
+ "learning_rate": 7.327628985856765e-06,
2305
+ "loss": 0.27832284569740295,
2306
+ "step": 656
2307
+ },
2308
+ {
2309
+ "epoch": 2.6215139442231075,
2310
+ "grad_norm": 0.3875587582588196,
2311
+ "learning_rate": 7.2735361932202965e-06,
2312
+ "loss": 0.48132815957069397,
2313
+ "step": 658
2314
+ },
2315
+ {
2316
+ "epoch": 2.6294820717131473,
2317
+ "grad_norm": 0.17317701876163483,
2318
+ "learning_rate": 7.219605383521067e-06,
2319
+ "loss": 0.7134672999382019,
2320
+ "step": 660
2321
+ },
2322
+ {
2323
+ "epoch": 2.637450199203187,
2324
+ "grad_norm": 0.7390320897102356,
2325
+ "learning_rate": 7.165838901038107e-06,
2326
+ "loss": 0.6096608638763428,
2327
+ "step": 662
2328
+ },
2329
+ {
2330
+ "epoch": 2.645418326693227,
2331
+ "grad_norm": 0.4265226423740387,
2332
+ "learning_rate": 7.112239082907433e-06,
2333
+ "loss": 0.4687889814376831,
2334
+ "step": 664
2335
+ },
2336
+ {
2337
+ "epoch": 2.653386454183267,
2338
+ "grad_norm": 0.3511049151420593,
2339
+ "learning_rate": 7.058808259020442e-06,
2340
+ "loss": 0.7662704586982727,
2341
+ "step": 666
2342
+ },
2343
+ {
2344
+ "epoch": 2.6613545816733066,
2345
+ "grad_norm": 0.14830322563648224,
2346
+ "learning_rate": 7.005548751922642e-06,
2347
+ "loss": 0.58231520652771,
2348
+ "step": 668
2349
+ },
2350
+ {
2351
+ "epoch": 2.6693227091633465,
2352
+ "grad_norm": 1.2010635137557983,
2353
+ "learning_rate": 6.952462876712707e-06,
2354
+ "loss": 0.5792977213859558,
2355
+ "step": 670
2356
+ },
2357
+ {
2358
+ "epoch": 2.6772908366533863,
2359
+ "grad_norm": 0.09235794842243195,
2360
+ "learning_rate": 6.899552940941829e-06,
2361
+ "loss": 0.25369662046432495,
2362
+ "step": 672
2363
+ },
2364
+ {
2365
+ "epoch": 2.685258964143426,
2366
+ "grad_norm": 0.2072373628616333,
2367
+ "learning_rate": 6.846821244513411e-06,
2368
+ "loss": 0.8279775381088257,
2369
+ "step": 674
2370
+ },
2371
+ {
2372
+ "epoch": 2.6932270916334664,
2373
+ "grad_norm": 1.2984479665756226,
2374
+ "learning_rate": 6.794270079583101e-06,
2375
+ "loss": 0.5745002031326294,
2376
+ "step": 676
2377
+ },
2378
+ {
2379
+ "epoch": 2.7011952191235062,
2380
+ "grad_norm": 0.3513108193874359,
2381
+ "learning_rate": 6.741901730459166e-06,
2382
+ "loss": 0.5112911462783813,
2383
+ "step": 678
2384
+ },
2385
+ {
2386
+ "epoch": 2.709163346613546,
2387
+ "grad_norm": 0.3224731385707855,
2388
+ "learning_rate": 6.68971847350317e-06,
2389
+ "loss": 0.8467031717300415,
2390
+ "step": 680
2391
+ },
2392
+ {
2393
+ "epoch": 2.717131474103586,
2394
+ "grad_norm": 0.1862608939409256,
2395
+ "learning_rate": 6.6377225770310514e-06,
2396
+ "loss": 0.8552311062812805,
2397
+ "step": 682
2398
+ },
2399
+ {
2400
+ "epoch": 2.7250996015936257,
2401
+ "grad_norm": 0.2126304805278778,
2402
+ "learning_rate": 6.585916301214519e-06,
2403
+ "loss": 0.6002206206321716,
2404
+ "step": 684
2405
+ },
2406
+ {
2407
+ "epoch": 2.7330677290836656,
2408
+ "grad_norm": 0.24358995258808136,
2409
+ "learning_rate": 6.534301897982774e-06,
2410
+ "loss": 0.3887878954410553,
2411
+ "step": 686
2412
+ },
2413
+ {
2414
+ "epoch": 2.7410358565737054,
2415
+ "grad_norm": 0.19447919726371765,
2416
+ "learning_rate": 6.482881610924674e-06,
2417
+ "loss": 0.83692467212677,
2418
+ "step": 688
2419
+ },
2420
+ {
2421
+ "epoch": 2.7490039840637452,
2422
+ "grad_norm": 0.4111102223396301,
2423
+ "learning_rate": 6.43165767519117e-06,
2424
+ "loss": 0.4429361820220947,
2425
+ "step": 690
2426
+ },
2427
+ {
2428
+ "epoch": 2.756972111553785,
2429
+ "grad_norm": 0.24252432584762573,
2430
+ "learning_rate": 6.380632317398168e-06,
2431
+ "loss": 0.9488629102706909,
2432
+ "step": 692
2433
+ },
2434
+ {
2435
+ "epoch": 2.764940239043825,
2436
+ "grad_norm": 1.053657054901123,
2437
+ "learning_rate": 6.3298077555297245e-06,
2438
+ "loss": 0.6902448534965515,
2439
+ "step": 694
2440
+ },
2441
+ {
2442
+ "epoch": 2.7729083665338647,
2443
+ "grad_norm": 0.5043600797653198,
2444
+ "learning_rate": 6.279186198841647e-06,
2445
+ "loss": 0.3843526840209961,
2446
+ "step": 696
2447
+ },
2448
+ {
2449
+ "epoch": 2.7808764940239046,
2450
+ "grad_norm": 0.2123395949602127,
2451
+ "learning_rate": 6.228769847765468e-06,
2452
+ "loss": 0.6492659449577332,
2453
+ "step": 698
2454
+ },
2455
+ {
2456
+ "epoch": 2.7888446215139444,
2457
+ "grad_norm": 0.2770644426345825,
2458
+ "learning_rate": 6.178560893812774e-06,
2459
+ "loss": 0.8826568126678467,
2460
+ "step": 700
