moogician commited on
Commit
bcefaa8
·
verified ·
1 Parent(s): 992ba79

Upload kodcode-v1-qwen36

Browse files
.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
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Qwen/Qwen3.6-27B
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: kodcode-v1-qwq
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
+ # kodcode-v1-qwq
18
+
19
+ This model is a fine-tuned version of [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) on the kodcode-v1 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
+ - learning_rate: 1e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 8
44
+ - gradient_accumulation_steps: 6
45
+ - total_train_batch_size: 48
46
+ - total_eval_batch_size: 64
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_steps: 0.1
50
+ - num_epochs: 3
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 5.6.0
59
+ - Pytorch 2.12.0+cu130
60
+ - Datasets 4.0.0
61
+ - Tokenizers 0.22.2
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 305241727172608.0,
4
+ "train_loss": 0.4993832171672866,
5
+ "train_runtime": 16221.4591,
6
+ "train_samples_per_second": 0.245,
7
+ "train_steps_per_second": 0.005
8
+ }
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 (preserve_thinking is defined and preserve_thinking is true) or (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 | string if args_value is string else args_value | tojson | safe %}
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 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 248046,
8
+ "hidden_size": 5120,
9
+ "image_token_id": 248056,
10
+ "language_model_only": false,
11
+ "model_type": "qwen3_5",
12
+ "pad_token_id": 248044,
13
+ "text_config": {
14
+ "attention_bias": false,
15
+ "attention_dropout": 0.0,
16
+ "attn_output_gate": true,
17
+ "bos_token_id": 248044,
18
+ "dtype": "bfloat16",
19
+ "eos_token_id": 248044,
20
+ "full_attention_interval": 4,
21
+ "head_dim": 256,
22
+ "hidden_act": "silu",
23
+ "hidden_size": 5120,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 17408,
26
+ "layer_types": [
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "full_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "full_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "full_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "full_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "full_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "full_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "full_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "full_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "full_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "full_attention",
67
+ "linear_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "full_attention",
71
+ "linear_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "full_attention",
75
+ "linear_attention",
76
+ "linear_attention",
77
+ "linear_attention",
78
+ "full_attention",
79
+ "linear_attention",
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "full_attention",
83
+ "linear_attention",
84
+ "linear_attention",
85
+ "linear_attention",
86
+ "full_attention",
87
+ "linear_attention",
88
+ "linear_attention",
89
+ "linear_attention",
90
+ "full_attention"
91
+ ],
92
+ "linear_conv_kernel_dim": 4,
93
+ "linear_key_head_dim": 128,
94
+ "linear_num_key_heads": 16,
95
+ "linear_num_value_heads": 48,
96
+ "linear_value_head_dim": 128,
97
+ "mamba_ssm_dtype": "float32",
98
+ "max_position_embeddings": 262144,
99
+ "model_type": "qwen3_5_text",
100
+ "mtp_num_hidden_layers": 1,
101
+ "mtp_use_dedicated_embeddings": false,
102
+ "num_attention_heads": 24,
103
+ "num_hidden_layers": 64,
104
+ "num_key_value_heads": 4,
105
+ "output_gate_type": "swish",
106
+ "pad_token_id": null,
107
+ "partial_rotary_factor": 0.25,
108
+ "rms_norm_eps": 1e-06,
109
+ "rope_parameters": {
110
+ "mrope_interleaved": true,
111
+ "mrope_section": [
112
+ 11,
113
+ 11,
114
+ 10
115
+ ],
116
+ "partial_rotary_factor": 0.25,
117
+ "rope_theta": 10000000,
118
+ "rope_type": "default"
119
+ },
120
+ "tie_word_embeddings": false,
121
+ "use_cache": false,
122
+ "vocab_size": 248320
123
+ },
124
+ "tie_word_embeddings": false,
125
+ "transformers_version": "5.6.0",
126
+ "use_cache": false,
127
+ "video_token_id": 248057,
128
+ "vision_config": {
129
+ "deepstack_visual_indexes": [],
130
+ "depth": 27,
131
+ "dtype": "bfloat16",
132
+ "hidden_act": "gelu_pytorch_tanh",
133
+ "hidden_size": 1152,
134
+ "in_channels": 3,
135
+ "initializer_range": 0.02,
136
+ "intermediate_size": 4304,
137
+ "model_type": "qwen3_5_vision",
138
+ "num_heads": 16,
139
+ "num_position_embeddings": 2304,
140
+ "out_hidden_size": 5120,
141
+ "patch_size": 16,
142
+ "spatial_merge_size": 2,
143
+ "temporal_patch_size": 2
144
+ },
145
+ "vision_end_token_id": 248054,
146
+ "vision_start_token_id": 248053
147
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 248046,
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.6.0"
13
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9847d75d7afd657f72dc3d78097001dcdf9c81fba0867da5743d43ca124a0434
