abritez commited on
Commit
83f5dbd
1 Parent(s): 3d09bd8

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 sha256:4d3beec9c55d11d028eaf3e776b5c68b8a33fe69cbfbf1781e06df6bee9cefd7
3
+ size 334030264
checkpoint-79326/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5888b5cba2491f4842a4206d7e56f392d3b1003fb01ae64c3793a9f044b79a22
3
+ size 668124218
checkpoint-79326/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347f32e2523705c2bd05d1be244e1ac1cd1a4105f743161a9ccff4b80e471d6a
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 +1,1179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.815689149560117,
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": 0.036656891495601175,
13
+ "grad_norm": 3.9739036560058594,
14
+ "learning_rate": 9.936968963517636e-05,
15
+ "loss": 7.911,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.07331378299120235,
20
+ "grad_norm": 3.5818135738372803,
21
+ "learning_rate": 9.873937927035273e-05,
22
+ "loss": 7.4132,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.10997067448680352,
27
+ "grad_norm": 3.6124236583709717,
28
+ "learning_rate": 9.810906890552909e-05,
29
+ "loss": 7.2685,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.1466275659824047,
34
+ "grad_norm": 3.609344720840454,
35
+ "learning_rate": 9.747875854070544e-05,
36
+ "loss": 7.1646,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.18328445747800587,
41
+ "grad_norm": 3.878251075744629,
42
+ "learning_rate": 9.684844817588181e-05,
43
+ "loss": 7.112,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.21994134897360704,
48
+ "grad_norm": 3.640087604522705,
49
+ "learning_rate": 9.621813781105817e-05,
50
+ "loss": 6.9647,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.2565982404692082,
55
+ "grad_norm": 4.396575927734375,
56
+ "learning_rate": 9.558782744623454e-05,
57
+ "loss": 6.9285,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.2932551319648094,
62
+ "grad_norm": 4.27196741104126,
63
+ "learning_rate": 9.49575170814109e-05,
64
+ "loss": 6.8817,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.32991202346041054,
69
+ "grad_norm": 5.039891719818115,
70
+ "learning_rate": 9.432720671658725e-05,
71
+ "loss": 6.8308,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.36656891495601174,
76
+ "grad_norm": 6.211440563201904,
77
+ "learning_rate": 9.369689635176361e-05,
78
+ "loss": 6.7133,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.4032258064516129,
83
+ "grad_norm": 5.089609622955322,
84
+ "learning_rate": 9.306658598693997e-05,
85
+ "loss": 6.596,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.4398826979472141,
90
+ "grad_norm": 7.917068004608154,
91
+ "learning_rate": 9.243627562211632e-05,
92
+ "loss": 6.5651,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.47653958944281527,
97
+ "grad_norm": 4.634731292724609,
98
+ "learning_rate": 9.18059652572927e-05,
99
+ "loss": 6.4742,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.5131964809384164,
104
+ "grad_norm": 5.389685153961182,
105
+ "learning_rate": 9.117565489246905e-05,
106
+ "loss": 6.3593,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.5498533724340176,
111
+ "grad_norm": 6.881243705749512,
112
+ "learning_rate": 9.054534452764542e-05,
113
+ "loss": 6.2916,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.5865102639296188,
118
+ "grad_norm": 6.123986721038818,
119
+ "learning_rate": 8.991503416282178e-05,
120
+ "loss": 6.2029,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.6231671554252199,
125
+ "grad_norm": 6.262916088104248,
126
+ "learning_rate": 8.928472379799813e-05,
127
+ "loss": 6.1005,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.6598240469208211,
132
+ "grad_norm": 7.570896625518799,
133
+ "learning_rate": 8.86544134331745e-05,
134
+ "loss": 6.0054,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.6964809384164223,
139
+ "grad_norm": 6.367081642150879,
