abritez commited on
Commit
73ac0c5
1 Parent(s): 64dc475

Upload 21 files

Browse files
checkpoint-79326/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.44.2",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
checkpoint-79326/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-79326/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf244031a1ce527ca1097b63df14d384a2c87b0335b766dcaba89c60f3fad9b3
3
+ size 334030264
checkpoint-79326/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f27d9071716bc56c9baaf7f9d1344e55f6599c179d11debdf8ad46383c55378
3
+ size 668124218
checkpoint-79326/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19e48c67d8028eb255c1083b2ff09212c27d44beb8928855b503118a6ceaf07d
3
+ size 14244
checkpoint-79326/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d363fd8e3f152e12c6d5a8e369a6c1fe045a31f9963e639bf3dfd383dfe20e5
3
+ size 1064
checkpoint-79326/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-79326/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-79326/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_len": 512,
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
checkpoint-79326/trainer_state.json ADDED
@@ -0,0 +1,1171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.526447931526391,
5
+ "eval_steps": 500,
6
+ "global_step": 79326,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.028530670470756064,
13
+ "grad_norm": 4.224736213684082,
14
+ "learning_rate": 9.936968963517636e-05,
15
+ "loss": 7.9606,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.05706134094151213,
20
+ "grad_norm": 3.775930881500244,
21
+ "learning_rate": 9.873937927035273e-05,
22
+ "loss": 7.4609,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.08559201141226819,
27
+ "grad_norm": 4.54003381729126,
28
+ "learning_rate": 9.810906890552909e-05,
29
+ "loss": 7.2264,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.11412268188302425,
34
+ "grad_norm": 4.762158393859863,
35
+ "learning_rate": 9.747875854070544e-05,
36
+ "loss": 7.1154,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.14265335235378032,
41
+ "grad_norm": 4.3742995262146,
42
+ "learning_rate": 9.684844817588181e-05,
43
+ "loss": 7.0396,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.17118402282453637,
48
+ "grad_norm": 6.319996356964111,
49
+ "learning_rate": 9.621813781105817e-05,
50
+ "loss": 6.9091,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.19971469329529243,
55
+ "grad_norm": 5.134556770324707,
56
+ "learning_rate": 9.558782744623454e-05,
57
+ "loss": 6.8436,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.2282453637660485,
62
+ "grad_norm": 5.821471691131592,
63
+ "learning_rate": 9.49575170814109e-05,
64
+ "loss": 6.7296,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.25677603423680456,
69
+ "grad_norm": 5.649785041809082,
70
+ "learning_rate": 9.432720671658725e-05,
71
+ "loss": 6.6347,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.28530670470756064,
76
+ "grad_norm": 4.85307502746582,
77
+ "learning_rate": 9.369689635176361e-05,
78
+ "loss": 6.5734,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.31383737517831667,
83
+ "grad_norm": 4.924481391906738,
84
+ "learning_rate": 9.306658598693997e-05,
85
+ "loss": 6.4956,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.34236804564907275,
90
+ "grad_norm": 5.568727970123291,
91
+ "learning_rate": 9.243627562211632e-05,
92
+ "loss": 6.4667,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.37089871611982883,
97
+ "grad_norm": 5.307117938995361,
98
+ "learning_rate": 9.18059652572927e-05,
99
+ "loss": 6.4108,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.39942938659058486,
104
+ "grad_norm": 5.159631729125977,
105
+ "learning_rate": 9.117565489246905e-05,
106
+ "loss": 6.3248,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.42796005706134094,
111
+ "grad_norm": 5.529886722564697,
112
+ "learning_rate": 9.054534452764542e-05,
113
+ "loss": 6.3069,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.456490727532097,