2461
+ },
2462
+ {
2463
+ "epoch": 2.7968127490039842,
2464
+ "grad_norm": 0.36284762620925903,
2465
+ "learning_rate": 6.1285615194799695e-06,
2466
+ "loss": 0.49446773529052734,
2467
+ "step": 702
2468
+ },
2469
+ {
2470
+ "epoch": 2.804780876494024,
2471
+ "grad_norm": 0.42989182472229004,
2472
+ "learning_rate": 6.0787738981533825e-06,
2473
+ "loss": 0.8925838470458984,
2474
+ "step": 704
2475
+ },
2476
+ {
2477
+ "epoch": 2.812749003984064,
2478
+ "grad_norm": 0.19607830047607422,
2479
+ "learning_rate": 6.0292001940148174e-06,
2480
+ "loss": 0.7888954281806946,
2481
+ "step": 706
2482
+ },
2483
+ {
2484
+ "epoch": 2.8207171314741037,
2485
+ "grad_norm": 0.3013284504413605,
2486
+ "learning_rate": 5.979842561947455e-06,
2487
+ "loss": 0.9048675298690796,
2488
+ "step": 708
2489
+ },
2490
+ {
2491
+ "epoch": 2.8286852589641436,
2492
+ "grad_norm": 0.1352807581424713,
2493
+ "learning_rate": 5.9307031474422074e-06,
2494
+ "loss": 0.45338767766952515,
2495
+ "step": 710
2496
+ },
2497
+ {
2498
+ "epoch": 2.8366533864541834,
2499
+ "grad_norm": 0.2785419225692749,
2500
+ "learning_rate": 5.88178408650445e-06,
2501
+ "loss": 0.8890714645385742,
2502
+ "step": 712
2503
+ },
2504
+ {
2505
+ "epoch": 2.8446215139442232,
2506
+ "grad_norm": 0.29292890429496765,
2507
+ "learning_rate": 5.833087505561148e-06,
2508
+ "loss": 0.5466417074203491,
2509
+ "step": 714
2510
+ },
2511
+ {
2512
+ "epoch": 2.852589641434263,
2513
+ "grad_norm": 0.37993285059928894,
2514
+ "learning_rate": 5.784615521368468e-06,
2515
+ "loss": 0.8255132436752319,
2516
+ "step": 716
2517
+ },
2518
+ {
2519
+ "epoch": 2.860557768924303,
2520
+ "grad_norm": 1.8282309770584106,
2521
+ "learning_rate": 5.736370240919735e-06,
2522
+ "loss": 0.5976371765136719,
2523
+ "step": 718
2524
+ },
2525
+ {
2526
+ "epoch": 2.8685258964143427,
2527
+ "grad_norm": 0.3135332465171814,
2528
+ "learning_rate": 5.688353761353862e-06,
2529
+ "loss": 0.5985286831855774,
2530
+ "step": 720
2531
+ },
2532
+ {
2533
+ "epoch": 2.8764940239043826,
2534
+ "grad_norm": 0.4926091730594635,
2535
+ "learning_rate": 5.640568169864173e-06,
2536
+ "loss": 0.5094777941703796,
2537
+ "step": 722
2538
+ },
2539
+ {
2540
+ "epoch": 2.8844621513944224,
2541
+ "grad_norm": 0.28557467460632324,
2542
+ "learning_rate": 5.5930155436076875e-06,
2543
+ "loss": 0.5855981111526489,
2544
+ "step": 724
2545
+ },
2546
+ {
2547
+ "epoch": 2.8924302788844622,
2548
+ "grad_norm": 0.1873752772808075,
2549
+ "learning_rate": 5.5456979496148385e-06,
2550
+ "loss": 0.8087204694747925,
2551
+ "step": 726
2552
+ },
2553
+ {
2554
+ "epoch": 2.900398406374502,
2555
+ "grad_norm": 0.17823685705661774,
2556
+ "learning_rate": 5.498617444699603e-06,
2557
+ "loss": 0.48339203000068665,
2558
+ "step": 728
2559
+ },
2560
+ {
2561
+ "epoch": 2.908366533864542,
2562
+ "grad_norm": 0.18616022169589996,
2563
+ "learning_rate": 5.451776075370114e-06,
2564
+ "loss": 0.8099565505981445,
2565
+ "step": 730
2566
+ },
2567
+ {
2568
+ "epoch": 2.9163346613545817,
2569
+ "grad_norm": 1.2350081205368042,
2570
+ "learning_rate": 5.405175877739684e-06,
2571
+ "loss": 0.23912093043327332,
2572
+ "step": 732
2573
+ },
2574
+ {
2575
+ "epoch": 2.9243027888446216,
2576
+ "grad_norm": 0.18930251896381378,
2577
+ "learning_rate": 5.3588188774383235e-06,
2578
+ "loss": 0.8681591153144836,
2579
+ "step": 734
2580
+ },
2581
+ {
2582
+ "epoch": 2.9322709163346614,
2583
+ "grad_norm": 0.6436243057250977,
2584
+ "learning_rate": 5.3127070895246604e-06,
2585
+ "loss": 0.37712156772613525,
2586
+ "step": 736
2587
+ },
2588
+ {
2589
+ "epoch": 2.9402390438247012,
2590
+ "grad_norm": 0.5814879536628723,
2591
+ "learning_rate": 5.266842518398369e-06,
2592
+ "loss": 0.5876435041427612,
2593
+ "step": 738
2594
+ },
2595
+ {
2596
+ "epoch": 2.948207171314741,
2597
+ "grad_norm": 0.19967974722385406,
2598
+ "learning_rate": 5.2212271577130495e-06,
2599
+ "loss": 0.8929345607757568,
2600
+ "step": 740
2601
+ },
2602
+ {
2603
+ "epoch": 2.956175298804781,
2604
+ "grad_norm": 0.5970357656478882,
2605
+ "learning_rate": 5.1758629902895375e-06,
2606
+ "loss": 0.24971675872802734,
2607
+ "step": 742
2608
+ },
2609
+ {
2610
+ "epoch": 2.9641434262948207,
2611
+ "grad_norm": 0.1709216833114624,
2612
+ "learning_rate": 5.1307519880297385e-06,
2613
+ "loss": 0.6873310804367065,
2614
+ "step": 744
2615
+ },
2616
+ {
2617
+ "epoch": 2.9721115537848606,
2618