140
+ "learning_rate": 8.802410306835086e-05,
141
+ "loss": 5.8283,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.7331378299120235,
146
+ "grad_norm": 6.622028350830078,
147
+ "learning_rate": 8.739379270352722e-05,
148
+ "loss": 5.7653,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.7697947214076246,
153
+ "grad_norm": 6.616864204406738,
154
+ "learning_rate": 8.676348233870359e-05,
155
+ "loss": 5.6764,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.8064516129032258,
160
+ "grad_norm": 7.048656463623047,
161
+ "learning_rate": 8.613317197387994e-05,
162
+ "loss": 5.5562,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.843108504398827,
167
+ "grad_norm": 6.860437870025635,
168
+ "learning_rate": 8.55028616090563e-05,
169
+ "loss": 5.4657,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.8797653958944281,
174
+ "grad_norm": 6.002134799957275,
175
+ "learning_rate": 8.487255124423267e-05,
176
+ "loss": 5.3649,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.9164222873900293,
181
+ "grad_norm": 7.97310209274292,
182
+ "learning_rate": 8.424224087940903e-05,
183
+ "loss": 5.3526,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.9530791788856305,
188
+ "grad_norm": 5.980320930480957,
189
+ "learning_rate": 8.361193051458538e-05,
190
+ "loss": 5.2898,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 0.9897360703812317,
195
+ "grad_norm": 7.705748558044434,
196
+ "learning_rate": 8.298162014976175e-05,
197
+ "loss": 5.1842,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 1.0,
202
+ "eval_loss": 5.10765266418457,
203
+ "eval_runtime": 51.2669,
204
+ "eval_samples_per_second": 751.187,
205
+ "eval_steps_per_second": 46.95,
206
+ "step": 13640
207
+ },
208
+ {
209
+ "epoch": 1.0263929618768328,
210
+ "grad_norm": 7.542203426361084,
211
+ "learning_rate": 8.23513097849381e-05,
212
+ "loss": 5.1511,
213
+ "step": 14000
214
+ },
215
+ {
216
+ "epoch": 1.063049853372434,
217
+ "grad_norm": 6.65974235534668,
218
+ "learning_rate": 8.172099942011447e-05,
219
+ "loss": 5.1524,
220
+ "step": 14500
221
+ },
222
+ {
223
+ "epoch": 1.099706744868035,
224
+ "grad_norm": 6.591290473937988,
225
+ "learning_rate": 8.109068905529082e-05,
226
+ "loss": 5.0419,
227
+ "step": 15000
228
+ },
229
+ {
230
+ "epoch": 1.1363636363636362,
231
+ "grad_norm": 6.578639507293701,
232
+ "learning_rate": 8.046037869046718e-05,
233
+ "loss": 4.9851,
234
+ "step": 15500
235
+ },
236
+ {
237
+ "epoch": 1.1730205278592376,
238
+ "grad_norm": 6.83113956451416,
239
+ "learning_rate": 7.983006832564355e-05,
240
+ "loss": 4.9795,
241
+ "step": 16000
242
+ },
243
+ {
244
+ "epoch": 1.2096774193548387,
245
+ "grad_norm": 6.948678493499756,
246
+ "learning_rate": 7.919975796081991e-05,
247
+ "loss": 4.9811,
248
+ "step": 16500
249
+ },
250
+ {
251
+ "epoch": 1.2463343108504399,
252
+ "grad_norm": 6.949957847595215,
253
+ "learning_rate": 7.856944759599628e-05,
254
+ "loss": 4.9127,
255
+ "step": 17000
256
+ },
257
+ {
258
+ "epoch": 1.282991202346041,
259
+ "grad_norm": 6.94000768661499,
260
+ "learning_rate": 7.793913723117263e-05,
261
+ "loss": 4.9336,
262
+ "step": 17500
263
+ },
264
+ {
265
+ "epoch": 1.3196480938416422,
266
+ "grad_norm": 6.532993316650391,
267
+ "learning_rate": 7.730882686634899e-05,
268
+ "loss": 4.8546,
269
+ "step": 18000
270
+ },
271
+ {
272
+ "epoch": 1.3563049853372435,
273
+ "grad_norm": 7.553442001342773,
274
+ "learning_rate": 7.667851650152536e-05,
275
+ "loss": 4.7791,
276
+ "step": 18500
277
+ },
278
+ {
279
+ "epoch": 1.3929618768328447,
280
+ "grad_norm": 6.4063720703125,
281
+ "learning_rate": 7.604820613670172e-05,
282
+ "loss": 4.8218,
283
+ "step": 19000
284
+ },
285
+ {
286
+ "epoch": 1.4296187683284458,
287
+ "grad_norm": 8.8884916305542,
288
+ "learning_rate": 7.541789577187807e-05,
289
+ "loss": 4.756,
290
+ "step": 19500
291
+ },
292
+ {
293
+ "epoch": 1.466275659824047,
