Sarim-Hash commited on
Commit
4d2fe7e
·
verified ·
1 Parent(s): 2923dee

Model save

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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - llama-factory
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: infra_exp_shrad_0
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # infra_exp_shrad_0
15
+
16
+ This model was trained from scratch on the None dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 2e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - distributed_type: multi-GPU
40
+ - num_devices: 2
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 128
43
+ - total_eval_batch_size: 16
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 1.0
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.52.4
56
+ - Pytorch 2.6.0+cu124
57
+ - Datasets 3.1.0
58
+ - Tokenizers 0.21.1
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 2,
18
+ "rms_norm_eps": 1e-06,
19
+ "rope_scaling": null,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": true,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.52.4",
25
+ "use_cache": false,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 151936
28
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.1,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.52.4"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c1271d401410695b66bd6599afe1da290b7c137ff33bcfb033e26f1ef428f9
3
+ size 3554214752
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 32768,
203
+ "pad_token": "<|endoftext|>",
204
+ "padding_side": "right",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1545, "loss": 0.7034, "lr": 1.1612903225806454e-06, "epoch": 0.00647615963733506, "percentage": 0.65, "elapsed_time": "0:03:51", "remaining_time": "9:51:48"}
2
+ {"current_steps": 20, "total_steps": 1545, "loss": 0.4954, "lr": 2.4516129032258066e-06, "epoch": 0.01295231927467012, "percentage": 1.29, "elapsed_time": "0:16:25", "remaining_time": "20:52:43"}
3
+ {"current_steps": 30, "total_steps": 1545, "loss": 0.2436, "lr": 3.741935483870968e-06, "epoch": 0.019428478912005182, "percentage": 1.94, "elapsed_time": "0:20:38", "remaining_time": "17:22:48"}
4
+ {"current_steps": 40, "total_steps": 1545, "loss": 0.1328, "lr": 5.032258064516129e-06, "epoch": 0.02590463854934024, "percentage": 2.59, "elapsed_time": "0:24:57", "remaining_time": "15:38:45"}
5
+ {"current_steps": 50, "total_steps": 1545, "loss": 0.0993, "lr": 6.3225806451612906e-06, "epoch": 0.0323807981866753, "percentage": 3.24, "elapsed_time": "0:29:00", "remaining_time": "14:27:18"}
6
+ {"current_steps": 60, "total_steps": 1545, "loss": 0.0817, "lr": 7.612903225806451e-06, "epoch": 0.038856957824010364, "percentage": 3.88, "elapsed_time": "0:33:01", "remaining_time": "13:37:18"}
7
+ {"current_steps": 70, "total_steps": 1545, "loss": 0.0691, "lr": 8.903225806451614e-06, "epoch": 0.04533311746134542, "percentage": 4.53, "elapsed_time": "0:36:57", "remaining_time": "12:58:36"}
8
+ {"current_steps": 80, "total_steps": 1545, "loss": 0.0662, "lr": 1.0193548387096774e-05, "epoch": 0.05180927709868048, "percentage": 5.18, "elapsed_time": "0:40:53", "remaining_time": "12:28:46"}
9
+ {"current_steps": 90, "total_steps": 1545, "loss": 0.0622, "lr": 1.1483870967741937e-05, "epoch": 0.05828543673601554, "percentage": 5.83, "elapsed_time": "0:44:52", "remaining_time": "12:05:23"}
10
+ {"current_steps": 100, "total_steps": 1545, "loss": 0.0605, "lr": 1.2774193548387097e-05, "epoch": 0.0647615963733506, "percentage": 6.47, "elapsed_time": "0:49:01", "remaining_time": "11:48:21"}
11
+ {"current_steps": 110, "total_steps": 1545, "loss": 0.0534, "lr": 1.406451612903226e-05, "epoch": 0.07123775601068566, "percentage": 7.12, "elapsed_time": "0:53:01", "remaining_time": "11:31:39"}
12
+ {"current_steps": 120, "total_steps": 1545, "loss": 0.0522, "lr": 1.535483870967742e-05, "epoch": 0.07771391564802073, "percentage": 7.77, "elapsed_time": "0:57:06", "remaining_time": "11:18:05"}
13
+ {"current_steps": 130, "total_steps": 1545, "loss": 0.0478, "lr": 1.6645161290322583e-05, "epoch": 0.08419007528535578, "percentage": 8.41, "elapsed_time": "1:01:00", "remaining_time": "11:04:07"}
14
+ {"current_steps": 140, "total_steps": 1545, "loss": 0.048, "lr": 1.7935483870967742e-05, "epoch": 0.09066623492269084, "percentage": 9.06, "elapsed_time": "1:04:59", "remaining_time": "10:52:11"}
15
+ {"current_steps": 150, "total_steps": 1545, "loss": 0.0548, "lr": 1.9225806451612907e-05, "epoch": 0.09714239456002591, "percentage": 9.71, "elapsed_time": "1:09:02", "remaining_time": "10:42:04"}
16
+ {"current_steps": 160, "total_steps": 1545, "loss": 0.0454, "lr": 1.9999591344664163e-05, "epoch": 0.10361855419736096, "percentage": 10.36, "elapsed_time": "1:12:56", "remaining_time": "10:31:25"}
17
+ {"current_steps": 170, "total_steps": 1545, "loss": 0.0449, "lr": 1.999499435570359e-05, "epoch": 0.11009471383469603, "percentage": 11.0, "elapsed_time": "1:17:02", "remaining_time": "10:23:04"}
18
+ {"current_steps": 180, "total_steps": 1545, "loss": 0.0411, "lr": 1.998529191458689e-05, "epoch": 0.11657087347203109, "percentage": 11.65, "elapsed_time": "1:21:04", "remaining_time": "10:14:45"}
19
+ {"current_steps": 190, "total_steps": 1545, "loss": 0.0386, "lr": 1.9970488977329757e-05, "epoch": 0.12304703310936614, "percentage": 12.3, "elapsed_time": "1:25:01", "remaining_time": "10:06:18"}
20
+ {"current_steps": 200, "total_steps": 1545, "loss": 0.0386, "lr": 1.9950593105285927e-05, "epoch": 0.1295231927467012, "percentage": 12.94, "elapsed_time": "1:29:02", "remaining_time": "9:58:50"}
21
+ {"current_steps": 210, "total_steps": 1545, "loss": 0.0371, "lr": 1.992561446128484e-05, "epoch": 0.13599935238403627, "percentage": 13.59, "elapsed_time": "1:33:01", "remaining_time": "9:51:23"}
22
+ {"current_steps": 220, "total_steps": 1545, "loss": 0.0389, "lr": 1.9895565804440435e-05, "epoch": 0.14247551202137132, "percentage": 14.24, "elapsed_time": "1:36:58", "remaining_time": "9:44:00"}
23
+ {"current_steps": 230, "total_steps": 1545, "loss": 0.0378, "lr": 1.986046248363381e-05, "epoch": 0.14895167165870637, "percentage": 14.89, "elapsed_time": "1:41:02", "remaining_time": "9:37:43"}
24
+ {"current_steps": 240, "total_steps": 1545, "loss": 0.0365, "lr": 1.9820322429672978e-05, "epoch": 0.15542783129604146, "percentage": 15.53, "elapsed_time": "1:45:07", "remaining_time": "9:31:37"}
25
+ {"current_steps": 250, "total_steps": 1545, "loss": 0.0366, "lr": 1.97751661461338e-05, "epoch": 0.1619039909333765, "percentage": 16.18, "elapsed_time": "1:49:07", "remaining_time": "9:25:17"}
26
+ {"current_steps": 260, "total_steps": 1545, "loss": 0.0342, "lr": 1.9725016698886748e-05, "epoch": 0.16838015057071157, "percentage": 16.83, "elapsed_time": "1:53:05", "remaining_time": "9:18:56"}
27
+ {"current_steps": 270, "total_steps": 1545, "loss": 0.0344, "lr": 1.9669899704314828e-05, "epoch": 0.17485631020804662, "percentage": 17.48, "elapsed_time": "1:57:00", "remaining_time": "9:12:31"}
28
+ {"current_steps": 280, "total_steps": 1545, "loss": 0.0347, "lr": 1.960984331622872e-05, "epoch": 0.18133246984538168, "percentage": 18.12, "elapsed_time": "2:00:58", "remaining_time": "9:06:32"}
29
+ {"current_steps": 290, "total_steps": 1545, "loss": 0.033, "lr": 1.9544878211485763e-05, "epoch": 0.18780862948271676, "percentage": 18.77, "elapsed_time": "2:04:54", "remaining_time": "9:00:30"}
30
+ {"current_steps": 300, "total_steps": 1545, "loss": 0.0337, "lr": 1.9475037574320217e-05, "epoch": 0.19428478912005182, "percentage": 19.42, "elapsed_time": "2:08:58", "remaining_time": "8:55:13"}
31
+ {"current_steps": 310, "total_steps": 1545, "loss": 0.0333, "lr": 1.9400357079392714e-05, "epoch": 0.20076094875738687, "percentage": 20.06, "elapsed_time": "2:12:56", "remaining_time": "8:49:36"}
32
+ {"current_steps": 320, "total_steps": 1545, "loss": 0.0329, "lr": 1.9320874873567598e-05, "epoch": 0.20723710839472193, "percentage": 20.71, "elapsed_time": "2:17:03", "remaining_time": "8:44:40"}
33
+ {"current_steps": 330, "total_steps": 1545, "loss": 0.0318, "lr": 1.923663155642748e-05, "epoch": 0.21371326803205698, "percentage": 21.36, "elapsed_time": "2:21:03", "remaining_time": "8:39:21"}
34
+ {"current_steps": 340, "total_steps": 1545, "loss": 0.0326, "lr": 1.9147670159534953e-05, "epoch": 0.22018942766939206, "percentage": 22.01, "elapsed_time": "2:24:58", "remaining_time": "8:33:49"}
35
+ {"current_steps": 350, "total_steps": 1545, "loss": 0.0304, "lr": 1.9054036124452e-05, "epoch": 0.22666558730672712, "percentage": 22.65, "elapsed_time": "2:28:54", "remaining_time": "8:28:24"}
36
+ {"current_steps": 360, "total_steps": 1545, "loss": 0.0318, "lr": 1.8955777279528414e-05, "epoch": 0.23314174694406217, "percentage": 23.3, "elapsed_time": "2:32:55", "remaining_time": "8:23:21"}
37
+ {"current_steps": 370, "total_steps": 1545, "loss": 0.0291, "lr": 1.8852943815471058e-05, "epoch": 0.23961790658139723, "percentage": 23.95, "elapsed_time": "2:37:00", "remaining_time": "8:18:37"}
38
+ {"current_steps": 380, "total_steps": 1545, "loss": 0.0326, "lr": 1.8745588259706366e-05, "epoch": 0.24609406621873228, "percentage": 24.6, "elapsed_time": "2:40:57", "remaining_time": "8:13:28"}
39
+ {"current_steps": 390, "total_steps": 1545, "loss": 0.0306, "lr": 1.863376544954931e-05, "epoch": 0.25257022585606737, "percentage": 25.24, "elapsed_time": "2:44:53", "remaining_time": "8:08:20"}
40
+ {"current_steps": 400, "total_steps": 1545, "loss": 0.0324, "lr": 1.8517532504192456e-05, "epoch": 0.2590463854934024, "percentage": 25.89, "elapsed_time": "2:48:54", "remaining_time": "8:03:30"}
41
+ {"current_steps": 410, "total_steps": 1545, "loss": 0.0279, "lr": 1.8396948795529405e-05, "epoch": 0.2655225451307375, "percentage": 26.54, "elapsed_time": "2:52:49", "remaining_time": "7:58:25"}
42
+ {"current_steps": 420, "total_steps": 1545, "loss": 0.0269, "lr": 1.8272075917827597e-05, "epoch": 0.27199870476807253, "percentage": 27.18, "elapsed_time": "2:56:42", "remaining_time": "7:53:19"}
43
+ {"current_steps": 430, "total_steps": 1545, "loss": 0.0289, "lr": 1.814297765626589e-05, "epoch": 0.2784748644054076, "percentage": 27.83, "elapsed_time": "3:00:41", "remaining_time": "7:48:32"}
44
+ {"current_steps": 440, "total_steps": 1545, "loss": 0.0275, "lr": 1.800971995435305e-05, "epoch": 0.28495102404274264, "percentage": 28.48, "elapsed_time": "3:04:32", "remaining_time": "7:43:26"}
45
+ {"current_steps": 450, "total_steps": 1545, "loss": 0.0312, "lr": 1.787237088024372e-05, "epoch": 0.2914271836800777, "percentage": 29.13, "elapsed_time": "3:08:30", "remaining_time": "7:38:42"}
46
+ {"current_steps": 460, "total_steps": 1545, "loss": 0.0282, "lr": 1.7731000591969182e-05, "epoch": 0.29790334331741275, "percentage": 29.77, "elapsed_time": "3:12:29", "remaining_time": "7:34:01"}
47
+ {"current_steps": 470, "total_steps": 1545, "loss": 0.0294, "lr": 1.758568130160053e-05, "epoch": 0.30437950295474786, "percentage": 30.42, "elapsed_time": "3:16:32", "remaining_time": "7:29:32"}
48
+ {"current_steps": 480, "total_steps": 1545, "loss": 0.027, "lr": 1.743648723836271e-05, "epoch": 0.3108556625920829, "percentage": 31.07, "elapsed_time": "3:20:31", "remaining_time": "7:24:54"}
49
+ {"current_steps": 490, "total_steps": 1545, "loss": 0.0265, "lr": 1.7283494610718153e-05, "epoch": 0.31733182222941797, "percentage": 31.72, "elapsed_time": "3:24:25", "remaining_time": "7:20:09"}
50
+ {"current_steps": 500, "total_steps": 1545, "loss": 0.029, "lr": 1.7126781567439418e-05, "epoch": 0.323807981866753, "percentage": 32.36, "elapsed_time": "3:28:22", "remaining_time": "7:15:30"}
51
+ {"current_steps": 510, "total_steps": 1545, "loss": 0.0267, "lr": 1.696642815769075e-05, "epoch": 0.3302841415040881, "percentage": 33.01, "elapsed_time": "3:32:11", "remaining_time": "7:10:37"}
52
+ {"current_steps": 520, "total_steps": 1545, "loss": 0.0282, "lr": 1.680251629013885e-05, "epoch": 0.33676030114142314, "percentage": 33.66, "elapsed_time": "3:36:00", "remaining_time": "7:05:46"}
53
+ {"current_steps": 530, "total_steps": 1545, "loss": 0.028, "lr": 1.663512969111392e-05, "epoch": 0.3432364607787582, "percentage": 34.3, "elapsed_time": "3:39:56", "remaining_time": "7:01:13"}
54
+ {"current_steps": 540, "total_steps": 1545, "loss": 0.0281, "lr": 1.6464353861842115e-05, "epoch": 0.34971262041609325, "percentage": 34.95, "elapsed_time": "3:43:57", "remaining_time": "6:56:48"}
55
+ {"current_steps": 550, "total_steps": 1545, "loss": 0.0269, "lr": 1.629027603477147e-05, "epoch": 0.3561887800534283, "percentage": 35.6, "elapsed_time": "3:47:57", "remaining_time": "6:52:23"}
56
+ {"current_steps": 560, "total_steps": 1545, "loss": 0.0279, "lr": 1.611298512901349e-05, "epoch": 0.36266493969076335, "percentage": 36.25, "elapsed_time": "3:51:49", "remaining_time": "6:47:45"}
57
+ {"current_steps": 570, "total_steps": 1545, "loss": 0.0274, "lr": 1.5932571704923168e-05, "epoch": 0.36914109932809847, "percentage": 36.89, "elapsed_time": "3:55:51", "remaining_time": "6:43:25"}
58
+ {"current_steps": 580, "total_steps": 1545, "loss": 0.0261, "lr": 1.57491279178407e-05, "epoch": 0.3756172589654335, "percentage": 37.54, "elapsed_time": "3:59:47", "remaining_time": "6:38:57"}
59
+ {"current_steps": 590, "total_steps": 1545, "loss": 0.0259, "lr": 1.5562747471018415e-05, "epoch": 0.3820934186027686, "percentage": 38.19, "elapsed_time": "4:03:47", "remaining_time": "6:34:35"}
60
+ {"current_steps": 600, "total_steps": 1545, "loss": 0.0278, "lr": 1.5373525567757124e-05, "epoch": 0.38856957824010363, "percentage": 38.83, "elapsed_time": "4:07:53", "remaining_time": "6:30:25"}
61
+ {"current_steps": 610, "total_steps": 1545, "loss": 0.0255, "lr": 1.518155886277613e-05, "epoch": 0.3950457378774387, "percentage": 39.48, "elapsed_time": "4:11:44", "remaining_time": "6:25:52"}
62
+ {"current_steps": 620, "total_steps": 1545, "loss": 0.0233, "lr": 1.498694541284195e-05, "epoch": 0.40152189751477374, "percentage": 40.13, "elapsed_time": "4:15:40", "remaining_time": "6:21:27"}
63
+ {"current_steps": 630, "total_steps": 1545, "loss": 0.0265, "lr": 1.4789784626680819e-05, "epoch": 0.4079980571521088, "percentage": 40.78, "elapsed_time": "4:19:51", "remaining_time": "6:17:24"}
64
+ {"current_steps": 640, "total_steps": 1545, "loss": 0.0249, "lr": 1.4590177214200609e-05, "epoch": 0.41447421678944385, "percentage": 41.42, "elapsed_time": "4:23:54", "remaining_time": "6:13:10"}
65
+ {"current_steps": 650, "total_steps": 1545, "loss": 0.0243, "lr": 1.4388225135048137e-05, "epoch": 0.4209503764267789, "percentage": 42.07, "elapsed_time": "4:27:42", "remaining_time": "6:08:37"}
66
+ {"current_steps": 660, "total_steps": 1545, "loss": 0.0223, "lr": 1.4184031546528077e-05, "epoch": 0.42742653606411396, "percentage": 42.72, "elapsed_time": "4:31:39", "remaining_time": "6:04:16"}
67
+ {"current_steps": 670, "total_steps": 1545, "loss": 0.0279, "lr": 1.3977700750910112e-05, "epoch": 0.433902695701449, "percentage": 43.37, "elapsed_time": "4:35:34", "remaining_time": "5:59:53"}
68
+ {"current_steps": 680, "total_steps": 1545, "loss": 0.0247, "lr": 1.3769338142151245e-05, "epoch": 0.4403788553387841, "percentage": 44.01, "elapsed_time": "4:39:31", "remaining_time": "5:55:34"}
69
+ {"current_steps": 690, "total_steps": 1545, "loss": 0.0242, "lr": 1.3559050152060465e-05, "epoch": 0.4468550149761192, "percentage": 44.66, "elapsed_time": "4:43:33", "remaining_time": "5:51:21"}
70
+ {"current_steps": 700, "total_steps": 1545, "loss": 0.0242, "lr": 1.3346944195933294e-05, "epoch": 0.45333117461345424, "percentage": 45.31, "elapsed_time": "4:47:37", "remaining_time": "5:47:12"}
71
+ {"current_steps": 710, "total_steps": 1545, "loss": 0.0255, "lr": 1.313312861768394e-05, "epoch": 0.4598073342507893, "percentage": 45.95, "elapsed_time": "4:51:42", "remaining_time": "5:43:03"}
72
+ {"current_steps": 720, "total_steps": 1545, "loss": 0.0244, "lr": 1.2917712634503148e-05, "epoch": 0.46628349388812435, "percentage": 46.6, "elapsed_time": "4:55:30", "remaining_time": "5:38:35"}
73
+ {"current_steps": 730, "total_steps": 1545, "loss": 0.024, "lr": 1.2700806281069942e-05, "epoch": 0.4727596535254594, "percentage": 47.25, "elapsed_time": "4:59:30", "remaining_time": "5:34:22"}
74
+ {"current_steps": 740, "total_steps": 1545, "loss": 0.0236, "lr": 1.2482520353345819e-05, "epoch": 0.47923581316279446, "percentage": 47.9, "elapsed_time": "5:03:40", "remaining_time": "5:30:20"}
75
+ {"current_steps": 750, "total_steps": 1545, "loss": 0.024, "lr": 1.2262966351980075e-05, "epoch": 0.4857119728001295, "percentage": 48.54, "elapsed_time": "5:07:34", "remaining_time": "5:26:02"}
76
+ {"current_steps": 760, "total_steps": 1545, "loss": 0.0245, "lr": 1.2042256425355165e-05, "epoch": 0.49218813243746456, "percentage": 49.19, "elapsed_time": "5:11:45", "remaining_time": "5:22:00"}
77
+ {"current_steps": 770, "total_steps": 1545, "loss": 0.0228, "lr": 1.1820503312301218e-05, "epoch": 0.4986642920747996, "percentage": 49.84, "elapsed_time": "5:15:50", "remaining_time": "5:17:53"}
78
+ {"current_steps": 780, "total_steps": 1545, "loss": 0.0213, "lr": 1.1597820284508927e-05, "epoch": 0.5051404517121347, "percentage": 50.49, "elapsed_time": "5:19:48", "remaining_time": "5:13:39"}
79
+ {"current_steps": 790, "total_steps": 1545, "loss": 0.0241, "lr": 1.1374321088670277e-05, "epoch": 0.5116166113494698, "percentage": 51.13, "elapsed_time": "5:23:49", "remaining_time": "5:09:28"}
80
+ {"current_steps": 800, "total_steps": 1545, "loss": 0.0245, "lr": 1.1150119888376631e-05, "epoch": 0.5180927709868048, "percentage": 51.78, "elapsed_time": "5:27:56", "remaining_time": "5:05:24"}
81
+ {"current_steps": 810, "total_steps": 1545, "loss": 0.0256, "lr": 1.0925331205803861e-05, "epoch": 0.5245689306241399, "percentage": 52.43, "elapsed_time": "5:32:05", "remaining_time": "5:01:20"}
82
+ {"current_steps": 820, "total_steps": 1545, "loss": 0.0219, "lr": 1.0700069863214317e-05, "epoch": 0.531045090261475, "percentage": 53.07, "elapsed_time": "5:36:09", "remaining_time": "4:57:12"}
83
+ {"current_steps": 830, "total_steps": 1545, "loss": 0.0219, "lr": 1.047445092430552e-05, "epoch": 0.53752124989881, "percentage": 53.72, "elapsed_time": "5:40:04", "remaining_time": "4:52:57"}
84
+ {"current_steps": 840, "total_steps": 1545, "loss": 0.0237, "lr": 1.0248589635435505e-05, "epoch": 0.5439974095361451, "percentage": 54.37, "elapsed_time": "5:44:08", "remaining_time": "4:48:50"}
85
+ {"current_steps": 850, "total_steps": 1545, "loss": 0.0227, "lr": 1.0022601366754889e-05, "epoch": 0.5504735691734801, "percentage": 55.02, "elapsed_time": "5:48:16", "remaining_time": "4:44:45"}
86
+ {"current_steps": 860, "total_steps": 1545, "loss": 0.0233, "lr": 9.796601553275697e-06, "epoch": 0.5569497288108152, "percentage": 55.66, "elapsed_time": "5:52:12", "remaining_time": "4:40:32"}
87
+ {"current_steps": 870, "total_steps": 1545, "loss": 0.0239, "lr": 9.570705635907038e-06, "epoch": 0.5634258884481502, "percentage": 56.31, "elapsed_time": "5:56:08", "remaining_time": "4:36:19"}
88
+ {"current_steps": 880, "total_steps": 1545, "loss": 0.0234, "lr": 9.3450290024878e-06, "epoch": 0.5699020480854853, "percentage": 56.96, "elapsed_time": "6:00:07", "remaining_time": "4:32:08"}
89
+ {"current_steps": 890, "total_steps": 1545, "loss": 0.0226, "lr": 9.119686928846437e-06, "epoch": 0.5763782077228203, "percentage": 57.61, "elapsed_time": "6:04:12", "remaining_time": "4:28:02"}
90
+ {"current_steps": 900, "total_steps": 1545, "loss": 0.0215, "lr": 8.894794519917947e-06, "epoch": 0.5828543673601554, "percentage": 58.25, "elapsed_time": "6:08:15", "remaining_time": "4:23:55"}
91
+ {"current_steps": 910, "total_steps": 1545, "loss": 0.022, "lr": 8.670466650948208e-06, "epoch": 0.5893305269974904, "percentage": 58.9, "elapsed_time": "6:12:15", "remaining_time": "4:19:45"}
92
+ {"current_steps": 920, "total_steps": 1545, "loss": 0.0202, "lr": 8.446817908815566e-06, "epoch": 0.5958066866348255, "percentage": 59.55, "elapsed_time": "6:16:15", "remaining_time": "4:15:36"}
93
+ {"current_steps": 930, "total_steps": 1545, "loss": 0.0199, "lr": 8.223962533499757e-06, "epoch": 0.6022828462721606, "percentage": 60.19, "elapsed_time": "6:20:14", "remaining_time": "4:11:27"}
94
+ {"current_steps": 940, "total_steps": 1545, "loss": 0.0222, "lr": 8.002014359728046e-06, "epoch": 0.6087590059094957, "percentage": 60.84, "elapsed_time": "6:24:13", "remaining_time": "4:07:17"}
95
+ {"current_steps": 950, "total_steps": 1545, "loss": 0.0198, "lr": 7.781086758828314e-06, "epoch": 0.6152351655468308, "percentage": 61.49, "elapsed_time": "6:28:07", "remaining_time": "4:03:05"}
96
+ {"current_steps": 960, "total_steps": 1545, "loss": 0.0209, "lr": 7.561292580818906e-06, "epoch": 0.6217113251841658, "percentage": 62.14, "elapsed_time": "6:31:54", "remaining_time": "3:58:49"}
97
+ {"current_steps": 970, "total_steps": 1545, "loss": 0.0213, "lr": 7.342744096764727e-06, "epoch": 0.6281874848215009, "percentage": 62.78, "elapsed_time": "6:35:51", "remaining_time": "3:54:39"}
98
+ {"current_steps": 980, "total_steps": 1545, "loss": 0.0206, "lr": 7.125552941429077e-06, "epoch": 0.6346636444588359, "percentage": 63.43, "elapsed_time": "6:39:50", "remaining_time": "3:50:31"}
99
+ {"current_steps": 990, "total_steps": 1545, "loss": 0.02, "lr": 6.909830056250527e-06, "epoch": 0.641139804096171, "percentage": 64.08, "elapsed_time": "6:43:48", "remaining_time": "3:46:22"}
100
+ {"current_steps": 1000, "total_steps": 1545, "loss": 0.0216, "lr": 6.695685632673919e-06, "epoch": 0.647615963733506, "percentage": 64.72, "elapsed_time": "6:47:49", "remaining_time": "3:42:16"}
101
+ {"current_steps": 1010, "total_steps": 1545, "loss": 0.0211, "lr": 6.48322905586449e-06, "epoch": 0.6540921233708411, "percentage": 65.37, "elapsed_time": "6:51:47", "remaining_time": "3:38:07"}
102
+ {"current_steps": 1020, "total_steps": 1545, "loss": 0.0209, "lr": 6.272568848833809e-06, "epoch": 0.6605682830081762, "percentage": 66.02, "elapsed_time": "6:55:44", "remaining_time": "3:33:58"}
103
+ {"current_steps": 1030, "total_steps": 1545, "loss": 0.0189, "lr": 6.06381261700614e-06, "epoch": 0.6670444426455112, "percentage": 66.67, "elapsed_time": "6:59:35", "remaining_time": "3:29:47"}
104
+ {"current_steps": 1040, "total_steps": 1545, "loss": 0.0209, "lr": 5.857066993253501e-06, "epoch": 0.6735206022828463, "percentage": 67.31, "elapsed_time": "7:03:31", "remaining_time": "3:25:39"}
105
+ {"current_steps": 1050, "total_steps": 1545, "loss": 0.0195, "lr": 5.652437583427478e-06, "epoch": 0.6799967619201813, "percentage": 67.96, "elapsed_time": "7:07:20", "remaining_time": "3:21:27"}
106
+ {"current_steps": 1060, "total_steps": 1545, "loss": 0.022, "lr": 5.450028912415672e-06, "epoch": 0.6864729215575164, "percentage": 68.61, "elapsed_time": "7:11:29", "remaining_time": "3:17:25"}
107
+ {"current_steps": 1070, "total_steps": 1545, "loss": 0.0204, "lr": 5.249944370750293e-06, "epoch": 0.6929490811948514, "percentage": 69.26, "elapsed_time": "7:15:28", "remaining_time": "3:13:19"}
108
+ {"current_steps": 1080, "total_steps": 1545, "loss": 0.0202, "lr": 5.0522861617961694e-06, "epoch": 0.6994252408321865, "percentage": 69.9, "elapsed_time": "7:19:24", "remaining_time": "3:09:11"}
109
+ {"current_steps": 1090, "total_steps": 1545, "loss": 0.0206, "lr": 4.857155249545197e-06, "epoch": 0.7059014004695215, "percentage": 70.55, "elapsed_time": "7:23:27", "remaining_time": "3:05:06"}
110
+ {"current_steps": 1100, "total_steps": 1545, "loss": 0.0204, "lr": 4.66465130704382e-06, "epoch": 0.7123775601068566, "percentage": 71.2, "elapsed_time": "7:27:33", "remaining_time": "3:01:03"}
111
+ {"current_steps": 1110, "total_steps": 1545, "loss": 0.0194, "lr": 4.474872665479974e-06, "epoch": 0.7188537197441917, "percentage": 71.84, "elapsed_time": "7:31:31", "remaining_time": "2:56:57"}
112
+ {"current_steps": 1120, "total_steps": 1545, "loss": 0.0209, "lr": 4.2879162639553925e-06, "epoch": 0.7253298793815267, "percentage": 72.49, "elapsed_time": "7:35:38", "remaining_time": "2:52:54"}
113
+ {"current_steps": 1130, "total_steps": 1545, "loss": 0.0207, "lr": 4.103877599969056e-06, "epoch": 0.7318060390188618, "percentage": 73.14, "elapsed_time": "7:39:41", "remaining_time": "2:48:49"}
114
+ {"current_steps": 1140, "total_steps": 1545, "loss": 0.021, "lr": 3.922850680636968e-06, "epoch": 0.7382821986561969, "percentage": 73.79, "elapsed_time": "7:43:41", "remaining_time": "2:44:43"}
115
+ {"current_steps": 1150, "total_steps": 1545, "loss": 0.0213, "lr": 3.744927974673237e-06, "epoch": 0.744758358293532, "percentage": 74.43, "elapsed_time": "7:47:50", "remaining_time": "2:40:41"}
116
+ {"current_steps": 1160, "total_steps": 1545, "loss": 0.0201, "lr": 3.5702003651569883e-06, "epoch": 0.751234517930867, "percentage": 75.08, "elapsed_time": "7:51:43", "remaining_time": "2:36:33"}
117
+ {"current_steps": 1170, "total_steps": 1545, "loss": 0.0196, "lr": 3.3987571031091735e-06, "epoch": 0.7577106775682021, "percentage": 75.73, "elapsed_time": "7:55:49", "remaining_time": "2:32:30"}
118
+ {"current_steps": 1180, "total_steps": 1545, "loss": 0.0213, "lr": 3.230685761903094e-06, "epoch": 0.7641868372055372, "percentage": 76.38, "elapsed_time": "7:59:46", "remaining_time": "2:28:24"}
119
+ {"current_steps": 1190, "total_steps": 1545, "loss": 0.0199, "lr": 3.0660721925318483e-06, "epoch": 0.7706629968428722, "percentage": 77.02, "elapsed_time": "8:03:47", "remaining_time": "2:24:19"}
120
+ {"current_steps": 1200, "total_steps": 1545, "loss": 0.0204, "lr": 2.905000479755531e-06, "epoch": 0.7771391564802073, "percentage": 77.67, "elapsed_time": "8:07:49", "remaining_time": "2:20:15"}
121
+ {"current_steps": 1210, "total_steps": 1545, "loss": 0.0193, "lr": 2.7475528991507106e-06, "epoch": 0.7836153161175423, "percentage": 78.32, "elapsed_time": "8:11:51", "remaining_time": "2:16:10"}
122
+ {"current_steps": 1220, "total_steps": 1545, "loss": 0.0211, "lr": 2.5938098750839414e-06, "epoch": 0.7900914757548774, "percentage": 78.96, "elapsed_time": "8:15:54", "remaining_time": "2:12:06"}
123
+ {"current_steps": 1230, "total_steps": 1545, "loss": 0.0185, "lr": 2.443849939630959e-06, "epoch": 0.7965676353922124, "percentage": 79.61, "elapsed_time": "8:19:58", "remaining_time": "2:08:02"}
124
+ {"current_steps": 1240, "total_steps": 1545, "loss": 0.0191, "lr": 2.2977496924624223e-06, "epoch": 0.8030437950295475, "percentage": 80.26, "elapsed_time": "8:23:52", "remaining_time": "2:03:56"}
125
+ {"current_steps": 1250, "total_steps": 1545, "loss": 0.0222, "lr": 2.155583761716703e-06, "epoch": 0.8095199546668825, "percentage": 80.91, "elapsed_time": "8:27:51", "remaining_time": "1:59:51"}
126
+ {"current_steps": 1260, "total_steps": 1545, "loss": 0.0213, "lr": 2.0174247658798054e-06, "epoch": 0.8159961143042176, "percentage": 81.55, "elapsed_time": "8:31:49", "remaining_time": "1:55:46"}
127
+ {"current_steps": 1270, "total_steps": 1545, "loss": 0.0199, "lr": 1.8833432766917514e-06, "epoch": 0.8224722739415526, "percentage": 82.2, "elapsed_time": "8:35:50", "remaining_time": "1:51:41"}
128
+ {"current_steps": 1280, "total_steps": 1545, "loss": 0.0212, "lr": 1.7534077830984697e-06, "epoch": 0.8289484335788877, "percentage": 82.85, "elapsed_time": "8:39:55", "remaining_time": "1:47:38"}
129
+ {"current_steps": 1290, "total_steps": 1545, "loss": 0.0199, "lr": 1.6276846562676085e-06, "epoch": 0.8354245932162228, "percentage": 83.5, "elapsed_time": "8:43:58", "remaining_time": "1:43:34"}
130
+ {"current_steps": 1300, "total_steps": 1545, "loss": 0.0196, "lr": 1.506238115686044e-06, "epoch": 0.8419007528535578, "percentage": 84.14, "elapsed_time": "8:47:52", "remaining_time": "1:39:28"}
131
+ {"current_steps": 1310, "total_steps": 1545, "loss": 0.0202, "lr": 1.3891301963565473e-06, "epoch": 0.8483769124908929, "percentage": 84.79, "elapsed_time": "8:51:48", "remaining_time": "1:35:24"}
132
+ {"current_steps": 1320, "total_steps": 1545, "loss": 0.0187, "lr": 1.2764207171102206e-06, "epoch": 0.8548530721282279, "percentage": 85.44, "elapsed_time": "8:55:45", "remaining_time": "1:31:19"}
133
+ {"current_steps": 1330, "total_steps": 1545, "loss": 0.0203, "lr": 1.1681672500509866e-06, "epoch": 0.861329231765563, "percentage": 86.08, "elapsed_time": "8:59:44", "remaining_time": "1:27:15"}
134
+ {"current_steps": 1340, "total_steps": 1545, "loss": 0.0201, "lr": 1.0644250911477306e-06, "epoch": 0.867805391402898, "percentage": 86.73, "elapsed_time": "9:03:40", "remaining_time": "1:23:10"}
135
+ {"current_steps": 1350, "total_steps": 1545, "loss": 0.0178, "lr": 9.652472319890372e-07, "epoch": 0.8742815510402332, "percentage": 87.38, "elapsed_time": "9:07:39", "remaining_time": "1:19:06"}
136
+ {"current_steps": 1360, "total_steps": 1545, "loss": 0.0203, "lr": 8.706843327150605e-07, "epoch": 0.8807577106775683, "percentage": 88.03, "elapsed_time": "9:11:36", "remaining_time": "1:15:02"}
137
+ {"current_steps": 1370, "total_steps": 1545, "loss": 0.017, "lr": 7.807846961402699e-07, "epoch": 0.8872338703149033, "percentage": 88.67, "elapsed_time": "9:15:31", "remaining_time": "1:10:57"}
138
+ {"current_steps": 1380, "total_steps": 1545, "loss": 0.0189, "lr": 6.955942430803298e-07, "epoch": 0.8937100299522384, "percentage": 89.32, "elapsed_time": "9:19:36", "remaining_time": "1:06:54"}
139
+ {"current_steps": 1390, "total_steps": 1545, "loss": 0.0211, "lr": 6.151564888957084e-07, "epoch": 0.9001861895895734, "percentage": 89.97, "elapsed_time": "9:23:33", "remaining_time": "1:02:50"}
140
+ {"current_steps": 1400, "total_steps": 1545, "loss": 0.0193, "lr": 5.395125212639895e-07, "epoch": 0.9066623492269085, "percentage": 90.61, "elapsed_time": "9:27:33", "remaining_time": "0:58:46"}
141
+ {"current_steps": 1410, "total_steps": 1545, "loss": 0.0185, "lr": 4.6870097919224923e-07, "epoch": 0.9131385088642435, "percentage": 91.26, "elapsed_time": "9:31:30", "remaining_time": "0:54:43"}
142
+ {"current_steps": 1420, "total_steps": 1545, "loss": 0.0183, "lr": 4.0275803328021946e-07, "epoch": 0.9196146685015786, "percentage": 91.91, "elapsed_time": "9:35:23", "remaining_time": "0:50:39"}
143
+ {"current_steps": 1430, "total_steps": 1545, "loss": 0.0194, "lr": 3.417173672443075e-07, "epoch": 0.9260908281389136, "percentage": 92.56, "elapsed_time": "9:39:28", "remaining_time": "0:46:36"}
144
+ {"current_steps": 1440, "total_steps": 1545, "loss": 0.0189, "lr": 2.8561016071192884e-07, "epoch": 0.9325669877762487, "percentage": 93.2, "elapsed_time": "9:43:28", "remaining_time": "0:42:32"}
145
+ {"current_steps": 1450, "total_steps": 1545, "loss": 0.0182, "lr": 2.3446507329492274e-07, "epoch": 0.9390431474135837, "percentage": 93.85, "elapsed_time": "9:47:32", "remaining_time": "0:38:29"}
146
+ {"current_steps": 1460, "total_steps": 1545, "loss": 0.0198, "lr": 1.8830822995019593e-07, "epoch": 0.9455193070509188, "percentage": 94.5, "elapsed_time": "9:51:17", "remaining_time": "0:34:25"}
147
+ {"current_steps": 1470, "total_steps": 1545, "loss": 0.019, "lr": 1.4716320763507152e-07, "epoch": 0.9519954666882539, "percentage": 95.15, "elapsed_time": "9:55:17", "remaining_time": "0:30:22"}
148
+ {"current_steps": 1480, "total_steps": 1545, "loss": 0.0186, "lr": 1.1105102326415929e-07, "epoch": 0.9584716263255889, "percentage": 95.79, "elapsed_time": "9:59:19", "remaining_time": "0:26:19"}
149
+ {"current_steps": 1490, "total_steps": 1545, "loss": 0.0193, "lr": 7.999012297389419e-08, "epoch": 0.964947785962924, "percentage": 96.44, "elapsed_time": "10:03:25", "remaining_time": "0:22:16"}
150
+ {"current_steps": 1500, "total_steps": 1545, "loss": 0.0196, "lr": 5.399637270023683e-08, "epoch": 0.971423945600259, "percentage": 97.09, "elapsed_time": "10:07:21", "remaining_time": "0:18:13"}
151
+ {"current_steps": 1510, "total_steps": 1545, "loss": 0.0188, "lr": 3.308305007433399e-08, "epoch": 0.9779001052375941, "percentage": 97.73, "elapsed_time": "10:11:21", "remaining_time": "0:14:10"}
152
+ {"current_steps": 1520, "total_steps": 1545, "loss": 0.0175, "lr": 1.726083764029607e-08, "epoch": 0.9843762648749291, "percentage": 98.38, "elapsed_time": "10:15:18", "remaining_time": "0:10:07"}
153
+ {"current_steps": 1530, "total_steps": 1545, "loss": 0.0206, "lr": 6.5378173985441994e-09, "epoch": 0.9908524245122642, "percentage": 99.03, "elapsed_time": "10:19:13", "remaining_time": "0:06:04"}
154
+ {"current_steps": 1540, "total_steps": 1545, "loss": 0.0197, "lr": 9.194666775158567e-10, "epoch": 0.9973285841495992, "percentage": 99.68, "elapsed_time": "10:23:18", "remaining_time": "0:02:01"}
155
+ {"current_steps": 1545, "total_steps": 1545, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "10:25:12", "remaining_time": "0:00:00"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81eb6bc514d850241659c7350c40e2591812bdd837e345f8f78a5d22258faf2e
3
+ size 7480
vocab.json ADDED
The diff for this file is too large to render. See raw diff