+ "grad_norm": 0.32703879475593567,
2619
+ "learning_rate": 5.085896111830908e-06,
2620
+ "loss": 0.7358705997467041,
2621
+ "step": 746
2622
+ },
2623
+ {
2624
+ "epoch": 2.9800796812749004,
2625
+ "grad_norm": 0.6799337267875671,
2626
+ "learning_rate": 5.041297311500417e-06,
2627
+ "loss": 0.40029191970825195,
2628
+ "step": 748
2629
+ },
2630
+ {
2631
+ "epoch": 2.9880478087649402,
2632
+ "grad_norm": 0.2632702589035034,
2633
+ "learning_rate": 4.996957525670984e-06,
2634
+ "loss": 0.11657044291496277,
2635
+ "step": 750
2636
+ },
2637
+ {
2638
+ "epoch": 2.99601593625498,
2639
+ "grad_norm": 0.18080343306064606,
2640
+ "learning_rate": 4.952878681716416e-06,
2641
+ "loss": 0.832659125328064,
2642
+ "step": 752
2643
+ },
2644
+ {
2645
+ "epoch": 3.00398406374502,
2646
+ "grad_norm": 0.18914125859737396,
2647
+ "learning_rate": 4.9090626956678355e-06,
2648
+ "loss": 0.4053405225276947,
2649
+ "step": 754
2650
+ },
2651
+ {
2652
+ "epoch": 3.0119521912350598,
2653
+ "grad_norm": 0.27092087268829346,
2654
+ "learning_rate": 4.865511472130379e-06,
2655
+ "loss": 0.37303829193115234,
2656
+ "step": 756
2657
+ },
2658
+ {
2659
+ "epoch": 3.0199203187250996,
2660
+ "grad_norm": 0.450639545917511,
2661
+ "learning_rate": 4.822226904200422e-06,
2662
+ "loss": 0.16986803710460663,
2663
+ "step": 758
2664
+ },
2665
+ {
2666
+ "epoch": 3.0278884462151394,
2667
+ "grad_norm": 0.3367942273616791,
2668
+ "learning_rate": 4.779210873383273e-06,
2669
+ "loss": 0.3704196810722351,
2670
+ "step": 760
2671
+ },
2672
+ {
2673
+ "epoch": 3.0358565737051793,
2674
+ "grad_norm": 1.1672158241271973,
2675
+ "learning_rate": 4.7364652495114e-06,
2676
+ "loss": 0.2740946114063263,
2677
+ "step": 762
2678
+ },
2679
+ {
2680
+ "epoch": 3.043824701195219,
2681
+ "grad_norm": 0.2160903364419937,
2682
+ "learning_rate": 4.693991890663152e-06,
2683
+ "loss": 0.5514514446258545,
2684
+ "step": 764
2685
+ },
2686
+ {
2687
+ "epoch": 3.051792828685259,
2688
+ "grad_norm": 0.40776246786117554,
2689
+ "learning_rate": 4.651792643081986e-06,
2690
+ "loss": 0.18550026416778564,
2691
+ "step": 766
2692
+ },
2693
+ {
2694
+ "epoch": 3.0597609561752988,
2695
+ "grad_norm": 1.529194951057434,
2696
+ "learning_rate": 4.609869341096217e-06,
2697
+ "loss": 0.3695829212665558,
2698
+ "step": 768
2699
+ },
2700
+ {
2701
+ "epoch": 3.0677290836653386,
2702
+ "grad_norm": 0.2934879660606384,
2703
+ "learning_rate": 4.568223807039282e-06,
2704
+ "loss": 0.40844109654426575,
2705
+ "step": 770
2706
+ },
2707
+ {
2708
+ "epoch": 3.0756972111553784,
2709
+ "grad_norm": 0.3209177553653717,
2710
+ "learning_rate": 4.52685785117052e-06,
2711
+ "loss": 0.6010529398918152,
2712
+ "step": 772
2713
+ },
2714
+ {
2715
+ "epoch": 3.0836653386454183,
2716
+ "grad_norm": 0.4266740083694458,
2717
+ "learning_rate": 4.485773271596503e-06,
2718
+ "loss": 0.5307098627090454,
2719
+ "step": 774
2720
+ },
2721
+ {
2722
+ "epoch": 3.091633466135458,
2723
+ "grad_norm": 0.05216313526034355,
2724
+ "learning_rate": 4.444971854192848e-06,
2725
+ "loss": 0.31485700607299805,
2726
+ "step": 776
2727
+ },
2728
+ {
2729
+ "epoch": 3.099601593625498,
2730
+ "grad_norm": 0.25069746375083923,
2731
+ "learning_rate": 4.404455372526615e-06,
2732
+ "loss": 0.3358692228794098,
2733
+ "step": 778
2734
+ },
2735
+ {
2736
+ "epoch": 3.1075697211155378,
2737
+ "grad_norm": 0.3168417513370514,
2738
+ "learning_rate": 4.3642255877791876e-06,
2739
+ "loss": 0.5717326402664185,
2740
+ "step": 780
2741
+ },
2742
+ {
2743
+ "epoch": 3.1155378486055776,
2744
+ "grad_norm": 0.08099119365215302,
2745
+ "learning_rate": 4.324284248669742e-06,
2746
+ "loss": 0.13734716176986694,
2747
+ "step": 782
2748
+ },
2749
+ {
2750
+ "epoch": 3.1235059760956174,
2751
+ "grad_norm": 0.1908828169107437,
2752
+ "learning_rate": 4.2846330913792136e-06,
2753
+ "loss": 0.6576658487319946,
2754
+ "step": 784
2755
+ },
2756
+ {
2757
+ "epoch": 3.1314741035856573,
2758
+ "grad_norm": 0.2333727329969406,
2759
+ "learning_rate": 4.245273839474835e-06,
2760
+ "loss": 0.4396320879459381,
2761
+ "step": 786
2762
+ },
2763
+ {
2764
+ "epoch": 3.139442231075697,
2765
+ "grad_norm": 2.3938891887664795,
2766
+ "learning_rate": 4.20620820383523e-06,
2767
+ "loss": 0.3137848973274231,
2768
+ "step": 788
2769
+ },
2770
+ {
2771
+ "epoch": 3.147410358565737,
2772
+ "grad_norm": 0.1568251997232437,
2773
+ "learning_rate": 4.167437882576009e-06,
2774
+ "loss": 0.2973101735115051,
2775
+ "step": 790
2776
+ },
2777
+ {
2778
+ "epoch": 3.1553784860557768,
2779
+ "grad_norm": 0.4758032560348511,
2780
+ "learning_rate": 4.128964560975993e-06,
2781
+ "loss": 0.36776888370513916,
2782
+ "step": 792
2783
+ },
2784
+ {
2785
+ "epoch": 3.1633466135458166,
2786
+ "grad_norm": 0.07684729248285294,
2787
+ "learning_rate": 4.090789911403938e-06,
2788
+ "loss": 0.16028432548046112,
2789
+ "step": 794
2790
+ },
2791
+ {
2792
+ "epoch": 3.1713147410358564,
2793
+ "grad_norm": 0.38295745849609375,
2794
+ "learning_rate": 4.0529155932458444e-06,
2795
+ "loss": 0.35760873556137085,
2796
+ "step": 796
2797
+ },
2798
+ {
2799
+ "epoch": 3.1792828685258963,
2800
+ "grad_norm": 0.2896295189857483,
2801
+ "learning_rate": 4.015343252832824e-06,
2802
+ "loss": 0.41373881697654724,
2803
+ "step": 798
2804
+ },
2805
+ {
2806
+ "epoch": 3.187250996015936,
2807
+ "grad_norm": 0.3329697847366333,
2808
+ "learning_rate": 3.978074523369533e-06,
2809
+ "loss": 0.5053466558456421,
2810
+ "step": 800
2811
+ },
2812
+ {
2813
+ "epoch": 3.195219123505976,
2814
+ "grad_norm": 0.15466375648975372,
2815
+ "learning_rate": 3.941111024863193e-06,
2816
+ "loss": 0.42649704217910767,
2817
+ "step": 802
2818
+ },
2819
+ {
2820
+ "epoch": 3.2031872509960158,
2821
+ "grad_norm": 1.1632299423217773,
2822
+ "learning_rate": 3.90445436405316e-06,
2823
+ "loss": 0.28943392634391785,
2824
+ "step": 804
2825
+ },
2826
+ {
2827
+ "epoch": 3.2111553784860556,
2828
+ "grad_norm": 0.9543743133544922,
2829
+ "learning_rate": 3.86810613434109e-06,
2830
+ "loss": 0.5052630305290222,
2831
+ "step": 806
2832
+ },
2833
+ {
2834
+ "epoch": 3.2191235059760954,
2835
+ "grad_norm": 0.3861115574836731,
2836
+ "learning_rate": 3.832067915721661e-06,
2837
+ "loss": 0.06477329879999161,
2838
+ "step": 808
2839
+ },
2840
+ {
2841
+ "epoch": 3.2270916334661353,
2842
+ "grad_norm": 0.3546229898929596,
2843
+ "learning_rate": 3.7963412747139204e-06,
2844
+ "loss": 0.38985639810562134,
2845
+ "step": 810
2846
+ },
2847
+ {
2848
+ "epoch": 3.235059760956175,
2849
+ "grad_norm": 0.37589749693870544,
2850
+ "learning_rate": 3.7609277642931642e-06,
2851
+ "loss": 0.2961961328983307,
2852
+ "step": 812
2853
+ },
2854
+ {
2855
+ "epoch": 3.243027888446215,
2856
+ "grad_norm": 0.21967440843582153,
2857
+ "learning_rate": 3.725828923823447e-06,
2858
+ "loss": 0.477074533700943,
2859
+ "step": 814
2860
+ },
2861
+ {
2862
+ "epoch": 3.2509960159362548,
2863
+ "grad_norm": 0.5088498592376709,
2864
+ "learning_rate": 3.6910462789906697e-06,
2865
+ "loss": 0.09672769904136658,
2866
+ "step": 816
2867
+ },
2868
+ {
2869
+ "epoch": 3.2589641434262946,
2870
+ "grad_norm": 3.130514621734619,
2871
+ "learning_rate": 3.6565813417362476e-06,
2872
+ "loss": 0.5637337565422058,
2873
+ "step": 818
2874
+ },
2875
+ {
2876
+ "epoch": 3.2669322709163344,
2877
+ "grad_norm": 1.0084922313690186,
2878
+ "learning_rate": 3.622435610191398e-06,
2879
+ "loss": 0.22835613787174225,
2880
+ "step": 820
2881
+ },
2882
+ {
2883
+ "epoch": 3.2749003984063743,
2884
+ "grad_norm": 0.7883324027061462,
2885
+ "learning_rate": 3.5886105686120267e-06,
2886
+ "loss": 0.23144333064556122,
2887
+ "step": 822
2888
+ },
2889
+ {
2890
+ "epoch": 3.2828685258964145,
2891
+ "grad_norm": 1.4939353466033936,
2892
+ "learning_rate": 3.5551076873141875e-06,
2893
+ "loss": 0.32171422243118286,
2894
+ "step": 824
2895
+ },
2896
+ {
2897
+ "epoch": 3.2908366533864544,
2898
+ "grad_norm": 0.250313937664032,
2899
+ "learning_rate": 3.5219284226101992e-06,
2900
+ "loss": 0.5594013333320618,
2901
+ "step": 826
2902
+ },
2903
+ {
2904
+ "epoch": 3.298804780876494,
2905
+ "grad_norm": 0.3546219766139984,
2906
+ "learning_rate": 3.4890742167453134e-06,
2907
+ "loss": 0.6331716775894165,
2908
+ "step": 828
2909
+ },
2910
+ {
2911
+ "epoch": 3.306772908366534,
2912
+ "grad_norm": 0.39389073848724365,
2913
+ "learning_rate": 3.4565464978350447e-06,
2914
+ "loss": 0.46244314312934875,
2915
+ "step": 830
2916
+ },
2917
+ {
2918
+ "epoch": 3.314741035856574,
2919
+ "grad_norm": 0.3902747333049774,
2920
+ "learning_rate": 3.4243466798030813e-06,
2921
+ "loss": 0.24344006180763245,
2922
+ "step": 832
2923
+ },
2924
+ {
2925
+ "epoch": 3.3227091633466137,
2926
+ "grad_norm": 0.6764956712722778,
2927
+ "learning_rate": 3.3924761623198276e-06,
2928
+ "loss": 0.21558792889118195,
2929
+ "step": 834
2930
+ },
2931
+ {
2932
+ "epoch": 3.3306772908366535,
2933
+ "grad_norm": 0.38500118255615234,
2934
+ "learning_rate": 3.360936330741563e-06,
2935
+ "loss": 0.3872177302837372,
2936
+ "step": 836
2937
+ },
2938
+ {
2939
+ "epoch": 3.3386454183266934,
2940
+ "grad_norm": 2.351408004760742,
2941
+ "learning_rate": 3.329728556050219e-06,
2942
+ "loss": 0.45764562487602234,
2943
+ "step": 838
2944
+ },
2945
+ {
2946
+ "epoch": 3.346613545816733,
2947
+ "grad_norm": 2.8567023277282715,
2948
+ "learning_rate": 3.2988541947937948e-06,
2949
+ "loss": 0.0879729688167572,
2950
+ "step": 840
2951
+ },
2952
+ {
2953
+ "epoch": 3.354581673306773,
2954
+ "grad_norm": 0.3541049063205719,
2955
+ "learning_rate": 3.2683145890273803e-06,
2956
+ "loss": 0.3018583655357361,
2957
+ "step": 842
2958
+ },
2959
+ {
2960
+ "epoch": 3.362549800796813,
2961
+ "grad_norm": 0.19183960556983948,
2962
+ "learning_rate": 3.2381110662548244e-06,
2963
+ "loss": 0.36365094780921936,
2964
+ "step": 844
2965
+ },
2966
+ {
2967
+ "epoch": 3.3705179282868527,
2968
+ "grad_norm": 0.2597419023513794,
2969
+ "learning_rate": 3.208244939371029e-06,
2970
+ "loss": 0.6369303464889526,
2971
+ "step": 846
2972
+ },
2973
+ {
2974
+ "epoch": 3.3784860557768925,
2975
+ "grad_norm": 0.261401891708374,
2976
+ "learning_rate": 3.178717506604878e-06,
2977
+ "loss": 0.579558789730072,
2978
+ "step": 848
2979
+ },
2980
+ {
2981
+ "epoch": 3.3864541832669324,
2982
+ "grad_norm": 0.9293565154075623,
2983
+ "learning_rate": 3.1495300514628137e-06,
2984
+ "loss": 0.4159211218357086,
2985
+ "step": 850
2986
+ },
2987
+ {
2988
+ "epoch": 3.394422310756972,
2989
+ "grad_norm": 0.2699755132198334,
2990
+ "learning_rate": 3.120683842673029e-06,
2991
+ "loss": 0.5360977053642273,
2992
+ "step": 852
2993
+ },
2994
+ {
2995
+ "epoch": 3.402390438247012,
2996
+ "grad_norm": 0.2359551638364792,
2997
+ "learning_rate": 3.092180134130341e-06,
2998
+ "loss": 0.3280014395713806,
2999
+ "step": 854
3000
+ },
3001
+ {
3002
+ "epoch": 3.410358565737052,
3003
+ "grad_norm": 0.270657479763031,
3004
+ "learning_rate": 3.064020164841661e-06,
3005
+ "loss": 0.4834939241409302,
3006
+ "step": 856
3007
+ },
3008
+ {
3009
+ "epoch": 3.4183266932270917,
3010
+ "grad_norm": 0.22715269029140472,
3011
+ "learning_rate": 3.03620515887216e-06,
3012
+ "loss": 0.5365287065505981,
3013
+ "step": 858
3014
+ },
3015
+ {
3016
+ "epoch": 3.4262948207171315,
3017
+ "grad_norm": 0.26945826411247253,
3018
+ "learning_rate": 3.0087363252920392e-06,
3019
+ "loss": 0.6132234930992126,
3020
+ "step": 860
3021
+ },
3022
+ {
3023
+ "epoch": 3.4342629482071714,
3024
+ "grad_norm": 0.3072214722633362,
3025
+ "learning_rate": 2.9816148581239945e-06,
3026
+ "loss": 0.3467521667480469,
3027
+ "step": 862
3028
+ },
3029
+ {
3030
+ "epoch": 3.442231075697211,
3031
+ "grad_norm": 0.43960896134376526,
3032
+ "learning_rate": 2.954841936291304e-06,
3033
+ "loss": 0.2627929449081421,
3034
+ "step": 864
3035
+ },
3036
+ {
3037
+ "epoch": 3.450199203187251,
3038
+ "grad_norm": 0.283093124628067,
3039
+ "learning_rate": 2.9284187235665706e-06,
3040
+ "loss": 0.48483937978744507,
3041
+ "step": 866
3042
+ },
3043
+ {
3044
+ "epoch": 3.458167330677291,
3045
+ "grad_norm": 0.25170329213142395,
3046
+ "learning_rate": 2.902346368521161e-06,
3047
+ "loss": 0.3998684883117676,
3048
+ "step": 868
3049
+ },
3050
+ {
3051
+ "epoch": 3.4661354581673307,
3052
+ "grad_norm": 0.6622265577316284,
3053
+ "learning_rate": 2.8766260044752596e-06,
3054
+ "loss": 0.36085110902786255,
3055
+ "step": 870
3056
+ },
3057
+ {
3058
+ "epoch": 3.4741035856573705,
3059
+ "grad_norm": 0.042979441583156586,
3060
+ "learning_rate": 2.851258749448613e-06,
3061
+ "loss": 0.3579687774181366,
3062
+ "step": 872
3063
+ },
3064
+ {
3065
+ "epoch": 3.4820717131474104,
3066
+ "grad_norm": 0.07233504951000214,
3067
+ "learning_rate": 2.8262457061119275e-06,
3068
+ "loss": 0.3310646712779999,
3069
+ "step": 874
3070
+ },
3071
+ {
3072
+ "epoch": 3.49003984063745,
3073
+ "grad_norm": 0.19331711530685425,
3074
+ "learning_rate": 2.801587961738936e-06,
3075
+ "loss": 0.28486010432243347,
3076
+ "step": 876
3077
+ },
3078
+ {
3079
+ "epoch": 3.49800796812749,
3080
+ "grad_norm": 0.24624978005886078,
3081
+ "learning_rate": 2.7772865881591487e-06,
3082
+ "loss": 0.35191646218299866,
3083
+ "step": 878
3084
+ },
3085
+ {
3086
+ "epoch": 3.50597609561753,
3087
+ "grad_norm": 0.07663383334875107,
3088
+ "learning_rate": 2.7533426417112463e-06,
3089
+ "loss": 0.23816527426242828,
3090
+ "step": 880
3091
+ },
3092
+ {
3093
+ "epoch": 3.5139442231075697,
3094
+ "grad_norm": 0.1692771017551422,
3095
+ "learning_rate": 2.729757163197175e-06,
3096
+ "loss": 0.20403024554252625,
3097
+ "step": 882
3098
+ },
3099
+ {
3100
+ "epoch": 3.5219123505976095,
3101
+ "grad_norm": 0.4337323009967804,
3102
+ "learning_rate": 2.706531177836896e-06,
3103
+ "loss": 0.04598721116781235,
3104
+ "step": 884
3105
+ },
3106
+ {
3107
+ "epoch": 3.5298804780876494,
3108
+ "grad_norm": 0.34074339270591736,
3109
+ "learning_rate": 2.683665695223827e-06,
3110
+ "loss": 0.4786261022090912,
3111
+ "step": 886
3112
+ },
3113
+ {
3114
+ "epoch": 3.537848605577689,
3115
+ "grad_norm": 0.2945248782634735,
3116
+ "learning_rate": 2.661161709280954e-06,
3117
+ "loss": 0.5180566310882568,
3118
+ "step": 888
3119
+ },
3120
+ {
3121
+ "epoch": 3.545816733067729,
3122
+ "grad_norm": 0.2568756937980652,
3123
+ "learning_rate": 2.6390201982176284e-06,
3124
+ "loss": 0.3125327527523041,
3125
+ "step": 890
3126
+ },
3127
+ {
3128
+ "epoch": 3.553784860557769,
3129
+ "grad_norm": 1.1016383171081543,
3130
+ "learning_rate": 2.617242124487048e-06,
3131
+ "loss": 0.3341105580329895,
3132
+ "step": 892
3133
+ },
3134
+ {
3135
+ "epoch": 3.5617529880478087,
3136
+ "grad_norm": 0.25893574953079224,
3137
+ "learning_rate": 2.595828434744411e-06,
3138
+ "loss": 0.7315629124641418,
3139
+ "step": 894
3140
+ },
3141
+ {
3142
+ "epoch": 3.5697211155378485,
3143
+ "grad_norm": 0.10278267413377762,
3144
+ "learning_rate": 2.574780059805779e-06,
3145
+ "loss": 0.09938185662031174,
3146
+ "step": 896
3147
+ },
3148
+ {
3149
+ "epoch": 3.5776892430278884,
3150
+ "grad_norm": 0.2548079788684845,
3151
+ "learning_rate": 2.5540979146076145e-06,
3152
+ "loss": 0.3255918323993683,
3153
+ "step": 898
3154
+ },
3155
+ {
3156
+ "epoch": 3.585657370517928,
3157
+ "grad_norm": 0.3227812349796295,
3158
+ "learning_rate": 2.5337828981669966e-06,
3159
+ "loss": 0.13555879890918732,
3160
+ "step": 900
3161
+ },
3162
+ {
3163
+ "epoch": 3.593625498007968,
3164
+ "grad_norm": 0.5672808289527893,
3165
+ "learning_rate": 2.513835893542561e-06,
3166
+ "loss": 0.1049320250749588,
3167
+ "step": 902
3168
+ },
3169
+ {
3170
+ "epoch": 3.601593625498008,
3171
+ "grad_norm": 0.25081929564476013,
3172
+ "learning_rate": 2.494257767796101e-06,
3173
+ "loss": 0.3797585070133209,
3174
+ "step": 904
3175
+ },
3176
+ {
3177
+ "epoch": 3.6095617529880477,
3178
+ "grad_norm": 0.4710356891155243,
3179
+ "learning_rate": 2.475049371954888e-06,
3180
+ "loss": 0.3027661144733429,
3181
+ "step": 906
3182
+ },
3183
+ {
3184
+ "epoch": 3.6175298804780875,
3185
+ "grad_norm": 0.2510360777378082,
3186
+ "learning_rate": 2.4562115409746662e-06,
3187
+ "loss": 0.5094070434570312,
3188
+ "step": 908
3189
+ },
3190
+ {
3191
+ "epoch": 3.6254980079681274,
3192
+ "grad_norm": 0.43042221665382385,
3193
+ "learning_rate": 2.4377450937033753e-06,
3194
+ "loss": 0.4744018614292145,
3195
+ "step": 910
3196
+ },
3197
+ {
3198
+ "epoch": 3.633466135458167,
3199
+ "grad_norm": 0.06483194977045059,
3200
+ "learning_rate": 2.419650832845541e-06,
3201
+ "loss": 0.04786789417266846,
3202
+ "step": 912
3203
+ },
3204
+ {
3205
+ "epoch": 3.641434262948207,
3206
+ "grad_norm": 0.25760993361473083,
3207
+ "learning_rate": 2.40192954492739e-06,
3208
+ "loss": 0.40470847487449646,
3209
+ "step": 914
3210
+ },
3211
+ {
3212
+ "epoch": 3.649402390438247,
3213
+ "grad_norm": 0.7198867201805115,
3214
+ "learning_rate": 2.3845820002626623e-06,
3215
+ "loss": 0.5723772048950195,
3216
+ "step": 916
3217
+ },
3218
+ {
3219
+ "epoch": 3.6573705179282867,
3220
+ "grad_norm": 0.5992567539215088,
3221
+ "learning_rate": 2.3676089529191234e-06,
3222
+ "loss": 0.06981807202100754,
3223
+ "step": 918
3224
+ },
3225
+ {
3226
+ "epoch": 3.6653386454183265,
3227
+ "grad_norm": 0.2739182412624359,
3228
+ "learning_rate": 2.3510111406857915e-06,
3229
+ "loss": 0.533017098903656,
3230
+ "step": 920
3231
+ },
3232
+ {
3233
+ "epoch": 3.6733067729083664,
3234
+ "grad_norm": 0.16629727184772491,
3235
+ "learning_rate": 2.3347892850408575e-06,
3236
+ "loss": 0.07635924965143204,
3237
+ "step": 922
3238
+ },
3239
+ {
3240
+ "epoch": 3.681274900398406,
3241
+ "grad_norm": 0.5157669186592102,
3242
+ "learning_rate": 2.3189440911203328e-06,
3243
+ "loss": 0.3664593994617462,
3244
+ "step": 924
3245
+ },
3246
+ {
3247
+ "epoch": 3.6892430278884465,
3248
+ "grad_norm": 0.27757561206817627,
3249
+ "learning_rate": 2.3034762476873973e-06,
3250
+ "loss": 0.1329723596572876,
3251
+ "step": 926
3252
+ },
3253
+ {
3254
+ "epoch": 3.6972111553784863,
3255
+ "grad_norm": 0.4265131950378418,
3256
+ "learning_rate": 2.2883864271024524e-06,
3257
+ "loss": 0.31522467732429504,
3258
+ "step": 928
3259
+ },
3260
+ {
3261
+ "epoch": 3.705179282868526,
3262
+ "grad_norm": 0.10874529927968979,
3263
+ "learning_rate": 2.273675285293905e-06,
3264
+ "loss": 0.42426741123199463,
3265
+ "step": 930
3266
+ },
3267
+ {
3268
+ "epoch": 3.713147410358566,
3269
+ "grad_norm": 0.35626259446144104,
3270
+ "learning_rate": 2.2593434617296474e-06,
3271
+ "loss": 0.5419244170188904,
3272
+ "step": 932
3273
+ },
3274
+ {
3275
+ "epoch": 3.721115537848606,
3276
+ "grad_norm": 1.1875288486480713,
3277
+ "learning_rate": 2.2453915793892665e-06,
3278
+ "loss": 0.23740825057029724,
3279
+ "step": 934
3280
+ },
3281
+ {
3282
+ "epoch": 3.7290836653386457,
3283
+ "grad_norm": 0.21155528724193573,
3284
+ "learning_rate": 2.231820244736958e-06,
3285
+ "loss": 0.5010062456130981,
3286
+ "step": 936
3287
+ },
3288
+ {
3289
+ "epoch": 3.7370517928286855,
3290
+ "grad_norm": 0.35504090785980225,
3291
+ "learning_rate": 2.2186300476951693e-06,
3292
+ "loss": 0.16797490417957306,
3293
+ "step": 938
3294
+ },
3295
+ {
3296
+ "epoch": 3.7450199203187253,
3297
+ "grad_norm": 0.3238517940044403,
3298
+ "learning_rate": 2.2058215616189578e-06,
3299
+ "loss": 0.5096255540847778,
3300
+ "step": 940
3301
+ },
3302
+ {
3303
+ "epoch": 3.752988047808765,
3304
+ "grad_norm": 0.36483195424079895,
3305
+ "learning_rate": 2.1933953432710588e-06,
3306
+ "loss": 0.2782249450683594,
3307
+ "step": 942
3308
+ },
3309
+ {
3310
+ "epoch": 3.760956175298805,
3311
+ "grad_norm": 0.46273383498191833,
3312
+ "learning_rate": 2.181351932797695e-06,
3313
+ "loss": 0.31418055295944214,
3314
+ "step": 944
3315
+ },
3316
+ {
3317
+ "epoch": 3.768924302788845,
3318
+ "grad_norm": 0.4258814752101898,
3319
+ "learning_rate": 2.169691853705094e-06,
3320
+ "loss": 0.6382843255996704,
3321
+ "step": 946
3322
+ },
3323
+ {
3324
+ "epoch": 3.7768924302788847,
3325
+ "grad_norm": 0.2860477864742279,
3326
+ "learning_rate": 2.1584156128367303e-06,
3327
+ "loss": 0.32270297408103943,
3328
+ "step": 948
3329
+ },
3330
+ {
3331
+ "epoch": 3.7848605577689245,
3332
+ "grad_norm": 0.21522466838359833,
3333
+ "learning_rate": 2.147523700351291e-06,
3334
+ "loss": 0.5712357759475708,
3335
+ "step": 950
3336
+ },
3337
+ {
3338
+ "epoch": 3.7928286852589643,
3339
+ "grad_norm": 0.2516200840473175,
3340
+ "learning_rate": 2.137016589701375e-06,
3341
+ "loss": 0.5555206537246704,
3342
+ "step": 952
3343
+ },
3344
+ {
3345
+ "epoch": 3.800796812749004,
3346
+ "grad_norm": 0.23942607641220093,
3347
+ "learning_rate": 2.126894737612914e-06,
3348
+ "loss": 0.2843998968601227,
3349
+ "step": 954
3350
+ },
3351
+ {
3352
+ "epoch": 3.808764940239044,
3353
+ "grad_norm": 1.4363948106765747,
3354
+ "learning_rate": 2.117158584065313e-06,
3355
+ "loss": 0.4706723392009735,
3356
+ "step": 956
3357
+ },
3358
+ {
3359
+ "epoch": 3.816733067729084,
3360
+ "grad_norm": 0.670280396938324,
3361
+ "learning_rate": 2.107808552272329e-06,
3362
+ "loss": 0.27754148840904236,
3363
+ "step": 958
3364
+ },
3365
+ {
3366
+ "epoch": 3.8247011952191237,
3367
+ "grad_norm": 0.40577781200408936,
3368
+ "learning_rate": 2.0988450486636745e-06,
3369
+ "loss": 0.1861335188150406,
3370
+ "step": 960
3371
+ },
3372
+ {
3373
+ "epoch": 3.8326693227091635,
3374
+ "grad_norm": 0.12758664786815643,
3375
+ "learning_rate": 2.090268462867351e-06,
3376
+ "loss": 0.34570229053497314,
3377
+ "step": 962
3378
+ },
3379
+ {
3380
+ "epoch": 3.8406374501992033,
3381
+ "grad_norm": 0.3902248740196228,
3382
+ "learning_rate": 2.0820791676927093e-06,
3383
+ "loss": 0.6225243210792542,
3384
+ "step": 964
3385
+ },
3386
+ {
3387
+ "epoch": 3.848605577689243,
3388
+ "grad_norm": 0.42479851841926575,
3389
+ "learning_rate": 2.0742775191142496e-06,
3390
+ "loss": 0.1883630007505417,
3391
+ "step": 966
3392
+ },
3393
+ {
3394
+ "epoch": 3.856573705179283,
3395
+ "grad_norm": 0.32185542583465576,
3396
+ "learning_rate": 2.066863856256143e-06,
3397
+ "loss": 0.39622795581817627,
3398
+ "step": 968
3399
+ },
3400
+ {
3401
+ "epoch": 3.864541832669323,
3402
+ "grad_norm": 0.315428227186203,
3403
+ "learning_rate": 2.0598385013774933e-06,
3404
+ "loss": 0.3555518686771393,
3405
+ "step": 970
3406
+ },
3407
+ {
3408
+ "epoch": 3.8725099601593627,
3409
+ "grad_norm": 0.10775071382522583,
3410
+ "learning_rate": 2.053201759858327e-06,
3411
+ "loss": 0.3210831582546234,
3412
+ "step": 972
3413
+ },
3414
+ {
3415
+ "epoch": 3.8804780876494025,
3416
+ "grad_norm": 0.11887846142053604,
3417
+ "learning_rate": 2.0469539201863224e-06,
3418
+ "loss": 0.2502799928188324,
3419
+ "step": 974
3420
+ },
3421
+ {
3422
+ "epoch": 3.8884462151394423,
3423
+ "grad_norm": 0.31070947647094727,
3424
+ "learning_rate": 2.0410952539442624e-06,
3425
+ "loss": 0.5481354594230652,
3426
+ "step": 976
3427
+ },
3428
+ {
3429
+ "epoch": 3.896414342629482,
3430
+ "grad_norm": 0.31816530227661133,
3431
+ "learning_rate": 2.0356260157982393e-06,
3432
+ "loss": 0.2996366322040558,
3433
+ "step": 978
3434
+ },
3435
+ {
3436
+ "epoch": 3.904382470119522,
3437
+ "grad_norm": 0.18345490097999573,
3438
+ "learning_rate": 2.030546443486575e-06,
3439
+ "loss": 0.24936345219612122,
3440
+ "step": 980
3441
+ },
3442
+ {
3443
+ "epoch": 3.912350597609562,
3444
+ "grad_norm": 0.26529887318611145,
3445
+ "learning_rate": 2.0258567578094947e-06,
3446
+ "loss": 0.19975776970386505,
3447
+ "step": 982
3448
+ },
3449
+ {
3450
+ "epoch": 3.9203187250996017,
3451
+ "grad_norm": 0.25069504976272583,
3452
+ "learning_rate": 2.0215571626195242e-06,
3453
+ "loss": 0.5472447872161865,
3454
+ "step": 984
3455
+ },
3456
+ {
3457
+ "epoch": 3.9282868525896415,
3458
+ "grad_norm": 0.33956313133239746,
3459
+ "learning_rate": 2.0176478448126306e-06,
3460
+ "loss": 0.14271996915340424,
3461
+ "step": 986
3462
+ },
3463
+ {
3464
+ "epoch": 3.9362549800796813,
3465
+ "grad_norm": 0.8762012124061584,
3466
+ "learning_rate": 2.014128974320099e-06,
3467
+ "loss": 0.494120717048645,
3468
+ "step": 988
3469
+ },
3470
+ {
3471
+ "epoch": 3.944223107569721,
3472
+ "grad_norm": 0.06045879051089287,
3473
+ "learning_rate": 2.011000704101143e-06,
3474
+ "loss": 0.3118327856063843,
3475
+ "step": 990
3476
+ },
3477
+ {
3478
+ "epoch": 3.952191235059761,
3479
+ "grad_norm": 0.22002360224723816,
3480
+ "learning_rate": 2.00826317013626e-06,
3481
+ "loss": 0.53458571434021,
3482
+ "step": 992
3483
+ },
3484
+ {
3485
+ "epoch": 3.960159362549801,
3486
+ "grad_norm": 0.08198000490665436,
3487
+ "learning_rate": 2.0059164914213175e-06,
3488
+ "loss": 0.1380147933959961,
3489
+ "step": 994
3490
+ },
3491
+ {
3492
+ "epoch": 3.9681274900398407,
3493
+ "grad_norm": 0.6921637058258057,
3494
+ "learning_rate": 2.00396076996238e-06,
3495
+ "loss": 0.5101975798606873,
3496
+ "step": 996
3497
+ },
3498
+ {
3499
+ "epoch": 3.9760956175298805,
3500
+ "grad_norm": 0.09050004929304123,
3501
+ "learning_rate": 2.0023960907712782e-06,
3502
+ "loss": 0.3632965683937073,
3503
+ "step": 998
3504
+ },
3505
+ {
3506
+ "epoch": 3.9840637450199203,
3507
+ "grad_norm": 0.2718322277069092,
3508
+ "learning_rate": 2.0012225218619097e-06,
3509
+ "loss": 0.24679109454154968,
3510
+ "step": 1000
3511
+ },
3512
+ {
3513
+ "epoch": 3.99203187250996,
3514
+ "grad_norm": 0.2601509988307953,
3515
+ "learning_rate": 2.0004401142472857e-06,
3516
+ "loss": 0.5495860576629639,
3517
+ "step": 1002
3518
+ },
3519
+ {
3520
+ "epoch": 4.0,
3521
+ "grad_norm": 0.0840764045715332,
3522
+ "learning_rate": 2.000048901937313e-06,
3523
+ "loss": 0.12128544598817825,
3524
+ "step": 1004
3525
+ },
3526
+ {
3527
+ "epoch": 4.0,
3528
+ "step": 1004,
3529
+ "total_flos": 3.519329211045118e+18,
3530
+ "train_loss": 0.7596988798197047,
3531
+ "train_runtime": 8661.0758,
3532
+ "train_samples_per_second": 6.955,
3533
+ "train_steps_per_second": 0.116
3534
+ }
3535
+ ],
3536
+ "logging_steps": 2,
3537
+ "max_steps": 1004,
3538
+ "num_input_tokens_seen": 0,
3539
+ "num_train_epochs": 4,
3540
+ "save_steps": 99999,
3541
+ "stateful_callbacks": {
3542
+ "TrainerControl": {
3543
+ "args": {
3544
+ "should_epoch_stop": false,
3545
+ "should_evaluate": false,
3546
+ "should_log": false,
3547
+ "should_save": false,
3548
+ "should_training_stop": false
3549
+ },
3550
+ "attributes": {}
3551
+ }
3552
+ },
3553
+ "total_flos": 3.519329211045118e+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:e2dae75b55731660e84e9bdaf07e0f5add551266c5c06e6965e9cc1e4dcced9a
3
+ size 5649
training_loss.png ADDED