294
+ "grad_norm": 7.412301540374756,
295
+ "learning_rate": 7.478758540705444e-05,
296
+ "loss": 4.7164,
297
+ "step": 20000
298
+ },
299
+ {
300
+ "epoch": 1.502932551319648,
301
+ "grad_norm": 5.796535491943359,
302
+ "learning_rate": 7.41572750422308e-05,
303
+ "loss": 4.7209,
304
+ "step": 20500
305
+ },
306
+ {
307
+ "epoch": 1.5395894428152492,
308
+ "grad_norm": 6.591666221618652,
309
+ "learning_rate": 7.352696467740716e-05,
310
+ "loss": 4.6933,
311
+ "step": 21000
312
+ },
313
+ {
314
+ "epoch": 1.5762463343108504,
315
+ "grad_norm": 8.342963218688965,
316
+ "learning_rate": 7.289665431258353e-05,
317
+ "loss": 4.6505,
318
+ "step": 21500
319
+ },
320
+ {
321
+ "epoch": 1.6129032258064515,
322
+ "grad_norm": 7.765003681182861,
323
+ "learning_rate": 7.226634394775988e-05,
324
+ "loss": 4.5958,
325
+ "step": 22000
326
+ },
327
+ {
328
+ "epoch": 1.6495601173020527,
329
+ "grad_norm": 8.44519329071045,
330
+ "learning_rate": 7.163603358293624e-05,
331
+ "loss": 4.5874,
332
+ "step": 22500
333
+ },
334
+ {
335
+ "epoch": 1.6862170087976538,
336
+ "grad_norm": 10.166460037231445,
337
+ "learning_rate": 7.100572321811261e-05,
338
+ "loss": 4.588,
339
+ "step": 23000
340
+ },
341
+ {
342
+ "epoch": 1.7228739002932552,
343
+ "grad_norm": 6.965490341186523,
344
+ "learning_rate": 7.037541285328895e-05,
345
+ "loss": 4.6057,
346
+ "step": 23500
347
+ },
348
+ {
349
+ "epoch": 1.7595307917888563,
350
+ "grad_norm": 7.495148181915283,
351
+ "learning_rate": 6.974510248846532e-05,
352
+ "loss": 4.5788,
353
+ "step": 24000
354
+ },
355
+ {
356
+ "epoch": 1.7961876832844574,
357
+ "grad_norm": 8.987942695617676,
358
+ "learning_rate": 6.911479212364168e-05,
359
+ "loss": 4.5289,
360
+ "step": 24500
361
+ },
362
+ {
363
+ "epoch": 1.8328445747800588,
364
+ "grad_norm": 6.871776580810547,
365
+ "learning_rate": 6.848448175881804e-05,
366
+ "loss": 4.5326,
367
+ "step": 25000
368
+ },
369
+ {
370
+ "epoch": 1.86950146627566,
371
+ "grad_norm": 6.7767744064331055,
372
+ "learning_rate": 6.78541713939944e-05,
373
+ "loss": 4.4945,
374
+ "step": 25500
375
+ },
376
+ {
377
+ "epoch": 1.906158357771261,
378
+ "grad_norm": 10.17478084564209,
379
+ "learning_rate": 6.722386102917076e-05,
380
+ "loss": 4.4387,
381
+ "step": 26000
382
+ },
383
+ {
384
+ "epoch": 1.9428152492668622,
385
+ "grad_norm": 8.18852424621582,
386
+ "learning_rate": 6.659355066434713e-05,
387
+ "loss": 4.4369,
388
+ "step": 26500
389
+ },
390
+ {
391
+ "epoch": 1.9794721407624634,
392
+ "grad_norm": 10.012794494628906,
393
+ "learning_rate": 6.596324029952349e-05,
394
+ "loss": 4.3956,
395
+ "step": 27000
396
+ },
397
+ {
398
+ "epoch": 2.0,
399
+ "eval_loss": 4.3589653968811035,
400
+ "eval_runtime": 52.0275,
401
+ "eval_samples_per_second": 740.205,
402
+ "eval_steps_per_second": 46.264,
403
+ "step": 27280
404
+ },
405
+ {
406
+ "epoch": 2.0161290322580645,
407
+ "grad_norm": 7.973904132843018,
408
+ "learning_rate": 6.533292993469985e-05,
409
+ "loss": 4.4279,
410
+ "step": 27500
411
+ },
412
+ {
413
+ "epoch": 2.0527859237536656,
414
+ "grad_norm": 7.848902225494385,
415
+ "learning_rate": 6.470261956987622e-05,
416
+ "loss": 4.3801,
417
+ "step": 28000
418
+ },
419
+ {
420
+ "epoch": 2.089442815249267,
421
+ "grad_norm": 7.455059051513672,
422
+ "learning_rate": 6.407230920505257e-05,
423
+ "loss": 4.3868,
424
+ "step": 28500
425
+ },
426
+ {
427
+ "epoch": 2.126099706744868,
428
+ "grad_norm": 8.987055778503418,
429
+ "learning_rate": 6.344199884022893e-05,
430
+ "loss": 4.3451,
431
+ "step": 29000
432
+ },
433
+ {
434
+ "epoch": 2.162756598240469,
435
+ "grad_norm": 7.139368534088135,
436
+ "learning_rate": 6.28116884754053e-05,
437
+ "loss": 4.3601,
438
+ "step": 29500
439
+ },
440
+ {
441
+ "epoch": 2.19941348973607,
442
+ "grad_norm": 7.4019317626953125,
443
+ "learning_rate": 6.218137811058166e-05,
444
+ "loss": 4.3565,
445
+ "step": 30000
446