118
+ "grad_norm": 9.25552749633789,
119
+ "learning_rate": 8.991503416282178e-05,
120
+ "loss": 6.2188,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.48502139800285304,
125
+ "grad_norm": 7.253251075744629,
126
+ "learning_rate": 8.928472379799813e-05,
127
+ "loss": 6.0356,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.5135520684736091,
132
+ "grad_norm": 8.699528694152832,
133
+ "learning_rate": 8.86544134331745e-05,
134
+ "loss": 6.0202,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.5420827389443652,
139
+ "grad_norm": 7.144530296325684,
140
+ "learning_rate": 8.802410306835086e-05,
141
+ "loss": 5.8857,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.5706134094151213,
146
+ "grad_norm": 7.254436492919922,
147
+ "learning_rate": 8.739379270352722e-05,
148
+ "loss": 5.8363,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.5991440798858774,
153
+ "grad_norm": 7.687765121459961,
154
+ "learning_rate": 8.676348233870359e-05,
155
+ "loss": 5.7397,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.6276747503566333,
160
+ "grad_norm": 6.547056674957275,
161
+ "learning_rate": 8.613317197387994e-05,
162
+ "loss": 5.6764,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.6562054208273894,
167
+ "grad_norm": 9.949172973632812,
168
+ "learning_rate": 8.55028616090563e-05,
169
+ "loss": 5.6305,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.6847360912981455,
174
+ "grad_norm": 8.107893943786621,
175
+ "learning_rate": 8.487255124423267e-05,
176
+ "loss": 5.5956,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.7132667617689016,
181
+ "grad_norm": 6.340846538543701,
182
+ "learning_rate": 8.424224087940903e-05,
183
+ "loss": 5.5119,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.7417974322396577,
188
+ "grad_norm": 7.98532247543335,
189
+ "learning_rate": 8.361193051458538e-05,
190
+ "loss": 5.4685,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 0.7703281027104137,
195
+ "grad_norm": 8.349475860595703,
196
+ "learning_rate": 8.298162014976175e-05,
197
+ "loss": 5.4685,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 0.7988587731811697,
202
+ "grad_norm": 8.270821571350098,
203
+ "learning_rate": 8.23513097849381e-05,
204
+ "loss": 5.4529,
205
+ "step": 14000
206
+ },
207
+ {
208
+ "epoch": 0.8273894436519258,
209
+ "grad_norm": 7.967436790466309,
210
+ "learning_rate": 8.172099942011447e-05,
211
+ "loss": 5.369,
212
+ "step": 14500
213
+ },
214
+ {
215
+ "epoch": 0.8559201141226819,
216
+ "grad_norm": 6.520368576049805,
217
+ "learning_rate": 8.109068905529082e-05,
218
+ "loss": 5.3417,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 0.884450784593438,
223
+ "grad_norm": 7.0926713943481445,
224
+ "learning_rate": 8.046037869046718e-05,
225
+ "loss": 5.3051,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 0.912981455064194,
230
+ "grad_norm": 7.306639194488525,
231
+ "learning_rate": 7.983006832564355e-05,
232
+ "loss": 5.275,
233
+ "step": 16000
234
+ },
235
+ {
236
+ "epoch": 0.9415121255349501,
237
+ "grad_norm": 7.494438171386719,
238
+ "learning_rate": 7.919975796081991e-05,
239
+ "loss": 5.2383,
240
+ "step": 16500
241
+ },
242
+ {
243
+ "epoch": 0.9700427960057061,
244
+ "grad_norm": 7.95282506942749,
245
+ "learning_rate": 7.856944759599628e-05,
246
+ "loss": 5.2275,
247
+ "step": 17000
248
+ },
249
+ {
250
+ "epoch": 0.9985734664764622,
251
+ "grad_norm": 8.143848419189453,
252
+ "learning_rate": 7.793913723117263e-05,
253
+ "loss": 5.1984,
254
+ "step": 17500
255
+ },
256
+ {
257
+ "epoch": 1.0,
258
+ "eval_loss": 5.088438034057617,
259
+ "eval_runtime": 60.5124,
260
+ "eval_samples_per_second": 817.683,
261
+ "eval_steps_per_second": 51.113,
262
+ "step": 17525
263
+ },
264
+ {
265
+ "epoch": 1.0271041369472182,
266
+ "grad_norm": 7.758360862731934,
267
+ "learning_rate": 7.730882686634899e-05,
268
+ "loss": 5.1319,
269
+ "step": 18000
270
+ },
271
+ {
272
+ "epoch": 1.0556348074179742,
273
+ "grad_norm": 6.7139177322387695,
274
+ "learning_rate": 7.667851650152536e-05,
275
+ "loss": 5.1087,
276
+ "step": 18500
277
+ },
278
+ {
279
+ "epoch": 1.0841654778887304,
280
+ "grad_norm": 6.584017753601074,
281
+ "learning_rate": 7.604820613670172e-05,
282
+ "loss": 5.0938,
283
+ "step": 19000
284
+ },
285
+ {
286
+ "epoch": 1.1126961483594864,
287
+ "grad_norm": 7.792596817016602,
288
+ "learning_rate": 7.541789577187807e-05,
289
+ "loss": 5.0448,
290
+ "step": 19500
291
+ },
292
+ {
293
+ "epoch": 1.1412268188302426,
294
+ "grad_norm": 7.243467807769775,
295
+ "learning_rate": 7.478758540705444e-05,
296
+ "loss": 5.0423,
297
+ "step": 20000
298
+ },
299
+ {
300
+ "epoch": 1.1697574893009985,
301
+ "grad_norm": 8.1492338180542,
302
+ "learning_rate": 7.41572750422308e-05,
303
+ "loss": 4.9913,
304
+ "step": 20500
305
+ },
306
+ {
307
+ "epoch": 1.1982881597717547,
308
+ "grad_norm": 7.754183292388916,
309
+ "learning_rate": 7.352696467740716e-05,
310
+ "loss": 4.9983,
311
+ "step": 21000
312
+ },
313
+ {
314
+ "epoch": 1.2268188302425107,
315
+ "grad_norm": 7.245093822479248,
316
+ "learning_rate": 7.289665431258353e-05,
317
+ "loss": 4.9729,
318
+ "step": 21500
319
+ },
320
+ {
321
+ "epoch": 1.2553495007132667,
322
+ "grad_norm": 7.720768451690674,
323
+ "learning_rate": 7.226634394775988e-05,
324
+ "loss": 4.9499,
325
+ "step": 22000
326
+ },
327
+ {
328
+ "epoch": 1.2838801711840229,
329
+ "grad_norm": 7.034431457519531,
330
+ "learning_rate": 7.163603358293624e-05,
331
+ "loss": 4.9368,
332
+ "step": 22500
333
+ },
334
+ {
335
+ "epoch": 1.3124108416547788,
336
+ "grad_norm": 9.341329574584961,
337
+ "learning_rate": 7.100572321811261e-05,
338
+ "loss": 4.8745,
339
+ "step": 23000
340
+ },
341
+ {
342
+ "epoch": 1.340941512125535,
343
+ "grad_norm": 6.874212265014648,
344
+ "learning_rate": 7.037541285328895e-05,
345
+ "loss": 4.877,
346
+ "step": 23500
347
+ },
348
+ {
349
+ "epoch": 1.369472182596291,
350
+ "grad_norm": 8.832662582397461,
351
+ "learning_rate": 6.974510248846532e-05,
352
+ "loss": 4.8839,
353
+ "step": 24000
354
+ },
355
+ {
356
+ "epoch": 1.3980028530670472,
357
+ "grad_norm": 6.884407997131348,
358
+ "learning_rate": 6.911479212364168e-05,
359
+ "loss": 4.8456,
360
+ "step": 24500
361
+ },
362
+ {
363
+ "epoch": 1.4265335235378032,
364
+ "grad_norm": 8.421597480773926,
365
+ "learning_rate": 6.848448175881804e-05,
366
+ "loss": 4.8491,
367
+ "step": 25000
368
+ },
369
+ {
370
+ "epoch": 1.4550641940085591,
371
+ "grad_norm": 8.932446479797363,
372
+ "learning_rate": 6.78541713939944e-05,
373
+ "loss": 4.7936,
374
+ "step": 25500
375
+ },
376
+ {
377
+ "epoch": 1.4835948644793153,
378
+ "grad_norm": 9.981544494628906,
379
+ "learning_rate": 6.722386102917076e-05,
380
+ "loss": 4.816,
381
+ "step": 26000
382
+ },
383
+ {
384
+ "epoch": 1.5121255349500713,
385
+ "grad_norm": 7.8625922203063965,
386
+ "learning_rate": 6.659355066434713e-05,
387
+ "loss": 4.7983,
388
+ "step": 26500
389
+ },
390
+ {
391
+ "epoch": 1.5406562054208273,
392
+ "grad_norm": 9.113426208496094,
393
+ "learning_rate": 6.596324029952349e-05,
394
+ "loss": 4.7438,
395
+ "step": 27000
396
+ },
397
+ {
398
+ "epoch": 1.5691868758915835,
399
+ "grad_norm": 8.4766206741333,
400
+ "learning_rate": 6.533292993469985e-05,
401
+ "loss": 4.7544,
402
+ "step": 27500
403
+ },
404
+ {
405
+ "epoch": 1.5977175463623396,
406
+ "grad_norm": 9.448740005493164,
407
+ "learning_rate": 6.470261956987622e-05,
408
+ "loss": 4.7244,
409
+ "step": 28000
410
+ },
411
+ {
412
+ "epoch": 1.6262482168330956,
413
+ "grad_norm": 7.334268093109131,
414
+ "learning_rate": 6.407230920505257e-05,
415
+ "loss": 4.7225,
416
+ "step": 28500
417
+ },
418
+ {
419
+ "epoch": 1.6547788873038516,
420
+ "grad_norm": 8.931607246398926,
421
+ "learning_rate": 6.344199884022893e-05,
422
+ "loss": 4.6495,
423
+ "step": 29000
424
+ },
425
+ {
426
+ "epoch": 1.6833095577746078,
427
+ "grad_norm": 7.774843215942383,
428
+ "learning_rate": 6.28116884754053e-05,
