EC2 Default User commited on
Commit
8494dcb
·
1 Parent(s): 5228d78

add ckpt for epoch 1

Browse files
checkpoint-13434/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-large-v3",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 1280,
17
+ "decoder_attention_heads": 20,
18
+ "decoder_ffn_dim": 5120,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 32,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 20,
24
+ "encoder_ffn_dim": 5120,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 32,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": null,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
+ "max_length": 448,
38
+ "max_source_positions": 1500,
39
+ "max_target_positions": 448,
40
+ "median_filter_width": 7,
41
+ "model_type": "whisper",
42
+ "num_hidden_layers": 32,
43
+ "num_mel_bins": 128,
44
+ "pad_token_id": 50256,
45
+ "scale_embedding": false,
46
+ "suppress_tokens": [],
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.37.2",
49
+ "use_cache": true,
50
+ "use_weighted_layer_sum": false,
51
+ "vocab_size": 51866
52
+ }
checkpoint-13434/generation_config.json ADDED
@@ -0,0 +1,265 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 7,
5
+ 0
6
+ ],
7
+ [
8
+ 10,
9
+ 17
10
+ ],
11
+ [
12
+ 12,
13
+ 18
14
+ ],
15
+ [
16
+ 13,
17
+ 12
18
+ ],
19
+ [
20
+ 16,
21
+ 1
22
+ ],
23
+ [
24
+ 17,
25
+ 14
26
+ ],
27
+ [
28
+ 19,
29
+ 11
30
+ ],
31
+ [
32
+ 21,
33
+ 4
34
+ ],
35
+ [
36
+ 24,
37
+ 1
38
+ ],
39
+ [
40
+ 25,
41
+ 6
42
+ ]
43
+ ],
44
+ "begin_suppress_tokens": [
45
+ 220,
46
+ 50257
47
+ ],
48
+ "bos_token_id": 50257,
49
+ "decoder_start_token_id": 50258,
50
+ "eos_token_id": 50257,
51
+ "forced_decoder_ids": [
52
+ [
53
+ 1,
54
+ null
55
+ ],
56
+ [
57
+ 2,
58
+ 50360
59
+ ]
60
+ ],
61
+ "is_multilingual": true,
62
+ "lang_to_id": {
63
+ "<|af|>": 50327,
64
+ "<|am|>": 50334,
65
+ "<|ar|>": 50272,
66
+ "<|as|>": 50350,
67
+ "<|az|>": 50304,
68
+ "<|ba|>": 50355,
69
+ "<|be|>": 50330,
70
+ "<|bg|>": 50292,
71
+ "<|bn|>": 50302,
72
+ "<|bo|>": 50347,
73
+ "<|br|>": 50309,
74
+ "<|bs|>": 50315,
75
+ "<|ca|>": 50270,
76
+ "<|cs|>": 50283,
77
+ "<|cy|>": 50297,
78
+ "<|da|>": 50285,
79
+ "<|de|>": 50261,
80
+ "<|el|>": 50281,
81
+ "<|en|>": 50259,
82
+ "<|es|>": 50262,
83
+ "<|et|>": 50307,
84
+ "<|eu|>": 50310,
85
+ "<|fa|>": 50300,
86
+ "<|fi|>": 50277,
87
+ "<|fo|>": 50338,
88
+ "<|fr|>": 50265,
89
+ "<|gl|>": 50319,
90
+ "<|gu|>": 50333,
91
+ "<|haw|>": 50352,
92
+ "<|ha|>": 50354,
93
+ "<|he|>": 50279,
94
+ "<|hi|>": 50276,
95
+ "<|hr|>": 50291,
96
+ "<|ht|>": 50339,
97
+ "<|hu|>": 50286,
98
+ "<|hy|>": 50312,
99
+ "<|id|>": 50275,
100
+ "<|is|>": 50311,
101
+ "<|it|>": 50274,
102
+ "<|ja|>": 50266,
103
+ "<|jw|>": 50356,
104
+ "<|ka|>": 50329,
105
+ "<|kk|>": 50316,
106
+ "<|km|>": 50323,
107
+ "<|kn|>": 50306,
108
+ "<|ko|>": 50264,
109
+ "<|la|>": 50294,
110
+ "<|lb|>": 50345,
111
+ "<|ln|>": 50353,
112
+ "<|lo|>": 50336,
113
+ "<|lt|>": 50293,
114
+ "<|lv|>": 50301,
115
+ "<|mg|>": 50349,
116
+ "<|mi|>": 50295,
117
+ "<|mk|>": 50308,
118
+ "<|ml|>": 50296,
119
+ "<|mn|>": 50314,
120
+ "<|mr|>": 50320,
121
+ "<|ms|>": 50282,
122
+ "<|mt|>": 50343,
123
+ "<|my|>": 50346,
124
+ "<|ne|>": 50313,
125
+ "<|nl|>": 50271,
126
+ "<|nn|>": 50342,
127
+ "<|no|>": 50288,
128
+ "<|oc|>": 50328,
129
+ "<|pa|>": 50321,
130
+ "<|pl|>": 50269,
131
+ "<|ps|>": 50340,
132
+ "<|pt|>": 50267,
133
+ "<|ro|>": 50284,
134
+ "<|ru|>": 50263,
135
+ "<|sa|>": 50344,
136
+ "<|sd|>": 50332,
137
+ "<|si|>": 50322,
138
+ "<|sk|>": 50298,
139
+ "<|sl|>": 50305,
140
+ "<|sn|>": 50324,
141
+ "<|so|>": 50326,
142
+ "<|sq|>": 50317,
143
+ "<|sr|>": 50303,
144
+ "<|su|>": 50357,
145
+ "<|sv|>": 50273,
146
+ "<|sw|>": 50318,
147
+ "<|ta|>": 50287,
148
+ "<|te|>": 50299,
149
+ "<|tg|>": 50331,
150
+ "<|th|>": 50289,
151
+ "<|tk|>": 50341,
152
+ "<|tl|>": 50348,
153
+ "<|tr|>": 50268,
154
+ "<|tt|>": 50351,
155
+ "<|uk|>": 50280,
156
+ "<|ur|>": 50290,
157
+ "<|uz|>": 50337,
158
+ "<|vi|>": 50278,
159
+ "<|yi|>": 50335,
160
+ "<|yo|>": 50325,
161
+ "<|yue|>": 50358,
162
+ "<|zh|>": 50260
163
+ },
164
+ "max_initial_timestamp_index": 50,
165
+ "max_length": 448,
166