+ },
447
+ {
448
+ "epoch": 2.236070381231672,
449
+ "grad_norm": 8.461463928222656,
450
+ "learning_rate": 6.155106774575801e-05,
451
+ "loss": 4.2893,
452
+ "step": 30500
453
+ },
454
+ {
455
+ "epoch": 2.2727272727272725,
456
+ "grad_norm": 8.040552139282227,
457
+ "learning_rate": 6.0920757380934376e-05,
458
+ "loss": 4.2938,
459
+ "step": 31000
460
+ },
461
+ {
462
+ "epoch": 2.309384164222874,
463
+ "grad_norm": 8.279471397399902,
464
+ "learning_rate": 6.029044701611074e-05,
465
+ "loss": 4.2922,
466
+ "step": 31500
467
+ },
468
+ {
469
+ "epoch": 2.346041055718475,
470
+ "grad_norm": 7.4184699058532715,
471
+ "learning_rate": 5.96601366512871e-05,
472
+ "loss": 4.2655,
473
+ "step": 32000
474
+ },
475
+ {
476
+ "epoch": 2.3826979472140764,
477
+ "grad_norm": 9.337892532348633,
478
+ "learning_rate": 5.902982628646345e-05,
479
+ "loss": 4.2428,
480
+ "step": 32500
481
+ },
482
+ {
483
+ "epoch": 2.4193548387096775,
484
+ "grad_norm": 8.708230018615723,
485
+ "learning_rate": 5.8399515921639816e-05,
486
+ "loss": 4.2081,
487
+ "step": 33000
488
+ },
489
+ {
490
+ "epoch": 2.4560117302052786,
491
+ "grad_norm": 7.0168938636779785,
492
+ "learning_rate": 5.776920555681617e-05,
493
+ "loss": 4.2089,
494
+ "step": 33500
495
+ },
496
+ {
497
+ "epoch": 2.4926686217008798,
498
+ "grad_norm": 9.225556373596191,
499
+ "learning_rate": 5.7138895191992536e-05,
500
+ "loss": 4.226,
501
+ "step": 34000
502
+ },
503
+ {
504
+ "epoch": 2.529325513196481,
505
+ "grad_norm": 7.094930648803711,
506
+ "learning_rate": 5.65085848271689e-05,
507
+ "loss": 4.1786,
508
+ "step": 34500
509
+ },
510
+ {
511
+ "epoch": 2.565982404692082,
512
+ "grad_norm": 7.8396711349487305,
513
+ "learning_rate": 5.587827446234526e-05,
514
+ "loss": 4.2071,
515
+ "step": 35000
516
+ },
517
+ {
518
+ "epoch": 2.602639296187683,
519
+ "grad_norm": 8.818264961242676,
520
+ "learning_rate": 5.524796409752162e-05,
521
+ "loss": 4.1563,
522
+ "step": 35500
523
+ },
524
+ {
525
+ "epoch": 2.6392961876832843,
526
+ "grad_norm": 7.717746734619141,
527
+ "learning_rate": 5.461765373269798e-05,
528
+ "loss": 4.165,
529
+ "step": 36000
530
+ },
531
+ {
532
+ "epoch": 2.6759530791788855,
533
+ "grad_norm": 6.068331718444824,
534
+ "learning_rate": 5.3987343367874346e-05,
535
+ "loss": 4.1111,
536
+ "step": 36500
537
+ },
538
+ {
539
+ "epoch": 2.712609970674487,
540
+ "grad_norm": 8.796777725219727,
541
+ "learning_rate": 5.33570330030507e-05,
542
+ "loss": 4.1574,
543
+ "step": 37000
544
+ },
545
+ {
546
+ "epoch": 2.7492668621700878,
547
+ "grad_norm": 8.890911102294922,
548
+ "learning_rate": 5.2726722638227066e-05,
549
+ "loss": 4.1259,
550
+ "step": 37500
551
+ },
552
+ {
553
+ "epoch": 2.7859237536656893,
554
+ "grad_norm": 8.333062171936035,
555
+ "learning_rate": 5.209641227340343e-05,
556
+ "loss": 4.1107,
557
+ "step": 38000
558
+ },
559
+ {
560
+ "epoch": 2.8225806451612905,
561
+ "grad_norm": 8.116930961608887,
562
+ "learning_rate": 5.146610190857979e-05,
563
+ "loss": 4.1155,
564
+ "step": 38500
565
+ },
566
+ {
567
+ "epoch": 2.8592375366568916,
568
+ "grad_norm": 11.292548179626465,
569
+ "learning_rate": 5.083579154375615e-05,
570
+ "loss": 4.0813,
571
+ "step": 39000
572
+ },
573
+ {
574
+ "epoch": 2.8958944281524928,
575
+ "grad_norm": 8.076095581054688,
576
+ "learning_rate": 5.020548117893251e-05,
577
+ "loss": 4.1091,
578
+ "step": 39500
579
+ },
580
+ {
581
+ "epoch": 2.932551319648094,
582
+ "grad_norm": 6.882072925567627,
583
+ "learning_rate": 4.957517081410887e-05,
584
+ "loss": 4.082,
585
+ "step": 40000
586
+ },
587
+ {
588
+ "epoch": 2.969208211143695,
589
+ "grad_norm": 8.762887954711914,
590
+ "learning_rate": 4.894486044928523e-05,
591
+ "loss": 4.0442,
592
+ "step": 40500
593
+ },
594
+ {
595
+ "epoch": 3.0,
596
+ "eval_loss": 3.9874393939971924,
597
+ "eval_runtime": 51.3732,
598
+ "eval_samples_per_second": 749.632,
599