429
+ "loss": 4.7006,
430
+ "step": 29500
431
+ },
432
+ {
433
+ "epoch": 1.7118402282453637,
434
+ "grad_norm": 7.911451816558838,
435
+ "learning_rate": 6.218137811058166e-05,
436
+ "loss": 4.6525,
437
+ "step": 30000
438
+ },
439
+ {
440
+ "epoch": 1.7403708987161197,
441
+ "grad_norm": 7.005200386047363,
442
+ "learning_rate": 6.155106774575801e-05,
443
+ "loss": 4.6765,
444
+ "step": 30500
445
+ },
446
+ {
447
+ "epoch": 1.768901569186876,
448
+ "grad_norm": 8.889507293701172,
449
+ "learning_rate": 6.0920757380934376e-05,
450
+ "loss": 4.6397,
451
+ "step": 31000
452
+ },
453
+ {
454
+ "epoch": 1.797432239657632,
455
+ "grad_norm": 8.807517051696777,
456
+ "learning_rate": 6.029044701611074e-05,
457
+ "loss": 4.6291,
458
+ "step": 31500
459
+ },
460
+ {
461
+ "epoch": 1.825962910128388,
462
+ "grad_norm": 10.036596298217773,
463
+ "learning_rate": 5.96601366512871e-05,
464
+ "loss": 4.6033,
465
+ "step": 32000
466
+ },
467
+ {
468
+ "epoch": 1.854493580599144,
469
+ "grad_norm": 8.668290138244629,
470
+ "learning_rate": 5.902982628646345e-05,
471
+ "loss": 4.617,
472
+ "step": 32500
473
+ },
474
+ {
475
+ "epoch": 1.8830242510699002,
476
+ "grad_norm": 7.631191253662109,
477
+ "learning_rate": 5.8399515921639816e-05,
478
+ "loss": 4.591,
479
+ "step": 33000
480
+ },
481
+ {
482
+ "epoch": 1.9115549215406562,
483
+ "grad_norm": 7.901882171630859,
484
+ "learning_rate": 5.776920555681617e-05,
485
+ "loss": 4.593,
486
+ "step": 33500
487
+ },
488
+ {
489
+ "epoch": 1.9400855920114122,
490
+ "grad_norm": 8.088603973388672,
491
+ "learning_rate": 5.7138895191992536e-05,
492
+ "loss": 4.575,
493
+ "step": 34000
494
+ },
495
+ {
496
+ "epoch": 1.9686162624821684,
497
+ "grad_norm": 13.519835472106934,
498
+ "learning_rate": 5.65085848271689e-05,
499
+ "loss": 4.5674,
500
+ "step": 34500
501
+ },
502
+ {
503
+ "epoch": 1.9971469329529246,
504
+ "grad_norm": 7.497794151306152,
505
+ "learning_rate": 5.587827446234526e-05,
506
+ "loss": 4.5896,
507
+ "step": 35000
508
+ },
509
+ {
510
+ "epoch": 2.0,
511
+ "eval_loss": 4.483283996582031,
512
+ "eval_runtime": 55.5401,
513
+ "eval_samples_per_second": 890.889,
514
+ "eval_steps_per_second": 55.69,
515
+ "step": 35050
516
+ },
517
+ {
518
+ "epoch": 2.0256776034236803,
519
+ "grad_norm": 9.086140632629395,
520
+ "learning_rate": 5.524796409752162e-05,
521
+ "loss": 4.4731,
522
+ "step": 35500
523
+ },
524
+ {
525
+ "epoch": 2.0542082738944365,
526
+ "grad_norm": 7.284142017364502,
527
+ "learning_rate": 5.461765373269798e-05,
528
+ "loss": 4.5119,
529
+ "step": 36000
530
+ },
531
+ {
532
+ "epoch": 2.0827389443651927,
533
+ "grad_norm": 9.4158296585083,
534
+ "learning_rate": 5.3987343367874346e-05,
535
+ "loss": 4.4564,
536
+ "step": 36500
537
+ },
538
+ {
539
+ "epoch": 2.1112696148359484,
540
+ "grad_norm": 10.107216835021973,
541
+ "learning_rate": 5.33570330030507e-05,
542
+ "loss": 4.5029,
543
+ "step": 37000
544
+ },
545
+ {
546
+ "epoch": 2.1398002853067046,
547
+ "grad_norm": 8.506832122802734,
548
+ "learning_rate": 5.2726722638227066e-05,
549
+ "loss": 4.4487,
550
+ "step": 37500
551
+ },
552
+ {
553
+ "epoch": 2.168330955777461,
554
+ "grad_norm": 10.495549201965332,
555
+ "learning_rate": 5.209641227340343e-05,
556
+ "loss": 4.433,
557
+ "step": 38000
558
+ },
559
+ {
560
+ "epoch": 2.196861626248217,
561
+ "grad_norm": 8.59913444519043,
562
+ "learning_rate": 5.146610190857979e-05,
563
+ "loss": 4.4377,
564
+ "step": 38500
565
+ },
566
+ {
567
+ "epoch": 2.2253922967189728,
568
+ "grad_norm": 7.879130840301514,
569
+ "learning_rate": 5.083579154375615e-05,
570
+ "loss": 4.3888,
571
+ "step": 39000
572
+ },
573
+ {
574
+ "epoch": 2.253922967189729,
575
+ "grad_norm": 8.134923934936523,
576
+ "learning_rate": 5.020548117893251e-05,
577
+ "loss": 4.4215,
578
+ "step": 39500
579
+ },
580
+ {
581
+ "epoch": 2.282453637660485,
582
+ "grad_norm": 8.942688941955566,
583
+ "learning_rate": 4.957517081410887e-05,
584
+ "loss": 4.4249,
585
+ "step": 40000
586
+ },
587
+ {
588
+ "epoch": 2.310984308131241,
589
+ "grad_norm": 12.744963645935059,
590
+ "learning_rate": 4.894486044928523e-05,
591
+ "loss": 4.3957,
592
+ "step": 40500
593
+ },
594
+ {
595
+ "epoch": 2.339514978601997,
596
+ "grad_norm": 10.202946662902832,
597
+ "learning_rate": 4.831455008446159e-05,
598
+ "loss": 4.4239,
599
+ "step": 41000
600
+ },
601
+ {
602
+ "epoch": 2.3680456490727533,
603
+ "grad_norm": 7.9722418785095215,
604
+ "learning_rate": 4.768423971963795e-05,
605
+ "loss": 4.4196,
606
+ "step": 41500
607
+ },
608
+ {
609
+ "epoch": 2.3965763195435095,
610
+ "grad_norm": 8.571127891540527,
611
+ "learning_rate": 4.7053929354814315e-05,
612
+ "loss": 4.3274,
613
+ "step": 42000
614
+ },
615
+ {
616
+ "epoch": 2.425106990014265,
617
+ "grad_norm": 9.048084259033203,
618
+ "learning_rate": 4.642361898999067e-05,
619
+ "loss": 4.3422,
620
+ "step": 42500
621
+ },
622
+ {
623
+ "epoch": 2.4536376604850214,
624
+ "grad_norm": 9.029339790344238,
625
+ "learning_rate": 4.5793308625167035e-05,
626
+ "loss": 4.3474,
627
+ "step": 43000
628
+ },
629
+ {
630
+ "epoch": 2.4821683309557776,
631
+ "grad_norm": 8.281103134155273,
632
+ "learning_rate": 4.51629982603434e-05,
633
+ "loss": 4.3849,
634
+ "step": 43500
635
+ },
636
+ {
637
+ "epoch": 2.5106990014265333,
638
+ "grad_norm": 7.619591236114502,
639
+ "learning_rate": 4.4532687895519755e-05,
640
+ "loss": 4.3154,
641
+ "step": 44000
642
+ },
643
+ {
644
+ "epoch": 2.5392296718972895,
645
+ "grad_norm": 10.685304641723633,
646
+ "learning_rate": 4.390237753069611e-05,
647
+ "loss": 4.2803,
648
+ "step": 44500
649
+ },
650
+ {
651
+ "epoch": 2.5677603423680457,
652
+ "grad_norm": 8.622846603393555,
653
+ "learning_rate": 4.3272067165872475e-05,
654
+ "loss": 4.2911,
655
+ "step": 45000
656
+ },
657
+ {
658
+ "epoch": 2.596291012838802,
659
+ "grad_norm": 10.364981651306152,
660
+ "learning_rate": 4.264175680104884e-05,
661
+ "loss": 4.3172,
662
+ "step": 45500
663
+ },
664
+ {
665
+ "epoch": 2.6248216833095577,
666
+ "grad_norm": 6.996392726898193,
667
+ "learning_rate": 4.20114464362252e-05,
668
+ "loss": 4.3123,
669
+ "step": 46000
670
+ },
671
+ {
672
+ "epoch": 2.653352353780314,
673
+ "grad_norm": 9.445304870605469,
674
+ "learning_rate": 4.138113607140156e-05,
675
+ "loss": 4.2621,
676
+ "step": 46500
677
+ },
678
+ {
679
+ "epoch": 2.68188302425107,
680
+ "grad_norm": 9.185279846191406,
681
+ "learning_rate": 4.075082570657792e-05,
682
+ "loss": 4.2983,
683
+ "step": 47000
684
+ },
685
+ {
686
+ "epoch": 2.710413694721826,
687
+ "grad_norm": 7.654629230499268,
688
+ "learning_rate": 4.0120515341754285e-05,
689
+ "loss": 4.2994,
690
+ "step": 47500
691
+ },
692
+ {
693
+ "epoch": 2.738944365192582,
694
+ "grad_norm": 8.687335014343262,
695
+ "learning_rate": 3.949020497693065e-05,
696
+ "loss": 4.2667,
697
+ "step": 48000
698
+ },
699
+ {
700
+ "epoch": 2.767475035663338,
701
+ "grad_norm": 9.457321166992188,
702
+ "learning_rate": 3.8859894612107e-05,
703
+ "loss": 4.2709,
704
+ "step": 48500
705
+ },
706
+ {
707
+ "epoch": 2.7960057061340944,
708
+ "grad_norm": 9.891905784606934,
709
+ "learning_rate": 3.822958424728336e-05,
710
+ "loss": 4.217,
711
+ "step": 49000
712
+ },
713
+ {
714
+ "epoch": 2.82453637660485,
715
+ "grad_norm": 7.958982467651367,
716
+ "learning_rate": 3.7599273882459725e-05,
717
+ "loss": 4.219,
718
+ "step": 49500
719
+ },
720
+ {
721
+ "epoch": 2.8530670470756063,
722
+ "grad_norm": 9.362072944641113,
723
+ "learning_rate": 3.696896351763609e-05,
724
+ "loss": 4.2212,
725
+ "step": 50000
726
+ },
727
+ {
728
+ "epoch": 2.881597717546362,
729
+ "grad_norm": 9.81021499633789,
730
+ "learning_rate": 3.6338653152812445e-05,
731
+ "loss": 4.1786,
732
+ "step": 50500
733
+ },
734
+ {
735
+ "epoch": 2.9101283880171183,
736
+ "grad_norm": 9.377098083496094,
737
+ "learning_rate": 3.570834278798881e-05,
738
+ "loss": 4.1874,
739
+ "step": 51000
740
+ },
741
+ {
742
+ "epoch": 2.9386590584878745,
743
+ "grad_norm": 7.9157562255859375,
744
+ "learning_rate": 3.507803242316517e-05,
745
+ "loss": 4.2021,
746
+ "step": 51500
747
+ },
748
+ {
749
+ "epoch": 2.9671897289586306,
750
+ "grad_norm": 9.986918449401855,
751
+ "learning_rate": 3.444772205834153e-05,
752
+ "loss": 4.2068,
753
+ "step": 52000
754
+ },
755
+ {
756
+ "epoch": 2.995720399429387,
757
+ "grad_norm": 9.590192794799805,
758
+ "learning_rate": 3.381741169351789e-05,
759
+ "loss": 4.2007,
760
+ "step": 52500
761
+ },
762
+ {
763
+ "epoch": 3.0,
764
+ "eval_loss": 4.12980842590332,
765
+ "eval_runtime": 54.7837,
766
+ "eval_samples_per_second": 903.188,
767
+ "eval_steps_per_second": 56.458,
768
+ "step": 52575
769
+ },
770
+ {
771
+ "epoch": 3.0242510699001426,
772
+ "grad_norm": 10.125175476074219,
773
+ "learning_rate": 3.3187101328694254e-05,
774
+ "loss": 4.1689,
775
+ "step": 53000
776
+ },
777
+ {
778
+ "epoch": 3.0527817403708988,
779
+ "grad_norm": 9.876838684082031,
780
+ "learning_rate": 3.255679096387061e-05,
781
+ "loss": 4.1606,
782
+ "step": 53500
783
+ },
784
+ {
785
+ "epoch": 3.081312410841655,
786
+ "grad_norm": 8.361190795898438,
787
+ "learning_rate": 3.192648059904697e-05,
788
+ "loss": 4.1792,
789
+ "step": 54000
790
+ },
791
+ {
792
+ "epoch": 3.1098430813124107,
793
+ "grad_norm": 11.448074340820312,
794
+ "learning_rate": 3.129617023422333e-05,
795
+ "loss": 4.1463,
796
+ "step": 54500
797
+ },
798
+ {
799
+ "epoch": 3.138373751783167,
800
+ "grad_norm": 9.612030982971191,
801
+ "learning_rate": 3.0665859869399694e-05,
802
+ "loss": 4.1013,
803
+ "step": 55000
804
+ },
805
+ {
806
+ "epoch": 3.166904422253923,
807
+ "grad_norm": 8.74341106414795,
808
+ "learning_rate": 3.0035549504576054e-05,
809
+ "loss": 4.1097,
810
+ "step": 55500
811
+ },
812
+ {
813
+ "epoch": 3.195435092724679,
814
+ "grad_norm": 8.951421737670898,
815
+ "learning_rate": 2.9405239139752418e-05,
816
+ "loss": 4.1154,
817
+ "step": 56000
818
+ },
819
+ {
820
+ "epoch": 3.223965763195435,
821
+ "grad_norm": 9.474740028381348,
822
+ "learning_rate": 2.8774928774928778e-05,
823
+ "loss": 4.1132,
824
+ "step": 56500
825
+ },
826
+ {
827
+ "epoch": 3.2524964336661912,
828
+ "grad_norm": 10.41540241241455,
829
+ "learning_rate": 2.8144618410105137e-05,
830
+ "loss": 4.1416,
831
+ "step": 57000
832
+ },
833
+ {
834
+ "epoch": 3.281027104136947,
835
+ "grad_norm": 10.558377265930176,
836
+ "learning_rate": 2.75143080452815e-05,
837
+ "loss": 4.1209,
838
+ "step": 57500
839
+ },
840
+ {
841
+ "epoch": 3.309557774607703,
842
+ "grad_norm": 8.718255996704102,
843
+ "learning_rate": 2.6883997680457857e-05,
844
+ "loss": 4.0549,
845
+ "step": 58000
846
+ },
847
+ {
848
+ "epoch": 3.3380884450784594,
849
+ "grad_norm": 8.449244499206543,
850
+ "learning_rate": 2.6253687315634217e-05,
851
+ "loss": 4.1046,
852
+ "step": 58500
853
+ },
854
+ {
855
+ "epoch": 3.3666191155492156,
856
+ "grad_norm": 10.529504776000977,
857
+ "learning_rate": 2.562337695081058e-05,
858
+ "loss": 4.1058,
859
+ "step": 59000
860
+ },
861
+ {
862
+ "epoch": 3.3951497860199713,
863
+ "grad_norm": 8.345918655395508,
864
+ "learning_rate": 2.499306658598694e-05,
865
+ "loss": 4.0668,
866
+ "step": 59500
867
+ },
868
+ {
869
+ "epoch": 3.4236804564907275,
870
+ "grad_norm": 10.951416015625,
871
+ "learning_rate": 2.43627562211633e-05,
872
+ "loss": 4.1145,
873
+ "step": 60000
874
+ },
875
+ {
876
+ "epoch": 3.4522111269614837,
877
+ "grad_norm": 8.29075813293457,
878
+ "learning_rate": 2.3732445856339664e-05,
879
+ "loss": 4.0765,
880
+ "step": 60500
881
+ },
882
+ {
883
+ "epoch": 3.4807417974322394,
884
+ "grad_norm": 9.023518562316895,
885
+ "learning_rate": 2.3102135491516024e-05,
886
+ "loss": 4.0608,
887
+ "step": 61000
888
+ },
889
+ {
890
+ "epoch": 3.5092724679029956,
891
+ "grad_norm": 10.263666152954102,
892
+ "learning_rate": 2.2471825126692384e-05,
893
+ "loss": 4.0361,
894
+ "step": 61500
895
+ },
896
+ {
897
+ "epoch": 3.537803138373752,
898
+ "grad_norm": 10.308072090148926,
899
+ "learning_rate": 2.1841514761868744e-05,
900
+ "loss": 4.0801,
901
+ "step": 62000
902
+ },
903
+ {
904
+ "epoch": 3.566333808844508,
905
+ "grad_norm": 11.750104904174805,
906
+ "learning_rate": 2.1211204397045107e-05,
907
+ "loss": 4.0166,
908
+ "step": 62500
909
+ },
910
+ {
911
+ "epoch": 3.5948644793152638,
912
+ "grad_norm": 9.711214065551758,
913
+ "learning_rate": 2.0580894032221467e-05,
914
+ "loss": 4.1,
915
+ "step": 63000
916
+ },
917
+ {
918
+ "epoch": 3.62339514978602,
919
+ "grad_norm": 9.461030006408691,
920
+ "learning_rate": 1.9950583667397827e-05,
921
+ "loss": 4.0546,
922
+ "step": 63500
923
+ },
924
+ {
925
+ "epoch": 3.651925820256776,
926
+ "grad_norm": 9.695231437683105,
927
+ "learning_rate": 1.9320273302574187e-05,
928
+ "loss": 3.9823,
929
+ "step": 64000
930
+ },
931
+ {
932
+ "epoch": 3.680456490727532,
933
+ "grad_norm": 8.181650161743164,
934
+ "learning_rate": 1.868996293775055e-05,
935
+ "loss": 4.0467,
936
+ "step": 64500
937
+ },
938
+ {
939
+ "epoch": 3.708987161198288,
940
+ "grad_norm": 10.602164268493652,
941
+ "learning_rate": 1.805965257292691e-05,
942
+ "loss": 4.0006,
943
+ "step": 65000
944
+ },
945
+ {
946
+ "epoch": 3.7375178316690443,
947
+ "grad_norm": 8.176977157592773,
948
+ "learning_rate": 1.7429342208103274e-05,
949
+ "loss": 4.0594,
950
+ "step": 65500
951
+ },
952
+ {
953
+ "epoch": 3.7660485021398005,
954
+ "grad_norm": 11.314457893371582,
955
+ "learning_rate": 1.679903184327963e-05,
956
+ "loss": 3.9929,
957
+ "step": 66000
958
+ },
959
+ {
960
+ "epoch": 3.794579172610556,
961
+ "grad_norm": 10.995957374572754,
962
+ "learning_rate": 1.6168721478455993e-05,
963
+ "loss": 4.0191,
964
+ "step": 66500
965
+ },
966
+ {
967
+ "epoch": 3.8231098430813124,
968
+ "grad_norm": 8.929314613342285,
969
+ "learning_rate": 1.5538411113632353e-05,
970
+ "loss": 4.0284,
971
+ "step": 67000
972
+ },
973
+ {
974
+ "epoch": 3.8516405135520686,
975
+ "grad_norm": 9.887913703918457,
976
+ "learning_rate": 1.4908100748808715e-05,
977
+ "loss": 3.9552,
978
+ "step": 67500
979
+ },
980
+ {
981
+ "epoch": 3.8801711840228243,
982
+ "grad_norm": 12.043901443481445,
983
+ "learning_rate": 1.4277790383985077e-05,
984
+ "loss": 4.0139,
985
+ "step": 68000
986
+ },
987
+ {
988
+ "epoch": 3.9087018544935805,
989
+ "grad_norm": 8.444652557373047,
990
+ "learning_rate": 1.3647480019161435e-05,
991
+ "loss": 3.9746,
992
+ "step": 68500
993
+ },
994
+ {
995
+ "epoch": 3.9372325249643367,
996
+ "grad_norm": 9.180087089538574,
997
+ "learning_rate": 1.3017169654337797e-05,
998
+ "loss": 3.9663,
999
+ "step": 69000
1000
+ },
1001
+ {
1002
+ "epoch": 3.965763195435093,
1003
+ "grad_norm": 11.611577987670898,
1004
+ "learning_rate": 1.2386859289514158e-05,
1005
+ "loss": 3.939,
1006
+ "step": 69500
1007
+ },
1008
+ {
1009
+ "epoch": 3.9942938659058487,
1010
+ "grad_norm": 9.529749870300293,
1011
+ "learning_rate": 1.1756548924690518e-05,
1012
+ "loss": 3.9911,
1013
+ "step": 70000
1014
+ },
1015
+ {
1016
+ "epoch": 4.0,
1017
+ "eval_loss": 3.9361355304718018,
1018
+ "eval_runtime": 55.3368,
1019
+ "eval_samples_per_second": 894.161,
1020
+ "eval_steps_per_second": 55.894,
1021
+ "step": 70100
1022
+ },
1023
+ {
1024
+ "epoch": 4.022824536376604,
1025
+ "grad_norm": 10.018484115600586,
1026
+ "learning_rate": 1.112623855986688e-05,
1027
+ "loss": 3.9744,
1028
+ "step": 70500
1029
+ },
1030
+ {
1031
+ "epoch": 4.051355206847361,
1032
+ "grad_norm": 11.023027420043945,
1033
+ "learning_rate": 1.049592819504324e-05,
1034
+ "loss": 3.9143,
1035
+ "step": 71000
1036
+ },
1037
+ {
1038
+ "epoch": 4.079885877318117,
1039
+ "grad_norm": 11.09890079498291,
1040
+ "learning_rate": 9.8656178302196e-06,
1041
+ "loss": 3.967,
1042
+ "step": 71500
1043
+ },
1044
+ {
1045
+ "epoch": 4.108416547788873,
1046
+ "grad_norm": 11.603713035583496,
1047
+ "learning_rate": 9.235307465395961e-06,
1048
+ "loss": 3.9525,
1049
+ "step": 72000
1050
+ },
1051
+ {
1052
+ "epoch": 4.136947218259629,
1053
+ "grad_norm": 8.631877899169922,
1054
+ "learning_rate": 8.604997100572321e-06,
1055
+ "loss": 3.9658,
1056
+ "step": 72500
1057
+ },
1058
+ {
1059
+ "epoch": 4.165477888730385,
1060
+ "grad_norm": 7.5662407875061035,
1061
+ "learning_rate": 7.974686735748683e-06,
1062
+ "loss": 3.9118,
1063
+ "step": 73000
1064
+ },
1065
+ {
1066
+ "epoch": 4.194008559201142,
1067
+ "grad_norm": 10.707962036132812,
1068
+ "learning_rate": 7.344376370925044e-06,
1069
+ "loss": 3.948,
1070
+ "step": 73500
1071
+ },
1072
+ {
1073
+ "epoch": 4.222539229671897,
1074
+ "grad_norm": 11.31724739074707,
1075
+ "learning_rate": 6.714066006101405e-06,
1076
+ "loss": 3.9319,
1077
+ "step": 74000
1078
+ },
1079
+ {
1080
+ "epoch": 4.251069900142653,
1081
+ "grad_norm": 9.398261070251465,
1082
+ "learning_rate": 6.083755641277765e-06,
1083
+ "loss": 3.9621,
1084
+ "step": 74500
1085
+ },
1086
+ {
1087
+ "epoch": 4.279600570613409,
1088
+ "grad_norm": 11.119857788085938,
1089
+ "learning_rate": 5.453445276454126e-06,
1090
+ "loss": 3.9429,
1091
+ "step": 75000
1092
+ },
1093
+ {
1094
+ "epoch": 4.3081312410841655,
1095
+ "grad_norm": 11.433586120605469,
1096
+ "learning_rate": 4.823134911630487e-06,
1097
+ "loss": 3.9126,
1098
+ "step": 75500
1099
+ },
1100
+ {
1101
+ "epoch": 4.336661911554922,
1102
+ "grad_norm": 10.043067932128906,
1103
+ "learning_rate": 4.192824546806848e-06,
1104
+ "loss": 3.9218,
1105
+ "step": 76000
1106
+ },
1107
+ {
1108
+ "epoch": 4.365192582025678,
1109
+ "grad_norm": 9.148512840270996,
1110
+ "learning_rate": 3.5625141819832086e-06,
1111
+ "loss": 3.9124,
1112
+ "step": 76500
1113
+ },
1114
+ {
1115
+ "epoch": 4.393723252496434,
1116
+ "grad_norm": 9.347081184387207,
1117
+ "learning_rate": 2.9322038171595694e-06,
1118
+ "loss": 3.8917,
1119
+ "step": 77000
1120
+ },
1121
+ {
1122
+ "epoch": 4.422253922967189,
1123
+ "grad_norm": 8.787015914916992,
1124
+ "learning_rate": 2.30189345233593e-06,
1125
+ "loss": 3.9091,
1126
+ "step": 77500
1127
+ },
1128
+ {
1129
+ "epoch": 4.4507845934379455,
1130
+ "grad_norm": 8.788630485534668,
1131
+ "learning_rate": 1.671583087512291e-06,
1132
+ "loss": 3.9211,
1133
+ "step": 78000
1134
+ },
1135
+ {
1136
+ "epoch": 4.479315263908702,
1137
+ "grad_norm": 8.639442443847656,
1138
+ "learning_rate": 1.0412727226886518e-06,
1139
+ "loss": 3.9139,
1140
+ "step": 78500
1141
+ },
1142
+ {
1143
+ "epoch": 4.507845934379458,
1144
+ "grad_norm": 9.101580619812012,
1145
+ "learning_rate": 4.1096235786501275e-07,
1146
+ "loss": 3.911,
1147
+ "step": 79000
1148
+ }
1149
+ ],
1150
+ "logging_steps": 500,
1151
+ "max_steps": 79326,
1152
+ "num_input_tokens_seen": 0,
1153
+ "num_train_epochs": 5,
1154
+ "save_steps": 8192,
1155
+ "stateful_callbacks": {
1156
+ "TrainerControl": {
1157
+ "args": {
1158
+ "should_epoch_stop": false,
1159
+ "should_evaluate": false,
1160
+ "should_log": false,
1161
+ "should_save": true,
1162
+ "should_training_stop": true
1163
+ },
1164
+ "attributes": {}
1165
+ }
1166
+ },
1167
+ "total_flos": 1.6441172712886272e+16,
1168
+ "train_batch_size": 16,
1169
+ "trial_name": null,
1170
+ "trial_params": null
1171
+ }
checkpoint-79326/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e64f16ba5992c900a0773855a6367aac7e9b7d09381c3b8148299cd4d2728a9
3
+ size 5304
checkpoint-79326/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.44.2",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
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:cf244031a1ce527ca1097b63df14d384a2c87b0335b766dcaba89c60f3fad9b3
3
+ size 334030264
runs/Sep27_13-44-36_f5522999b0c2/events.out.tfevents.1727444677.f5522999b0c2.3988.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c5dfd358a0bf5b132318cb13da0d86e0abad0af8d5699dff756c8cf383131c
3
+ size 40540
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_len": 512,
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e64f16ba5992c900a0773855a6367aac7e9b7d09381c3b8148299cd4d2728a9
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff