toongs commited on
Commit
adf2be6
·
verified ·
1 Parent(s): cf91f83

Upload 9 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/Llava_Qwen2/checkpoints/Qwen2-1.5B-Instruct-Vision-150k-first-turn",
3
+ "architectures": [
4
+ "LlavaQwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "freeze_mm_mlp_adapter": false,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1536,
12
+ "image_aspect_ratio": "pad",
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8960,
15
+ "max_position_embeddings": 32768,
16
+ "max_window_layers": 28,
17
+ "mm_hidden_size": 768,
18
+ "mm_patch_merge_type": "flat",
19
+ "mm_projector_lr": null,
20
+ "mm_projector_type": "mlp2x_gelu",
21
+ "mm_use_im_patch_token": false,
22
+ "mm_use_im_start_end": false,
23
+ "mm_vision_select_feature": "patch",
24
+ "mm_vision_select_layer": -2,
25
+ "mm_vision_tower": "/workspace/Llava_Qwen2/models/lingual_siglip",
26
+ "model_type": "llava_qwen2",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 28,
29
+ "num_key_value_heads": 2,
30
+ "rms_norm_eps": 1e-06,
31
+ "rope_theta": 1000000.0,
32
+ "sliding_window": 32768,
33
+ "tie_word_embeddings": true,
34
+ "tokenizer_model_max_length": 4096,
35
+ "tokenizer_padding_side": "right",
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.37.2",
38
+ "tune_mm_mlp_adapter": false,
39
+ "use_cache": true,
40
+ "use_mm_proj": true,
41
+ "use_sliding_window": false,
42
+ "vocab_size": 151936
43
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.1,
11
+ "temperature": 0.7,
12
+ "top_k": 20,
13
+ "top_p": 0.8,
14
+ "transformers_version": "4.37.2"
15
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 4096,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
trainer_state.json ADDED
@@ -0,0 +1,1398 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.400736000878807,
5
+ "eval_steps": 500,
6
+ "global_step": 228,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 2.8571428571428573e-06,
14
+ "loss": 2.0419,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 5.7142857142857145e-06,
20
+ "loss": 2.1227,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 8.571428571428571e-06,
26
+ "loss": 2.0401,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 1.1428571428571429e-05,
32
+ "loss": 2.0777,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 1.4285714285714287e-05,
38
+ "loss": 1.9235,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 1.7142857142857142e-05,
44
+ "loss": 1.8527,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "learning_rate": 2e-05,
50
+ "loss": 1.8595,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "learning_rate": 1.9998989635940996e-05,
56
+ "loss": 1.8005,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "learning_rate": 1.9995958747931083e-05,
62
+ "loss": 1.7729,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.02,
67
+ "learning_rate": 1.9990907948430327e-05,
68
+ "loss": 1.7767,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.02,
73
+ "learning_rate": 1.998383825806799e-05,
74
+ "loss": 1.733,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.02,
79
+ "learning_rate": 1.9974751105436266e-05,
80
+ "loss": 1.7177,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.02,
85
+ "learning_rate": 1.9963648326801653e-05,
86
+ "loss": 1.6892,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "learning_rate": 1.9950532165733847e-05,
92
+ "loss": 1.6988,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.03,
97
+ "learning_rate": 1.993540527265239e-05,
98
+ "loss": 1.6935,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.03,
103
+ "learning_rate": 1.9918270704291104e-05,
104
+ "loss": 1.7013,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.03,
109
+ "learning_rate": 1.98991319230804e-05,
110
+ "loss": 1.6657,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.03,
115
+ "learning_rate": 1.9877992796447604e-05,
116
+ "loss": 1.663,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.03,
121
+ "learning_rate": 1.9854857596035476e-05,
122
+ "loss": 1.6739,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.04,
127
+ "learning_rate": 1.982973099683902e-05,
128
+ "loss": 1.6262,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.04,
133
+ "learning_rate": 1.9802618076260784e-05,
134
+ "loss": 1.7099,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.04,
139
+ "learning_rate": 1.9773524313084857e-05,
140
+ "loss": 1.6464,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.04,
145
+ "learning_rate": 1.9742455586369786e-05,
146
+ "loss": 1.6538,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.04,
151
+ "learning_rate": 1.9709418174260523e-05,
152
+ "loss": 1.6665,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.04,
157
+ "learning_rate": 1.9674418752719835e-05,
158
+ "loss": 1.6097,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.05,
163
+ "learning_rate": 1.963746439417924e-05,
164
+ "loss": 1.6503,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.05,
169
+ "learning_rate": 1.959856256610988e-05,
170
+ "loss": 1.658,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.05,
175
+ "learning_rate": 1.9557721129513538e-05,
176
+ "loss": 1.6575,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.05,
181
+ "learning_rate": 1.9514948337334144e-05,
182
+ "loss": 1.6055,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.05,
187
+ "learning_rate": 1.947025283279008e-05,
188
+ "loss": 1.6067,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.05,
193
+ "learning_rate": 1.9423643647627625e-05,
194
+ "loss": 1.5934,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.06,
199
+ "learning_rate": 1.937513020029588e-05,
200
+ "loss": 1.6424,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.06,
205
+ "learning_rate": 1.932472229404356e-05,
206
+ "loss": 1.6179,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.06,
211
+ "learning_rate": 1.9272430114938018e-05,
212
+ "loss": 1.5971,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.06,
217
+ "learning_rate": 1.9218264229806917e-05,
218
+ "loss": 1.5947,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.06,
223
+ "learning_rate": 1.9162235584102973e-05,
224
+ "loss": 1.5637,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.07,
229
+ "learning_rate": 1.9104355499692166e-05,
230
+ "loss": 1.6186,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.07,
235
+ "learning_rate": 1.9044635672565898e-05,
236
+ "loss": 1.5754,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.07,
241
+ "learning_rate": 1.8983088170477556e-05,
242
+ "loss": 1.6139,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.07,
247
+ "learning_rate": 1.8919725430503946e-05,
248
+ "loss": 1.5928,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.07,
253
+ "learning_rate": 1.8854560256532098e-05,
254
+ "loss": 1.5804,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.07,
259
+ "learning_rate": 1.8787605816671956e-05,
260
+ "loss": 1.6165,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.08,
265
+ "learning_rate": 1.8718875640595432e-05,
266
+ "loss": 1.6021,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.08,
271
+ "learning_rate": 1.864838361680247e-05,
272
+ "loss": 1.5869,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.08,
277
+ "learning_rate": 1.8576143989814524e-05,
278
+ "loss": 1.5575,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.08,
283
+ "learning_rate": 1.8502171357296144e-05,
284
+ "loss": 1.6145,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.08,
289
+ "learning_rate": 1.8426480667105178e-05,
290
+ "loss": 1.5553,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.08,
295
+ "learning_rate": 1.8349087214272222e-05,
296
+ "loss": 1.5679,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.09,
301
+ "learning_rate": 1.8270006637909907e-05,
302
+ "loss": 1.5606,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.09,
307
+ "learning_rate": 1.818925491805265e-05,
308
+ "loss": 1.5488,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.09,
313
+ "learning_rate": 1.810684837242755e-05,
314
+ "loss": 1.5561,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.09,
319
+ "learning_rate": 1.8022803653156983e-05,
320
+ "loss": 1.5796,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.09,
325
+ "learning_rate": 1.7937137743393695e-05,
326
+ "loss": 1.565,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.09,
331
+ "learning_rate": 1.784986795388895e-05,
332
+ "loss": 1.5969,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.1,
337
+ "learning_rate": 1.776101191949449e-05,
338
+ "loss": 1.5392,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.1,
343
+ "learning_rate": 1.7670587595599034e-05,
344
+ "loss": 1.5849,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.1,
349
+ "learning_rate": 1.757861325449997e-05,
350
+ "loss": 1.582,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.1,
355
+ "learning_rate": 1.7485107481711014e-05,
356
+ "loss": 1.5919,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.1,
361
+ "learning_rate": 1.7390089172206594e-05,
362
+ "loss": 1.5639,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.11,
367
+ "learning_rate": 1.7293577526603684e-05,
368
+ "loss": 1.5829,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.11,
373
+ "learning_rate": 1.719559204728188e-05,
374
+ "loss": 1.5662,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.11,
379
+ "learning_rate": 1.7096152534442515e-05,
380
+ "loss": 1.5844,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.11,
385
+ "learning_rate": 1.6995279082107537e-05,
386
+ "loss": 1.5202,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.11,
391
+ "learning_rate": 1.689299207405911e-05,
392
+ "loss": 1.5726,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.11,
397
+ "learning_rate": 1.678931217972055e-05,
398
+ "loss": 1.5644,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.12,
403
+ "learning_rate": 1.6684260349979637e-05,
404
+ "loss": 1.5389,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.12,
409
+ "learning_rate": 1.6577857812954994e-05,
410
+ "loss": 1.5473,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.12,
415
+ "learning_rate": 1.6470126069706456e-05,
416
+ "loss": 1.5519,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.12,
421
+ "learning_rate": 1.6361086889890307e-05,
422
+ "loss": 1.5158,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.12,
427
+ "learning_rate": 1.6250762307360206e-05,
428
+ "loss": 1.5203,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.12,
433
+ "learning_rate": 1.6139174615714753e-05,
434
+ "loss": 1.5331,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.13,
439
+ "learning_rate": 1.6026346363792565e-05,
440
+ "loss": 1.5399,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.13,
445
+ "learning_rate": 1.591230035111576e-05,
446
+ "loss": 1.5499,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.13,
451
+ "learning_rate": 1.5797059623282787e-05,
452
+ "loss": 1.5821,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.13,
457
+ "learning_rate": 1.568064746731156e-05,
458
+ "loss": 1.5463,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.13,
463
+ "learning_rate": 1.5563087406933762e-05,
464
+ "loss": 1.5557,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.14,
469
+ "learning_rate": 1.5444403197841345e-05,
470
+ "loss": 1.5475,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.14,
475
+ "learning_rate": 1.5324618822886167e-05,
476
+ "loss": 1.5414,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.14,
481
+ "learning_rate": 1.5203758487233677e-05,
482
+ "loss": 1.5411,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.14,
487
+ "learning_rate": 1.5081846613471736e-05,
488
+ "loss": 1.5498,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.14,
493
+ "learning_rate": 1.4958907836675467e-05,
494
+ "loss": 1.5434,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.14,
499
+ "learning_rate": 1.4834966999429179e-05,
500
+ "loss": 1.5594,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.15,
505
+ "learning_rate": 1.4710049146806348e-05,
506
+ "loss": 1.538,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.15,
511
+ "learning_rate": 1.4584179521308703e-05,
512
+ "loss": 1.5279,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.15,
517
+ "learning_rate": 1.4457383557765385e-05,
518
+ "loss": 1.5677,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.15,
523
+ "learning_rate": 1.4329686878193271e-05,
524
+ "loss": 1.5504,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.15,
529
+ "learning_rate": 1.4201115286619464e-05,
530
+ "loss": 1.5561,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.15,
535
+ "learning_rate": 1.4071694763866988e-05,
536
+ "loss": 1.5122,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.16,
541
+ "learning_rate": 1.3941451462304778e-05,
542
+ "loss": 1.5893,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.16,
547
+ "learning_rate": 1.3810411700563005e-05,
548
+ "loss": 1.5561,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.16,
553
+ "learning_rate": 1.3678601958214779e-05,
554
+ "loss": 1.5287,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.16,
559
+ "learning_rate": 1.3546048870425356e-05,
560
+ "loss": 1.5305,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.16,
565
+ "learning_rate": 1.3412779222569907e-05,
566
+ "loss": 1.5191,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.17,
571
+ "learning_rate": 1.3278819944820893e-05,
572
+ "loss": 1.5404,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.17,
577
+ "learning_rate": 1.314419810670624e-05,
578
+ "loss": 1.5356,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.17,
583
+ "learning_rate": 1.3008940911639302e-05,
584
+ "loss": 1.5509,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.17,
589
+ "learning_rate": 1.2873075691421808e-05,
590
+ "loss": 1.5729,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.17,
595
+ "learning_rate": 1.2736629900720832e-05,
596
+ "loss": 1.5401,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.17,
601
+ "learning_rate": 1.2599631111520956e-05,
602
+ "loss": 1.5466,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.18,
607
+ "learning_rate": 1.2462107007552726e-05,
608
+ "loss": 1.5614,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.18,
613
+ "learning_rate": 1.2324085378698529e-05,
614
+ "loss": 1.5177,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.18,
619
+ "learning_rate": 1.2185594115376991e-05,
620
+ "loss": 1.534,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.18,
625
+ "learning_rate": 1.2046661202907101e-05,
626
+ "loss": 1.5641,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.18,
631
+ "learning_rate": 1.1907314715853138e-05,
632
+ "loss": 1.5361,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.18,
637
+ "learning_rate": 1.176758281235155e-05,
638
+ "loss": 1.5613,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.19,
643
+ "learning_rate": 1.1627493728420978e-05,
644
+ "loss": 1.5139,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.19,
649
+ "learning_rate": 1.1487075772256517e-05,
650
+ "loss": 1.5168,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.19,
655
+ "learning_rate": 1.1346357318509395e-05,
656
+ "loss": 1.5248,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.19,
661
+ "learning_rate": 1.1205366802553231e-05,
662
+ "loss": 1.5336,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.19,
667
+ "learning_rate": 1.1064132714738024e-05,
668
+ "loss": 1.5257,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.2,
673
+ "learning_rate": 1.092268359463302e-05,
674
+ "loss": 1.5574,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.2,
679
+ "learning_rate": 1.0781048025259648e-05,
680
+ "loss": 1.5435,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.2,
685
+ "learning_rate": 1.0639254627315658e-05,
686
+ "loss": 1.5381,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.2,
691
+ "learning_rate": 1.049733205339167e-05,
692
+ "loss": 1.5247,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.2,
697
+ "learning_rate": 1.0355308982181254e-05,
698
+ "loss": 1.5423,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.2,
703
+ "learning_rate": 1.0213214112685747e-05,
704
+ "loss": 1.5186,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.21,
709
+ "learning_rate": 1.0071076158414977e-05,
710
+ "loss": 1.5536,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.21,
715
+ "learning_rate": 9.928923841585025e-06,
716
+ "loss": 1.5147,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.21,
721
+ "learning_rate": 9.786785887314255e-06,
722
+ "loss": 1.5233,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.21,
727
+ "learning_rate": 9.644691017818752e-06,
728
+ "loss": 1.549,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.21,
733
+ "learning_rate": 9.502667946608332e-06,
734
+ "loss": 1.5046,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.21,
739
+ "learning_rate": 9.360745372684346e-06,
740
+ "loss": 1.5089,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.22,
745
+ "learning_rate": 9.218951974740354e-06,
746
+ "loss": 1.5225,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.22,
751
+ "learning_rate": 9.07731640536698e-06,
752
+ "loss": 1.5566,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.22,
757
+ "learning_rate": 8.935867285261977e-06,
758
+ "loss": 1.4955,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.22,
763
+ "learning_rate": 8.79463319744677e-06,
764
+ "loss": 1.5357,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.22,
769
+ "learning_rate": 8.653642681490608e-06,
770
+ "loss": 1.5426,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.22,
775
+ "learning_rate": 8.512924227743482e-06,
776
+ "loss": 1.5394,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.23,
781
+ "learning_rate": 8.372506271579022e-06,
782
+ "loss": 1.5105,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.23,
787
+ "learning_rate": 8.232417187648454e-06,
788
+ "loss": 1.5238,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.23,
793
+ "learning_rate": 8.092685284146865e-06,
794
+ "loss": 1.5085,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.23,
799
+ "learning_rate": 7.953338797092902e-06,
800
+ "loss": 1.4983,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.23,
805
+ "learning_rate": 7.814405884623012e-06,
806
+ "loss": 1.5384,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.24,
811
+ "learning_rate": 7.675914621301476e-06,
812
+ "loss": 1.5294,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.24,
817
+ "learning_rate": 7.5378929924472735e-06,
818
+ "loss": 1.558,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.24,
823
+ "learning_rate": 7.400368888479048e-06,
824
+ "loss": 1.5188,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.24,
829
+ "learning_rate": 7.263370099279173e-06,
830
+ "loss": 1.5527,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.24,
835
+ "learning_rate": 7.126924308578196e-06,
836
+ "loss": 1.5368,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.24,
841
+ "learning_rate": 6.9910590883607e-06,
842
+ "loss": 1.5541,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.25,
847
+ "learning_rate": 6.855801893293765e-06,
848
+ "loss": 1.5142,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.25,
853
+ "learning_rate": 6.721180055179113e-06,
854
+ "loss": 1.524,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.25,
859
+ "learning_rate": 6.587220777430097e-06,
860
+ "loss": 1.5234,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.25,
865
+ "learning_rate": 6.453951129574644e-06,
866
+ "loss": 1.5979,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.25,
871
+ "learning_rate": 6.321398041785225e-06,
872
+ "loss": 1.588,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.25,
877
+ "learning_rate": 6.189588299436997e-06,
878
+ "loss": 1.4905,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.26,
883
+ "learning_rate": 6.058548537695225e-06,
884
+ "loss": 1.5129,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.26,
889
+ "learning_rate": 5.928305236133016e-06,
890
+ "loss": 1.5519,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.26,
895
+ "learning_rate": 5.798884713380542e-06,
896
+ "loss": 1.5366,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.26,
901
+ "learning_rate": 5.67031312180673e-06,
902
+ "loss": 1.5418,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.26,
907
+ "learning_rate": 5.542616442234618e-06,
908
+ "loss": 1.5212,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.27,
913
+ "learning_rate": 5.415820478691301e-06,
914
+ "loss": 1.5012,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.27,
919
+ "learning_rate": 5.2899508531936526e-06,
920
+ "loss": 1.542,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.27,
925
+ "learning_rate": 5.165033000570825e-06,
926
+ "loss": 1.5637,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.27,
931
+ "learning_rate": 5.041092163324537e-06,
932
+ "loss": 1.5441,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.27,
937
+ "learning_rate": 4.918153386528271e-06,
938
+ "loss": 1.5215,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.27,
943
+ "learning_rate": 4.7962415127663265e-06,
944
+ "loss": 1.5035,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.28,
949
+ "learning_rate": 4.675381177113837e-06,
950
+ "loss": 1.5253,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.28,
955
+ "learning_rate": 4.555596802158653e-06,
956
+ "loss": 1.5,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.28,
961
+ "learning_rate": 4.436912593066241e-06,
962
+ "loss": 1.5098,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.28,
967
+ "learning_rate": 4.319352532688444e-06,
968
+ "loss": 1.5607,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.28,
973
+ "learning_rate": 4.2029403767172175e-06,
974
+ "loss": 1.5356,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.28,
979
+ "learning_rate": 4.087699648884248e-06,
980
+ "loss": 1.5478,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.29,
985
+ "learning_rate": 3.973653636207437e-06,
986
+ "loss": 1.5812,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.29,
991
+ "learning_rate": 3.860825384285247e-06,
992
+ "loss": 1.4965,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.29,
997
+ "learning_rate": 3.7492376926397966e-06,
998
+ "loss": 1.5407,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.29,
1003
+ "learning_rate": 3.6389131101096953e-06,
1004
+ "loss": 1.4986,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.29,
1009
+ "learning_rate": 3.529873930293546e-06,
1010
+ "loss": 1.5161,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.3,
1015
+ "learning_rate": 3.422142187045011e-06,
1016
+ "loss": 1.5216,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.3,
1021
+ "learning_rate": 3.3157396500203655e-06,
1022
+ "loss": 1.5343,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.3,
1027
+ "learning_rate": 3.2106878202794513e-06,
1028
+ "loss": 1.4906,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.3,
1033
+ "learning_rate": 3.1070079259408934e-06,
1034
+ "loss": 1.5339,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.3,
1039
+ "learning_rate": 3.004720917892464e-06,
1040
+ "loss": 1.5335,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.3,
1045
+ "learning_rate": 2.90384746555749e-06,
1046
+ "loss": 1.4958,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.31,
1051
+ "learning_rate": 2.804407952718119e-06,
1052
+ "loss": 1.4891,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.31,
1057
+ "learning_rate": 2.7064224733963197e-06,
1058
+ "loss": 1.5082,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.31,
1063
+ "learning_rate": 2.6099108277934105e-06,
1064
+ "loss": 1.5197,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.31,
1069
+ "learning_rate": 2.514892518288988e-06,
1070
+ "loss": 1.5156,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.31,
1075
+ "learning_rate": 2.421386745500034e-06,
1076
+ "loss": 1.5117,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.31,
1081
+ "learning_rate": 2.329412404400969e-06,
1082
+ "loss": 1.5217,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.32,
1087
+ "learning_rate": 2.238988080505513e-06,
1088
+ "loss": 1.5377,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.32,
1093
+ "learning_rate": 2.150132046111054e-06,
1094
+ "loss": 1.5183,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.32,
1099
+ "learning_rate": 2.0628622566063063e-06,
1100
+ "loss": 1.5288,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.32,
1105
+ "learning_rate": 1.977196346843019e-06,
1106
+ "loss": 1.5509,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.32,
1111
+ "learning_rate": 1.8931516275724527e-06,
1112
+ "loss": 1.4979,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.33,
1117
+ "learning_rate": 1.8107450819473505e-06,
1118
+ "loss": 1.5506,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.33,
1123
+ "learning_rate": 1.7299933620900945e-06,
1124
+ "loss": 1.5076,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.33,
1129
+ "learning_rate": 1.6509127857277784e-06,
1130
+ "loss": 1.5278,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.33,
1135
+ "learning_rate": 1.573519332894824e-06,
1136
+ "loss": 1.5406,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.33,
1141
+ "learning_rate": 1.4978286427038602e-06,
1142
+ "loss": 1.5436,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.33,
1147
+ "learning_rate": 1.4238560101854815e-06,
1148
+ "loss": 1.4894,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.34,
1153
+ "learning_rate": 1.3516163831975337e-06,
1154
+ "loss": 1.4934,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.34,
1159
+ "learning_rate": 1.2811243594045697e-06,
1160
+ "loss": 1.495,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.34,
1165
+ "learning_rate": 1.2123941833280472e-06,
1166
+ "loss": 1.5111,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.34,
1171
+ "learning_rate": 1.1454397434679022e-06,
1172
+ "loss": 1.5202,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.34,
1177
+ "learning_rate": 1.080274569496057e-06,
1178
+ "loss": 1.5215,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.34,
1183
+ "learning_rate": 1.0169118295224488e-06,
1184
+ "loss": 1.5132,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.35,
1189
+ "learning_rate": 9.55364327434105e-07,
1190
+ "loss": 1.5496,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.35,
1195
+ "learning_rate": 8.956445003078351e-07,
1196
+ "loss": 1.5646,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.35,
1201
+ "learning_rate": 8.377644158970277e-07,
1202
+ "loss": 1.5008,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.35,
1207
+ "learning_rate": 7.81735770193085e-07,
1208
+ "loss": 1.5344,
1209
+ "step": 200
1210
+ },
1211
+ {
1212
+ "epoch": 0.35,
1213
+ "learning_rate": 7.275698850619861e-07,
1214
+ "loss": 1.51,
1215
+ "step": 201
1216
+ },
1217
+ {
1218
+ "epoch": 0.36,
1219
+ "learning_rate": 6.752777059564431e-07,
1220
+ "loss": 1.5111,
1221
+ "step": 202
1222
+ },
1223
+ {
1224
+ "epoch": 0.36,
1225
+ "learning_rate": 6.248697997041219e-07,
1226
+ "loss": 1.5183,
1227
+ "step": 203
1228
+ },
1229
+ {
1230
+ "epoch": 0.36,
1231
+ "learning_rate": 5.763563523723769e-07,
1232
+ "loss": 1.5033,
1233
+ "step": 204
1234
+ },
1235
+ {
1236
+ "epoch": 0.36,
1237
+ "learning_rate": 5.29747167209923e-07,
1238
+ "loss": 1.5569,
1239
+ "step": 205
1240
+ },
1241
+ {
1242
+ "epoch": 0.36,
1243
+ "learning_rate": 4.850516626658585e-07,
1244
+ "loss": 1.5635,
1245
+ "step": 206
1246
+ },
1247
+ {
1248
+ "epoch": 0.36,
1249
+ "learning_rate": 4.4227887048646335e-07,
1250
+ "loss": 1.5331,
1251
+ "step": 207
1252
+ },
1253
+ {
1254
+ "epoch": 0.37,
1255
+ "learning_rate": 4.014374338901206e-07,
1256
+ "loss": 1.5119,
1257
+ "step": 208
1258
+ },
1259
+ {
1260
+ "epoch": 0.37,
1261
+ "learning_rate": 3.6253560582076075e-07,
1262
+ "loss": 1.5153,
1263
+ "step": 209
1264
+ },
1265
+ {
1266
+ "epoch": 0.37,
1267
+ "learning_rate": 3.255812472801689e-07,
1268
+ "loss": 1.5168,
1269
+ "step": 210
1270
+ },
1271
+ {
1272
+ "epoch": 0.37,
1273
+ "learning_rate": 2.905818257394799e-07,
1274
+ "loss": 1.5449,
1275
+ "step": 211
1276
+ },
1277
+ {
1278
+ "epoch": 0.37,
1279
+ "learning_rate": 2.5754441363021854e-07,
1280
+ "loss": 1.5279,
1281
+ "step": 212
1282
+ },
1283
+ {
1284
+ "epoch": 0.37,
1285
+ "learning_rate": 2.264756869151441e-07,
1286
+ "loss": 1.5379,
1287
+ "step": 213
1288
+ },
1289
+ {
1290
+ "epoch": 0.38,
1291
+ "learning_rate": 1.973819237392205e-07,
1292
+ "loss": 1.5277,
1293
+ "step": 214
1294
+ },
1295
+ {
1296
+ "epoch": 0.38,
1297
+ "learning_rate": 1.7026900316098217e-07,
1298
+ "loss": 1.5191,
1299
+ "step": 215
1300
+ },
1301
+ {
1302
+ "epoch": 0.38,
1303
+ "learning_rate": 1.4514240396452438e-07,
1304
+ "loss": 1.4924,
1305
+ "step": 216
1306
+ },
1307
+ {
1308
+ "epoch": 0.38,
1309
+ "learning_rate": 1.2200720355239893e-07,
1310
+ "loss": 1.5482,
1311
+ "step": 217
1312
+ },
1313
+ {
1314
+ "epoch": 0.38,
1315
+ "learning_rate": 1.0086807691960243e-07,
1316
+ "loss": 1.5033,
1317
+ "step": 218
1318
+ },
1319
+ {
1320
+ "epoch": 0.38,
1321
+ "learning_rate": 8.172929570889553e-08,
1322
+ "loss": 1.5469,
1323
+ "step": 219
1324
+ },
1325
+ {
1326
+ "epoch": 0.39,
1327
+ "learning_rate": 6.459472734760997e-08,
1328
+ "loss": 1.5517,
1329
+ "step": 220
1330
+ },
1331
+ {
1332
+ "epoch": 0.39,
1333
+ "learning_rate": 4.9467834266154756e-08,
1334
+ "loss": 1.5006,
1335
+ "step": 221
1336
+ },
1337
+ {
1338
+ "epoch": 0.39,
1339
+ "learning_rate": 3.635167319834709e-08,
1340
+ "loss": 1.5133,
1341
+ "step": 222
1342
+ },
1343
+ {
1344
+ "epoch": 0.39,
1345
+ "learning_rate": 2.524889456373525e-08,
1346
+ "loss": 1.5053,
1347
+ "step": 223
1348
+ },
1349
+ {
1350
+ "epoch": 0.39,
1351
+ "learning_rate": 1.6161741932017026e-08,
1352
+ "loss": 1.4884,
1353
+ "step": 224
1354
+ },
1355
+ {
1356
+ "epoch": 0.4,
1357
+ "learning_rate": 9.092051569674632e-09,
1358
+ "loss": 1.4829,
1359
+ "step": 225
1360
+ },
1361
+ {
1362
+ "epoch": 0.4,
1363
+ "learning_rate": 4.041252068918145e-09,
1364
+ "loss": 1.5512,
1365
+ "step": 226
1366
+ },
1367
+ {
1368
+ "epoch": 0.4,
1369
+ "learning_rate": 1.0103640590064524e-09,
1370
+ "loss": 1.5033,
1371
+ "step": 227
1372
+ },
1373
+ {
1374
+ "epoch": 0.4,
1375
+ "learning_rate": 0.0,
1376
+ "loss": 1.514,
1377
+ "step": 228
1378
+ },
1379
+ {
1380
+ "epoch": 0.4,
1381
+ "step": 228,
1382
+ "total_flos": 2.7771263153025843e+17,
1383
+ "train_loss": 1.567653910632719,
1384
+ "train_runtime": 13699.6849,
1385
+ "train_samples_per_second": 17.011,
1386
+ "train_steps_per_second": 0.017
1387
+ }
1388
+ ],
1389
+ "logging_steps": 1.0,
1390
+ "max_steps": 228,
1391
+ "num_input_tokens_seen": 0,
1392
+ "num_train_epochs": 1,
1393
+ "save_steps": 50000,
1394
+ "total_flos": 2.7771263153025843e+17,
1395
+ "train_batch_size": 2,
1396
+ "trial_name": null,
1397
+ "trial_params": null
1398
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1528c2091a3594b8f894b6174080c74c3574828867430d04b8e2c5e16c1d2b61
3
+ size 5240
vocab.json ADDED
The diff for this file is too large to render. See raw diff