+ "eval_steps_per_second": 46.853,
600
+ "step": 40920
601
+ },
602
+ {
603
+ "epoch": 3.005865102639296,
604
+ "grad_norm": 6.891060829162598,
605
+ "learning_rate": 4.831455008446159e-05,
606
+ "loss": 4.0661,
607
+ "step": 41000
608
+ },
609
+ {
610
+ "epoch": 3.0425219941348973,
611
+ "grad_norm": 9.079097747802734,
612
+ "learning_rate": 4.768423971963795e-05,
613
+ "loss": 3.999,
614
+ "step": 41500
615
+ },
616
+ {
617
+ "epoch": 3.0791788856304985,
618
+ "grad_norm": 9.445289611816406,
619
+ "learning_rate": 4.7053929354814315e-05,
620
+ "loss": 4.045,
621
+ "step": 42000
622
+ },
623
+ {
624
+ "epoch": 3.1158357771260996,
625
+ "grad_norm": 7.992264270782471,
626
+ "learning_rate": 4.642361898999067e-05,
627
+ "loss": 4.0385,
628
+ "step": 42500
629
+ },
630
+ {
631
+ "epoch": 3.1524926686217007,
632
+ "grad_norm": 8.101459503173828,
633
+ "learning_rate": 4.5793308625167035e-05,
634
+ "loss": 3.9818,
635
+ "step": 43000
636
+ },
637
+ {
638
+ "epoch": 3.189149560117302,
639
+ "grad_norm": 7.8059492111206055,
640
+ "learning_rate": 4.51629982603434e-05,
641
+ "loss": 3.9905,
642
+ "step": 43500
643
+ },
644
+ {
645
+ "epoch": 3.225806451612903,
646
+ "grad_norm": 10.241538047790527,
647
+ "learning_rate": 4.4532687895519755e-05,
648
+ "loss": 3.9456,
649
+ "step": 44000
650
+ },
651
+ {
652
+ "epoch": 3.2624633431085046,
653
+ "grad_norm": 8.502156257629395,
654
+ "learning_rate": 4.390237753069611e-05,
655
+ "loss": 3.9347,
656
+ "step": 44500
657
+ },
658
+ {
659
+ "epoch": 3.2991202346041058,
660
+ "grad_norm": 7.6501641273498535,
661
+ "learning_rate": 4.3272067165872475e-05,
662
+ "loss": 3.9469,
663
+ "step": 45000
664
+ },
665
+ {
666
+ "epoch": 3.335777126099707,
667
+ "grad_norm": 8.457347869873047,
668
+ "learning_rate": 4.264175680104884e-05,
669
+ "loss": 3.9397,
670
+ "step": 45500
671
+ },
672
+ {
673
+ "epoch": 3.372434017595308,
674
+ "grad_norm": 8.348608016967773,
675
+ "learning_rate": 4.20114464362252e-05,
676
+ "loss": 3.9413,
677
+ "step": 46000
678
+ },
679
+ {
680
+ "epoch": 3.409090909090909,
681
+ "grad_norm": 10.004755020141602,
682
+ "learning_rate": 4.138113607140156e-05,
683
+ "loss": 3.9057,
684
+ "step": 46500
685
+ },
686
+ {
687
+ "epoch": 3.4457478005865103,
688
+ "grad_norm": 7.643105983734131,
689
+ "learning_rate": 4.075082570657792e-05,
690
+ "loss": 3.9165,
691
+ "step": 47000
692
+ },
693
+ {
694
+ "epoch": 3.4824046920821115,
695
+ "grad_norm": 9.214630126953125,
696
+ "learning_rate": 4.0120515341754285e-05,
697
+ "loss": 3.8871,
698
+ "step": 47500
699
+ },
700
+ {
701
+ "epoch": 3.5190615835777126,
702
+ "grad_norm": 7.3644700050354,
703
+ "learning_rate": 3.949020497693065e-05,
704
+ "loss": 3.9115,
705
+ "step": 48000
706
+ },
707
+ {
708
+ "epoch": 3.5557184750733137,
709
+ "grad_norm": 8.032934188842773,
710
+ "learning_rate": 3.8859894612107e-05,
711
+ "loss": 3.8775,
712
+ "step": 48500
713
+ },
714
+ {
715
+ "epoch": 3.592375366568915,
716
+ "grad_norm": 8.48763370513916,
717
+ "learning_rate": 3.822958424728336e-05,
718
+ "loss": 3.8719,
719
+ "step": 49000
720
+ },
721
+ {
722
+ "epoch": 3.629032258064516,
723
+ "grad_norm": 7.765323162078857,
724
+ "learning_rate": 3.7599273882459725e-05,
725
+ "loss": 3.8727,
726
+ "step": 49500
727
+ },
728
+ {
729
+ "epoch": 3.665689149560117,
730
+ "grad_norm": 9.104835510253906,
731
+ "learning_rate": 3.696896351763609e-05,
732
+ "loss": 3.847,
733
+ "step": 50000
734
+ },
735
+ {
736
+ "epoch": 3.7023460410557183,
737
+ "grad_norm": 7.518016815185547,
738
+ "learning_rate": 3.6338653152812445e-05,
739
+ "loss": 3.8503,
740
+ "step": 50500
741
+ },
742
+ {
743
+ "epoch": 3.73900293255132,
744
+ "grad_norm": 9.076459884643555,
745
+ "learning_rate": 3.570834278798881e-05,
746
+ "loss": 3.8496,
747
+ "step": 51000
748
+ },
749
+ {
750
+ "epoch": 3.7756598240469206,
751
+ "grad_norm": 9.251144409179688,
752
+ "learning_rate": 3.507803242316517e-05,
753
+ "loss": 3.8394,
754
+ "step": 51500
755
+ },
756
+ {
757
+ "epoch": 3.812316715542522,
758
+ "grad_norm": 9.594878196716309,
759
+ "learning_rate": 3.444772205834153e-05,
760
+ "loss": 3.8104,
761
+ "step": 52000
762
+ },
763
+ {
764
+ "epoch": 3.8489736070381233,
765
+ "grad_norm": 7.103595733642578,
766
+ "learning_rate": 3.381741169351789e-05,
767
+ "loss": 3.8329,
768
+ "step": 52500
769
+ },
770
+ {
771
+ "epoch": 3.8856304985337244,
772
+ "grad_norm": 7.397706985473633,
773
+ "learning_rate": 3.3187101328694254e-05,
774
+ "loss": 3.8172,
775
+ "step": 53000
776
+ },
777
+ {
778
+ "epoch": 3.9222873900293256,
779
+ "grad_norm": 8.312359809875488,
780
+ "learning_rate": 3.255679096387061e-05,
781
+ "loss": 3.8246,
782
+ "step": 53500
783
+ },
784
+ {
785
+ "epoch": 3.9589442815249267,
786
+ "grad_norm": 7.361260414123535,
787
+ "learning_rate": 3.192648059904697e-05,
788
+ "loss": 3.8078,
789
+ "step": 54000
790
+ },
791
+ {
792
+ "epoch": 3.995601173020528,
793
+ "grad_norm": 9.614564895629883,
794
+ "learning_rate": 3.129617023422333e-05,
795
+ "loss": 3.7865,
796
+ "step": 54500
797
+ },
798
+ {
799
+ "epoch": 4.0,
800
+ "eval_loss": 3.7747433185577393,
801
+ "eval_runtime": 51.2384,
802
+ "eval_samples_per_second": 751.604,
803
+ "eval_steps_per_second": 46.976,
804
+ "step": 54560
805
+ },
806
+ {
807
+ "epoch": 4.032258064516129,
808
+ "grad_norm": 9.029661178588867,
809
+ "learning_rate": 3.0665859869399694e-05,
810
+ "loss": 3.7978,
811
+ "step": 55000
812
+ },
813
+ {
814
+ "epoch": 4.068914956011731,
815
+ "grad_norm": 9.358321189880371,
816
+ "learning_rate": 3.0035549504576054e-05,
817
+ "loss": 3.821,
818
+ "step": 55500
819
+ },
820
+ {
821
+ "epoch": 4.105571847507331,
822
+ "grad_norm": 9.089591979980469,
823
+ "learning_rate": 2.9405239139752418e-05,
824
+ "loss": 3.7474,
825
+ "step": 56000
826
+ },
827
+ {
828
+ "epoch": 4.142228739002933,
829
+ "grad_norm": 9.139451026916504,
830
+ "learning_rate": 2.8774928774928778e-05,
831
+ "loss": 3.7571,
832
+ "step": 56500
833
+ },
834
+ {
835
+ "epoch": 4.178885630498534,
836
+ "grad_norm": 9.728781700134277,
837
+ "learning_rate": 2.8144618410105137e-05,
838
+ "loss": 3.8133,
839
+ "step": 57000
840
+ },
841
+ {
842
+ "epoch": 4.215542521994135,
843
+ "grad_norm": 8.330384254455566,
844
+ "learning_rate": 2.75143080452815e-05,
845
+ "loss": 3.7412,
846
+ "step": 57500
847
+ },
848
+ {
849
+ "epoch": 4.252199413489736,
850
+ "grad_norm": 9.436174392700195,
851
+ "learning_rate": 2.6883997680457857e-05,
852
+ "loss": 3.7338,
853
+ "step": 58000
854
+ },
855
+ {
856
+ "epoch": 4.288856304985337,
857
+ "grad_norm": 12.170429229736328,
858
+ "learning_rate": 2.6253687315634217e-05,
859
+ "loss": 3.7215,
860
+ "step": 58500
861
+ },
862
+ {
863
+ "epoch": 4.325513196480938,
864
+ "grad_norm": 8.019417762756348,
865
+ "learning_rate": 2.562337695081058e-05,
866
+ "loss": 3.7096,
867
+ "step": 59000
868
+ },
869
+ {
870
+ "epoch": 4.36217008797654,
871
+ "grad_norm": 7.6509480476379395,
872
+ "learning_rate": 2.499306658598694e-05,
873
+ "loss": 3.7279,
874
+ "step": 59500
875
+ },
876
+ {
877
+ "epoch": 4.39882697947214,
878
+ "grad_norm": 8.255581855773926,
879
+ "learning_rate": 2.43627562211633e-05,
880
+ "loss": 3.749,
881
+ "step": 60000
882
+ },
883
+ {
884
+ "epoch": 4.435483870967742,
885
+ "grad_norm": 9.91395378112793,
886
+ "learning_rate": 2.3732445856339664e-05,
887
+ "loss": 3.6773,
888
+ "step": 60500
889
+ },
890
+ {
891
+ "epoch": 4.472140762463344,
892
+ "grad_norm": 9.325223922729492,
893
+ "learning_rate": 2.3102135491516024e-05,
894
+ "loss": 3.7204,
895
+ "step": 61000
896
+ },
897
+ {
898
+ "epoch": 4.508797653958944,
899
+ "grad_norm": 9.393867492675781,
900
+ "learning_rate": 2.2471825126692384e-05,
901
+ "loss": 3.6893,
902
+ "step": 61500
903
+ },
904
+ {
905
+ "epoch": 4.545454545454545,
906