+ "no_timestamps_token_id": 50364,
167
+ "pad_token_id": 50257,
168
+ "prev_sot_token_id": 50362,
169
+ "return_timestamps": false,
170
+ "suppress_tokens": [
171
+ 1,
172
+ 2,
173
+ 7,
174
+ 8,
175
+ 9,
176
+ 10,
177
+ 14,
178
+ 25,
179
+ 26,
180
+ 27,
181
+ 28,
182
+ 29,
183
+ 31,
184
+ 58,
185
+ 59,
186
+ 60,
187
+ 61,
188
+ 62,
189
+ 63,
190
+ 90,
191
+ 91,
192
+ 92,
193
+ 93,
194
+ 359,
195
+ 503,
196
+ 522,
197
+ 542,
198
+ 873,
199
+ 893,
200
+ 902,
201
+ 918,
202
+ 922,
203
+ 931,
204
+ 1350,
205
+ 1853,
206
+ 1982,
207
+ 2460,
208
+ 2627,
209
+ 3246,
210
+ 3253,
211
+ 3268,
212
+ 3536,
213
+ 3846,
214
+ 3961,
215
+ 4183,
216
+ 4667,
217
+ 6585,
218
+ 6647,
219
+ 7273,
220
+ 9061,
221
+ 9383,
222
+ 10428,
223
+ 10929,
224
+ 11938,
225
+ 12033,
226
+ 12331,
227
+ 12562,
228
+ 13793,
229
+ 14157,
230
+ 14635,
231
+ 15265,
232
+ 15618,
233
+ 16553,
234
+ 16604,
235
+ 18362,
236
+ 18956,
237
+ 20075,
238
+ 21675,
239
+ 22520,
240
+ 26130,
241
+ 26161,
242
+ 26435,
243
+ 28279,
244
+ 29464,
245
+ 31650,
246
+ 32302,
247
+ 32470,
248
+ 36865,
249
+ 42863,
250
+ 47425,
251
+ 49870,
252
+ 50254,
253
+ 50258,
254
+ 50359,
255
+ 50360,
256
+ 50361,
257
+ 50362,
258
+ 50363
259
+ ],
260
+ "task_to_id": {
261
+ "transcribe": 50360,
262
+ "translate": 50359
263
+ },
264
+ "transformers_version": "4.37.2"
265
+ }
checkpoint-13434/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e104c5d94c9f70c586d91edff23454f3991abc05c871d8fef14719d19ca7646
3
+ size 4993448880
checkpoint-13434/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00416544c06480dd667961484e6d60eefb56117b6d19ea00becd34ff3e22a455
3
+ size 1180663192
checkpoint-13434/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-13434/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fae0f99004916a2f5a93f75382ac922b7305fcc4c75a4373bfe8c928f1df3a5
3
+ size 3095446256
checkpoint-13434/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 128,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
checkpoint-13434/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daaa2fa80992dd09b881e96173980f85cdc14a9686276d51ad5f2b7779b8f965
3
+ size 14244
checkpoint-13434/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455dffed108ac3695c9b8cd976d3101391be365934df585b007d4623e632d6d6
3
+ size 1064
checkpoint-13434/trainer_state.json ADDED
@@ -0,0 +1,1275 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 13434,
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": 2.5227460711331677e-08,
14
+ "loss": 3.3575,
15
+ "step": 64
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 5.128205128205128e-08,
20
+ "loss": 3.3023,
21
+ "step": 128
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 7.775020678246484e-08,
26
+ "loss": 2.9134,
27
+ "step": 192
28
+ },
29
+ {
30
+ "epoch": 0.02,
31
+ "learning_rate": 1.0421836228287841e-07,
32
+ "loss": 2.7766,
33
+ "step": 256
34
+ },
35
+ {
36
+ "epoch": 0.02,
37
+ "learning_rate": 1.3068651778329198e-07,
38
+ "loss": 2.6203,
39
+ "step": 320
40
+ },
41
+ {
42
+ "epoch": 0.03,
43
+ "learning_rate": 1.5715467328370554e-07,
44
+ "loss": 2.221,
45
+ "step": 384
46
+ },
47
+ {
48
+ "epoch": 0.03,
49
+ "learning_rate": 1.836228287841191e-07,
50
+ "loss": 1.6761,
51
+ "step": 448
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "learning_rate": 2.1009098428453268e-07,
56
+ "loss": 1.3371,
57
+ "step": 512
58
+ },
59
+ {
60
+ "epoch": 0.04,
61
+ "learning_rate": 2.3655913978494625e-07,
62
+ "loss": 1.102,
63
+ "step": 576
64
+ },
65
+ {
66
+ "epoch": 0.05,
67
+ "learning_rate": 2.6302729528535976e-07,
68
+ "loss": 0.9863,
69
+ "step": 640
70
+ },
71
+ {
72
+ "epoch": 0.05,
73
+ "learning_rate": 2.8949545078577336e-07,
74
+ "loss": 0.8123,
75
+ "step": 704
76
+ },
77
+ {
78
+ "epoch": 0.06,
79
+ "learning_rate": 3.159636062861869e-07,
80
+ "loss": 0.6005,
81
+ "step": 768
82
+ },
83
+ {
84
+ "epoch": 0.06,
85
+ "learning_rate": 3.424317617866005e-07,
86
+ "loss": 0.4275,
87
+ "step": 832
88
+ },
89
+ {
90
+ "epoch": 0.07,
91
+ "learning_rate": 3.6889991728701403e-07,
92
+ "loss": 0.4868,
93
+ "step": 896
94
+ },
95
+ {
96
+ "epoch": 0.07,
97
+ "learning_rate": 3.9536807278742763e-07,
98
+ "loss": 0.4454,
99
+ "step": 960
100
+ },
101
+ {
102
+ "epoch": 0.08,
103
+ "learning_rate": 4.2183622828784117e-07,
104
+ "loss": 0.3431,
105
+ "step": 1024
106
+ },
107
+ {
108
+ "epoch": 0.08,
109
+ "learning_rate": 4.4830438378825477e-07,
110
+ "loss": 0.3373,
111
+ "step": 1088
112
+ },
113
+ {
114
+ "epoch": 0.09,
115
+ "learning_rate": 4.743589743589743e-07,
116
+ "loss": 0.351,
117
+ "step": 1152
118
+ },
119
+ {
120
+ "epoch": 0.09,
121
+ "learning_rate": 5.00827129859388e-07,
122
+ "loss": 0.3565,
123
+ "step": 1216
124
+ },
125
+ {
126
+ "epoch": 0.1,
127
+ "learning_rate": 5.272952853598015e-07,
128
+ "loss": 0.2179,
129
+ "step": 1280
130
+ },
131
+ {
132
+ "epoch": 0.1,
133
+ "learning_rate": 5.537634408602149e-07,
134
+ "loss": 0.3892,
135
+ "step": 1344
136
+ },
137
+ {
138
+ "epoch": 0.1,
139
+ "learning_rate": 5.802315963606285e-07,
140
+ "loss": 0.3388,
141
+ "step": 1408
142
+ },
143
+ {
144
+ "epoch": 0.11,
145
+ "learning_rate": 6.066997518610421e-07,
146
+ "loss": 0.4345,
147
+ "step": 1472
148
+ },
149
+ {
150
+ "epoch": 0.11,
151
+ "learning_rate": 6.331679073614557e-07,
152
+ "loss": 0.1948,
153
+ "step": 1536
154
+ },
155
+ {
156
+ "epoch": 0.12,
157
+ "learning_rate": 6.596360628618692e-07,
158
+ "loss": 0.2907,
159
+ "step": 1600
160
+ },
161
+ {
162
+ "epoch": 0.12,
163
+ "learning_rate": 6.861042183622828e-07,
164
+ "loss": 0.3393,
165
+ "step": 1664
166
+ },
167
+ {
168
+ "epoch": 0.13,
169
+ "learning_rate": 7.125723738626964e-07,
170
+ "loss": 0.2568,
171
+ "step": 1728
172
+ },
173
+ {
174
+ "epoch": 0.13,
175
+ "learning_rate": 7.3904052936311e-07,
176
+ "loss": 0.3041,
177
+ "step": 1792
178
+ },
179
+ {
180
+ "epoch": 0.14,
181
+ "learning_rate": 7.655086848635235e-07,
182
+ "loss": 0.3316,
183
+ "step": 1856
184
+ },
185
+ {
186
+ "epoch": 0.14,
187
+ "learning_rate": 7.919768403639371e-07,
188
+ "loss": 0.3193,
189
+ "step": 1920
190
+ },
191
+ {
192
+ "epoch": 0.15,
193
+ "learning_rate": 8.184449958643507e-07,
194
+ "loss": 0.3393,
195
+ "step": 1984
196
+ },
197
+ {
198
+ "epoch": 0.15,
199
+ "learning_rate": 8.449131513647643e-07,
200
+ "loss": 0.2933,
201
+ "step": 2048
202
+ },
203
+ {
204
+ "epoch": 0.16,
205
+ "learning_rate": 8.713813068651778e-07,
206
+ "loss": 0.236,
207
+ "step": 2112
208
+ },
209
+ {
210
+ "epoch": 0.16,
211
+ "learning_rate": 8.978494623655913e-07,
212
+ "loss": 0.305,
213
+ "step": 2176
214
+ },
215
+ {
216
+ "epoch": 0.17,
217
+ "learning_rate": 9.243176178660049e-07,
218
+ "loss": 0.2158,
219
+ "step": 2240
220
+ },
221
+ {
222
+ "epoch": 0.17,
223
+ "learning_rate": 9.507857733664185e-07,
224
+ "loss": 0.3261,
225
+ "step": 2304
226
+ },
227
+ {
228
+ "epoch": 0.18,
229
+ "learning_rate": 9.77253928866832e-07,
230
+ "loss": 0.2282,
231
+ "step": 2368
232
+ },
233
+ {
234
+ "epoch": 0.18,
235
+ "learning_rate": 9.997624326892619e-07,
236
+ "loss": 0.3758,
237
+ "step": 2432
238
+ },
239
+ {
240
+ "epoch": 0.19,
241
+ "learning_rate": 9.980730651462358e-07,
242
+ "loss": 0.2466,
243
+ "step": 2496
244
+ },
245
+ {
246
+ "epoch": 0.19,
247
+ "learning_rate": 9.963836976032098e-07,
248
+ "loss": 0.2283,
249
+ "step": 2560
250
+ },
251
+ {
252
+ "epoch": 0.2,
253
+ "learning_rate": 9.946943300601838e-07,
254
+ "loss": 0.2605,
255
+ "step": 2624
256
+ },
257
+ {
258
+ "epoch": 0.2,
259
+ "learning_rate": 9.930049625171575e-07,
260
+ "loss": 0.2818,
261
+ "step": 2688
262
+ },
263
+ {
264
+ "epoch": 0.2,
265
+ "learning_rate": 9.913155949741315e-07,
266
+ "loss": 0.3004,
267
+ "step": 2752
268
+ },
269
+ {
270
+ "epoch": 0.21,
271
+ "learning_rate": 9.896262274311054e-07,
272
+ "loss": 0.2703,
273
+ "step": 2816
274
+ },
275
+ {
276
+ "epoch": 0.21,
277
+ "learning_rate": 9.879368598880794e-07,
278
+ "loss": 0.2924,
279
+ "step": 2880
280
+ },
281
+ {
282
+ "epoch": 0.22,
283
+ "learning_rate": 9.862474923450532e-07,
284
+ "loss": 0.3661,
285
+ "step": 2944
286
+ },
287
+ {
288
+ "epoch": 0.22,
289
+ "learning_rate": 9.845581248020271e-07,
290
+ "loss": 0.3517,
291
+ "step": 3008
292
+ },
293
+ {
294
+ "epoch": 0.23,
295
+ "learning_rate": 9.82868757259001e-07,
296
+ "loss": 0.2773,
297
+ "step": 3072
298
+ },
299
+ {
300
+ "epoch": 0.23,
301
+ "learning_rate": 9.81179389715975e-07,
302
+ "loss": 0.3023,
303
+ "step": 3136
304
+ },
305
+ {
306
+ "epoch": 0.24,
307
+ "learning_rate": 9.79490022172949e-07,
308
+ "loss": 0.2831,
309
+ "step": 3200
310
+ },
311
+ {
312
+ "epoch": 0.24,
313
+ "learning_rate": 9.77800654629923e-07,
314
+ "loss": 0.2693,
315
+ "step": 3264
316
+ },
317
+ {
318
+ "epoch": 0.25,
319
+ "learning_rate": 9.76111287086897e-07,
320
+ "loss": 0.2534,
321
+ "step": 3328
322
+ },
323
+ {
324
+ "epoch": 0.25,
325
+ "learning_rate": 9.744219195438707e-07,
326
+ "loss": 0.183,
327
+ "step": 3392
328
+ },
329
+ {
330
+ "epoch": 0.26,
331
+ "learning_rate": 9.727325520008446e-07,
332
+ "loss": 0.1786,
333
+ "step": 3456
334
+ },
335
+ {
336
+ "epoch": 0.26,
337
+ "learning_rate": 9.710431844578186e-07,
338
+ "loss": 0.3985,
339
+ "step": 3520
340
+ },
341
+ {
342
+ "epoch": 0.27,
343
+ "learning_rate": 9.693538169147924e-07,
344
+ "loss": 0.2585,
345
+ "step": 3584
346
+ },
347
+ {
348
+ "epoch": 0.27,
349
+ "learning_rate": 9.676644493717663e-07,
350
+ "loss": 0.2088,
351
+ "step": 3648
352
+ },
353
+ {
354
+ "epoch": 0.28,
355
+ "learning_rate": 9.659750818287403e-07,
356
+ "loss": 0.1913,
357
+ "step": 3712
358
+ },
359
+ {
360
+ "epoch": 0.28,
361
+ "learning_rate": 9.642857142857142e-07,
362
+ "loss": 0.2747,
363
+ "step": 3776
364
+ },
365
+ {
366
+ "epoch": 0.29,
367
+ "learning_rate": 9.625963467426882e-07,
368
+ "loss": 0.2283,
369
+ "step": 3840
370
+ },
371
+ {
372
+ "epoch": 0.29,
373
+ "learning_rate": 9.609069791996622e-07,
374
+ "loss": 0.305,
375
+ "step": 3904
376
+ },
377
+ {
378
+ "epoch": 0.3,
379
+ "learning_rate": 9.59217611656636e-07,
380
+ "loss": 0.2648,
381
+ "step": 3968
382
+ },
383
+ {
384
+ "epoch": 0.3,
385
+ "learning_rate": 9.575282441136099e-07,
386
+ "loss": 0.2277,
387
+ "step": 4032
388
+ },
389
+ {
390
+ "epoch": 0.3,
391
+ "learning_rate": 9.558388765705839e-07,
392
+ "loss": 0.2445,
393
+ "step": 4096
394
+ },
395
+ {
396
+ "epoch": 0.31,
397
+ "learning_rate": 9.541495090275578e-07,
398
+ "loss": 0.3094,
399
+ "step": 4160
400
+ },
401
+ {
402
+ "epoch": 0.31,
403
+ "learning_rate": 9.524601414845317e-07,
404
+ "loss": 0.2558,
405
+ "step": 4224
406
+ },
407
+ {
408
+ "epoch": 0.32,
409
+ "learning_rate": 9.507707739415056e-07,
410
+ "loss": 0.2467,
411
+ "step": 4288
412
+ },
413
+ {
414
+ "epoch": 0.32,
415
+ "learning_rate": 9.490814063984796e-07,
416
+ "loss": 0.2412,
417
+ "step": 4352
418
+ },
419
+ {
420
+ "epoch": 0.33,
421
+ "learning_rate": 9.473920388554535e-07,
422
+ "loss": 0.2564,
423
+ "step": 4416
424
+ },
425
+ {
426
+ "epoch": 0.33,
427
+ "learning_rate": 9.457026713124273e-07,
428
+ "loss": 0.2373,
429
+ "step": 4480
430
+ },
431
+ {
432
+ "epoch": 0.34,
433
+ "learning_rate": 9.440133037694013e-07,
434
+ "loss": 0.34,
435
+ "step": 4544
436
+ },
437
+ {
438
+ "epoch": 0.34,
439
+ "learning_rate": 9.423239362263751e-07,
440
+ "loss": 0.2398,
441
+ "step": 4608
442
+ },
443
+ {
444
+ "epoch": 0.35,
445
+ "learning_rate": 9.406345686833491e-07,
446
+ "loss": 0.2493,
447
+ "step": 4672
448
+ },
449
+ {
450
+ "epoch": 0.35,
451
+ "learning_rate": 9.389452011403231e-07,
452
+ "loss": 0.2398,
453
+ "step": 4736
454
+ },
455
+ {
456
+ "epoch": 0.36,
457
+ "learning_rate": 9.37255833597297e-07,
458
+ "loss": 0.2536,
459
+ "step": 4800
460
+ },
461
+ {
462
+ "epoch": 0.36,
463
+ "learning_rate": 9.355664660542709e-07,
464
+ "loss": 0.3538,
465
+ "step": 4864
466
+ },
467
+ {
468
+ "epoch": 0.37,
469
+ "learning_rate": 9.338770985112448e-07,
470
+ "loss": 0.2481,
471
+ "step": 4928
472
+ },
473
+ {
474
+ "epoch": 0.37,
475
+ "learning_rate": 9.321877309682187e-07,
476
+ "loss": 0.2152,
477
+ "step": 4992
478
+ },
479
+ {
480
+ "epoch": 0.38,
481
+ "learning_rate": 9.304983634251927e-07,
482
+ "loss": 0.3056,
483
+ "step": 5056
484
+ },
485
+ {
486
+ "epoch": 0.38,
487
+ "learning_rate": 9.288089958821665e-07,
488
+ "loss": 0.2473,
489
+ "step": 5120
490
+ },
491
+ {
492
+ "epoch": 0.39,
493
+ "learning_rate": 9.271196283391405e-07,
494
+ "loss": 0.234,
495
+ "step": 5184
496
+ },
497
+ {
498
+ "epoch": 0.39,
499
+ "learning_rate": 9.254302607961144e-07,
500
+ "loss": 0.1578,
501
+ "step": 5248
502
+ },
503
+ {
504
+ "epoch": 0.4,
505
+ "learning_rate": 9.237672896209481e-07,
506
+ "loss": 0.2566,
507
+ "step": 5312
508
+ },
509
+ {
510
+ "epoch": 0.4,
511
+ "learning_rate": 9.22077922077922e-07,
512
+ "loss": 0.3794,
513
+ "step": 5376
514
+ },
515
+ {
516
+ "epoch": 0.4,
517
+ "learning_rate": 9.203885545348959e-07,
518
+ "loss": 0.2453,
519
+ "step": 5440
520
+ },
521
+ {
522
+ "epoch": 0.41,
523
+ "learning_rate": 9.186991869918699e-07,
524
+ "loss": 0.2361,
525
+ "step": 5504
526
+ },
527
+ {
528
+ "epoch": 0.41,
529
+ "learning_rate": 9.170098194488438e-07,
530
+ "loss": 0.1734,
531
+ "step": 5568
532
+ },
533
+ {
534
+ "epoch": 0.42,
535
+ "learning_rate": 9.153204519058178e-07,
536
+ "loss": 0.1762,
537
+ "step": 5632
538
+ },
539
+ {
540
+ "epoch": 0.42,
541
+ "learning_rate": 9.136310843627916e-07,
542
+ "loss": 0.2933,
543
+ "step": 5696
544
+ },
545
+ {
546
+ "epoch": 0.43,
547
+ "learning_rate": 9.119417168197655e-07,
548
+ "loss": 0.3152,
549
+ "step": 5760
550
+ },
551
+ {
552
+ "epoch": 0.43,
553
+ "learning_rate": 9.102523492767395e-07,
554
+ "loss": 0.1966,
555
+ "step": 5824
556
+ },
557
+ {
558
+ "epoch": 0.44,
559
+ "learning_rate": 9.085629817337133e-07,
560
+ "loss": 0.298,
561
+ "step": 5888
562
+ },
563
+ {
564
+ "epoch": 0.44,
565
+ "learning_rate": 9.068736141906873e-07,
566
+ "loss": 0.2437,
567
+ "step": 5952
568
+ },
569
+ {
570
+ "epoch": 0.45,
571
+ "learning_rate": 9.051842466476613e-07,
572
+ "loss": 0.305,
573
+ "step": 6016
574
+ },
575
+ {
576
+ "epoch": 0.45,
577
+ "learning_rate": 9.034948791046352e-07,
578
+ "loss": 0.1959,
579
+ "step": 6080
580
+ },
581
+ {
582
+ "epoch": 0.46,
583
+ "learning_rate": 9.018055115616091e-07,
584
+ "loss": 0.2465,
585
+ "step": 6144
586
+ },
587
+ {
588
+ "epoch": 0.46,
589
+ "learning_rate": 9.00116144018583e-07,
590
+ "loss": 0.2624,
591
+ "step": 6208
592
+ },
593
+ {
594
+ "epoch": 0.47,
595
+ "learning_rate": 8.984267764755569e-07,
596
+ "loss": 0.2772,
597
+ "step": 6272
598
+ },
599
+ {
600
+ "epoch": 0.47,
601
+ "learning_rate": 8.967374089325309e-07,
602
+ "loss": 0.2208,
603
+ "step": 6336
604
+ },
605
+ {
606
+ "epoch": 0.48,
607
+ "learning_rate": 8.950480413895047e-07,
608
+ "loss": 0.2695,
609
+ "step": 6400
610
+ },
611
+ {
612
+ "epoch": 0.48,
613
+ "learning_rate": 8.933586738464787e-07,
614
+ "loss": 0.3235,
615
+ "step": 6464
616
+ },
617
+ {
618
+ "epoch": 0.49,
619
+ "learning_rate": 8.916693063034526e-07,
620
+ "loss": 0.2802,
621
+ "step": 6528
622
+ },
623
+ {
624
+ "epoch": 0.49,
625
+ "learning_rate": 8.899799387604265e-07,
626
+ "loss": 0.2383,
627
+ "step": 6592
628
+ },
629
+ {
630
+ "epoch": 0.5,
631
+ "learning_rate": 8.882905712174005e-07,
632
+ "loss": 0.2238,
633
+ "step": 6656
634
+ },
635
+ {
636
+ "epoch": 0.5,
637
+ "learning_rate": 8.866012036743744e-07,
638
+ "loss": 0.2847,
639
+ "step": 6720
640
+ },
641
+ {
642
+ "epoch": 0.5,
643
+ "learning_rate": 8.849118361313483e-07,
644
+ "loss": 0.2713,
645
+ "step": 6784
646
+ },
647
+ {
648
+ "epoch": 0.51,
649
+ "learning_rate": 8.832224685883221e-07,
650
+ "loss": 0.2156,
651
+ "step": 6848
652
+ },
653
+ {
654
+ "epoch": 0.51,
655
+ "learning_rate": 8.815331010452961e-07,
656
+ "loss": 0.2832,
657
+ "step": 6912
658
+ },
659
+ {
660
+ "epoch": 0.52,
661
+ "learning_rate": 8.798437335022701e-07,
662
+ "loss": 0.2675,
663
+ "step": 6976
664
+ },
665
+ {
666
+ "epoch": 0.52,
667
+ "learning_rate": 8.781543659592439e-07,
668
+ "loss": 0.2506,
669
+ "step": 7040
670
+ },
671
+ {
672
+ "epoch": 0.53,
673
+ "learning_rate": 8.764649984162179e-07,
674
+ "loss": 0.2807,
675
+ "step": 7104
676
+ },
677
+ {
678
+ "epoch": 0.53,
679
+ "learning_rate": 8.747756308731918e-07,
680
+ "loss": 0.2802,
681
+ "step": 7168
682
+ },
683
+ {
684
+ "epoch": 0.54,
685
+ "learning_rate": 8.730862633301658e-07,
686
+ "loss": 0.2125,
687
+ "step": 7232
688
+ },
689
+ {
690
+ "epoch": 0.54,
691
+ "learning_rate": 8.713968957871396e-07,
692
+ "loss": 0.2739,
693
+ "step": 7296
694
+ },
695
+ {
696
+ "epoch": 0.55,
697
+ "learning_rate": 8.697075282441135e-07,
698
+ "loss": 0.2341,
699
+ "step": 7360
700
+ },
701
+ {
702
+ "epoch": 0.55,
703
+ "learning_rate": 8.680181607010875e-07,
704
+ "loss": 0.2267,
705
+ "step": 7424
706
+ },
707
+ {
708
+ "epoch": 0.56,
709
+ "learning_rate": 8.663287931580614e-07,
710
+ "loss": 0.3504,
711
+ "step": 7488
712
+ },
713
+ {
714
+ "epoch": 0.56,
715
+ "learning_rate": 8.646394256150353e-07,
716
+ "loss": 0.2675,
717
+ "step": 7552
718
+ },
719
+ {
720
+ "epoch": 0.57,
721
+ "learning_rate": 8.629500580720093e-07,
722
+ "loss": 0.1694,
723
+ "step": 7616
724
+ },
725
+ {
726
+ "epoch": 0.57,
727
+ "learning_rate": 8.612606905289832e-07,
728
+ "loss": 0.2865,
729
+ "step": 7680
730
+ },
731
+ {
732
+ "epoch": 0.58,
733
+ "learning_rate": 8.595713229859571e-07,
734
+ "loss": 0.2737,
735
+ "step": 7744
736
+ },
737
+ {
738
+ "epoch": 0.58,
739
+ "learning_rate": 8.578819554429309e-07,
740
+ "loss": 0.2201,
741
+ "step": 7808
742
+ },
743
+ {
744
+ "epoch": 0.59,
745
+ "learning_rate": 8.561925878999049e-07,
746
+ "loss": 0.1701,
747
+ "step": 7872
748
+ },
749
+ {
750
+ "epoch": 0.59,
751
+ "learning_rate": 8.545032203568789e-07,
752
+ "loss": 0.2566,
753
+ "step": 7936
754
+ },
755
+ {
756
+ "epoch": 0.6,
757
+ "learning_rate": 8.528138528138527e-07,
758
+ "loss": 0.274,
759
+ "step": 8000
760
+ },
761
+ {
762
+ "epoch": 0.6,
763
+ "learning_rate": 8.511244852708267e-07,
764
+ "loss": 0.3413,
765
+ "step": 8064
766
+ },
767
+ {
768
+ "epoch": 0.61,
769
+ "learning_rate": 8.494351177278007e-07,
770
+ "loss": 0.2035,
771
+ "step": 8128
772
+ },
773
+ {
774
+ "epoch": 0.61,
775
+ "learning_rate": 8.477721465526343e-07,
776
+ "loss": 0.2612,
777
+ "step": 8192
778
+ },
779
+ {
780
+ "epoch": 0.61,
781
+ "learning_rate": 8.460827790096083e-07,
782
+ "loss": 0.2322,
783
+ "step": 8256
784
+ },
785
+ {
786
+ "epoch": 0.62,
787
+ "learning_rate": 8.443934114665822e-07,
788
+ "loss": 0.1929,
789
+ "step": 8320
790
+ },
791
+ {
792
+ "epoch": 0.62,
793
+ "learning_rate": 8.427040439235561e-07,
794
+ "loss": 0.2212,
795
+ "step": 8384
796
+ },
797
+ {
798
+ "epoch": 0.63,
799
+ "learning_rate": 8.4101467638053e-07,
800
+ "loss": 0.1912,
801
+ "step": 8448
802
+ },
803
+ {
804
+ "epoch": 0.63,
805
+ "learning_rate": 8.39325308837504e-07,
806
+ "loss": 0.3325,
807
+ "step": 8512
808
+ },
809
+ {
810
+ "epoch": 0.64,
811
+ "learning_rate": 8.376359412944777e-07,
812
+ "loss": 0.2341,
813
+ "step": 8576
814
+ },
815
+ {
816
+ "epoch": 0.64,
817
+ "learning_rate": 8.359465737514517e-07,
818
+ "loss": 0.248,
819
+ "step": 8640
820
+ },
821
+ {
822
+ "epoch": 0.65,
823
+ "learning_rate": 8.342572062084257e-07,
824
+ "loss": 0.268,
825
+ "step": 8704
826
+ },
827
+ {
828
+ "epoch": 0.65,
829
+ "learning_rate": 8.325678386653996e-07,
830
+ "loss": 0.3279,
831
+ "step": 8768
832
+ },
833
+ {
834
+ "epoch": 0.66,
835
+ "learning_rate": 8.308784711223735e-07,
836
+ "loss": 0.2175,
837
+ "step": 8832
838
+ },
839
+ {
840
+ "epoch": 0.66,
841
+ "learning_rate": 8.291891035793475e-07,
842
+ "loss": 0.2641,
843
+ "step": 8896
844
+ },
845
+ {
846
+ "epoch": 0.67,
847
+ "learning_rate": 8.274997360363214e-07,
848
+ "loss": 0.2435,
849
+ "step": 8960
850
+ },
851
+ {
852
+ "epoch": 0.67,
853
+ "learning_rate": 8.258103684932953e-07,
854
+ "loss": 0.208,
855
+ "step": 9024
856
+ },
857
+ {
858
+ "epoch": 0.68,
859
+ "learning_rate": 8.241210009502691e-07,
860
+ "loss": 0.2631,
861
+ "step": 9088
862
+ },
863
+ {
864
+ "epoch": 0.68,
865
+ "learning_rate": 8.224316334072431e-07,
866
+ "loss": 0.2774,
867
+ "step": 9152
868
+ },
869
+ {
870
+ "epoch": 0.69,
871
+ "learning_rate": 8.207422658642171e-07,
872
+ "loss": 0.2279,
873
+ "step": 9216
874
+ },
875
+ {
876
+ "epoch": 0.69,
877
+ "learning_rate": 8.190528983211909e-07,
878
+ "loss": 0.1885,
879
+ "step": 9280
880
+ },
881
+ {
882
+ "epoch": 0.7,
883
+ "learning_rate": 8.173635307781649e-07,
884
+ "loss": 0.2396,
885
+ "step": 9344
886
+ },
887
+ {
888
+ "epoch": 0.7,
889
+ "learning_rate": 8.156741632351388e-07,
890
+ "loss": 0.269,
891
+ "step": 9408
892
+ },
893
+ {
894
+ "epoch": 0.71,
895
+ "learning_rate": 8.139847956921128e-07,
896
+ "loss": 0.315,
897
+ "step": 9472
898
+ },
899
+ {
900
+ "epoch": 0.71,
901
+ "learning_rate": 8.122954281490867e-07,
902
+ "loss": 0.2165,
903
+ "step": 9536
904
+ },
905
+ {
906
+ "epoch": 0.71,
907
+ "learning_rate": 8.106060606060605e-07,
908
+ "loss": 0.2035,
909
+ "step": 9600
910
+ },
911
+ {
912
+ "epoch": 0.72,
913
+ "learning_rate": 8.089166930630345e-07,
914
+ "loss": 0.2472,
915
+ "step": 9664
916
+ },
917
+ {
918
+ "epoch": 0.72,
919
+ "learning_rate": 8.072273255200083e-07,
920
+ "loss": 0.2641,
921
+ "step": 9728
922
+ },
923
+ {
924
+ "epoch": 0.73,
925
+ "learning_rate": 8.055379579769823e-07,
926
+ "loss": 0.1937,
927
+ "step": 9792
928
+ },
929
+ {
930
+ "epoch": 0.73,
931
+ "learning_rate": 8.038485904339563e-07,
932
+ "loss": 0.2108,
933
+ "step": 9856
934
+ },
935
+ {
936
+ "epoch": 0.74,
937
+ "learning_rate": 8.021592228909302e-07,
938
+ "loss": 0.2866,
939
+ "step": 9920
940
+ },
941
+ {
942
+ "epoch": 0.74,
943
+ "learning_rate": 8.004698553479041e-07,
944
+ "loss": 0.2707,
945
+ "step": 9984
946
+ },
947
+ {
948
+ "epoch": 0.75,
949
+ "learning_rate": 7.98780487804878e-07,
950
+ "loss": 0.2249,
951
+ "step": 10048
952
+ },
953
+ {
954
+ "epoch": 0.75,
955
+ "learning_rate": 7.970911202618519e-07,
956
+ "loss": 0.2183,
957
+ "step": 10112
958
+ },
959
+ {
960
+ "epoch": 0.76,
961
+ "learning_rate": 7.954017527188258e-07,
962
+ "loss": 0.234,
963
+ "step": 10176
964
+ },
965
+ {
966
+ "epoch": 0.76,
967
+ "learning_rate": 7.937123851757997e-07,
968
+ "loss": 0.2504,
969
+ "step": 10240
970
+ },
971
+ {
972
+ "epoch": 0.77,
973
+ "learning_rate": 7.920230176327737e-07,
974
+ "loss": 0.1973,
975
+ "step": 10304
976
+ },
977
+ {
978
+ "epoch": 0.77,
979
+ "learning_rate": 7.903336500897477e-07,
980
+ "loss": 0.2003,
981
+ "step": 10368
982
+ },
983
+ {
984
+ "epoch": 0.78,
985
+ "learning_rate": 7.886442825467215e-07,
986
+ "loss": 0.2558,
987
+ "step": 10432
988
+ },
989
+ {
990
+ "epoch": 0.78,
991
+ "learning_rate": 7.869549150036955e-07,
992
+ "loss": 0.2694,
993
+ "step": 10496
994
+ },
995
+ {
996
+ "epoch": 0.79,
997
+ "learning_rate": 7.852655474606694e-07,
998
+ "loss": 0.2633,
999
+ "step": 10560
1000
+ },
1001
+ {
1002
+ "epoch": 0.79,
1003
+ "learning_rate": 7.835761799176432e-07,
1004
+ "loss": 0.2649,
1005
+ "step": 10624
1006
+ },
1007
+ {
1008
+ "epoch": 0.8,
1009
+ "learning_rate": 7.818868123746172e-07,
1010
+ "loss": 0.2874,
1011
+ "step": 10688
1012
+ },
1013
+ {
1014
+ "epoch": 0.8,
1015
+ "learning_rate": 7.801974448315911e-07,
1016
+ "loss": 0.2393,
1017
+ "step": 10752
1018
+ },
1019
+ {
1020
+ "epoch": 0.81,
1021
+ "learning_rate": 7.785080772885651e-07,
1022
+ "loss": 0.2303,
1023
+ "step": 10816
1024
+ },
1025
+ {
1026
+ "epoch": 0.81,
1027
+ "learning_rate": 7.768451061133987e-07,
1028
+ "loss": 0.2417,
1029
+ "step": 10880
1030
+ },
1031
+ {
1032
+ "epoch": 0.81,
1033
+ "learning_rate": 7.751557385703727e-07,
1034
+ "loss": 0.272,
1035
+ "step": 10944
1036
+ },
1037
+ {
1038
+ "epoch": 0.82,
1039
+ "learning_rate": 7.734663710273465e-07,
1040
+ "loss": 0.2005,
1041
+ "step": 11008
1042
+ },
1043
+ {
1044
+ "epoch": 0.82,
1045
+ "learning_rate": 7.717770034843205e-07,
1046
+ "loss": 0.1505,
1047
+ "step": 11072
1048
+ },
1049
+ {
1050
+ "epoch": 0.83,
1051
+ "learning_rate": 7.700876359412945e-07,
1052
+ "loss": 0.2839,
1053
+ "step": 11136
1054
+ },
1055
+ {
1056
+ "epoch": 0.83,
1057
+ "learning_rate": 7.683982683982684e-07,
1058
+ "loss": 0.2805,
1059
+ "step": 11200
1060
+ },
1061
+ {
1062
+ "epoch": 0.84,
1063
+ "learning_rate": 7.667089008552423e-07,
1064
+ "loss": 0.2407,
1065
+ "step": 11264
1066
+ },
1067
+ {
1068
+ "epoch": 0.84,
1069
+ "learning_rate": 7.650195333122162e-07,
1070
+ "loss": 0.1769,
1071
+ "step": 11328
1072
+ },
1073
+ {
1074
+ "epoch": 0.85,
1075
+ "learning_rate": 7.633301657691901e-07,
1076
+ "loss": 0.2223,
1077
+ "step": 11392
1078
+ },
1079
+ {
1080
+ "epoch": 0.85,
1081
+ "learning_rate": 7.61640798226164e-07,
1082
+ "loss": 0.2609,
1083
+ "step": 11456
1084
+ },
1085
+ {
1086
+ "epoch": 0.86,
1087
+ "learning_rate": 7.599514306831379e-07,
1088
+ "loss": 0.3837,
1089
+ "step": 11520
1090
+ },
1091
+ {
1092
+ "epoch": 0.86,
1093
+ "learning_rate": 7.582620631401119e-07,
1094
+ "loss": 0.2162,
1095
+ "step": 11584
1096
+ },
1097
+ {
1098
+ "epoch": 0.87,
1099
+ "learning_rate": 7.565726955970858e-07,
1100
+ "loss": 0.2076,
1101
+ "step": 11648
1102
+ },
1103
+ {
1104
+ "epoch": 0.87,
1105
+ "learning_rate": 7.548833280540597e-07,
1106
+ "loss": 0.266,
1107
+ "step": 11712
1108
+ },
1109
+ {
1110
+ "epoch": 0.88,
1111
+ "learning_rate": 7.531939605110337e-07,
1112
+ "loss": 0.1652,
1113
+ "step": 11776
1114
+ },
1115
+ {
1116
+ "epoch": 0.88,
1117
+ "learning_rate": 7.515045929680076e-07,
1118
+ "loss": 0.2416,
1119
+ "step": 11840
1120
+ },
1121
+ {
1122
+ "epoch": 0.89,
1123
+ "learning_rate": 7.498152254249815e-07,
1124
+ "loss": 0.2471,
1125
+ "step": 11904
1126
+ },
1127
+ {
1128
+ "epoch": 0.89,
1129
+ "learning_rate": 7.481258578819553e-07,
1130
+ "loss": 0.2285,
1131
+ "step": 11968
1132
+ },
1133
+ {
1134
+ "epoch": 0.9,
1135
+ "learning_rate": 7.464364903389293e-07,
1136
+ "loss": 0.2368,
1137
+ "step": 12032
1138
+ },
1139
+ {
1140
+ "epoch": 0.9,
1141
+ "learning_rate": 7.447471227959033e-07,
1142
+ "loss": 0.1847,
1143
+ "step": 12096
1144
+ },
1145
+ {
1146
+ "epoch": 0.91,
1147
+ "learning_rate": 7.430577552528771e-07,
1148
+ "loss": 0.2826,
1149
+ "step": 12160
1150
+ },
1151
+ {
1152
+ "epoch": 0.91,
1153
+ "learning_rate": 7.413683877098511e-07,
1154
+ "loss": 0.2931,
1155
+ "step": 12224
1156
+ },
1157
+ {
1158
+ "epoch": 0.91,
1159
+ "learning_rate": 7.396790201668251e-07,
1160
+ "loss": 0.1722,
1161
+ "step": 12288
1162
+ },
1163
+ {
1164
+ "epoch": 0.92,
1165
+ "learning_rate": 7.37989652623799e-07,
1166
+ "loss": 0.2673,
1167
+ "step": 12352
1168
+ },
1169
+ {
1170
+ "epoch": 0.92,
1171
+ "learning_rate": 7.363002850807728e-07,
1172
+ "loss": 0.2244,
1173
+ "step": 12416
1174
+ },
1175
+ {
1176
+ "epoch": 0.93,
1177
+ "learning_rate": 7.346109175377467e-07,
1178
+ "loss": 0.1532,
1179
+ "step": 12480
1180
+ },
1181
+ {
1182
+ "epoch": 0.93,
1183
+ "learning_rate": 7.329215499947207e-07,
1184
+ "loss": 0.2207,
1185
+ "step": 12544
1186
+ },
1187
+ {
1188
+ "epoch": 0.94,
1189
+ "learning_rate": 7.312321824516946e-07,
1190
+ "loss": 0.2362,
1191
+ "step": 12608
1192
+ },
1193
+ {
1194
+ "epoch": 0.94,
1195
+ "learning_rate": 7.295428149086685e-07,
1196
+ "loss": 0.2222,
1197
+ "step": 12672
1198
+ },
1199
+ {
1200
+ "epoch": 0.95,
1201
+ "learning_rate": 7.278534473656425e-07,
1202
+ "loss": 0.2664,
1203
+ "step": 12736
1204
+ },
1205
+ {
1206
+ "epoch": 0.95,
1207
+ "learning_rate": 7.261640798226164e-07,
1208
+ "loss": 0.1632,
1209
+ "step": 12800
1210
+ },
1211
+ {
1212
+ "epoch": 0.96,
1213
+ "learning_rate": 7.244747122795903e-07,
1214
+ "loss": 0.2212,
1215
+ "step": 12864
1216
+ },
1217
+ {
1218
+ "epoch": 0.96,
1219
+ "learning_rate": 7.227853447365642e-07,
1220
+ "loss": 0.2026,
1221
+ "step": 12928
1222
+ },
1223
+ {
1224
+ "epoch": 0.97,
1225
+ "learning_rate": 7.210959771935381e-07,
1226
+ "loss": 0.2562,
1227
+ "step": 12992
1228
+ },
1229
+ {
1230
+ "epoch": 0.97,
1231
+ "learning_rate": 7.194066096505121e-07,
1232
+ "loss": 0.2038,
1233
+ "step": 13056
1234
+ },
1235
+ {
1236
+ "epoch": 0.98,
1237
+ "learning_rate": 7.177436384753458e-07,
1238
+ "loss": 0.1829,
1239
+ "step": 13120
1240
+ },
1241
+ {
1242
+ "epoch": 0.98,
1243
+ "learning_rate": 7.160542709323197e-07,
1244
+ "loss": 0.217,
1245
+ "step": 13184
1246
+ },
1247
+ {
1248
+ "epoch": 0.99,
1249
+ "learning_rate": 7.143649033892935e-07,
1250
+ "loss": 0.2303,
1251
+ "step": 13248
1252
+ },
1253
+ {
1254
+ "epoch": 0.99,
1255
+ "learning_rate": 7.126755358462675e-07,
1256
+ "loss": 0.1996,
1257
+ "step": 13312
1258
+ },
1259
+ {
1260
+ "epoch": 1.0,
1261
+ "learning_rate": 7.109861683032415e-07,
1262
+ "loss": 0.206,
1263
+ "step": 13376
1264
+ }
1265
+ ],
1266
+ "logging_steps": 64,
1267
+ "max_steps": 40302,
1268
+ "num_input_tokens_seen": 0,
1269
+ "num_train_epochs": 3,
1270
+ "save_steps": 500,
1271
+ "total_flos": 4.564199225032704e+19,
1272
+ "train_batch_size": 1,
1273
+ "trial_name": null,
1274
+ "trial_params": null
1275
+ }
checkpoint-13434/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78386e842565101e214de6fd490f11cca7ee20779a9fedba99952f8538bae8ab
3
+ size 4920