3
+ size 49825162976
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6516c2c3addd0b901b108e882df698ad97376f80895ba3433ac229cd60c9922a
3
+ size 4888445168
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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 sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": false,
13
+ "local_files_only": false,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "padding_side": "right",
26
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
27
+ "processor_class": "Qwen3VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>"
34
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 305241727172608.0,
4
+ "train_loss": 0.4993832171672866,
5
+ "train_runtime": 16221.4591,
6
+ "train_samples_per_second": 0.245,
7
+ "train_steps_per_second": 0.005
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 84, "loss": 0.6798985004425049, "lr": 0.0, "epoch": 0.03614457831325301, "percentage": 1.19, "elapsed_time": "0:02:38", "remaining_time": "3:39:37"}
2
+ {"current_steps": 2, "total_steps": 84, "loss": 0.6897931098937988, "lr": 1.111111111111111e-06, "epoch": 0.07228915662650602, "percentage": 2.38, "elapsed_time": "0:06:18", "remaining_time": "4:18:54"}
3
+ {"current_steps": 3, "total_steps": 84, "loss": 0.6687372326850891, "lr": 2.222222222222222e-06, "epoch": 0.10843373493975904, "percentage": 3.57, "elapsed_time": "0:09:14", "remaining_time": "4:09:22"}
4
+ {"current_steps": 4, "total_steps": 84, "loss": 0.6511715054512024, "lr": 3.3333333333333333e-06, "epoch": 0.14457831325301204, "percentage": 4.76, "elapsed_time": "0:12:42", "remaining_time": "4:14:08"}
5
+ {"current_steps": 5, "total_steps": 84, "loss": 0.6404632329940796, "lr": 4.444444444444444e-06, "epoch": 0.18072289156626506, "percentage": 5.95, "elapsed_time": "0:15:47", "remaining_time": "4:09:32"}
6
+ {"current_steps": 6, "total_steps": 84, "loss": 0.6380958557128906, "lr": 5.555555555555557e-06, "epoch": 0.21686746987951808, "percentage": 7.14, "elapsed_time": "0:19:27", "remaining_time": "4:12:53"}
7
+ {"current_steps": 7, "total_steps": 84, "loss": 0.624602735042572, "lr": 6.666666666666667e-06, "epoch": 0.25301204819277107, "percentage": 8.33, "elapsed_time": "0:23:12", "remaining_time": "4:15:18"}
8
+ {"current_steps": 8, "total_steps": 84, "loss": 0.6305320858955383, "lr": 7.77777777777778e-06, "epoch": 0.2891566265060241, "percentage": 9.52, "elapsed_time": "0:25:57", "remaining_time": "4:06:40"}
9
+ {"current_steps": 9, "total_steps": 84, "loss": 0.6563503742218018, "lr": 8.888888888888888e-06, "epoch": 0.3253012048192771, "percentage": 10.71, "elapsed_time": "0:28:30", "remaining_time": "3:57:33"}
10
+ {"current_steps": 10, "total_steps": 84, "loss": 0.6455645561218262, "lr": 1e-05, "epoch": 0.3614457831325301, "percentage": 11.9, "elapsed_time": "0:30:58", "remaining_time": "3:49:11"}
11
+ {"current_steps": 11, "total_steps": 84, "loss": 0.628766655921936, "lr": 9.995614150494293e-06, "epoch": 0.39759036144578314, "percentage": 13.1, "elapsed_time": "0:33:35", "remaining_time": "3:42:57"}
12
+ {"current_steps": 12, "total_steps": 84, "loss": 0.6071541905403137, "lr": 9.982464296247523e-06, "epoch": 0.43373493975903615, "percentage": 14.29, "elapsed_time": "0:36:45", "remaining_time": "3:40:33"}
13
+ {"current_steps": 13, "total_steps": 84, "loss": 0.6209861636161804, "lr": 9.960573506572391e-06, "epoch": 0.46987951807228917, "percentage": 15.48, "elapsed_time": "0:40:41", "remaining_time": "3:42:14"}
14
+ {"current_steps": 14, "total_steps": 84, "loss": 0.6150267124176025, "lr": 9.929980185352525e-06, "epoch": 0.5060240963855421, "percentage": 16.67, "elapsed_time": "0:43:55", "remaining_time": "3:39:36"}
15
+ {"current_steps": 15, "total_steps": 84, "loss": 0.6164926290512085, "lr": 9.890738003669029e-06, "epoch": 0.5421686746987951, "percentage": 17.86, "elapsed_time": "0:46:35", "remaining_time": "3:34:20"}
16
+ {"current_steps": 16, "total_steps": 84, "loss": 0.6059902906417847, "lr": 9.842915805643156e-06, "epoch": 0.5783132530120482, "percentage": 19.05, "elapsed_time": "0:50:32", "remaining_time": "3:34:47"}
17
+ {"current_steps": 17, "total_steps": 84, "loss": 0.6016689538955688, "lr": 9.786597487660336e-06, "epoch": 0.6144578313253012, "percentage": 20.24, "elapsed_time": "0:54:03", "remaining_time": "3:33:01"}
18
+ {"current_steps": 18, "total_steps": 84, "loss": 0.5898147821426392, "lr": 9.721881851187406e-06, "epoch": 0.6506024096385542, "percentage": 21.43, "elapsed_time": "0:57:45", "remaining_time": "3:31:46"}
19
+ {"current_steps": 19, "total_steps": 84, "loss": 0.5911672115325928, "lr": 9.648882429441258e-06, "epoch": 0.6867469879518072, "percentage": 22.62, "elapsed_time": "1:01:03", "remaining_time": "3:28:52"}
20
+ {"current_steps": 20, "total_steps": 84, "loss": 0.5862749814987183, "lr": 9.567727288213005e-06, "epoch": 0.7228915662650602, "percentage": 23.81, "elapsed_time": "1:04:25", "remaining_time": "3:26:08"}
21
+ {"current_steps": 21, "total_steps": 84, "loss": 0.5881009101867676, "lr": 9.478558801197065e-06, "epoch": 0.7590361445783133, "percentage": 25.0, "elapsed_time": "1:07:13", "remaining_time": "3:21:39"}
22
+ {"current_steps": 22, "total_steps": 84, "loss": 0.5938855409622192, "lr": 9.381533400219319e-06, "epoch": 0.7951807228915663, "percentage": 26.19, "elapsed_time": "1:09:34", "remaining_time": "3:16:05"}
23
+ {"current_steps": 23, "total_steps": 84, "loss": 0.580564558506012, "lr": 9.276821300802535e-06, "epoch": 0.8313253012048193, "percentage": 27.38, "elapsed_time": "1:12:19", "remaining_time": "3:11:49"}
24
+ {"current_steps": 24, "total_steps": 84, "loss": 0.6000862121582031, "lr": 9.164606203550498e-06, "epoch": 0.8674698795180723, "percentage": 28.57, "elapsed_time": "1:15:40", "remaining_time": "3:09:11"}
25
+ {"current_steps": 25, "total_steps": 84, "loss": 0.5746794939041138, "lr": 9.045084971874738e-06, "epoch": 0.9036144578313253, "percentage": 29.76, "elapsed_time": "1:18:25", "remaining_time": "3:05:04"}
26
+ {"current_steps": 26, "total_steps": 84, "loss": 0.577430784702301, "lr": 8.9184672866292e-06, "epoch": 0.9397590361445783, "percentage": 30.95, "elapsed_time": "1:22:30", "remaining_time": "3:04:02"}
27
+ {"current_steps": 27, "total_steps": 84, "loss": 0.5721206068992615, "lr": 8.784975278258783e-06, "epoch": 0.9759036144578314, "percentage": 32.14, "elapsed_time": "1:25:41", "remaining_time": "3:00:53"}
28
+ {"current_steps": 28, "total_steps": 84, "loss": 0.5727310180664062, "lr": 8.644843137107058e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:28:56", "remaining_time": "2:57:52"}
29
+ {"current_steps": 29, "total_steps": 84, "loss": 0.5036242008209229, "lr": 8.498316702566828e-06, "epoch": 1.036144578313253, "percentage": 34.52, "elapsed_time": "1:32:29", "remaining_time": "2:55:25"}
30
+ {"current_steps": 30, "total_steps": 84, "loss": 0.5078785419464111, "lr": 8.345653031794292e-06, "epoch": 1.072289156626506, "percentage": 35.71, "elapsed_time": "1:35:32", "remaining_time": "2:51:59"}
31
+ {"current_steps": 31, "total_steps": 84, "loss": 0.4693022668361664, "lr": 8.18711994874345e-06, "epoch": 1.108433734939759, "percentage": 36.9, "elapsed_time": "1:37:54", "remaining_time": "2:47:23"}
32
+ {"current_steps": 32, "total_steps": 84, "loss": 0.4865715503692627, "lr": 8.022995574311876e-06, "epoch": 1.144578313253012, "percentage": 38.1, "elapsed_time": "1:41:02", "remaining_time": "2:44:11"}
33
+ {"current_steps": 33, "total_steps": 84, "loss": 0.49929895997047424, "lr": 7.85356783842216e-06, "epoch": 1.180722891566265, "percentage": 39.29, "elapsed_time": "1:43:41", "remaining_time": "2:40:14"}
34
+ {"current_steps": 34, "total_steps": 84, "loss": 0.49614834785461426, "lr": 7.679133974894984e-06, "epoch": 1.216867469879518, "percentage": 40.48, "elapsed_time": "1:47:07", "remaining_time": "2:37:32"}
35
+ {"current_steps": 35, "total_steps": 84, "loss": 0.49161770939826965, "lr": 7.500000000000001e-06, "epoch": 1.2530120481927711, "percentage": 41.67, "elapsed_time": "1:50:15", "remaining_time": "2:34:21"}
36
+ {"current_steps": 36, "total_steps": 84, "loss": 0.48665398359298706, "lr": 7.31648017559931e-06, "epoch": 1.2891566265060241, "percentage": 42.86, "elapsed_time": "1:53:49", "remaining_time": "2:31:46"}
37
+ {"current_steps": 37, "total_steps": 84, "loss": 0.4777125120162964, "lr": 7.128896457825364e-06, "epoch": 1.3253012048192772, "percentage": 44.05, "elapsed_time": "1:56:41", "remaining_time": "2:28:14"}
38
+ {"current_steps": 38, "total_steps": 84, "loss": 0.4852375388145447, "lr": 6.9375779322605154e-06, "epoch": 1.3614457831325302, "percentage": 45.24, "elapsed_time": "1:59:37", "remaining_time": "2:24:48"}
39
+ {"current_steps": 39, "total_steps": 84, "loss": 0.46885544061660767, "lr": 6.7428602366090764e-06, "epoch": 1.3975903614457832, "percentage": 46.43, "elapsed_time": "2:03:31", "remaining_time": "2:22:31"}
40
+ {"current_steps": 40, "total_steps": 84, "loss": 0.4777418375015259, "lr": 6.545084971874738e-06, "epoch": 1.4337349397590362, "percentage": 47.62, "elapsed_time": "2:06:31", "remaining_time": "2:19:10"}
41
+ {"current_steps": 41, "total_steps": 84, "loss": 0.4813598096370697, "lr": 6.344599103076329e-06, "epoch": 1.4698795180722892, "percentage": 48.81, "elapsed_time": "2:10:06", "remaining_time": "2:16:27"}
42
+ {"current_steps": 42, "total_steps": 84, "loss": 0.4753226637840271, "lr": 6.141754350553279e-06, "epoch": 1.5060240963855422, "percentage": 50.0, "elapsed_time": "2:14:25", "remaining_time": "2:14:25"}
43
+ {"current_steps": 43, "total_steps": 84, "loss": 0.497364342212677, "lr": 5.936906572928625e-06, "epoch": 1.5421686746987953, "percentage": 51.19, "elapsed_time": "2:17:16", "remaining_time": "2:10:53"}
44
+ {"current_steps": 44, "total_steps": 84, "loss": 0.4533390402793884, "lr": 5.730415142812059e-06, "epoch": 1.5783132530120483, "percentage": 52.38, "elapsed_time": "2:20:01", "remaining_time": "2:07:17"}
45
+ {"current_steps": 45, "total_steps": 84, "loss": 0.47720852494239807, "lr": 5.522642316338268e-06, "epoch": 1.6144578313253013, "percentage": 53.57, "elapsed_time": "2:22:25", "remaining_time": "2:03:26"}
46
+ {"current_steps": 46, "total_steps": 84, "loss": 0.4630257785320282, "lr": 5.3139525976465675e-06, "epoch": 1.6506024096385543, "percentage": 54.76, "elapsed_time": "2:25:39", "remaining_time": "2:00:19"}
47
+ {"current_steps": 47, "total_steps": 84, "loss": 0.4707484245300293, "lr": 5.1047120994167855e-06, "epoch": 1.6867469879518073, "percentage": 55.95, "elapsed_time": "2:29:28", "remaining_time": "1:57:40"}
48
+ {"current_steps": 48, "total_steps": 84, "loss": 0.5026432871818542, "lr": 4.895287900583216e-06, "epoch": 1.7228915662650603, "percentage": 57.14, "elapsed_time": "2:33:14", "remaining_time": "1:54:55"}
49
+ {"current_steps": 49, "total_steps": 84, "loss": 0.4894215762615204, "lr": 4.686047402353433e-06, "epoch": 1.7590361445783134, "percentage": 58.33, "elapsed_time": "2:35:48", "remaining_time": "1:51:17"}
50
+ {"current_steps": 50, "total_steps": 84, "loss": 0.48538342118263245, "lr": 4.477357683661734e-06, "epoch": 1.7951807228915664, "percentage": 59.52, "elapsed_time": "2:39:37", "remaining_time": "1:48:32"}
51
+ {"current_steps": 51, "total_steps": 84, "loss": 0.45954716205596924, "lr": 4.269584857187942e-06, "epoch": 1.8313253012048194, "percentage": 60.71, "elapsed_time": "2:42:09", "remaining_time": "1:44:55"}
52
+ {"current_steps": 52, "total_steps": 84, "loss": 0.4566912055015564, "lr": 4.063093427071376e-06, "epoch": 1.8674698795180724, "percentage": 61.9, "elapsed_time": "2:45:29", "remaining_time": "1:41:50"}
53
+ {"current_steps": 53, "total_steps": 84, "loss": 0.48027291893959045, "lr": 3.8582456494467214e-06, "epoch": 1.9036144578313254, "percentage": 63.1, "elapsed_time": "2:49:23", "remaining_time": "1:39:04"}
54
+ {"current_steps": 54, "total_steps": 84, "loss": 0.49082323908805847, "lr": 3.655400896923672e-06, "epoch": 1.9397590361445785, "percentage": 64.29, "elapsed_time": "2:53:00", "remaining_time": "1:36:06"}
55
+ {"current_steps": 55, "total_steps": 84, "loss": 0.47446680068969727, "lr": 3.4549150281252635e-06, "epoch": 1.9759036144578315, "percentage": 65.48, "elapsed_time": "2:56:00", "remaining_time": "1:32:48"}
56
+ {"current_steps": 56, "total_steps": 84, "loss": 0.47039300203323364, "lr": 3.2571397633909252e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:57:50", "remaining_time": "1:28:55"}
57
+ {"current_steps": 57, "total_steps": 84, "loss": 0.3891071379184723, "lr": 3.0624220677394854e-06, "epoch": 2.036144578313253, "percentage": 67.86, "elapsed_time": "3:01:23", "remaining_time": "1:25:55"}
58
+ {"current_steps": 58, "total_steps": 84, "loss": 0.43356871604919434, "lr": 2.871103542174637e-06, "epoch": 2.072289156626506, "percentage": 69.05, "elapsed_time": "3:05:00", "remaining_time": "1:22:55"}
59
+ {"current_steps": 59, "total_steps": 84, "loss": 0.40094226598739624, "lr": 2.683519824400693e-06, "epoch": 2.108433734939759, "percentage": 70.24, "elapsed_time": "3:08:29", "remaining_time": "1:19:51"}
60
+ {"current_steps": 60, "total_steps": 84, "loss": 0.4142378270626068, "lr": 2.5000000000000015e-06, "epoch": 2.144578313253012, "percentage": 71.43, "elapsed_time": "3:10:55", "remaining_time": "1:16:22"}
61
+ {"current_steps": 61, "total_steps": 84, "loss": 0.3956088721752167, "lr": 2.320866025105016e-06, "epoch": 2.180722891566265, "percentage": 72.62, "elapsed_time": "3:13:33", "remaining_time": "1:12:58"}
62
+ {"current_steps": 62, "total_steps": 84, "loss": 0.38991785049438477, "lr": 2.146432161577842e-06, "epoch": 2.216867469879518, "percentage": 73.81, "elapsed_time": "3:17:05", "remaining_time": "1:09:55"}
63
+ {"current_steps": 63, "total_steps": 84, "loss": 0.3925628364086151, "lr": 1.977004425688126e-06, "epoch": 2.253012048192771, "percentage": 75.0, "elapsed_time": "3:20:22", "remaining_time": "1:06:47"}
64
+ {"current_steps": 64, "total_steps": 84, "loss": 0.39590010046958923, "lr": 1.8128800512565514e-06, "epoch": 2.289156626506024, "percentage": 76.19, "elapsed_time": "3:23:49", "remaining_time": "1:03:41"}
65
+ {"current_steps": 65, "total_steps": 84, "loss": 0.4138052761554718, "lr": 1.6543469682057105e-06, "epoch": 2.325301204819277, "percentage": 77.38, "elapsed_time": "3:27:24", "remaining_time": "1:00:37"}
66
+ {"current_steps": 66, "total_steps": 84, "loss": 0.40755337476730347, "lr": 1.5016832974331725e-06, "epoch": 2.36144578313253, "percentage": 78.57, "elapsed_time": "3:31:12", "remaining_time": "0:57:36"}
67
+ {"current_steps": 67, "total_steps": 84, "loss": 0.4035053253173828, "lr": 1.3551568628929434e-06, "epoch": 2.397590361445783, "percentage": 79.76, "elapsed_time": "3:35:02", "remaining_time": "0:54:33"}
68
+ {"current_steps": 68, "total_steps": 84, "loss": 0.41533365845680237, "lr": 1.2150247217412186e-06, "epoch": 2.433734939759036, "percentage": 80.95, "elapsed_time": "3:39:34", "remaining_time": "0:51:39"}
69
+ {"current_steps": 69, "total_steps": 84, "loss": 0.36712491512298584, "lr": 1.0815327133708015e-06, "epoch": 2.4698795180722892, "percentage": 82.14, "elapsed_time": "3:42:35", "remaining_time": "0:48:23"}
70
+ {"current_steps": 70, "total_steps": 84, "loss": 0.3851737380027771, "lr": 9.549150281252633e-07, "epoch": 2.5060240963855422, "percentage": 83.33, "elapsed_time": "3:44:59", "remaining_time": "0:44:59"}
71
+ {"current_steps": 71, "total_steps": 84, "loss": 0.4188123345375061, "lr": 8.353937964495029e-07, "epoch": 2.5421686746987953, "percentage": 84.52, "elapsed_time": "3:48:37", "remaining_time": "0:41:51"}
72
+ {"current_steps": 72, "total_steps": 84, "loss": 0.40590065717697144, "lr": 7.23178699197467e-07, "epoch": 2.5783132530120483, "percentage": 85.71, "elapsed_time": "3:51:20", "remaining_time": "0:38:33"}
73
+ {"current_steps": 73, "total_steps": 84, "loss": 0.38054245710372925, "lr": 6.184665997806832e-07, "epoch": 2.6144578313253013, "percentage": 86.9, "elapsed_time": "3:55:18", "remaining_time": "0:35:27"}
74
+ {"current_steps": 74, "total_steps": 84, "loss": 0.4026598334312439, "lr": 5.214411988029355e-07, "epoch": 2.6506024096385543, "percentage": 88.1, "elapsed_time": "3:57:59", "remaining_time": "0:32:09"}
75
+ {"current_steps": 75, "total_steps": 84, "loss": 0.4054795503616333, "lr": 4.322727117869951e-07, "epoch": 2.6867469879518073, "percentage": 89.29, "elapsed_time": "4:01:41", "remaining_time": "0:29:00"}
76
+ {"current_steps": 76, "total_steps": 84, "loss": 0.37800586223602295, "lr": 3.511175705587433e-07, "epoch": 2.7228915662650603, "percentage": 90.48, "elapsed_time": "4:04:42", "remaining_time": "0:25:45"}
77
+ {"current_steps": 77, "total_steps": 84, "loss": 0.3979753255844116, "lr": 2.7811814881259503e-07, "epoch": 2.7590361445783134, "percentage": 91.67, "elapsed_time": "4:07:47", "remaining_time": "0:22:31"}
78
+ {"current_steps": 78, "total_steps": 84, "loss": 0.3682253956794739, "lr": 2.134025123396638e-07, "epoch": 2.7951807228915664, "percentage": 92.86, "elapsed_time": "4:10:22", "remaining_time": "0:19:15"}
79
+ {"current_steps": 79, "total_steps": 84, "loss": 0.4290738105773926, "lr": 1.5708419435684463e-07, "epoch": 2.8313253012048194, "percentage": 94.05, "elapsed_time": "4:13:23", "remaining_time": "0:16:02"}
80
+ {"current_steps": 80, "total_steps": 84, "loss": 0.3954327702522278, "lr": 1.0926199633097156e-07, "epoch": 2.8674698795180724, "percentage": 95.24, "elapsed_time": "4:16:33", "remaining_time": "0:12:49"}
81
+ {"current_steps": 81, "total_steps": 84, "loss": 0.4111490845680237, "lr": 7.001981464747565e-08, "epoch": 2.9036144578313254, "percentage": 96.43, "elapsed_time": "4:19:32", "remaining_time": "0:09:36"}
82
+ {"current_steps": 82, "total_steps": 84, "loss": 0.38509202003479004, "lr": 3.9426493427611177e-08, "epoch": 2.9397590361445785, "percentage": 97.62, "elapsed_time": "4:21:54", "remaining_time": "0:06:23"}
83
+ {"current_steps": 83, "total_steps": 84, "loss": 0.4102988541126251, "lr": 1.753570375247815e-08, "epoch": 2.9759036144578315, "percentage": 98.81, "elapsed_time": "4:25:21", "remaining_time": "0:03:11"}
84
+ {"current_steps": 84, "total_steps": 84, "loss": 0.42839542031288147, "lr": 4.385849505708084e-09, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:28:01", "remaining_time": "0:00:00"}
85
+ {"current_steps": 84, "total_steps": 84, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:30:20", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,631 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 84,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.03614457831325301,
14
+ "grad_norm": 2.243542194366455,
15
+ "learning_rate": 0.0,
16
+ "loss": 0.6798985004425049,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.07228915662650602,
21
+ "grad_norm": 2.272136926651001,
22
+ "learning_rate": 1.111111111111111e-06,
23
+ "loss": 0.6897931098937988,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.10843373493975904,
28
+ "grad_norm": 2.009799003601074,
29
+ "learning_rate": 2.222222222222222e-06,
30
+ "loss": 0.6687372326850891,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.14457831325301204,
35
+ "grad_norm": 1.5434411764144897,
36
+ "learning_rate": 3.3333333333333333e-06,
37
+ "loss": 0.6511715054512024,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.18072289156626506,
42
+ "grad_norm": 1.2117929458618164,
43
+ "learning_rate": 4.444444444444444e-06,
44
+ "loss": 0.6404632329940796,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.21686746987951808,
49
+ "grad_norm": 1.288975477218628,
50
+ "learning_rate": 5.555555555555557e-06,
51
+ "loss": 0.6380958557128906,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.25301204819277107,
56
+ "grad_norm": 1.1806610822677612,
57
+ "learning_rate": 6.666666666666667e-06,
58
+ "loss": 0.624602735042572,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.2891566265060241,
63
+ "grad_norm": 1.2804715633392334,
64
+ "learning_rate": 7.77777777777778e-06,
65
+ "loss": 0.6305320858955383,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.3253012048192771,
70
+ "grad_norm": 1.0711824893951416,
71
+ "learning_rate": 8.888888888888888e-06,
72
+ "loss": 0.6563503742218018,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.3614457831325301,
77
+ "grad_norm": 1.0959501266479492,
78
+ "learning_rate": 1e-05,
79
+ "loss": 0.6455645561218262,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.39759036144578314,
84
+ "grad_norm": 1.0095149278640747,
85
+ "learning_rate": 9.995614150494293e-06,
86
+ "loss": 0.628766655921936,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.43373493975903615,
91
+ "grad_norm": 1.5699474811553955,
92
+ "learning_rate": 9.982464296247523e-06,
93
+ "loss": 0.6071541905403137,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.46987951807228917,
98
+ "grad_norm": 0.7985743284225464,
99
+ "learning_rate": 9.960573506572391e-06,
100
+ "loss": 0.6209861636161804,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.5060240963855421,
105
+ "grad_norm": 0.714244544506073,
106
+ "learning_rate": 9.929980185352525e-06,
107
+ "loss": 0.6150267124176025,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.5421686746987951,
112
+ "grad_norm": 0.6876276135444641,
113
+ "learning_rate": 9.890738003669029e-06,
114
+ "loss": 0.6164926290512085,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.5783132530120482,
119
+ "grad_norm": 0.6876976490020752,
120
+ "learning_rate": 9.842915805643156e-06,
121
+ "loss": 0.6059902906417847,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.6144578313253012,
126
+ "grad_norm": 0.6507225036621094,
127
+ "learning_rate": 9.786597487660336e-06,
128
+ "loss": 0.6016689538955688,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.6506024096385542,
133
+ "grad_norm": 0.5742944478988647,
134
+ "learning_rate": 9.721881851187406e-06,
135
+ "loss": 0.5898147821426392,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.6867469879518072,
140
+ "grad_norm": 0.5965182185173035,
141
+ "learning_rate": 9.648882429441258e-06,
142
+ "loss": 0.5911672115325928,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.7228915662650602,
147
+ "grad_norm": 0.6031558513641357,
148
+ "learning_rate": 9.567727288213005e-06,
149
+ "loss": 0.5862749814987183,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.7590361445783133,
154
+ "grad_norm": 0.5991913080215454,
155
+ "learning_rate": 9.478558801197065e-06,
156
+ "loss": 0.5881009101867676,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.7951807228915663,
161
+ "grad_norm": 0.5532190203666687,
162
+ "learning_rate": 9.381533400219319e-06,
163
+ "loss": 0.5938855409622192,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.8313253012048193,
168
+ "grad_norm": 0.5534331202507019,
169
+ "learning_rate": 9.276821300802535e-06,
170
+ "loss": 0.580564558506012,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.8674698795180723,
175
+ "grad_norm": 0.635610044002533,
176
+ "learning_rate": 9.164606203550498e-06,
177
+ "loss": 0.6000862121582031,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.9036144578313253,
182
+ "grad_norm": 0.5146282315254211,
183
+ "learning_rate": 9.045084971874738e-06,
184
+ "loss": 0.5746794939041138,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.9397590361445783,
189
+ "grad_norm": 0.543429970741272,
190
+ "learning_rate": 8.9184672866292e-06,
191
+ "loss": 0.577430784702301,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.9759036144578314,
196
+ "grad_norm": 0.4730767011642456,
197
+ "learning_rate": 8.784975278258783e-06,
198
+ "loss": 0.5721206068992615,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 1.0,
203
+ "grad_norm": 0.578737735748291,
204
+ "learning_rate": 8.644843137107058e-06,
205
+ "loss": 0.5727310180664062,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 1.036144578313253,
210
+ "grad_norm": 0.5965927243232727,
211
+ "learning_rate": 8.498316702566828e-06,
212
+ "loss": 0.5036242008209229,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 1.072289156626506,
217
+ "grad_norm": 0.533427894115448,
218
+ "learning_rate": 8.345653031794292e-06,
219
+ "loss": 0.5078785419464111,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 1.108433734939759,
224
+ "grad_norm": 0.51552814245224,
225
+ "learning_rate": 8.18711994874345e-06,
226
+ "loss": 0.4693022668361664,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 1.144578313253012,
231
+ "grad_norm": 0.5974420309066772,
232
+ "learning_rate": 8.022995574311876e-06,
233
+ "loss": 0.4865715503692627,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 1.180722891566265,
238
+ "grad_norm": 0.5751659274101257,
239
+ "learning_rate": 7.85356783842216e-06,
240
+ "loss": 0.49929895997047424,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 1.216867469879518,
245
+ "grad_norm": 0.5281147956848145,
246
+ "learning_rate": 7.679133974894984e-06,
247
+ "loss": 0.49614834785461426,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 1.2530120481927711,
252
+ "grad_norm": 0.5489075183868408,
253
+ "learning_rate": 7.500000000000001e-06,
254
+ "loss": 0.49161770939826965,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 1.2891566265060241,
259
+ "grad_norm": 0.6569790244102478,
260
+ "learning_rate": 7.31648017559931e-06,
261
+ "loss": 0.48665398359298706,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 1.3253012048192772,
266
+ "grad_norm": 0.5829439163208008,
267
+ "learning_rate": 7.128896457825364e-06,
268
+ "loss": 0.4777125120162964,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 1.3614457831325302,
273
+ "grad_norm": 0.49731743335723877,
274
+ "learning_rate": 6.9375779322605154e-06,
275
+ "loss": 0.4852375388145447,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 1.3975903614457832,
280
+ "grad_norm": 0.5951570868492126,
281
+ "learning_rate": 6.7428602366090764e-06,
282
+ "loss": 0.46885544061660767,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 1.4337349397590362,
287
+ "grad_norm": 0.5189629793167114,
288
+ "learning_rate": 6.545084971874738e-06,
289
+ "loss": 0.4777418375015259,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 1.4698795180722892,
294
+ "grad_norm": 0.5602889060974121,
295
+ "learning_rate": 6.344599103076329e-06,
296
+ "loss": 0.4813598096370697,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 1.5060240963855422,
301
+ "grad_norm": 0.5076647996902466,
302
+ "learning_rate": 6.141754350553279e-06,
303
+ "loss": 0.4753226637840271,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 1.5421686746987953,
308
+ "grad_norm": 0.4632566571235657,
309
+ "learning_rate": 5.936906572928625e-06,
310
+ "loss": 0.497364342212677,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 1.5783132530120483,
315
+ "grad_norm": 0.489469438791275,
316
+ "learning_rate": 5.730415142812059e-06,
317
+ "loss": 0.4533390402793884,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 1.6144578313253013,
322
+ "grad_norm": 0.5627046227455139,
323
+ "learning_rate": 5.522642316338268e-06,
324
+ "loss": 0.47720852494239807,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 1.6506024096385543,
329
+ "grad_norm": 0.615321934223175,
330
+ "learning_rate": 5.3139525976465675e-06,
331
+ "loss": 0.4630257785320282,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 1.6867469879518073,
336
+ "grad_norm": 0.7377497553825378,
337
+ "learning_rate": 5.1047120994167855e-06,
338
+ "loss": 0.4707484245300293,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 1.7228915662650603,
343
+ "grad_norm": 0.44864723086357117,
344
+ "learning_rate": 4.895287900583216e-06,
345
+ "loss": 0.5026432871818542,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 1.7590361445783134,
350
+ "grad_norm": 0.48998555541038513,
351
+ "learning_rate": 4.686047402353433e-06,
352
+ "loss": 0.4894215762615204,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 1.7951807228915664,
357
+ "grad_norm": 0.4500783383846283,
358
+ "learning_rate": 4.477357683661734e-06,
359
+ "loss": 0.48538342118263245,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 1.8313253012048194,
364
+ "grad_norm": 0.4918319880962372,
365
+ "learning_rate": 4.269584857187942e-06,
366
+ "loss": 0.45954716205596924,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 1.8674698795180724,
371
+ "grad_norm": 0.5150398015975952,
372
+ "learning_rate": 4.063093427071376e-06,
373
+ "loss": 0.4566912055015564,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 1.9036144578313254,
378
+ "grad_norm": 0.44811761379241943,
379
+ "learning_rate": 3.8582456494467214e-06,
380
+ "loss": 0.48027291893959045,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 1.9397590361445785,
385
+ "grad_norm": 0.609320342540741,
386
+ "learning_rate": 3.655400896923672e-06,
387
+ "loss": 0.49082323908805847,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 1.9759036144578315,
392
+ "grad_norm": 0.46881070733070374,
393
+ "learning_rate": 3.4549150281252635e-06,
394
+ "loss": 0.47446680068969727,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 2.0,
399
+ "grad_norm": 0.5909848213195801,
400
+ "learning_rate": 3.2571397633909252e-06,
401
+ "loss": 0.47039300203323364,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 2.036144578313253,
406
+ "grad_norm": 0.709743857383728,
407
+ "learning_rate": 3.0624220677394854e-06,
408
+ "loss": 0.3891071379184723,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 2.072289156626506,
413
+ "grad_norm": 0.5000724792480469,
414
+ "learning_rate": 2.871103542174637e-06,
415
+ "loss": 0.43356871604919434,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 2.108433734939759,
420
+ "grad_norm": 0.5290446877479553,
421
+ "learning_rate": 2.683519824400693e-06,
422
+ "loss": 0.40094226598739624,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 2.144578313253012,
427
+ "grad_norm": 0.5125427842140198,
428
+ "learning_rate": 2.5000000000000015e-06,
429
+ "loss": 0.4142378270626068,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 2.180722891566265,
434
+ "grad_norm": 0.6648615002632141,
435
+ "learning_rate": 2.320866025105016e-06,
436
+ "loss": 0.3956088721752167,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 2.216867469879518,
441
+ "grad_norm": 0.8099228739738464,
442
+ "learning_rate": 2.146432161577842e-06,
443
+ "loss": 0.38991785049438477,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 2.253012048192771,
448
+ "grad_norm": 0.53780198097229,
449
+ "learning_rate": 1.977004425688126e-06,
450
+ "loss": 0.3925628364086151,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 2.289156626506024,
455
+ "grad_norm": 0.6565864086151123,
456
+ "learning_rate": 1.8128800512565514e-06,
457
+ "loss": 0.39590010046958923,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 2.325301204819277,
462
+ "grad_norm": 0.48299795389175415,
463
+ "learning_rate": 1.6543469682057105e-06,
464
+ "loss": 0.4138052761554718,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 2.36144578313253,
469
+ "grad_norm": 0.5652570128440857,
470
+ "learning_rate": 1.5016832974331725e-06,
471
+ "loss": 0.40755337476730347,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 2.397590361445783,
476
+ "grad_norm": 1.1212197542190552,
477
+ "learning_rate": 1.3551568628929434e-06,
478
+ "loss": 0.4035053253173828,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 2.433734939759036,
483
+ "grad_norm": 0.5047882795333862,
484
+ "learning_rate": 1.2150247217412186e-06,
485
+ "loss": 0.41533365845680237,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 2.4698795180722892,
490
+ "grad_norm": 0.5447006821632385,
491
+ "learning_rate": 1.0815327133708015e-06,
492
+ "loss": 0.36712491512298584,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 2.5060240963855422,
497
+ "grad_norm": 0.5147467851638794,
498
+ "learning_rate": 9.549150281252633e-07,
499
+ "loss": 0.3851737380027771,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 2.5421686746987953,
504
+ "grad_norm": 0.47967737913131714,
505
+ "learning_rate": 8.353937964495029e-07,
506
+ "loss": 0.4188123345375061,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 2.5783132530120483,
511
+ "grad_norm": 0.5074743628501892,
512
+ "learning_rate": 7.23178699197467e-07,
513
+ "loss": 0.40590065717697144,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 2.6144578313253013,
518
+ "grad_norm": 0.46036818623542786,
519
+ "learning_rate": 6.184665997806832e-07,
520
+ "loss": 0.38054245710372925,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 2.6506024096385543,
525
+ "grad_norm": 1.1342926025390625,
526
+ "learning_rate": 5.214411988029355e-07,
527
+ "loss": 0.4026598334312439,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 2.6867469879518073,
532
+ "grad_norm": 0.46817532181739807,
533
+ "learning_rate": 4.322727117869951e-07,
534
+ "loss": 0.4054795503616333,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 2.7228915662650603,
539
+ "grad_norm": 0.7104460597038269,
540
+ "learning_rate": 3.511175705587433e-07,
541
+ "loss": 0.37800586223602295,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 2.7590361445783134,
546
+ "grad_norm": 0.5266546010971069,
547
+ "learning_rate": 2.7811814881259503e-07,
548
+ "loss": 0.3979753255844116,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 2.7951807228915664,
553
+ "grad_norm": 0.4721384644508362,
554
+ "learning_rate": 2.134025123396638e-07,
555
+ "loss": 0.3682253956794739,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 2.8313253012048194,
560
+ "grad_norm": 0.426792174577713,
561
+ "learning_rate": 1.5708419435684463e-07,
562
+ "loss": 0.4290738105773926,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 2.8674698795180724,
567
+ "grad_norm": 0.4718446433544159,
568
+ "learning_rate": 1.0926199633097156e-07,
569
+ "loss": 0.3954327702522278,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 2.9036144578313254,
574
+ "grad_norm": 0.4800931215286255,
575
+ "learning_rate": 7.001981464747565e-08,
576
+ "loss": 0.4111490845680237,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 2.9397590361445785,
581
+ "grad_norm": 0.5462878346443176,
582
+ "learning_rate": 3.9426493427611177e-08,
583
+ "loss": 0.38509202003479004,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 2.9759036144578315,
588
+ "grad_norm": 0.44628024101257324,
589
+ "learning_rate": 1.753570375247815e-08,
590
+ "loss": 0.4102988541126251,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 3.0,
595
+ "grad_norm": 0.5103145837783813,
596
+ "learning_rate": 4.385849505708084e-09,
597
+ "loss": 0.42839542031288147,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 3.0,
602
+ "step": 84,
603
+ "total_flos": 305241727172608.0,
604
+ "train_loss": 0.4993832171672866,
605
+ "train_runtime": 16221.4591,
606
+ "train_samples_per_second": 0.245,
607
+ "train_steps_per_second": 0.005
608
+ }
609
+ ],
610
+ "logging_steps": 1,
611
+ "max_steps": 84,
612
+ "num_input_tokens_seen": 0,
613
+ "num_train_epochs": 3,
614
+ "save_steps": 100000,
615
+ "stateful_callbacks": {
616
+ "TrainerControl": {
617
+ "args": {
618
+ "should_epoch_stop": false,
619
+ "should_evaluate": false,
620
+ "should_log": false,
621
+ "should_save": true,
622
+ "should_training_stop": true
623
+ },
624
+ "attributes": {}
625
+ }
626
+ },
627
+ "total_flos": 305241727172608.0,
628
+ "train_batch_size": 1,
629
+ "trial_name": null,
630
+ "trial_params": null
631
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff9e20c50bdf5d1dfc7be963ba586a1db3663f5a46fc4f7da01cde27668eda42
3
+ size 7953
training_loss.png ADDED