+ "grad_norm": 8.97889232635498,
907
+ "learning_rate": 2.1841514761868744e-05,
908
+ "loss": 3.6765,
909
+ "step": 62000
910
+ },
911
+ {
912
+ "epoch": 4.5821114369501466,
913
+ "grad_norm": 7.196798324584961,
914
+ "learning_rate": 2.1211204397045107e-05,
915
+ "loss": 3.6679,
916
+ "step": 62500
917
+ },
918
+ {
919
+ "epoch": 4.618768328445748,
920
+ "grad_norm": 9.22948932647705,
921
+ "learning_rate": 2.0580894032221467e-05,
922
+ "loss": 3.6591,
923
+ "step": 63000
924
+ },
925
+ {
926
+ "epoch": 4.655425219941349,
927
+ "grad_norm": 8.780097961425781,
928
+ "learning_rate": 1.9950583667397827e-05,
929
+ "loss": 3.6391,
930
+ "step": 63500
931
+ },
932
+ {
933
+ "epoch": 4.69208211143695,
934
+ "grad_norm": 10.625210762023926,
935
+ "learning_rate": 1.9320273302574187e-05,
936
+ "loss": 3.6819,
937
+ "step": 64000
938
+ },
939
+ {
940
+ "epoch": 4.728739002932551,
941
+ "grad_norm": 7.736958980560303,
942
+ "learning_rate": 1.868996293775055e-05,
943
+ "loss": 3.6486,
944
+ "step": 64500
945
+ },
946
+ {
947
+ "epoch": 4.765395894428153,
948
+ "grad_norm": 8.629966735839844,
949
+ "learning_rate": 1.805965257292691e-05,
950
+ "loss": 3.6629,
951
+ "step": 65000
952
+ },
953
+ {
954
+ "epoch": 4.802052785923753,
955
+ "grad_norm": 7.5463762283325195,
956
+ "learning_rate": 1.7429342208103274e-05,
957
+ "loss": 3.6398,
958
+ "step": 65500
959
+ },
960
+ {
961
+ "epoch": 4.838709677419355,
962
+ "grad_norm": 7.877403736114502,
963
+ "learning_rate": 1.679903184327963e-05,
964
+ "loss": 3.6593,
965
+ "step": 66000
966
+ },
967
+ {
968
+ "epoch": 4.875366568914956,
969
+ "grad_norm": 8.22919750213623,
970
+ "learning_rate": 1.6168721478455993e-05,
971
+ "loss": 3.6139,
972
+ "step": 66500
973
+ },
974
+ {
975
+ "epoch": 4.912023460410557,
976
+ "grad_norm": 9.631176948547363,
977
+ "learning_rate": 1.5538411113632353e-05,
978
+ "loss": 3.6452,
979
+ "step": 67000
980
+ },
981
+ {
982
+ "epoch": 4.948680351906159,
983
+ "grad_norm": 8.381847381591797,
984
+ "learning_rate": 1.4908100748808715e-05,
985
+ "loss": 3.6273,
986
+ "step": 67500
987
+ },
988
+ {
989
+ "epoch": 4.9853372434017595,
990
+ "grad_norm": 9.712096214294434,
991
+ "learning_rate": 1.4277790383985077e-05,
992
+ "loss": 3.5952,
993
+ "step": 68000
994
+ },
995
+ {
996
+ "epoch": 5.0,
997
+ "eval_loss": 3.599792003631592,
998
+ "eval_runtime": 51.3354,
999
+ "eval_samples_per_second": 750.184,
1000
+ "eval_steps_per_second": 46.888,
1001
+ "step": 68200
1002
+ },
1003
+ {
1004
+ "epoch": 5.021994134897361,
1005
+ "grad_norm": 9.814529418945312,
1006
+ "learning_rate": 1.3647480019161435e-05,
1007
+ "loss": 3.6124,
1008
+ "step": 68500
1009
+ },
1010
+ {
1011
+ "epoch": 5.058651026392962,
1012
+ "grad_norm": 9.232531547546387,
1013
+ "learning_rate": 1.3017169654337797e-05,
1014
+ "loss": 3.6207,
1015
+ "step": 69000
1016
+ },
1017
+ {
1018
+ "epoch": 5.095307917888563,
1019
+ "grad_norm": 9.92640495300293,
1020
+ "learning_rate": 1.2386859289514158e-05,
1021
+ "loss": 3.6176,
1022
+ "step": 69500
1023
+ },
1024
+ {
1025
+ "epoch": 5.131964809384164,
1026
+ "grad_norm": 9.3385591506958,
1027
+ "learning_rate": 1.1756548924690518e-05,
1028
+ "loss": 3.6151,
1029
+ "step": 70000
1030
+ },
1031
+ {
1032
+ "epoch": 5.168621700879766,
1033
+ "grad_norm": 8.617002487182617,
1034
+ "learning_rate": 1.112623855986688e-05,
1035
+ "loss": 3.621,
1036
+ "step": 70500
1037
+ },
1038
+ {
1039
+ "epoch": 5.205278592375366,
1040
+ "grad_norm": 8.497230529785156,
1041
+ "learning_rate": 1.049592819504324e-05,
1042
+ "loss": 3.6085,
1043
+ "step": 71000
1044
+ },
1045
+ {
1046
+ "epoch": 5.241935483870968,
1047
+ "grad_norm": 8.745635986328125,
1048
+ "learning_rate": 9.8656178302196e-06,
1049
+ "loss": 3.5636,
1050
+ "step": 71500
1051
+ },
1052
+ {
1053
+ "epoch": 5.278592375366569,
1054
+ "grad_norm": 7.370077610015869,
1055
+ "learning_rate": 9.235307465395961e-06,
1056
+ "loss": 3.5896,
1057
+ "step": 72000
1058
+ },
1059
+ {
1060
+ "epoch": 5.31524926686217,
1061
+ "grad_norm": 9.268915176391602,
1062
+ "learning_rate": 8.604997100572321e-06,
1063
+ "loss": 3.5571,
1064
+ "step": 72500
1065
+ },
1066
+ {
1067
+ "epoch": 5.351906158357771,
1068
+ "grad_norm": 8.88790225982666,
1069
+ "learning_rate": 7.974686735748683e-06,
1070
+ "loss": 3.5424,
1071
+ "step": 73000
1072
+ },
1073
+ {
1074
+ "epoch": 5.3885630498533725,
1075
+ "grad_norm": 6.400046348571777,
1076
+ "learning_rate": 7.344376370925044e-06,
1077
+ "loss": 3.5482,
1078
+ "step": 73500
1079
+ },
1080
+ {
1081
+ "epoch": 5.425219941348973,
1082
+ "grad_norm": 8.085587501525879,
1083
+ "learning_rate": 6.714066006101405e-06,
1084
+ "loss": 3.5732,
1085
+ "step": 74000
1086
+ },
1087
+ {
1088
+ "epoch": 5.461876832844575,
1089
+ "grad_norm": 8.79615306854248,
1090
+ "learning_rate": 6.083755641277765e-06,
1091
+ "loss": 3.5689,
1092
+ "step": 74500
1093
+ },
1094
+ {
1095
+ "epoch": 5.4985337243401755,
1096
+ "grad_norm": 9.852959632873535,
1097
+ "learning_rate": 5.453445276454126e-06,
1098
+ "loss": 3.542,
1099
+ "step": 75000
1100
+ },
1101
+ {
1102
+ "epoch": 5.535190615835777,
1103
+ "grad_norm": 9.936841011047363,
1104
+ "learning_rate": 4.823134911630487e-06,
1105
+ "loss": 3.5407,
1106
+ "step": 75500
1107
+ },
1108
+ {
1109
+ "epoch": 5.571847507331379,
1110
+ "grad_norm": 9.2828950881958,
1111
+ "learning_rate": 4.192824546806848e-06,
1112
+ "loss": 3.547,
1113
+ "step": 76000
1114
+ },
1115
+ {
1116
+ "epoch": 5.608504398826979,
1117
+ "grad_norm": 8.38242244720459,
1118
+ "learning_rate": 3.5625141819832086e-06,
1119
+ "loss": 3.5334,
1120
+ "step": 76500
1121
+ },
1122
+ {
1123
+ "epoch": 5.645161290322581,
1124
+ "grad_norm": 7.721536159515381,
1125
+ "learning_rate": 2.9322038171595694e-06,
1126
+ "loss": 3.5499,
1127
+ "step": 77000
1128
+ },
1129
+ {
1130
+ "epoch": 5.681818181818182,
1131
+ "grad_norm": 8.407939910888672,
1132
+ "learning_rate": 2.30189345233593e-06,
1133
+ "loss": 3.4661,
1134
+ "step": 77500
1135
+ },
1136
+ {
1137
+ "epoch": 5.718475073313783,
1138
+ "grad_norm": 9.764538764953613,
1139
+ "learning_rate": 1.671583087512291e-06,
1140
+ "loss": 3.5483,
1141
+ "step": 78000
1142
+ },
1143
+ {
1144
+ "epoch": 5.755131964809384,
1145
+ "grad_norm": 8.228140830993652,
1146
+ "learning_rate": 1.0412727226886518e-06,
1147
+ "loss": 3.5607,
1148
+ "step": 78500
1149
+ },
1150
+ {
1151
+ "epoch": 5.7917888563049855,
1152
+ "grad_norm": 11.577902793884277,
1153
+ "learning_rate": 4.1096235786501275e-07,
1154
+ "loss": 3.5589,
1155
+ "step": 79000
1156
+ }
1157
+ ],
1158
+ "logging_steps": 500,
1159
+ "max_steps": 79326,
1160
+ "num_input_tokens_seen": 0,
1161
+ "num_train_epochs": 6,
1162
+ "save_steps": 8192,
1163
+ "stateful_callbacks": {
1164
+ "TrainerControl": {
1165
+ "args": {
1166
+ "should_epoch_stop": false,
1167
+ "should_evaluate": false,
1168
+ "should_log": false,
1169
+ "should_save": true,
1170
+ "should_training_stop": true
1171
+ },
1172
+ "attributes": {}
1173
+ }
1174
+ },
1175
+ "total_flos": 2.5090344956154816e+16,
1176
+ "train_batch_size": 16,
1177
+ "trial_name": null,
1178
+ "trial_params": null
1179
+ }
checkpoint-79326/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:676dd131dab84bc88e00e7a4524046f1cf21d1d4d935bf87e4874cfca4c52596
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 sha256:4d3beec9c55d11d028eaf3e776b5c68b8a33fe69cbfbf1781e06df6bee9cefd7
3
+ size 334030264
runs/Oct03_11-53-34_1c87c8c911de/events.out.tfevents.1727956415.1c87c8c911de.2181.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:610aa86640e6ffd42dbb9dc379647a934922d3438a1d831513866ec8cd00c4bf
3
+ size 40811
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 sha256:676dd131dab84bc88e00e7a4524046f1cf21d1d4d935bf87e4874cfca4c52596
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff