Hugging Face's logo

nlpie
/
modernalbert-large-v1.0

Fill-Mask
Transformers
PyTorch
TensorBoard
Safetensors
ModernALBERT
modernalbert
albert
mixture-of-experts
lora
recursive-transformer
flash-attention
rotary-embeddings
custom_code
Model card Files
xet
 Metrics Community
mohammadmahdinouri commited on
Commit
9b91b42
·
verified ·
1 Parent(s): 9bf8976

checkpoint-77000

Browse files
Files changed (40) hide show
  1. checkpoint_22_1a37557/config.json +36 -0
  2. checkpoint_22_1a37557/last-checkpoint/config.json +36 -0
  3. checkpoint_22_1a37557/last-checkpoint/optimizer.pt +3 -0
  4. checkpoint_22_1a37557/last-checkpoint/pytorch_model.bin +3 -0
  5. checkpoint_22_1a37557/last-checkpoint/rng_state_0.pth +3 -0
  6. checkpoint_22_1a37557/last-checkpoint/rng_state_1.pth +3 -0
  7. checkpoint_22_1a37557/last-checkpoint/rng_state_2.pth +3 -0
  8. checkpoint_22_1a37557/last-checkpoint/rng_state_3.pth +3 -0
  9. checkpoint_22_1a37557/last-checkpoint/scheduler.pt +3 -0
  10. checkpoint_22_1a37557/last-checkpoint/special_tokens_map.json +37 -0
  11. checkpoint_22_1a37557/last-checkpoint/tokenizer.json +0 -0
  12. checkpoint_22_1a37557/last-checkpoint/tokenizer_config.json +945 -0
  13. checkpoint_22_1a37557/last-checkpoint/trainer_state.json +0 -0
  14. checkpoint_22_1a37557/last-checkpoint/training_args.bin +3 -0
  15. checkpoint_22_1a37557/pytorch_model.bin +3 -0
  16. checkpoint_22_1a37557/runs/Sep16_13-28-46_nid006603/events.out.tfevents.1758022141.nid006603.208166.0 +3 -0
  17. checkpoint_22_1a37557/runs/Sep16_22-37-21_nid007081/events.out.tfevents.1758055057.nid007081.55404.0 +3 -0
  18. checkpoint_22_1a37557/runs/Sep17_11-23-31_nid007191/events.out.tfevents.1758101018.nid007191.214208.0 +3 -0
  19. checkpoint_22_1a37557/runs/Sep17_11-29-28_nid007081/events.out.tfevents.1758101384.nid007081.193734.0 +3 -0
  20. checkpoint_22_1a37557/runs/Sep17_19-36-25_nid007121/events.out.tfevents.1758130601.nid007121.254584.0 +3 -0
  21. checkpoint_22_1a37557/runs/Sep18_11-52-14_nid006700/events.out.tfevents.1758189144.nid006700.235488.0 +3 -0
  22. checkpoint_22_1a37557/runs/Sep18_13-07-30_nid007493/events.out.tfevents.1758193660.nid007493.21667.0 +3 -0
  23. checkpoint_22_1a37557/runs/Sep18_13-32-51_nid007359/events.out.tfevents.1758195179.nid007359.157961.0 +3 -0
  24. checkpoint_22_1a37557/runs/Sep21_00-31-58_nid007009/events.out.tfevents.1758407534.nid007009.261270.0 +3 -0
  25. checkpoint_22_1a37557/runs/Sep21_12-15-19_nid006869/events.out.tfevents.1758449727.nid006869.65351.0 +3 -0
  26. checkpoint_22_1a37557/runs/Sep21_22-35-48_nid006862/events.out.tfevents.1758486957.nid006862.27495.0 +3 -0
  27. checkpoint_22_1a37557/runs/Sep22_11-48-41_nid007371/events.out.tfevents.1758534529.nid007371.8735.0 +3 -0
  28. checkpoint_22_1a37557/runs/Sep22_22-13-05_nid007556/events.out.tfevents.1758571994.nid007556.119655.0 +3 -0
  29. checkpoint_22_1a37557/runs/Sep22_23-39-07_nid006886/events.out.tfevents.1758577155.nid006886.36302.0 +3 -0
  30. checkpoint_22_1a37557/training_args.bin +3 -0
  31. last-checkpoint/optimizer.pt +1 -1
  32. last-checkpoint/pytorch_model.bin +1 -1
  33. last-checkpoint/rng_state_0.pth +1 -1
  34. last-checkpoint/rng_state_1.pth +1 -1
  35. last-checkpoint/rng_state_2.pth +1 -1
  36. last-checkpoint/rng_state_3.pth +1 -1
  37. last-checkpoint/scheduler.pt +1 -1
  38. last-checkpoint/trainer_state.json +3503 -3
  39. pytorch_model.bin +1 -1
  40. runs/Sep21_22-35-48_nid006862/events.out.tfevents.1758486957.nid006862.27495.0 +2 -2
checkpoint_22_1a37557/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_reduction": 16,
3
+ "architectures": [
4
+ "DistillationWrapper"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "embedding_size": 128,
10
+ "expert_intermediate_size": 4096,
11
+ "group_depth": 4,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 1024,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 2624,
17
+ "layer_norm_eps": 1e-06,
18
+ "load_balancing_loss_coef": 0.2,
19
+ "lora_alpha": 32,
20
+ "lora_rank": 16,
21
+ "max_position_embeddings": 8192,
22
+ "model_type": "ModernALBERT",
23
+ "num_attention_heads": 16,
24
+ "num_expert_modules": 4,
25
+ "num_experts": 8,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 0,
28
+ "router_jitter_noise": 0.01,
29
+ "top_k": 2,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.51.3",
32
+ "use_adapter": true,
33
+ "use_cache": true,
34
+ "use_moa": true,
35
+ "vocab_size": 50368
36
+ }
checkpoint_22_1a37557/last-checkpoint/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_reduction": 16,
3
+ "architectures": [
4
+ "DistillationWrapper"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "embedding_size": 128,
10
+ "expert_intermediate_size": 4096,
11
+ "group_depth": 4,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 1024,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 2624,
17
+ "layer_norm_eps": 1e-06,
18
+ "load_balancing_loss_coef": 0.2,
19
+ "lora_alpha": 32,
20
+ "lora_rank": 16,
21
+ "max_position_embeddings": 8192,
22
+ "model_type": "ModernALBERT",
23
+ "num_attention_heads": 16,
24
+ "num_expert_modules": 4,
25
+ "num_experts": 8,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 0,
28
+ "router_jitter_noise": 0.01,
29
+ "top_k": 2,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.51.3",
32
+ "use_adapter": true,
33
+ "use_cache": true,
34
+ "use_moa": true,
35
+ "vocab_size": 50368
36
+ }
checkpoint_22_1a37557/last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14eacc26cc8f2d7d24a18d717a27affdda9492c8421f614002f0c3e11d141f5
3
+ size 715030586
checkpoint_22_1a37557/last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceff69453bc3bbc57a4f9b5eb49a9a94959f85c187e4440cbe0b782550d42810
3
+ size 1032262338
checkpoint_22_1a37557/last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74db159099f0482eed89ab44fed86362ba92d9190180c0fcf779e183fb243ecd
3
+ size 14960
checkpoint_22_1a37557/last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e46c4b3b00aabd7339ed5282e1c5df6ae4965a31443babb1025d1712c8be824
3
+ size 14960
checkpoint_22_1a37557/last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea8e7380f0717c05d2c0a9160ae122f90de399c875868598d1c7d6697e9094f
3
+ size 14960
checkpoint_22_1a37557/last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2d7cf1f7a94f69ac1a2a862c6b832edf3ecf1c99796eb2bf1fb08125828f5a
3
+ size 14960
checkpoint_22_1a37557/last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73f7a324520e584f1601e016588ed4d6e830dead490ad9714c8169e9a2e6863e
3
+ size 1064
checkpoint_22_1a37557/last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint_22_1a37557/last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint_22_1a37557/last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 1024,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizer",
944
+ "unk_token": "[UNK]"
945
+ }
checkpoint_22_1a37557/last-checkpoint/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint_22_1a37557/last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c912691130e9f7814b22c7f5d99c458cf437027d868cc512886f63eeb7ca118
3
+ size 5432
checkpoint_22_1a37557/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceff69453bc3bbc57a4f9b5eb49a9a94959f85c187e4440cbe0b782550d42810
3
+ size 1032262338
checkpoint_22_1a37557/runs/Sep16_13-28-46_nid006603/events.out.tfevents.1758022141.nid006603.208166.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409ff9e69becc0373bc9e6fdb4d87862ce67d1eaac85ec890fe60067c2f5177f
3
+ size 364278
checkpoint_22_1a37557/runs/Sep16_22-37-21_nid007081/events.out.tfevents.1758055057.nid007081.55404.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7acdc4f03085e2343dfd59272ab71e31c4b31c8bec1be746b06ad834a39fadb0
3
+ size 426414
checkpoint_22_1a37557/runs/Sep17_11-23-31_nid007191/events.out.tfevents.1758101018.nid007191.214208.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dfcb957eeeb8b30a4853a0550e5f2d8f957da386b1e8d793e699058a26f8f72
3
+ size 5973
checkpoint_22_1a37557/runs/Sep17_11-29-28_nid007081/events.out.tfevents.1758101384.nid007081.193734.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e67029b744eef051aae6eea1141935a5d0ce066906dc528c04e4afc7f2b22a7
3
+ size 174136
checkpoint_22_1a37557/runs/Sep17_19-36-25_nid007121/events.out.tfevents.1758130601.nid007121.254584.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace09710e1e83fed7e7206ccfeab094d311cfa075796e315f7be7c9cfaeebb74
3
+ size 421642
checkpoint_22_1a37557/runs/Sep18_11-52-14_nid006700/events.out.tfevents.1758189144.nid006700.235488.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ce5cbab08dfdb1005c89363826e79861f63db75170bae649f4e32850cdb290
3
+ size 5337
checkpoint_22_1a37557/runs/Sep18_13-07-30_nid007493/events.out.tfevents.1758193660.nid007493.21667.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a1aebefd9a425f805f6b07c1900aa1b5fb5911c9693f4c1a7518a0ef6032b5
3
+ size 5337
checkpoint_22_1a37557/runs/Sep18_13-32-51_nid007359/events.out.tfevents.1758195179.nid007359.157961.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efef58ff9d96e2d57eb7f3aa7523e7414d9de6668ad003af406bf45a5112a6e1
3
+ size 421792
checkpoint_22_1a37557/runs/Sep21_00-31-58_nid007009/events.out.tfevents.1758407534.nid007009.261270.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fe85a6d06b21a0e0eb277c68debeb0a2e2b90ffe9004dcea50c836b8800b7d
3
+ size 351487
checkpoint_22_1a37557/runs/Sep21_12-15-19_nid006869/events.out.tfevents.1758449727.nid006869.65351.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:155723adf5c79bfdce72ead24549f974e4742ac3c1d01e8da580a816cc303c13
3
+ size 307627
checkpoint_22_1a37557/runs/Sep21_22-35-48_nid006862/events.out.tfevents.1758486957.nid006862.27495.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c18304c7be4f8fcbf9103348554cc17d450ed5d6aeec015355df0bcc7c35ffd4
3
+ size 349982
checkpoint_22_1a37557/runs/Sep22_11-48-41_nid007371/events.out.tfevents.1758534529.nid007371.8735.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6493e224c41cc53145cd37f2b47c39151a6b0df67a57b99a81241130dba812e5
3
+ size 306337
checkpoint_22_1a37557/runs/Sep22_22-13-05_nid007556/events.out.tfevents.1758571994.nid007556.119655.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0fabd4f48b915a6368acc63d0d0c776afc5443f39d2c5b0d4b1fb0a9c94e70d
3
+ size 22322
checkpoint_22_1a37557/runs/Sep22_23-39-07_nid006886/events.out.tfevents.1758577155.nid006886.36302.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc738e75cce61d87e5391e2dbba1c4cb2c014f773f1916d4d8d0e0e6af695cf6
3
+ size 112837
checkpoint_22_1a37557/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c912691130e9f7814b22c7f5d99c458cf437027d868cc512886f63eeb7ca118
3
+ size 5432
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17d5c7d5296243563494f3afea63efa21147fc119de7562020899eb9c56f1427
3
  size 715030586
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d662b3282648ed6427b80a4391ffd7798dad4532b97743247ca3cc4ca16fe4b7
3
  size 715030586
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50a9561c05504384f8a5358ec95beca3b2814433f472420dc733ce1dc363e842
3
  size 1032262338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c5e718e5fb652f04bf12e08e8623b730b6736e03622227a4c7a774463a05f7
3
  size 1032262338
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ce64cd2b10065510b2a3de9f0ac207f0ad8cd288020534fda1bedb2c5d2780e
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39a19e11cc715af85445b22811dfb67509f8dc3ea843060f7b47e0b9371bf0de
3
  size 14960
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78433868a2f3a72b8364e0a4caa0abbad26d6987562ec0ce4c93a648ae0d02e0
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53aa44a01a4f75b1b285b4dac854149485057a2261cd5cf2feb8a1b7d7af227f
3
  size 14960
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e165e3e4cda215fc8a379bfd6a5682d00880cf13bc9084e4cb5b9691f1c11de5
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5d3e3f904550a07dd4d3bfe7d134f4bb0f6041421ed737e1ab7ad9bbc77d71
3
  size 14960
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f60ba8297fe4b68e6f251c6d014a46bdf2808f72122cd82ba0af9d3164ed1dc9
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d65b6a80c12a8fb92f61de31a9609b92129cf839845469f7c2de58f37274a05
3
  size 14960
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:514d743b09cdf67b5f7ccba0c67283da3d20aa73a759bcf5ebfccf66234e08c8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8038700a783d3dbbe90c65ffd9f9176aad3cbeda38c8a7508ae0b5dcd99468
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.10665465814219437,
6
  "eval_steps": 500,
7
- "global_step": 72000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -50408,6 +50408,3506 @@
50408
  "learning_rate": 0.00048234355429470035,
50409
  "loss": 14.3753,
50410
  "step": 72000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50411
  }
50412
  ],
50413
  "logging_steps": 10,
@@ -50427,7 +53927,7 @@
50427
  "attributes": {}
50428
  }
50429
  },
50430
- "total_flos": 1.5559474665781566e+20,
50431
  "train_batch_size": 48,
50432
  "trial_name": null,
50433
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.11406123162429119,
6
  "eval_steps": 500,
7
+ "global_step": 77000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
50408
  "learning_rate": 0.00048234355429470035,
50409
  "loss": 14.3753,
50410
  "step": 72000
50411
+ },
50412
+ {
50413
+ "epoch": 0.10666947128915856,
50414
+ "grad_norm": 6.4375,
50415
+ "learning_rate": 0.0004823410848271966,
50416
+ "loss": 14.3704,
50417
+ "step": 72010
50418
+ },
50419
+ {
50420
+ "epoch": 0.10668428443612275,
50421
+ "grad_norm": 7.5,
50422
+ "learning_rate": 0.00048233861535969274,
50423
+ "loss": 14.4066,
50424
+ "step": 72020
50425
+ },
50426
+ {
50427
+ "epoch": 0.10669909758308695,
50428
+ "grad_norm": 6.15625,
50429
+ "learning_rate": 0.000482336145892189,
50430
+ "loss": 14.3868,
50431
+ "step": 72030
50432
+ },
50433
+ {
50434
+ "epoch": 0.10671391073005114,
50435
+ "grad_norm": 5.5625,
50436
+ "learning_rate": 0.0004823336764246852,
50437
+ "loss": 14.3865,
50438
+ "step": 72040
50439
+ },
50440
+ {
50441
+ "epoch": 0.10672872387701533,
50442
+ "grad_norm": 6.59375,
50443
+ "learning_rate": 0.0004823312069571814,
50444
+ "loss": 14.4174,
50445
+ "step": 72050
50446
+ },
50447
+ {
50448
+ "epoch": 0.10674353702397953,
50449
+ "grad_norm": 7.09375,
50450
+ "learning_rate": 0.00048232873748967764,
50451
+ "loss": 14.3849,
50452
+ "step": 72060
50453
+ },
50454
+ {
50455
+ "epoch": 0.10675835017094372,
50456
+ "grad_norm": 6.25,
50457
+ "learning_rate": 0.00048232626802217383,
50458
+ "loss": 14.4023,
50459
+ "step": 72070
50460
+ },
50461
+ {
50462
+ "epoch": 0.10677316331790791,
50463
+ "grad_norm": 6.34375,
50464
+ "learning_rate": 0.0004823237985546701,
50465
+ "loss": 14.3164,
50466
+ "step": 72080
50467
+ },
50468
+ {
50469
+ "epoch": 0.1067879764648721,
50470
+ "grad_norm": 6.34375,
50471
+ "learning_rate": 0.0004823213290871663,
50472
+ "loss": 14.3799,
50473
+ "step": 72090
50474
+ },
50475
+ {
50476
+ "epoch": 0.1068027896118363,
50477
+ "grad_norm": 6.75,
50478
+ "learning_rate": 0.0004823188596196625,
50479
+ "loss": 14.3739,
50480
+ "step": 72100
50481
+ },
50482
+ {
50483
+ "epoch": 0.10681760275880049,
50484
+ "grad_norm": 9.8125,
50485
+ "learning_rate": 0.00048231639015215873,
50486
+ "loss": 14.344,
50487
+ "step": 72110
50488
+ },
50489
+ {
50490
+ "epoch": 0.10683241590576469,
50491
+ "grad_norm": 5.71875,
50492
+ "learning_rate": 0.000482313920684655,
50493
+ "loss": 14.3513,
50494
+ "step": 72120
50495
+ },
50496
+ {
50497
+ "epoch": 0.10684722905272888,
50498
+ "grad_norm": 5.84375,
50499
+ "learning_rate": 0.0004823114512171511,
50500
+ "loss": 14.3595,
50501
+ "step": 72130
50502
+ },
50503
+ {
50504
+ "epoch": 0.10686204219969307,
50505
+ "grad_norm": 5.625,
50506
+ "learning_rate": 0.0004823089817496474,
50507
+ "loss": 14.3451,
50508
+ "step": 72140
50509
+ },
50510
+ {
50511
+ "epoch": 0.10687685534665727,
50512
+ "grad_norm": 6.34375,
50513
+ "learning_rate": 0.00048230651228214357,
50514
+ "loss": 14.3622,
50515
+ "step": 72150
50516
+ },
50517
+ {
50518
+ "epoch": 0.10689166849362146,
50519
+ "grad_norm": 5.9375,
50520
+ "learning_rate": 0.0004823040428146398,
50521
+ "loss": 14.423,
50522
+ "step": 72160
50523
+ },
50524
+ {
50525
+ "epoch": 0.10690648164058565,
50526
+ "grad_norm": 6.59375,
50527
+ "learning_rate": 0.000482301573347136,
50528
+ "loss": 14.4317,
50529
+ "step": 72170
50530
+ },
50531
+ {
50532
+ "epoch": 0.10692129478754984,
50533
+ "grad_norm": 6.34375,
50534
+ "learning_rate": 0.0004822991038796322,
50535
+ "loss": 14.2615,
50536
+ "step": 72180
50537
+ },
50538
+ {
50539
+ "epoch": 0.10693610793451404,
50540
+ "grad_norm": 6.46875,
50541
+ "learning_rate": 0.00048229663441212847,
50542
+ "loss": 14.3686,
50543
+ "step": 72190
50544
+ },
50545
+ {
50546
+ "epoch": 0.10695092108147823,
50547
+ "grad_norm": 6.03125,
50548
+ "learning_rate": 0.0004822941649446247,
50549
+ "loss": 14.3991,
50550
+ "step": 72200
50551
+ },
50552
+ {
50553
+ "epoch": 0.10696573422844242,
50554
+ "grad_norm": 7.03125,
50555
+ "learning_rate": 0.00048229169547712086,
50556
+ "loss": 14.4392,
50557
+ "step": 72210
50558
+ },
50559
+ {
50560
+ "epoch": 0.10698054737540662,
50561
+ "grad_norm": 5.875,
50562
+ "learning_rate": 0.0004822892260096171,
50563
+ "loss": 14.3823,
50564
+ "step": 72220
50565
+ },
50566
+ {
50567
+ "epoch": 0.10699536052237081,
50568
+ "grad_norm": 8.5,
50569
+ "learning_rate": 0.00048228675654211336,
50570
+ "loss": 14.3434,
50571
+ "step": 72230
50572
+ },
50573
+ {
50574
+ "epoch": 0.107010173669335,
50575
+ "grad_norm": 7.0,
50576
+ "learning_rate": 0.0004822842870746095,
50577
+ "loss": 14.4616,
50578
+ "step": 72240
50579
+ },
50580
+ {
50581
+ "epoch": 0.1070249868162992,
50582
+ "grad_norm": 6.34375,
50583
+ "learning_rate": 0.00048228181760710576,
50584
+ "loss": 14.3207,
50585
+ "step": 72250
50586
+ },
50587
+ {
50588
+ "epoch": 0.10703979996326339,
50589
+ "grad_norm": 6.53125,
50590
+ "learning_rate": 0.00048227934813960195,
50591
+ "loss": 14.4052,
50592
+ "step": 72260
50593
+ },
50594
+ {
50595
+ "epoch": 0.10705461311022758,
50596
+ "grad_norm": 7.0,
50597
+ "learning_rate": 0.0004822768786720982,
50598
+ "loss": 14.4183,
50599
+ "step": 72270
50600
+ },
50601
+ {
50602
+ "epoch": 0.10706942625719178,
50603
+ "grad_norm": 6.125,
50604
+ "learning_rate": 0.0004822744092045944,
50605
+ "loss": 14.372,
50606
+ "step": 72280
50607
+ },
50608
+ {
50609
+ "epoch": 0.10708423940415597,
50610
+ "grad_norm": 6.0,
50611
+ "learning_rate": 0.0004822719397370906,
50612
+ "loss": 14.3994,
50613
+ "step": 72290
50614
+ },
50615
+ {
50616
+ "epoch": 0.10709905255112016,
50617
+ "grad_norm": 7.4375,
50618
+ "learning_rate": 0.00048226947026958685,
50619
+ "loss": 14.374,
50620
+ "step": 72300
50621
+ },
50622
+ {
50623
+ "epoch": 0.10711386569808437,
50624
+ "grad_norm": 6.65625,
50625
+ "learning_rate": 0.0004822670008020831,
50626
+ "loss": 14.4159,
50627
+ "step": 72310
50628
+ },
50629
+ {
50630
+ "epoch": 0.10712867884504856,
50631
+ "grad_norm": 6.8125,
50632
+ "learning_rate": 0.00048226453133457924,
50633
+ "loss": 14.3665,
50634
+ "step": 72320
50635
+ },
50636
+ {
50637
+ "epoch": 0.10714349199201276,
50638
+ "grad_norm": 6.6875,
50639
+ "learning_rate": 0.0004822620618670755,
50640
+ "loss": 14.4168,
50641
+ "step": 72330
50642
+ },
50643
+ {
50644
+ "epoch": 0.10715830513897695,
50645
+ "grad_norm": 7.1875,
50646
+ "learning_rate": 0.0004822595923995717,
50647
+ "loss": 14.3254,
50648
+ "step": 72340
50649
+ },
50650
+ {
50651
+ "epoch": 0.10717311828594114,
50652
+ "grad_norm": 6.09375,
50653
+ "learning_rate": 0.00048225712293206794,
50654
+ "loss": 14.3048,
50655
+ "step": 72350
50656
+ },
50657
+ {
50658
+ "epoch": 0.10718793143290534,
50659
+ "grad_norm": 6.46875,
50660
+ "learning_rate": 0.00048225465346456414,
50661
+ "loss": 14.4112,
50662
+ "step": 72360
50663
+ },
50664
+ {
50665
+ "epoch": 0.10720274457986953,
50666
+ "grad_norm": 13.25,
50667
+ "learning_rate": 0.00048225218399706033,
50668
+ "loss": 14.4302,
50669
+ "step": 72370
50670
+ },
50671
+ {
50672
+ "epoch": 0.10721755772683372,
50673
+ "grad_norm": 6.03125,
50674
+ "learning_rate": 0.0004822497145295566,
50675
+ "loss": 14.3899,
50676
+ "step": 72380
50677
+ },
50678
+ {
50679
+ "epoch": 0.10723237087379792,
50680
+ "grad_norm": 5.875,
50681
+ "learning_rate": 0.0004822472450620528,
50682
+ "loss": 14.3835,
50683
+ "step": 72390
50684
+ },
50685
+ {
50686
+ "epoch": 0.10724718402076211,
50687
+ "grad_norm": 6.8125,
50688
+ "learning_rate": 0.000482244775594549,
50689
+ "loss": 14.299,
50690
+ "step": 72400
50691
+ },
50692
+ {
50693
+ "epoch": 0.1072619971677263,
50694
+ "grad_norm": 6.21875,
50695
+ "learning_rate": 0.00048224230612704523,
50696
+ "loss": 14.421,
50697
+ "step": 72410
50698
+ },
50699
+ {
50700
+ "epoch": 0.1072768103146905,
50701
+ "grad_norm": 6.9375,
50702
+ "learning_rate": 0.0004822398366595415,
50703
+ "loss": 14.3575,
50704
+ "step": 72420
50705
+ },
50706
+ {
50707
+ "epoch": 0.10729162346165469,
50708
+ "grad_norm": 6.9375,
50709
+ "learning_rate": 0.0004822373671920376,
50710
+ "loss": 14.3799,
50711
+ "step": 72430
50712
+ },
50713
+ {
50714
+ "epoch": 0.10730643660861888,
50715
+ "grad_norm": 7.40625,
50716
+ "learning_rate": 0.0004822348977245339,
50717
+ "loss": 14.3983,
50718
+ "step": 72440
50719
+ },
50720
+ {
50721
+ "epoch": 0.10732124975558308,
50722
+ "grad_norm": 6.03125,
50723
+ "learning_rate": 0.00048223242825703007,
50724
+ "loss": 14.3779,
50725
+ "step": 72450
50726
+ },
50727
+ {
50728
+ "epoch": 0.10733606290254727,
50729
+ "grad_norm": 5.75,
50730
+ "learning_rate": 0.0004822299587895263,
50731
+ "loss": 14.3256,
50732
+ "step": 72460
50733
+ },
50734
+ {
50735
+ "epoch": 0.10735087604951146,
50736
+ "grad_norm": 6.78125,
50737
+ "learning_rate": 0.0004822274893220225,
50738
+ "loss": 14.3509,
50739
+ "step": 72470
50740
+ },
50741
+ {
50742
+ "epoch": 0.10736568919647566,
50743
+ "grad_norm": 6.90625,
50744
+ "learning_rate": 0.0004822250198545187,
50745
+ "loss": 14.4086,
50746
+ "step": 72480
50747
+ },
50748
+ {
50749
+ "epoch": 0.10738050234343985,
50750
+ "grad_norm": 7.28125,
50751
+ "learning_rate": 0.00048222255038701497,
50752
+ "loss": 14.3817,
50753
+ "step": 72490
50754
+ },
50755
+ {
50756
+ "epoch": 0.10739531549040404,
50757
+ "grad_norm": 6.6875,
50758
+ "learning_rate": 0.0004822200809195112,
50759
+ "loss": 14.4064,
50760
+ "step": 72500
50761
+ },
50762
+ {
50763
+ "epoch": 0.10741012863736824,
50764
+ "grad_norm": 9.25,
50765
+ "learning_rate": 0.00048221761145200736,
50766
+ "loss": 14.3211,
50767
+ "step": 72510
50768
+ },
50769
+ {
50770
+ "epoch": 0.10742494178433243,
50771
+ "grad_norm": 7.8125,
50772
+ "learning_rate": 0.0004822151419845036,
50773
+ "loss": 14.4277,
50774
+ "step": 72520
50775
+ },
50776
+ {
50777
+ "epoch": 0.10743975493129662,
50778
+ "grad_norm": 6.0,
50779
+ "learning_rate": 0.00048221267251699986,
50780
+ "loss": 14.2962,
50781
+ "step": 72530
50782
+ },
50783
+ {
50784
+ "epoch": 0.10745456807826081,
50785
+ "grad_norm": 6.375,
50786
+ "learning_rate": 0.000482210203049496,
50787
+ "loss": 14.3101,
50788
+ "step": 72540
50789
+ },
50790
+ {
50791
+ "epoch": 0.10746938122522501,
50792
+ "grad_norm": 8.3125,
50793
+ "learning_rate": 0.00048220773358199226,
50794
+ "loss": 14.3469,
50795
+ "step": 72550
50796
+ },
50797
+ {
50798
+ "epoch": 0.1074841943721892,
50799
+ "grad_norm": 6.84375,
50800
+ "learning_rate": 0.00048220526411448845,
50801
+ "loss": 14.3612,
50802
+ "step": 72560
50803
+ },
50804
+ {
50805
+ "epoch": 0.1074990075191534,
50806
+ "grad_norm": 6.71875,
50807
+ "learning_rate": 0.0004822027946469847,
50808
+ "loss": 14.4118,
50809
+ "step": 72570
50810
+ },
50811
+ {
50812
+ "epoch": 0.10751382066611759,
50813
+ "grad_norm": 11.4375,
50814
+ "learning_rate": 0.0004822003251794809,
50815
+ "loss": 14.3553,
50816
+ "step": 72580
50817
+ },
50818
+ {
50819
+ "epoch": 0.10752863381308178,
50820
+ "grad_norm": 6.125,
50821
+ "learning_rate": 0.0004821978557119771,
50822
+ "loss": 14.3982,
50823
+ "step": 72590
50824
+ },
50825
+ {
50826
+ "epoch": 0.10754344696004597,
50827
+ "grad_norm": 6.78125,
50828
+ "learning_rate": 0.00048219538624447335,
50829
+ "loss": 14.3024,
50830
+ "step": 72600
50831
+ },
50832
+ {
50833
+ "epoch": 0.10755826010701017,
50834
+ "grad_norm": 5.96875,
50835
+ "learning_rate": 0.0004821929167769696,
50836
+ "loss": 14.3322,
50837
+ "step": 72610
50838
+ },
50839
+ {
50840
+ "epoch": 0.10757307325397436,
50841
+ "grad_norm": 5.78125,
50842
+ "learning_rate": 0.00048219044730946574,
50843
+ "loss": 14.2839,
50844
+ "step": 72620
50845
+ },
50846
+ {
50847
+ "epoch": 0.10758788640093857,
50848
+ "grad_norm": 8.625,
50849
+ "learning_rate": 0.000482187977841962,
50850
+ "loss": 14.3476,
50851
+ "step": 72630
50852
+ },
50853
+ {
50854
+ "epoch": 0.10760269954790276,
50855
+ "grad_norm": 6.1875,
50856
+ "learning_rate": 0.0004821855083744582,
50857
+ "loss": 14.4653,
50858
+ "step": 72640
50859
+ },
50860
+ {
50861
+ "epoch": 0.10761751269486695,
50862
+ "grad_norm": 6.1875,
50863
+ "learning_rate": 0.00048218303890695444,
50864
+ "loss": 14.3642,
50865
+ "step": 72650
50866
+ },
50867
+ {
50868
+ "epoch": 0.10763232584183115,
50869
+ "grad_norm": 6.65625,
50870
+ "learning_rate": 0.00048218056943945064,
50871
+ "loss": 14.3101,
50872
+ "step": 72660
50873
+ },
50874
+ {
50875
+ "epoch": 0.10764713898879534,
50876
+ "grad_norm": 5.625,
50877
+ "learning_rate": 0.00048217809997194684,
50878
+ "loss": 14.2539,
50879
+ "step": 72670
50880
+ },
50881
+ {
50882
+ "epoch": 0.10766195213575953,
50883
+ "grad_norm": 6.75,
50884
+ "learning_rate": 0.0004821756305044431,
50885
+ "loss": 14.3408,
50886
+ "step": 72680
50887
+ },
50888
+ {
50889
+ "epoch": 0.10767676528272373,
50890
+ "grad_norm": 6.84375,
50891
+ "learning_rate": 0.00048217316103693934,
50892
+ "loss": 14.4438,
50893
+ "step": 72690
50894
+ },
50895
+ {
50896
+ "epoch": 0.10769157842968792,
50897
+ "grad_norm": 7.03125,
50898
+ "learning_rate": 0.0004821706915694355,
50899
+ "loss": 14.3983,
50900
+ "step": 72700
50901
+ },
50902
+ {
50903
+ "epoch": 0.10770639157665211,
50904
+ "grad_norm": 9.1875,
50905
+ "learning_rate": 0.00048216822210193173,
50906
+ "loss": 14.3947,
50907
+ "step": 72710
50908
+ },
50909
+ {
50910
+ "epoch": 0.1077212047236163,
50911
+ "grad_norm": 14.875,
50912
+ "learning_rate": 0.000482165752634428,
50913
+ "loss": 14.4244,
50914
+ "step": 72720
50915
+ },
50916
+ {
50917
+ "epoch": 0.1077360178705805,
50918
+ "grad_norm": 7.09375,
50919
+ "learning_rate": 0.0004821632831669241,
50920
+ "loss": 14.3802,
50921
+ "step": 72730
50922
+ },
50923
+ {
50924
+ "epoch": 0.1077508310175447,
50925
+ "grad_norm": 13.875,
50926
+ "learning_rate": 0.0004821608136994204,
50927
+ "loss": 14.3724,
50928
+ "step": 72740
50929
+ },
50930
+ {
50931
+ "epoch": 0.10776564416450889,
50932
+ "grad_norm": 6.4375,
50933
+ "learning_rate": 0.00048215834423191657,
50934
+ "loss": 14.3463,
50935
+ "step": 72750
50936
+ },
50937
+ {
50938
+ "epoch": 0.10778045731147308,
50939
+ "grad_norm": 7.5,
50940
+ "learning_rate": 0.0004821558747644128,
50941
+ "loss": 14.3348,
50942
+ "step": 72760
50943
+ },
50944
+ {
50945
+ "epoch": 0.10779527045843727,
50946
+ "grad_norm": 6.78125,
50947
+ "learning_rate": 0.000482153405296909,
50948
+ "loss": 14.3908,
50949
+ "step": 72770
50950
+ },
50951
+ {
50952
+ "epoch": 0.10781008360540147,
50953
+ "grad_norm": 6.78125,
50954
+ "learning_rate": 0.0004821509358294052,
50955
+ "loss": 14.2991,
50956
+ "step": 72780
50957
+ },
50958
+ {
50959
+ "epoch": 0.10782489675236566,
50960
+ "grad_norm": 6.75,
50961
+ "learning_rate": 0.00048214846636190147,
50962
+ "loss": 14.4112,
50963
+ "step": 72790
50964
+ },
50965
+ {
50966
+ "epoch": 0.10783970989932985,
50967
+ "grad_norm": 6.0,
50968
+ "learning_rate": 0.0004821459968943977,
50969
+ "loss": 14.2657,
50970
+ "step": 72800
50971
+ },
50972
+ {
50973
+ "epoch": 0.10785452304629405,
50974
+ "grad_norm": 9.625,
50975
+ "learning_rate": 0.00048214352742689386,
50976
+ "loss": 14.29,
50977
+ "step": 72810
50978
+ },
50979
+ {
50980
+ "epoch": 0.10786933619325824,
50981
+ "grad_norm": 7.65625,
50982
+ "learning_rate": 0.0004821410579593901,
50983
+ "loss": 14.4061,
50984
+ "step": 72820
50985
+ },
50986
+ {
50987
+ "epoch": 0.10788414934022243,
50988
+ "grad_norm": 6.5,
50989
+ "learning_rate": 0.00048213858849188636,
50990
+ "loss": 14.4006,
50991
+ "step": 72830
50992
+ },
50993
+ {
50994
+ "epoch": 0.10789896248718663,
50995
+ "grad_norm": 7.90625,
50996
+ "learning_rate": 0.00048213611902438256,
50997
+ "loss": 14.4119,
50998
+ "step": 72840
50999
+ },
51000
+ {
51001
+ "epoch": 0.10791377563415082,
51002
+ "grad_norm": 7.25,
51003
+ "learning_rate": 0.00048213364955687876,
51004
+ "loss": 14.3216,
51005
+ "step": 72850
51006
+ },
51007
+ {
51008
+ "epoch": 0.10792858878111501,
51009
+ "grad_norm": 11.25,
51010
+ "learning_rate": 0.00048213118008937495,
51011
+ "loss": 14.4814,
51012
+ "step": 72860
51013
+ },
51014
+ {
51015
+ "epoch": 0.1079434019280792,
51016
+ "grad_norm": 7.59375,
51017
+ "learning_rate": 0.0004821287106218712,
51018
+ "loss": 14.4249,
51019
+ "step": 72870
51020
+ },
51021
+ {
51022
+ "epoch": 0.1079582150750434,
51023
+ "grad_norm": 5.5,
51024
+ "learning_rate": 0.0004821262411543674,
51025
+ "loss": 14.3188,
51026
+ "step": 72880
51027
+ },
51028
+ {
51029
+ "epoch": 0.10797302822200759,
51030
+ "grad_norm": 6.1875,
51031
+ "learning_rate": 0.0004821237716868636,
51032
+ "loss": 14.292,
51033
+ "step": 72890
51034
+ },
51035
+ {
51036
+ "epoch": 0.10798784136897178,
51037
+ "grad_norm": 9.875,
51038
+ "learning_rate": 0.00048212130221935985,
51039
+ "loss": 14.3545,
51040
+ "step": 72900
51041
+ },
51042
+ {
51043
+ "epoch": 0.10800265451593598,
51044
+ "grad_norm": 22.875,
51045
+ "learning_rate": 0.0004821188327518561,
51046
+ "loss": 14.3915,
51047
+ "step": 72910
51048
+ },
51049
+ {
51050
+ "epoch": 0.10801746766290017,
51051
+ "grad_norm": 8.0625,
51052
+ "learning_rate": 0.00048211636328435224,
51053
+ "loss": 14.3015,
51054
+ "step": 72920
51055
+ },
51056
+ {
51057
+ "epoch": 0.10803228080986436,
51058
+ "grad_norm": 7.84375,
51059
+ "learning_rate": 0.0004821138938168485,
51060
+ "loss": 14.3118,
51061
+ "step": 72930
51062
+ },
51063
+ {
51064
+ "epoch": 0.10804709395682856,
51065
+ "grad_norm": 5.8125,
51066
+ "learning_rate": 0.0004821114243493447,
51067
+ "loss": 14.3114,
51068
+ "step": 72940
51069
+ },
51070
+ {
51071
+ "epoch": 0.10806190710379276,
51072
+ "grad_norm": 7.625,
51073
+ "learning_rate": 0.00048210895488184094,
51074
+ "loss": 14.3406,
51075
+ "step": 72950
51076
+ },
51077
+ {
51078
+ "epoch": 0.10807672025075696,
51079
+ "grad_norm": 7.5625,
51080
+ "learning_rate": 0.00048210648541433714,
51081
+ "loss": 14.3249,
51082
+ "step": 72960
51083
+ },
51084
+ {
51085
+ "epoch": 0.10809153339772115,
51086
+ "grad_norm": 6.15625,
51087
+ "learning_rate": 0.00048210401594683334,
51088
+ "loss": 14.3502,
51089
+ "step": 72970
51090
+ },
51091
+ {
51092
+ "epoch": 0.10810634654468534,
51093
+ "grad_norm": 6.0625,
51094
+ "learning_rate": 0.0004821015464793296,
51095
+ "loss": 14.2856,
51096
+ "step": 72980
51097
+ },
51098
+ {
51099
+ "epoch": 0.10812115969164954,
51100
+ "grad_norm": 7.15625,
51101
+ "learning_rate": 0.00048209907701182584,
51102
+ "loss": 14.38,
51103
+ "step": 72990
51104
+ },
51105
+ {
51106
+ "epoch": 0.10813597283861373,
51107
+ "grad_norm": 6.84375,
51108
+ "learning_rate": 0.000482096607544322,
51109
+ "loss": 14.3467,
51110
+ "step": 73000
51111
+ },
51112
+ {
51113
+ "epoch": 0.10815078598557792,
51114
+ "grad_norm": 8.0,
51115
+ "learning_rate": 0.00048209413807681823,
51116
+ "loss": 14.3021,
51117
+ "step": 73010
51118
+ },
51119
+ {
51120
+ "epoch": 0.10816559913254212,
51121
+ "grad_norm": 6.5625,
51122
+ "learning_rate": 0.0004820916686093145,
51123
+ "loss": 14.3958,
51124
+ "step": 73020
51125
+ },
51126
+ {
51127
+ "epoch": 0.10818041227950631,
51128
+ "grad_norm": 5.59375,
51129
+ "learning_rate": 0.0004820891991418107,
51130
+ "loss": 14.2909,
51131
+ "step": 73030
51132
+ },
51133
+ {
51134
+ "epoch": 0.1081952254264705,
51135
+ "grad_norm": 5.71875,
51136
+ "learning_rate": 0.0004820867296743069,
51137
+ "loss": 14.3064,
51138
+ "step": 73040
51139
+ },
51140
+ {
51141
+ "epoch": 0.1082100385734347,
51142
+ "grad_norm": 14.9375,
51143
+ "learning_rate": 0.00048208426020680307,
51144
+ "loss": 14.462,
51145
+ "step": 73050
51146
+ },
51147
+ {
51148
+ "epoch": 0.10822485172039889,
51149
+ "grad_norm": 6.625,
51150
+ "learning_rate": 0.0004820817907392993,
51151
+ "loss": 14.3629,
51152
+ "step": 73060
51153
+ },
51154
+ {
51155
+ "epoch": 0.10823966486736308,
51156
+ "grad_norm": 6.09375,
51157
+ "learning_rate": 0.0004820793212717955,
51158
+ "loss": 14.3592,
51159
+ "step": 73070
51160
+ },
51161
+ {
51162
+ "epoch": 0.10825447801432728,
51163
+ "grad_norm": 6.75,
51164
+ "learning_rate": 0.0004820768518042917,
51165
+ "loss": 14.4305,
51166
+ "step": 73080
51167
+ },
51168
+ {
51169
+ "epoch": 0.10826929116129147,
51170
+ "grad_norm": 9.5,
51171
+ "learning_rate": 0.00048207438233678797,
51172
+ "loss": 14.4917,
51173
+ "step": 73090
51174
+ },
51175
+ {
51176
+ "epoch": 0.10828410430825566,
51177
+ "grad_norm": 6.96875,
51178
+ "learning_rate": 0.0004820719128692842,
51179
+ "loss": 14.3567,
51180
+ "step": 73100
51181
+ },
51182
+ {
51183
+ "epoch": 0.10829891745521986,
51184
+ "grad_norm": 8.4375,
51185
+ "learning_rate": 0.00048206944340178036,
51186
+ "loss": 14.3421,
51187
+ "step": 73110
51188
+ },
51189
+ {
51190
+ "epoch": 0.10831373060218405,
51191
+ "grad_norm": 6.375,
51192
+ "learning_rate": 0.0004820669739342766,
51193
+ "loss": 14.3321,
51194
+ "step": 73120
51195
+ },
51196
+ {
51197
+ "epoch": 0.10832854374914824,
51198
+ "grad_norm": 6.875,
51199
+ "learning_rate": 0.00048206450446677286,
51200
+ "loss": 14.3111,
51201
+ "step": 73130
51202
+ },
51203
+ {
51204
+ "epoch": 0.10834335689611244,
51205
+ "grad_norm": 7.09375,
51206
+ "learning_rate": 0.00048206203499926906,
51207
+ "loss": 14.2243,
51208
+ "step": 73140
51209
+ },
51210
+ {
51211
+ "epoch": 0.10835817004307663,
51212
+ "grad_norm": 7.3125,
51213
+ "learning_rate": 0.00048205956553176526,
51214
+ "loss": 14.3196,
51215
+ "step": 73150
51216
+ },
51217
+ {
51218
+ "epoch": 0.10837298319004082,
51219
+ "grad_norm": 9.6875,
51220
+ "learning_rate": 0.00048205709606426145,
51221
+ "loss": 14.2444,
51222
+ "step": 73160
51223
+ },
51224
+ {
51225
+ "epoch": 0.10838779633700502,
51226
+ "grad_norm": 5.8125,
51227
+ "learning_rate": 0.0004820546265967577,
51228
+ "loss": 14.345,
51229
+ "step": 73170
51230
+ },
51231
+ {
51232
+ "epoch": 0.10840260948396921,
51233
+ "grad_norm": 8.0,
51234
+ "learning_rate": 0.00048205215712925396,
51235
+ "loss": 14.3396,
51236
+ "step": 73180
51237
+ },
51238
+ {
51239
+ "epoch": 0.1084174226309334,
51240
+ "grad_norm": 45.0,
51241
+ "learning_rate": 0.0004820496876617501,
51242
+ "loss": 14.3727,
51243
+ "step": 73190
51244
+ },
51245
+ {
51246
+ "epoch": 0.1084322357778976,
51247
+ "grad_norm": 30.25,
51248
+ "learning_rate": 0.00048204721819424635,
51249
+ "loss": 14.3463,
51250
+ "step": 73200
51251
+ },
51252
+ {
51253
+ "epoch": 0.10844704892486179,
51254
+ "grad_norm": 6.375,
51255
+ "learning_rate": 0.0004820447487267426,
51256
+ "loss": 14.4822,
51257
+ "step": 73210
51258
+ },
51259
+ {
51260
+ "epoch": 0.10846186207182598,
51261
+ "grad_norm": 5.875,
51262
+ "learning_rate": 0.00048204227925923874,
51263
+ "loss": 14.4576,
51264
+ "step": 73220
51265
+ },
51266
+ {
51267
+ "epoch": 0.10847667521879018,
51268
+ "grad_norm": 8.375,
51269
+ "learning_rate": 0.000482039809791735,
51270
+ "loss": 14.3173,
51271
+ "step": 73230
51272
+ },
51273
+ {
51274
+ "epoch": 0.10849148836575437,
51275
+ "grad_norm": 6.5,
51276
+ "learning_rate": 0.0004820373403242312,
51277
+ "loss": 14.4046,
51278
+ "step": 73240
51279
+ },
51280
+ {
51281
+ "epoch": 0.10850630151271856,
51282
+ "grad_norm": 5.75,
51283
+ "learning_rate": 0.00048203487085672744,
51284
+ "loss": 14.298,
51285
+ "step": 73250
51286
+ },
51287
+ {
51288
+ "epoch": 0.10852111465968275,
51289
+ "grad_norm": 6.03125,
51290
+ "learning_rate": 0.00048203240138922364,
51291
+ "loss": 14.3296,
51292
+ "step": 73260
51293
+ },
51294
+ {
51295
+ "epoch": 0.10853592780664696,
51296
+ "grad_norm": 6.3125,
51297
+ "learning_rate": 0.00048202993192171984,
51298
+ "loss": 14.3393,
51299
+ "step": 73270
51300
+ },
51301
+ {
51302
+ "epoch": 0.10855074095361116,
51303
+ "grad_norm": 6.3125,
51304
+ "learning_rate": 0.0004820274624542161,
51305
+ "loss": 14.3553,
51306
+ "step": 73280
51307
+ },
51308
+ {
51309
+ "epoch": 0.10856555410057535,
51310
+ "grad_norm": 9.0625,
51311
+ "learning_rate": 0.00048202499298671234,
51312
+ "loss": 14.3433,
51313
+ "step": 73290
51314
+ },
51315
+ {
51316
+ "epoch": 0.10858036724753954,
51317
+ "grad_norm": 5.78125,
51318
+ "learning_rate": 0.0004820225235192085,
51319
+ "loss": 14.3324,
51320
+ "step": 73300
51321
+ },
51322
+ {
51323
+ "epoch": 0.10859518039450373,
51324
+ "grad_norm": 6.6875,
51325
+ "learning_rate": 0.00048202005405170473,
51326
+ "loss": 14.2732,
51327
+ "step": 73310
51328
+ },
51329
+ {
51330
+ "epoch": 0.10860999354146793,
51331
+ "grad_norm": 6.0625,
51332
+ "learning_rate": 0.000482017584584201,
51333
+ "loss": 14.3363,
51334
+ "step": 73320
51335
+ },
51336
+ {
51337
+ "epoch": 0.10862480668843212,
51338
+ "grad_norm": 7.3125,
51339
+ "learning_rate": 0.0004820151151166972,
51340
+ "loss": 14.3124,
51341
+ "step": 73330
51342
+ },
51343
+ {
51344
+ "epoch": 0.10863961983539631,
51345
+ "grad_norm": 7.65625,
51346
+ "learning_rate": 0.0004820126456491934,
51347
+ "loss": 14.398,
51348
+ "step": 73340
51349
+ },
51350
+ {
51351
+ "epoch": 0.10865443298236051,
51352
+ "grad_norm": 6.90625,
51353
+ "learning_rate": 0.0004820101761816896,
51354
+ "loss": 14.3801,
51355
+ "step": 73350
51356
+ },
51357
+ {
51358
+ "epoch": 0.1086692461293247,
51359
+ "grad_norm": 6.375,
51360
+ "learning_rate": 0.0004820077067141858,
51361
+ "loss": 14.386,
51362
+ "step": 73360
51363
+ },
51364
+ {
51365
+ "epoch": 0.1086840592762889,
51366
+ "grad_norm": 8.25,
51367
+ "learning_rate": 0.0004820052372466821,
51368
+ "loss": 14.2885,
51369
+ "step": 73370
51370
+ },
51371
+ {
51372
+ "epoch": 0.10869887242325309,
51373
+ "grad_norm": 6.625,
51374
+ "learning_rate": 0.0004820027677791782,
51375
+ "loss": 14.3718,
51376
+ "step": 73380
51377
+ },
51378
+ {
51379
+ "epoch": 0.10871368557021728,
51380
+ "grad_norm": 6.1875,
51381
+ "learning_rate": 0.00048200029831167447,
51382
+ "loss": 14.4839,
51383
+ "step": 73390
51384
+ },
51385
+ {
51386
+ "epoch": 0.10872849871718147,
51387
+ "grad_norm": 6.78125,
51388
+ "learning_rate": 0.0004819978288441707,
51389
+ "loss": 14.3485,
51390
+ "step": 73400
51391
+ },
51392
+ {
51393
+ "epoch": 0.10874331186414567,
51394
+ "grad_norm": 6.46875,
51395
+ "learning_rate": 0.00048199535937666686,
51396
+ "loss": 14.3527,
51397
+ "step": 73410
51398
+ },
51399
+ {
51400
+ "epoch": 0.10875812501110986,
51401
+ "grad_norm": 6.5625,
51402
+ "learning_rate": 0.0004819928899091631,
51403
+ "loss": 14.3879,
51404
+ "step": 73420
51405
+ },
51406
+ {
51407
+ "epoch": 0.10877293815807405,
51408
+ "grad_norm": 6.15625,
51409
+ "learning_rate": 0.00048199042044165936,
51410
+ "loss": 14.377,
51411
+ "step": 73430
51412
+ },
51413
+ {
51414
+ "epoch": 0.10878775130503825,
51415
+ "grad_norm": 6.34375,
51416
+ "learning_rate": 0.00048198795097415556,
51417
+ "loss": 14.3676,
51418
+ "step": 73440
51419
+ },
51420
+ {
51421
+ "epoch": 0.10880256445200244,
51422
+ "grad_norm": 6.3125,
51423
+ "learning_rate": 0.00048198548150665176,
51424
+ "loss": 14.391,
51425
+ "step": 73450
51426
+ },
51427
+ {
51428
+ "epoch": 0.10881737759896663,
51429
+ "grad_norm": 6.90625,
51430
+ "learning_rate": 0.00048198301203914795,
51431
+ "loss": 14.3297,
51432
+ "step": 73460
51433
+ },
51434
+ {
51435
+ "epoch": 0.10883219074593083,
51436
+ "grad_norm": 5.65625,
51437
+ "learning_rate": 0.0004819805425716442,
51438
+ "loss": 14.4611,
51439
+ "step": 73470
51440
+ },
51441
+ {
51442
+ "epoch": 0.10884700389289502,
51443
+ "grad_norm": 8.25,
51444
+ "learning_rate": 0.00048197807310414046,
51445
+ "loss": 14.2941,
51446
+ "step": 73480
51447
+ },
51448
+ {
51449
+ "epoch": 0.10886181703985921,
51450
+ "grad_norm": 6.375,
51451
+ "learning_rate": 0.0004819756036366366,
51452
+ "loss": 14.2764,
51453
+ "step": 73490
51454
+ },
51455
+ {
51456
+ "epoch": 0.1088766301868234,
51457
+ "grad_norm": 6.6875,
51458
+ "learning_rate": 0.00048197313416913285,
51459
+ "loss": 14.3026,
51460
+ "step": 73500
51461
+ },
51462
+ {
51463
+ "epoch": 0.1088914433337876,
51464
+ "grad_norm": 5.96875,
51465
+ "learning_rate": 0.0004819706647016291,
51466
+ "loss": 14.4734,
51467
+ "step": 73510
51468
+ },
51469
+ {
51470
+ "epoch": 0.10890625648075179,
51471
+ "grad_norm": 6.65625,
51472
+ "learning_rate": 0.0004819681952341253,
51473
+ "loss": 14.4118,
51474
+ "step": 73520
51475
+ },
51476
+ {
51477
+ "epoch": 0.10892106962771599,
51478
+ "grad_norm": 6.5,
51479
+ "learning_rate": 0.0004819657257666215,
51480
+ "loss": 14.2898,
51481
+ "step": 73530
51482
+ },
51483
+ {
51484
+ "epoch": 0.10893588277468018,
51485
+ "grad_norm": 7.28125,
51486
+ "learning_rate": 0.0004819632562991177,
51487
+ "loss": 14.2984,
51488
+ "step": 73540
51489
+ },
51490
+ {
51491
+ "epoch": 0.10895069592164437,
51492
+ "grad_norm": 6.03125,
51493
+ "learning_rate": 0.00048196078683161394,
51494
+ "loss": 14.305,
51495
+ "step": 73550
51496
+ },
51497
+ {
51498
+ "epoch": 0.10896550906860857,
51499
+ "grad_norm": 5.96875,
51500
+ "learning_rate": 0.00048195831736411014,
51501
+ "loss": 14.3654,
51502
+ "step": 73560
51503
+ },
51504
+ {
51505
+ "epoch": 0.10898032221557276,
51506
+ "grad_norm": 5.75,
51507
+ "learning_rate": 0.00048195584789660634,
51508
+ "loss": 14.376,
51509
+ "step": 73570
51510
+ },
51511
+ {
51512
+ "epoch": 0.10899513536253697,
51513
+ "grad_norm": 6.03125,
51514
+ "learning_rate": 0.0004819533784291026,
51515
+ "loss": 14.2802,
51516
+ "step": 73580
51517
+ },
51518
+ {
51519
+ "epoch": 0.10900994850950116,
51520
+ "grad_norm": 6.75,
51521
+ "learning_rate": 0.00048195090896159884,
51522
+ "loss": 14.3315,
51523
+ "step": 73590
51524
+ },
51525
+ {
51526
+ "epoch": 0.10902476165646535,
51527
+ "grad_norm": 5.71875,
51528
+ "learning_rate": 0.000481948439494095,
51529
+ "loss": 14.3388,
51530
+ "step": 73600
51531
+ },
51532
+ {
51533
+ "epoch": 0.10903957480342955,
51534
+ "grad_norm": 6.59375,
51535
+ "learning_rate": 0.00048194597002659123,
51536
+ "loss": 14.2081,
51537
+ "step": 73610
51538
+ },
51539
+ {
51540
+ "epoch": 0.10905438795039374,
51541
+ "grad_norm": 6.90625,
51542
+ "learning_rate": 0.0004819435005590875,
51543
+ "loss": 14.385,
51544
+ "step": 73620
51545
+ },
51546
+ {
51547
+ "epoch": 0.10906920109735793,
51548
+ "grad_norm": 6.46875,
51549
+ "learning_rate": 0.0004819410310915837,
51550
+ "loss": 14.314,
51551
+ "step": 73630
51552
+ },
51553
+ {
51554
+ "epoch": 0.10908401424432213,
51555
+ "grad_norm": 7.78125,
51556
+ "learning_rate": 0.0004819385616240799,
51557
+ "loss": 14.2866,
51558
+ "step": 73640
51559
+ },
51560
+ {
51561
+ "epoch": 0.10909882739128632,
51562
+ "grad_norm": 6.09375,
51563
+ "learning_rate": 0.0004819360921565761,
51564
+ "loss": 14.3543,
51565
+ "step": 73650
51566
+ },
51567
+ {
51568
+ "epoch": 0.10911364053825051,
51569
+ "grad_norm": 6.96875,
51570
+ "learning_rate": 0.0004819336226890723,
51571
+ "loss": 14.382,
51572
+ "step": 73660
51573
+ },
51574
+ {
51575
+ "epoch": 0.1091284536852147,
51576
+ "grad_norm": 6.71875,
51577
+ "learning_rate": 0.0004819311532215686,
51578
+ "loss": 14.3782,
51579
+ "step": 73670
51580
+ },
51581
+ {
51582
+ "epoch": 0.1091432668321789,
51583
+ "grad_norm": 6.28125,
51584
+ "learning_rate": 0.0004819286837540647,
51585
+ "loss": 14.2908,
51586
+ "step": 73680
51587
+ },
51588
+ {
51589
+ "epoch": 0.10915807997914309,
51590
+ "grad_norm": 7.1875,
51591
+ "learning_rate": 0.00048192621428656097,
51592
+ "loss": 14.3123,
51593
+ "step": 73690
51594
+ },
51595
+ {
51596
+ "epoch": 0.10917289312610728,
51597
+ "grad_norm": 146.0,
51598
+ "learning_rate": 0.0004819237448190572,
51599
+ "loss": 14.3786,
51600
+ "step": 73700
51601
+ },
51602
+ {
51603
+ "epoch": 0.10918770627307148,
51604
+ "grad_norm": 6.1875,
51605
+ "learning_rate": 0.0004819212753515534,
51606
+ "loss": 14.5119,
51607
+ "step": 73710
51608
+ },
51609
+ {
51610
+ "epoch": 0.10920251942003567,
51611
+ "grad_norm": 6.25,
51612
+ "learning_rate": 0.0004819188058840496,
51613
+ "loss": 14.2703,
51614
+ "step": 73720
51615
+ },
51616
+ {
51617
+ "epoch": 0.10921733256699986,
51618
+ "grad_norm": 6.625,
51619
+ "learning_rate": 0.00048191633641654586,
51620
+ "loss": 14.3644,
51621
+ "step": 73730
51622
+ },
51623
+ {
51624
+ "epoch": 0.10923214571396406,
51625
+ "grad_norm": 7.59375,
51626
+ "learning_rate": 0.00048191386694904206,
51627
+ "loss": 14.4364,
51628
+ "step": 73740
51629
+ },
51630
+ {
51631
+ "epoch": 0.10924695886092825,
51632
+ "grad_norm": 6.5,
51633
+ "learning_rate": 0.00048191139748153826,
51634
+ "loss": 14.3508,
51635
+ "step": 73750
51636
+ },
51637
+ {
51638
+ "epoch": 0.10926177200789244,
51639
+ "grad_norm": 7.0625,
51640
+ "learning_rate": 0.00048190892801403445,
51641
+ "loss": 14.3725,
51642
+ "step": 73760
51643
+ },
51644
+ {
51645
+ "epoch": 0.10927658515485664,
51646
+ "grad_norm": 8.1875,
51647
+ "learning_rate": 0.0004819064585465307,
51648
+ "loss": 14.4461,
51649
+ "step": 73770
51650
+ },
51651
+ {
51652
+ "epoch": 0.10929139830182083,
51653
+ "grad_norm": 9.375,
51654
+ "learning_rate": 0.00048190398907902696,
51655
+ "loss": 14.3441,
51656
+ "step": 73780
51657
+ },
51658
+ {
51659
+ "epoch": 0.10930621144878502,
51660
+ "grad_norm": 8.0625,
51661
+ "learning_rate": 0.0004819015196115231,
51662
+ "loss": 14.408,
51663
+ "step": 73790
51664
+ },
51665
+ {
51666
+ "epoch": 0.10932102459574922,
51667
+ "grad_norm": 7.0,
51668
+ "learning_rate": 0.00048189905014401935,
51669
+ "loss": 14.4041,
51670
+ "step": 73800
51671
+ },
51672
+ {
51673
+ "epoch": 0.10933583774271341,
51674
+ "grad_norm": 6.875,
51675
+ "learning_rate": 0.0004818965806765156,
51676
+ "loss": 14.3716,
51677
+ "step": 73810
51678
+ },
51679
+ {
51680
+ "epoch": 0.1093506508896776,
51681
+ "grad_norm": 6.1875,
51682
+ "learning_rate": 0.0004818941112090118,
51683
+ "loss": 14.2834,
51684
+ "step": 73820
51685
+ },
51686
+ {
51687
+ "epoch": 0.1093654640366418,
51688
+ "grad_norm": 6.34375,
51689
+ "learning_rate": 0.000481891641741508,
51690
+ "loss": 14.3748,
51691
+ "step": 73830
51692
+ },
51693
+ {
51694
+ "epoch": 0.10938027718360599,
51695
+ "grad_norm": 6.28125,
51696
+ "learning_rate": 0.0004818891722740042,
51697
+ "loss": 14.4562,
51698
+ "step": 73840
51699
+ },
51700
+ {
51701
+ "epoch": 0.10939509033057018,
51702
+ "grad_norm": 5.96875,
51703
+ "learning_rate": 0.00048188670280650044,
51704
+ "loss": 14.3244,
51705
+ "step": 73850
51706
+ },
51707
+ {
51708
+ "epoch": 0.10940990347753438,
51709
+ "grad_norm": 6.21875,
51710
+ "learning_rate": 0.0004818842333389967,
51711
+ "loss": 14.2985,
51712
+ "step": 73860
51713
+ },
51714
+ {
51715
+ "epoch": 0.10942471662449857,
51716
+ "grad_norm": 7.09375,
51717
+ "learning_rate": 0.00048188176387149284,
51718
+ "loss": 14.4069,
51719
+ "step": 73870
51720
+ },
51721
+ {
51722
+ "epoch": 0.10943952977146276,
51723
+ "grad_norm": 17.375,
51724
+ "learning_rate": 0.0004818792944039891,
51725
+ "loss": 14.3911,
51726
+ "step": 73880
51727
+ },
51728
+ {
51729
+ "epoch": 0.10945434291842696,
51730
+ "grad_norm": 5.6875,
51731
+ "learning_rate": 0.00048187682493648534,
51732
+ "loss": 14.3186,
51733
+ "step": 73890
51734
+ },
51735
+ {
51736
+ "epoch": 0.10946915606539116,
51737
+ "grad_norm": 5.9375,
51738
+ "learning_rate": 0.0004818743554689815,
51739
+ "loss": 14.3146,
51740
+ "step": 73900
51741
+ },
51742
+ {
51743
+ "epoch": 0.10948396921235536,
51744
+ "grad_norm": 6.78125,
51745
+ "learning_rate": 0.00048187188600147773,
51746
+ "loss": 14.3823,
51747
+ "step": 73910
51748
+ },
51749
+ {
51750
+ "epoch": 0.10949878235931955,
51751
+ "grad_norm": 6.46875,
51752
+ "learning_rate": 0.000481869416533974,
51753
+ "loss": 14.2935,
51754
+ "step": 73920
51755
+ },
51756
+ {
51757
+ "epoch": 0.10951359550628374,
51758
+ "grad_norm": 12.75,
51759
+ "learning_rate": 0.0004818669470664702,
51760
+ "loss": 14.4202,
51761
+ "step": 73930
51762
+ },
51763
+ {
51764
+ "epoch": 0.10952840865324794,
51765
+ "grad_norm": 7.59375,
51766
+ "learning_rate": 0.0004818644775989664,
51767
+ "loss": 14.2782,
51768
+ "step": 73940
51769
+ },
51770
+ {
51771
+ "epoch": 0.10954322180021213,
51772
+ "grad_norm": 8.0,
51773
+ "learning_rate": 0.0004818620081314626,
51774
+ "loss": 14.3104,
51775
+ "step": 73950
51776
+ },
51777
+ {
51778
+ "epoch": 0.10955803494717632,
51779
+ "grad_norm": 6.1875,
51780
+ "learning_rate": 0.0004818595386639588,
51781
+ "loss": 14.2493,
51782
+ "step": 73960
51783
+ },
51784
+ {
51785
+ "epoch": 0.10957284809414052,
51786
+ "grad_norm": 11.0625,
51787
+ "learning_rate": 0.0004818570691964551,
51788
+ "loss": 14.3157,
51789
+ "step": 73970
51790
+ },
51791
+ {
51792
+ "epoch": 0.10958766124110471,
51793
+ "grad_norm": 6.90625,
51794
+ "learning_rate": 0.0004818545997289512,
51795
+ "loss": 14.3624,
51796
+ "step": 73980
51797
+ },
51798
+ {
51799
+ "epoch": 0.1096024743880689,
51800
+ "grad_norm": 6.375,
51801
+ "learning_rate": 0.00048185213026144747,
51802
+ "loss": 14.3493,
51803
+ "step": 73990
51804
+ },
51805
+ {
51806
+ "epoch": 0.1096172875350331,
51807
+ "grad_norm": 6.53125,
51808
+ "learning_rate": 0.0004818496607939437,
51809
+ "loss": 14.2649,
51810
+ "step": 74000
51811
+ },
51812
+ {
51813
+ "epoch": 0.10963210068199729,
51814
+ "grad_norm": 6.09375,
51815
+ "learning_rate": 0.0004818471913264399,
51816
+ "loss": 14.3141,
51817
+ "step": 74010
51818
+ },
51819
+ {
51820
+ "epoch": 0.10964691382896148,
51821
+ "grad_norm": 5.8125,
51822
+ "learning_rate": 0.0004818447218589361,
51823
+ "loss": 14.2794,
51824
+ "step": 74020
51825
+ },
51826
+ {
51827
+ "epoch": 0.10966172697592567,
51828
+ "grad_norm": 7.03125,
51829
+ "learning_rate": 0.00048184225239143236,
51830
+ "loss": 14.369,
51831
+ "step": 74030
51832
+ },
51833
+ {
51834
+ "epoch": 0.10967654012288987,
51835
+ "grad_norm": 7.9375,
51836
+ "learning_rate": 0.00048183978292392856,
51837
+ "loss": 14.3045,
51838
+ "step": 74040
51839
+ },
51840
+ {
51841
+ "epoch": 0.10969135326985406,
51842
+ "grad_norm": 5.5625,
51843
+ "learning_rate": 0.0004818373134564248,
51844
+ "loss": 14.308,
51845
+ "step": 74050
51846
+ },
51847
+ {
51848
+ "epoch": 0.10970616641681825,
51849
+ "grad_norm": 6.90625,
51850
+ "learning_rate": 0.00048183484398892096,
51851
+ "loss": 14.3098,
51852
+ "step": 74060
51853
+ },
51854
+ {
51855
+ "epoch": 0.10972097956378245,
51856
+ "grad_norm": 6.25,
51857
+ "learning_rate": 0.0004818323745214172,
51858
+ "loss": 14.4085,
51859
+ "step": 74070
51860
+ },
51861
+ {
51862
+ "epoch": 0.10973579271074664,
51863
+ "grad_norm": 7.46875,
51864
+ "learning_rate": 0.00048182990505391346,
51865
+ "loss": 14.3232,
51866
+ "step": 74080
51867
+ },
51868
+ {
51869
+ "epoch": 0.10975060585771083,
51870
+ "grad_norm": 5.71875,
51871
+ "learning_rate": 0.0004818274355864096,
51872
+ "loss": 14.2862,
51873
+ "step": 74090
51874
+ },
51875
+ {
51876
+ "epoch": 0.10976541900467503,
51877
+ "grad_norm": 6.03125,
51878
+ "learning_rate": 0.00048182496611890585,
51879
+ "loss": 14.335,
51880
+ "step": 74100
51881
+ },
51882
+ {
51883
+ "epoch": 0.10978023215163922,
51884
+ "grad_norm": 6.15625,
51885
+ "learning_rate": 0.0004818224966514021,
51886
+ "loss": 14.3458,
51887
+ "step": 74110
51888
+ },
51889
+ {
51890
+ "epoch": 0.10979504529860341,
51891
+ "grad_norm": 6.15625,
51892
+ "learning_rate": 0.0004818200271838983,
51893
+ "loss": 14.3224,
51894
+ "step": 74120
51895
+ },
51896
+ {
51897
+ "epoch": 0.1098098584455676,
51898
+ "grad_norm": 6.0,
51899
+ "learning_rate": 0.0004818175577163945,
51900
+ "loss": 14.2839,
51901
+ "step": 74130
51902
+ },
51903
+ {
51904
+ "epoch": 0.1098246715925318,
51905
+ "grad_norm": 7.0,
51906
+ "learning_rate": 0.0004818150882488907,
51907
+ "loss": 14.3293,
51908
+ "step": 74140
51909
+ },
51910
+ {
51911
+ "epoch": 0.109839484739496,
51912
+ "grad_norm": 6.75,
51913
+ "learning_rate": 0.00048181261878138694,
51914
+ "loss": 14.3587,
51915
+ "step": 74150
51916
+ },
51917
+ {
51918
+ "epoch": 0.10985429788646019,
51919
+ "grad_norm": 6.5,
51920
+ "learning_rate": 0.0004818101493138832,
51921
+ "loss": 14.3828,
51922
+ "step": 74160
51923
+ },
51924
+ {
51925
+ "epoch": 0.10986911103342438,
51926
+ "grad_norm": 6.09375,
51927
+ "learning_rate": 0.00048180767984637934,
51928
+ "loss": 14.3368,
51929
+ "step": 74170
51930
+ },
51931
+ {
51932
+ "epoch": 0.10988392418038857,
51933
+ "grad_norm": 5.90625,
51934
+ "learning_rate": 0.0004818052103788756,
51935
+ "loss": 14.345,
51936
+ "step": 74180
51937
+ },
51938
+ {
51939
+ "epoch": 0.10989873732735277,
51940
+ "grad_norm": 6.53125,
51941
+ "learning_rate": 0.00048180274091137184,
51942
+ "loss": 14.2947,
51943
+ "step": 74190
51944
+ },
51945
+ {
51946
+ "epoch": 0.10991355047431696,
51947
+ "grad_norm": 7.59375,
51948
+ "learning_rate": 0.00048180027144386804,
51949
+ "loss": 14.4314,
51950
+ "step": 74200
51951
+ },
51952
+ {
51953
+ "epoch": 0.10992836362128115,
51954
+ "grad_norm": 7.15625,
51955
+ "learning_rate": 0.00048179780197636423,
51956
+ "loss": 14.3909,
51957
+ "step": 74210
51958
+ },
51959
+ {
51960
+ "epoch": 0.10994317676824536,
51961
+ "grad_norm": 5.78125,
51962
+ "learning_rate": 0.0004817953325088605,
51963
+ "loss": 14.2108,
51964
+ "step": 74220
51965
+ },
51966
+ {
51967
+ "epoch": 0.10995798991520955,
51968
+ "grad_norm": 5.9375,
51969
+ "learning_rate": 0.0004817928630413567,
51970
+ "loss": 14.3088,
51971
+ "step": 74230
51972
+ },
51973
+ {
51974
+ "epoch": 0.10997280306217375,
51975
+ "grad_norm": 7.71875,
51976
+ "learning_rate": 0.0004817903935738529,
51977
+ "loss": 14.3521,
51978
+ "step": 74240
51979
+ },
51980
+ {
51981
+ "epoch": 0.10998761620913794,
51982
+ "grad_norm": 6.5625,
51983
+ "learning_rate": 0.0004817879241063491,
51984
+ "loss": 14.32,
51985
+ "step": 74250
51986
+ },
51987
+ {
51988
+ "epoch": 0.11000242935610213,
51989
+ "grad_norm": 6.09375,
51990
+ "learning_rate": 0.0004817854546388453,
51991
+ "loss": 14.3618,
51992
+ "step": 74260
51993
+ },
51994
+ {
51995
+ "epoch": 0.11001724250306633,
51996
+ "grad_norm": 7.8125,
51997
+ "learning_rate": 0.0004817829851713416,
51998
+ "loss": 14.3107,
51999
+ "step": 74270
52000
+ },
52001
+ {
52002
+ "epoch": 0.11003205565003052,
52003
+ "grad_norm": 6.75,
52004
+ "learning_rate": 0.0004817805157038377,
52005
+ "loss": 14.2949,
52006
+ "step": 74280
52007
+ },
52008
+ {
52009
+ "epoch": 0.11004686879699471,
52010
+ "grad_norm": 5.8125,
52011
+ "learning_rate": 0.00048177804623633397,
52012
+ "loss": 14.3083,
52013
+ "step": 74290
52014
+ },
52015
+ {
52016
+ "epoch": 0.1100616819439589,
52017
+ "grad_norm": 6.15625,
52018
+ "learning_rate": 0.0004817755767688302,
52019
+ "loss": 14.3156,
52020
+ "step": 74300
52021
+ },
52022
+ {
52023
+ "epoch": 0.1100764950909231,
52024
+ "grad_norm": 7.40625,
52025
+ "learning_rate": 0.0004817731073013264,
52026
+ "loss": 14.4064,
52027
+ "step": 74310
52028
+ },
52029
+ {
52030
+ "epoch": 0.11009130823788729,
52031
+ "grad_norm": 13.1875,
52032
+ "learning_rate": 0.0004817706378338226,
52033
+ "loss": 14.2234,
52034
+ "step": 74320
52035
+ },
52036
+ {
52037
+ "epoch": 0.11010612138485149,
52038
+ "grad_norm": 5.90625,
52039
+ "learning_rate": 0.00048176816836631887,
52040
+ "loss": 14.3507,
52041
+ "step": 74330
52042
+ },
52043
+ {
52044
+ "epoch": 0.11012093453181568,
52045
+ "grad_norm": 6.96875,
52046
+ "learning_rate": 0.00048176569889881506,
52047
+ "loss": 14.2709,
52048
+ "step": 74340
52049
+ },
52050
+ {
52051
+ "epoch": 0.11013574767877987,
52052
+ "grad_norm": 6.1875,
52053
+ "learning_rate": 0.0004817632294313113,
52054
+ "loss": 14.3305,
52055
+ "step": 74350
52056
+ },
52057
+ {
52058
+ "epoch": 0.11015056082574406,
52059
+ "grad_norm": 15.1875,
52060
+ "learning_rate": 0.00048176075996380746,
52061
+ "loss": 14.277,
52062
+ "step": 74360
52063
+ },
52064
+ {
52065
+ "epoch": 0.11016537397270826,
52066
+ "grad_norm": 7.09375,
52067
+ "learning_rate": 0.0004817582904963037,
52068
+ "loss": 14.3007,
52069
+ "step": 74370
52070
+ },
52071
+ {
52072
+ "epoch": 0.11018018711967245,
52073
+ "grad_norm": 6.6875,
52074
+ "learning_rate": 0.00048175582102879996,
52075
+ "loss": 14.3853,
52076
+ "step": 74380
52077
+ },
52078
+ {
52079
+ "epoch": 0.11019500026663664,
52080
+ "grad_norm": 10.375,
52081
+ "learning_rate": 0.0004817533515612961,
52082
+ "loss": 14.3815,
52083
+ "step": 74390
52084
+ },
52085
+ {
52086
+ "epoch": 0.11020981341360084,
52087
+ "grad_norm": 22.625,
52088
+ "learning_rate": 0.00048175088209379235,
52089
+ "loss": 14.3315,
52090
+ "step": 74400
52091
+ },
52092
+ {
52093
+ "epoch": 0.11022462656056503,
52094
+ "grad_norm": 6.875,
52095
+ "learning_rate": 0.0004817484126262886,
52096
+ "loss": 14.2858,
52097
+ "step": 74410
52098
+ },
52099
+ {
52100
+ "epoch": 0.11023943970752922,
52101
+ "grad_norm": 6.65625,
52102
+ "learning_rate": 0.0004817459431587848,
52103
+ "loss": 14.3189,
52104
+ "step": 74420
52105
+ },
52106
+ {
52107
+ "epoch": 0.11025425285449342,
52108
+ "grad_norm": 17.0,
52109
+ "learning_rate": 0.000481743473691281,
52110
+ "loss": 14.48,
52111
+ "step": 74430
52112
+ },
52113
+ {
52114
+ "epoch": 0.11026906600145761,
52115
+ "grad_norm": 6.21875,
52116
+ "learning_rate": 0.0004817410042237772,
52117
+ "loss": 14.3736,
52118
+ "step": 74440
52119
+ },
52120
+ {
52121
+ "epoch": 0.1102838791484218,
52122
+ "grad_norm": 6.1875,
52123
+ "learning_rate": 0.00048173853475627344,
52124
+ "loss": 14.2558,
52125
+ "step": 74450
52126
+ },
52127
+ {
52128
+ "epoch": 0.110298692295386,
52129
+ "grad_norm": 6.15625,
52130
+ "learning_rate": 0.0004817360652887697,
52131
+ "loss": 14.3613,
52132
+ "step": 74460
52133
+ },
52134
+ {
52135
+ "epoch": 0.11031350544235019,
52136
+ "grad_norm": 6.125,
52137
+ "learning_rate": 0.00048173359582126584,
52138
+ "loss": 14.3263,
52139
+ "step": 74470
52140
+ },
52141
+ {
52142
+ "epoch": 0.11032831858931438,
52143
+ "grad_norm": 6.78125,
52144
+ "learning_rate": 0.0004817311263537621,
52145
+ "loss": 14.2865,
52146
+ "step": 74480
52147
+ },
52148
+ {
52149
+ "epoch": 0.11034313173627858,
52150
+ "grad_norm": 5.84375,
52151
+ "learning_rate": 0.00048172865688625834,
52152
+ "loss": 14.4033,
52153
+ "step": 74490
52154
+ },
52155
+ {
52156
+ "epoch": 0.11035794488324277,
52157
+ "grad_norm": 7.5,
52158
+ "learning_rate": 0.00048172618741875454,
52159
+ "loss": 14.3948,
52160
+ "step": 74500
52161
+ },
52162
+ {
52163
+ "epoch": 0.11037275803020696,
52164
+ "grad_norm": 6.3125,
52165
+ "learning_rate": 0.00048172371795125073,
52166
+ "loss": 14.2654,
52167
+ "step": 74510
52168
+ },
52169
+ {
52170
+ "epoch": 0.11038757117717116,
52171
+ "grad_norm": 6.3125,
52172
+ "learning_rate": 0.000481721248483747,
52173
+ "loss": 14.3603,
52174
+ "step": 74520
52175
+ },
52176
+ {
52177
+ "epoch": 0.11040238432413535,
52178
+ "grad_norm": 6.8125,
52179
+ "learning_rate": 0.0004817187790162432,
52180
+ "loss": 14.2516,
52181
+ "step": 74530
52182
+ },
52183
+ {
52184
+ "epoch": 0.11041719747109956,
52185
+ "grad_norm": 7.28125,
52186
+ "learning_rate": 0.00048171630954873943,
52187
+ "loss": 14.2076,
52188
+ "step": 74540
52189
+ },
52190
+ {
52191
+ "epoch": 0.11043201061806375,
52192
+ "grad_norm": 7.1875,
52193
+ "learning_rate": 0.0004817138400812356,
52194
+ "loss": 14.3447,
52195
+ "step": 74550
52196
+ },
52197
+ {
52198
+ "epoch": 0.11044682376502794,
52199
+ "grad_norm": 6.8125,
52200
+ "learning_rate": 0.0004817113706137318,
52201
+ "loss": 14.2249,
52202
+ "step": 74560
52203
+ },
52204
+ {
52205
+ "epoch": 0.11046163691199214,
52206
+ "grad_norm": 7.96875,
52207
+ "learning_rate": 0.0004817089011462281,
52208
+ "loss": 14.3628,
52209
+ "step": 74570
52210
+ },
52211
+ {
52212
+ "epoch": 0.11047645005895633,
52213
+ "grad_norm": 6.625,
52214
+ "learning_rate": 0.0004817064316787242,
52215
+ "loss": 14.3258,
52216
+ "step": 74580
52217
+ },
52218
+ {
52219
+ "epoch": 0.11049126320592052,
52220
+ "grad_norm": 8.5,
52221
+ "learning_rate": 0.00048170396221122047,
52222
+ "loss": 14.3088,
52223
+ "step": 74590
52224
+ },
52225
+ {
52226
+ "epoch": 0.11050607635288472,
52227
+ "grad_norm": 6.78125,
52228
+ "learning_rate": 0.0004817014927437167,
52229
+ "loss": 14.2457,
52230
+ "step": 74600
52231
+ },
52232
+ {
52233
+ "epoch": 0.11052088949984891,
52234
+ "grad_norm": 6.5625,
52235
+ "learning_rate": 0.0004816990232762129,
52236
+ "loss": 14.3082,
52237
+ "step": 74610
52238
+ },
52239
+ {
52240
+ "epoch": 0.1105357026468131,
52241
+ "grad_norm": 6.6875,
52242
+ "learning_rate": 0.0004816965538087091,
52243
+ "loss": 14.2829,
52244
+ "step": 74620
52245
+ },
52246
+ {
52247
+ "epoch": 0.1105505157937773,
52248
+ "grad_norm": 6.96875,
52249
+ "learning_rate": 0.00048169408434120537,
52250
+ "loss": 14.4109,
52251
+ "step": 74630
52252
+ },
52253
+ {
52254
+ "epoch": 0.11056532894074149,
52255
+ "grad_norm": 6.625,
52256
+ "learning_rate": 0.00048169161487370156,
52257
+ "loss": 14.3165,
52258
+ "step": 74640
52259
+ },
52260
+ {
52261
+ "epoch": 0.11058014208770568,
52262
+ "grad_norm": 6.625,
52263
+ "learning_rate": 0.0004816891454061978,
52264
+ "loss": 14.3269,
52265
+ "step": 74650
52266
+ },
52267
+ {
52268
+ "epoch": 0.11059495523466988,
52269
+ "grad_norm": 6.21875,
52270
+ "learning_rate": 0.00048168667593869396,
52271
+ "loss": 14.3402,
52272
+ "step": 74660
52273
+ },
52274
+ {
52275
+ "epoch": 0.11060976838163407,
52276
+ "grad_norm": 6.375,
52277
+ "learning_rate": 0.0004816842064711902,
52278
+ "loss": 14.2344,
52279
+ "step": 74670
52280
+ },
52281
+ {
52282
+ "epoch": 0.11062458152859826,
52283
+ "grad_norm": 6.21875,
52284
+ "learning_rate": 0.00048168173700368646,
52285
+ "loss": 14.2689,
52286
+ "step": 74680
52287
+ },
52288
+ {
52289
+ "epoch": 0.11063939467556246,
52290
+ "grad_norm": 7.125,
52291
+ "learning_rate": 0.00048167926753618265,
52292
+ "loss": 14.3377,
52293
+ "step": 74690
52294
+ },
52295
+ {
52296
+ "epoch": 0.11065420782252665,
52297
+ "grad_norm": 5.8125,
52298
+ "learning_rate": 0.00048167679806867885,
52299
+ "loss": 14.3934,
52300
+ "step": 74700
52301
+ },
52302
+ {
52303
+ "epoch": 0.11066902096949084,
52304
+ "grad_norm": 5.75,
52305
+ "learning_rate": 0.0004816743286011751,
52306
+ "loss": 14.3468,
52307
+ "step": 74710
52308
+ },
52309
+ {
52310
+ "epoch": 0.11068383411645503,
52311
+ "grad_norm": 6.5,
52312
+ "learning_rate": 0.0004816718591336713,
52313
+ "loss": 14.3222,
52314
+ "step": 74720
52315
+ },
52316
+ {
52317
+ "epoch": 0.11069864726341923,
52318
+ "grad_norm": 6.28125,
52319
+ "learning_rate": 0.00048166938966616755,
52320
+ "loss": 14.3136,
52321
+ "step": 74730
52322
+ },
52323
+ {
52324
+ "epoch": 0.11071346041038342,
52325
+ "grad_norm": 5.8125,
52326
+ "learning_rate": 0.0004816669201986637,
52327
+ "loss": 14.3292,
52328
+ "step": 74740
52329
+ },
52330
+ {
52331
+ "epoch": 0.11072827355734761,
52332
+ "grad_norm": 7.1875,
52333
+ "learning_rate": 0.00048166445073115994,
52334
+ "loss": 14.3351,
52335
+ "step": 74750
52336
+ },
52337
+ {
52338
+ "epoch": 0.11074308670431181,
52339
+ "grad_norm": 5.875,
52340
+ "learning_rate": 0.0004816619812636562,
52341
+ "loss": 14.3235,
52342
+ "step": 74760
52343
+ },
52344
+ {
52345
+ "epoch": 0.110757899851276,
52346
+ "grad_norm": 5.53125,
52347
+ "learning_rate": 0.00048165951179615234,
52348
+ "loss": 14.4081,
52349
+ "step": 74770
52350
+ },
52351
+ {
52352
+ "epoch": 0.1107727129982402,
52353
+ "grad_norm": 5.90625,
52354
+ "learning_rate": 0.0004816570423286486,
52355
+ "loss": 14.3723,
52356
+ "step": 74780
52357
+ },
52358
+ {
52359
+ "epoch": 0.11078752614520439,
52360
+ "grad_norm": 7.28125,
52361
+ "learning_rate": 0.00048165457286114484,
52362
+ "loss": 14.3032,
52363
+ "step": 74790
52364
+ },
52365
+ {
52366
+ "epoch": 0.11080233929216858,
52367
+ "grad_norm": 6.03125,
52368
+ "learning_rate": 0.00048165210339364104,
52369
+ "loss": 14.2766,
52370
+ "step": 74800
52371
+ },
52372
+ {
52373
+ "epoch": 0.11081715243913277,
52374
+ "grad_norm": 7.625,
52375
+ "learning_rate": 0.00048164963392613723,
52376
+ "loss": 14.2802,
52377
+ "step": 74810
52378
+ },
52379
+ {
52380
+ "epoch": 0.11083196558609697,
52381
+ "grad_norm": 6.25,
52382
+ "learning_rate": 0.0004816471644586335,
52383
+ "loss": 14.2297,
52384
+ "step": 74820
52385
+ },
52386
+ {
52387
+ "epoch": 0.11084677873306116,
52388
+ "grad_norm": 7.125,
52389
+ "learning_rate": 0.0004816446949911297,
52390
+ "loss": 14.2651,
52391
+ "step": 74830
52392
+ },
52393
+ {
52394
+ "epoch": 0.11086159188002535,
52395
+ "grad_norm": 5.59375,
52396
+ "learning_rate": 0.00048164222552362593,
52397
+ "loss": 14.2738,
52398
+ "step": 74840
52399
+ },
52400
+ {
52401
+ "epoch": 0.11087640502698956,
52402
+ "grad_norm": 6.0,
52403
+ "learning_rate": 0.0004816397560561221,
52404
+ "loss": 14.3277,
52405
+ "step": 74850
52406
+ },
52407
+ {
52408
+ "epoch": 0.11089121817395375,
52409
+ "grad_norm": 6.125,
52410
+ "learning_rate": 0.0004816372865886183,
52411
+ "loss": 14.3357,
52412
+ "step": 74860
52413
+ },
52414
+ {
52415
+ "epoch": 0.11090603132091795,
52416
+ "grad_norm": 6.84375,
52417
+ "learning_rate": 0.0004816348171211146,
52418
+ "loss": 14.3048,
52419
+ "step": 74870
52420
+ },
52421
+ {
52422
+ "epoch": 0.11092084446788214,
52423
+ "grad_norm": 6.28125,
52424
+ "learning_rate": 0.0004816323476536108,
52425
+ "loss": 14.3594,
52426
+ "step": 74880
52427
+ },
52428
+ {
52429
+ "epoch": 0.11093565761484633,
52430
+ "grad_norm": 5.875,
52431
+ "learning_rate": 0.00048162987818610697,
52432
+ "loss": 14.3663,
52433
+ "step": 74890
52434
+ },
52435
+ {
52436
+ "epoch": 0.11095047076181053,
52437
+ "grad_norm": 6.53125,
52438
+ "learning_rate": 0.0004816274087186032,
52439
+ "loss": 14.4241,
52440
+ "step": 74900
52441
+ },
52442
+ {
52443
+ "epoch": 0.11096528390877472,
52444
+ "grad_norm": 5.875,
52445
+ "learning_rate": 0.0004816249392510994,
52446
+ "loss": 14.218,
52447
+ "step": 74910
52448
+ },
52449
+ {
52450
+ "epoch": 0.11098009705573891,
52451
+ "grad_norm": 6.625,
52452
+ "learning_rate": 0.0004816224697835956,
52453
+ "loss": 14.3064,
52454
+ "step": 74920
52455
+ },
52456
+ {
52457
+ "epoch": 0.1109949102027031,
52458
+ "grad_norm": 6.40625,
52459
+ "learning_rate": 0.00048162000031609187,
52460
+ "loss": 14.34,
52461
+ "step": 74930
52462
+ },
52463
+ {
52464
+ "epoch": 0.1110097233496673,
52465
+ "grad_norm": 9.1875,
52466
+ "learning_rate": 0.00048161753084858806,
52467
+ "loss": 14.3565,
52468
+ "step": 74940
52469
+ },
52470
+ {
52471
+ "epoch": 0.11102453649663149,
52472
+ "grad_norm": 6.34375,
52473
+ "learning_rate": 0.0004816150613810843,
52474
+ "loss": 14.3032,
52475
+ "step": 74950
52476
+ },
52477
+ {
52478
+ "epoch": 0.11103934964359569,
52479
+ "grad_norm": 9.3125,
52480
+ "learning_rate": 0.00048161259191358046,
52481
+ "loss": 14.2906,
52482
+ "step": 74960
52483
+ },
52484
+ {
52485
+ "epoch": 0.11105416279055988,
52486
+ "grad_norm": 6.53125,
52487
+ "learning_rate": 0.0004816101224460767,
52488
+ "loss": 14.3689,
52489
+ "step": 74970
52490
+ },
52491
+ {
52492
+ "epoch": 0.11106897593752407,
52493
+ "grad_norm": 6.90625,
52494
+ "learning_rate": 0.00048160765297857296,
52495
+ "loss": 14.3633,
52496
+ "step": 74980
52497
+ },
52498
+ {
52499
+ "epoch": 0.11108378908448827,
52500
+ "grad_norm": 6.21875,
52501
+ "learning_rate": 0.00048160518351106915,
52502
+ "loss": 14.3559,
52503
+ "step": 74990
52504
+ },
52505
+ {
52506
+ "epoch": 0.11109860223145246,
52507
+ "grad_norm": 6.125,
52508
+ "learning_rate": 0.00048160271404356535,
52509
+ "loss": 14.2913,
52510
+ "step": 75000
52511
+ },
52512
+ {
52513
+ "epoch": 0.11111341537841665,
52514
+ "grad_norm": 6.6875,
52515
+ "learning_rate": 0.0004816002445760616,
52516
+ "loss": 14.3335,
52517
+ "step": 75010
52518
+ },
52519
+ {
52520
+ "epoch": 0.11112822852538085,
52521
+ "grad_norm": 6.625,
52522
+ "learning_rate": 0.0004815977751085578,
52523
+ "loss": 14.3282,
52524
+ "step": 75020
52525
+ },
52526
+ {
52527
+ "epoch": 0.11114304167234504,
52528
+ "grad_norm": 7.59375,
52529
+ "learning_rate": 0.00048159530564105405,
52530
+ "loss": 14.2957,
52531
+ "step": 75030
52532
+ },
52533
+ {
52534
+ "epoch": 0.11115785481930923,
52535
+ "grad_norm": 7.15625,
52536
+ "learning_rate": 0.0004815928361735502,
52537
+ "loss": 14.3336,
52538
+ "step": 75040
52539
+ },
52540
+ {
52541
+ "epoch": 0.11117266796627343,
52542
+ "grad_norm": 5.40625,
52543
+ "learning_rate": 0.00048159036670604644,
52544
+ "loss": 14.2651,
52545
+ "step": 75050
52546
+ },
52547
+ {
52548
+ "epoch": 0.11118748111323762,
52549
+ "grad_norm": 6.34375,
52550
+ "learning_rate": 0.0004815878972385427,
52551
+ "loss": 14.2851,
52552
+ "step": 75060
52553
+ },
52554
+ {
52555
+ "epoch": 0.11120229426020181,
52556
+ "grad_norm": 6.03125,
52557
+ "learning_rate": 0.00048158542777103884,
52558
+ "loss": 14.3259,
52559
+ "step": 75070
52560
+ },
52561
+ {
52562
+ "epoch": 0.111217107407166,
52563
+ "grad_norm": 6.96875,
52564
+ "learning_rate": 0.0004815829583035351,
52565
+ "loss": 14.267,
52566
+ "step": 75080
52567
+ },
52568
+ {
52569
+ "epoch": 0.1112319205541302,
52570
+ "grad_norm": 6.65625,
52571
+ "learning_rate": 0.00048158048883603134,
52572
+ "loss": 14.4197,
52573
+ "step": 75090
52574
+ },
52575
+ {
52576
+ "epoch": 0.11124673370109439,
52577
+ "grad_norm": 8.5625,
52578
+ "learning_rate": 0.00048157801936852754,
52579
+ "loss": 14.3869,
52580
+ "step": 75100
52581
+ },
52582
+ {
52583
+ "epoch": 0.11126154684805858,
52584
+ "grad_norm": 7.1875,
52585
+ "learning_rate": 0.00048157554990102373,
52586
+ "loss": 14.3311,
52587
+ "step": 75110
52588
+ },
52589
+ {
52590
+ "epoch": 0.11127635999502278,
52591
+ "grad_norm": 9.4375,
52592
+ "learning_rate": 0.00048157308043352,
52593
+ "loss": 14.2169,
52594
+ "step": 75120
52595
+ },
52596
+ {
52597
+ "epoch": 0.11129117314198697,
52598
+ "grad_norm": 6.75,
52599
+ "learning_rate": 0.0004815706109660162,
52600
+ "loss": 14.4135,
52601
+ "step": 75130
52602
+ },
52603
+ {
52604
+ "epoch": 0.11130598628895116,
52605
+ "grad_norm": 6.21875,
52606
+ "learning_rate": 0.00048156814149851243,
52607
+ "loss": 14.2987,
52608
+ "step": 75140
52609
+ },
52610
+ {
52611
+ "epoch": 0.11132079943591536,
52612
+ "grad_norm": 6.9375,
52613
+ "learning_rate": 0.0004815656720310086,
52614
+ "loss": 14.2905,
52615
+ "step": 75150
52616
+ },
52617
+ {
52618
+ "epoch": 0.11133561258287955,
52619
+ "grad_norm": 6.0625,
52620
+ "learning_rate": 0.0004815632025635048,
52621
+ "loss": 14.4229,
52622
+ "step": 75160
52623
+ },
52624
+ {
52625
+ "epoch": 0.11135042572984376,
52626
+ "grad_norm": 6.15625,
52627
+ "learning_rate": 0.0004815607330960011,
52628
+ "loss": 14.3141,
52629
+ "step": 75170
52630
+ },
52631
+ {
52632
+ "epoch": 0.11136523887680795,
52633
+ "grad_norm": 7.40625,
52634
+ "learning_rate": 0.0004815582636284973,
52635
+ "loss": 14.3162,
52636
+ "step": 75180
52637
+ },
52638
+ {
52639
+ "epoch": 0.11138005202377214,
52640
+ "grad_norm": 8.8125,
52641
+ "learning_rate": 0.00048155579416099347,
52642
+ "loss": 14.333,
52643
+ "step": 75190
52644
+ },
52645
+ {
52646
+ "epoch": 0.11139486517073634,
52647
+ "grad_norm": 6.125,
52648
+ "learning_rate": 0.0004815533246934897,
52649
+ "loss": 14.2839,
52650
+ "step": 75200
52651
+ },
52652
+ {
52653
+ "epoch": 0.11140967831770053,
52654
+ "grad_norm": 5.875,
52655
+ "learning_rate": 0.0004815508552259859,
52656
+ "loss": 14.3233,
52657
+ "step": 75210
52658
+ },
52659
+ {
52660
+ "epoch": 0.11142449146466472,
52661
+ "grad_norm": 6.75,
52662
+ "learning_rate": 0.00048154838575848217,
52663
+ "loss": 14.3544,
52664
+ "step": 75220
52665
+ },
52666
+ {
52667
+ "epoch": 0.11143930461162892,
52668
+ "grad_norm": 6.4375,
52669
+ "learning_rate": 0.00048154591629097837,
52670
+ "loss": 14.2333,
52671
+ "step": 75230
52672
+ },
52673
+ {
52674
+ "epoch": 0.11145411775859311,
52675
+ "grad_norm": 6.53125,
52676
+ "learning_rate": 0.00048154344682347456,
52677
+ "loss": 14.2612,
52678
+ "step": 75240
52679
+ },
52680
+ {
52681
+ "epoch": 0.1114689309055573,
52682
+ "grad_norm": 7.34375,
52683
+ "learning_rate": 0.0004815409773559708,
52684
+ "loss": 14.2524,
52685
+ "step": 75250
52686
+ },
52687
+ {
52688
+ "epoch": 0.1114837440525215,
52689
+ "grad_norm": 6.875,
52690
+ "learning_rate": 0.00048153850788846696,
52691
+ "loss": 14.2245,
52692
+ "step": 75260
52693
+ },
52694
+ {
52695
+ "epoch": 0.11149855719948569,
52696
+ "grad_norm": 6.65625,
52697
+ "learning_rate": 0.0004815360384209632,
52698
+ "loss": 14.3399,
52699
+ "step": 75270
52700
+ },
52701
+ {
52702
+ "epoch": 0.11151337034644988,
52703
+ "grad_norm": 5.96875,
52704
+ "learning_rate": 0.00048153356895345946,
52705
+ "loss": 14.3245,
52706
+ "step": 75280
52707
+ },
52708
+ {
52709
+ "epoch": 0.11152818349341408,
52710
+ "grad_norm": 6.9375,
52711
+ "learning_rate": 0.00048153109948595566,
52712
+ "loss": 14.3032,
52713
+ "step": 75290
52714
+ },
52715
+ {
52716
+ "epoch": 0.11154299664037827,
52717
+ "grad_norm": 7.5625,
52718
+ "learning_rate": 0.00048152863001845185,
52719
+ "loss": 14.2328,
52720
+ "step": 75300
52721
+ },
52722
+ {
52723
+ "epoch": 0.11155780978734246,
52724
+ "grad_norm": 19.5,
52725
+ "learning_rate": 0.0004815261605509481,
52726
+ "loss": 14.2641,
52727
+ "step": 75310
52728
+ },
52729
+ {
52730
+ "epoch": 0.11157262293430666,
52731
+ "grad_norm": 6.5625,
52732
+ "learning_rate": 0.0004815236910834443,
52733
+ "loss": 14.325,
52734
+ "step": 75320
52735
+ },
52736
+ {
52737
+ "epoch": 0.11158743608127085,
52738
+ "grad_norm": 13.625,
52739
+ "learning_rate": 0.00048152122161594055,
52740
+ "loss": 14.2854,
52741
+ "step": 75330
52742
+ },
52743
+ {
52744
+ "epoch": 0.11160224922823504,
52745
+ "grad_norm": 88.0,
52746
+ "learning_rate": 0.0004815187521484367,
52747
+ "loss": 14.2821,
52748
+ "step": 75340
52749
+ },
52750
+ {
52751
+ "epoch": 0.11161706237519924,
52752
+ "grad_norm": 5.59375,
52753
+ "learning_rate": 0.00048151628268093294,
52754
+ "loss": 14.3705,
52755
+ "step": 75350
52756
+ },
52757
+ {
52758
+ "epoch": 0.11163187552216343,
52759
+ "grad_norm": 6.75,
52760
+ "learning_rate": 0.0004815138132134292,
52761
+ "loss": 14.307,
52762
+ "step": 75360
52763
+ },
52764
+ {
52765
+ "epoch": 0.11164668866912762,
52766
+ "grad_norm": 6.125,
52767
+ "learning_rate": 0.0004815113437459254,
52768
+ "loss": 14.2658,
52769
+ "step": 75370
52770
+ },
52771
+ {
52772
+ "epoch": 0.11166150181609182,
52773
+ "grad_norm": 5.90625,
52774
+ "learning_rate": 0.0004815088742784216,
52775
+ "loss": 14.3068,
52776
+ "step": 75380
52777
+ },
52778
+ {
52779
+ "epoch": 0.11167631496305601,
52780
+ "grad_norm": 6.28125,
52781
+ "learning_rate": 0.00048150640481091784,
52782
+ "loss": 14.2042,
52783
+ "step": 75390
52784
+ },
52785
+ {
52786
+ "epoch": 0.1116911281100202,
52787
+ "grad_norm": 5.6875,
52788
+ "learning_rate": 0.00048150393534341404,
52789
+ "loss": 14.339,
52790
+ "step": 75400
52791
+ },
52792
+ {
52793
+ "epoch": 0.1117059412569844,
52794
+ "grad_norm": 7.25,
52795
+ "learning_rate": 0.00048150146587591023,
52796
+ "loss": 14.3058,
52797
+ "step": 75410
52798
+ },
52799
+ {
52800
+ "epoch": 0.11172075440394859,
52801
+ "grad_norm": 6.625,
52802
+ "learning_rate": 0.0004814989964084065,
52803
+ "loss": 14.3043,
52804
+ "step": 75420
52805
+ },
52806
+ {
52807
+ "epoch": 0.11173556755091278,
52808
+ "grad_norm": 14.9375,
52809
+ "learning_rate": 0.0004814965269409027,
52810
+ "loss": 14.3158,
52811
+ "step": 75430
52812
+ },
52813
+ {
52814
+ "epoch": 0.11175038069787697,
52815
+ "grad_norm": 6.25,
52816
+ "learning_rate": 0.00048149405747339893,
52817
+ "loss": 14.3287,
52818
+ "step": 75440
52819
+ },
52820
+ {
52821
+ "epoch": 0.11176519384484117,
52822
+ "grad_norm": 7.375,
52823
+ "learning_rate": 0.0004814915880058951,
52824
+ "loss": 14.3725,
52825
+ "step": 75450
52826
+ },
52827
+ {
52828
+ "epoch": 0.11178000699180536,
52829
+ "grad_norm": 6.75,
52830
+ "learning_rate": 0.0004814891185383913,
52831
+ "loss": 14.2925,
52832
+ "step": 75460
52833
+ },
52834
+ {
52835
+ "epoch": 0.11179482013876955,
52836
+ "grad_norm": 7.15625,
52837
+ "learning_rate": 0.0004814866490708876,
52838
+ "loss": 14.3199,
52839
+ "step": 75470
52840
+ },
52841
+ {
52842
+ "epoch": 0.11180963328573375,
52843
+ "grad_norm": 6.28125,
52844
+ "learning_rate": 0.0004814841796033838,
52845
+ "loss": 14.2684,
52846
+ "step": 75480
52847
+ },
52848
+ {
52849
+ "epoch": 0.11182444643269795,
52850
+ "grad_norm": 13.375,
52851
+ "learning_rate": 0.00048148171013587997,
52852
+ "loss": 14.2827,
52853
+ "step": 75490
52854
+ },
52855
+ {
52856
+ "epoch": 0.11183925957966215,
52857
+ "grad_norm": 6.25,
52858
+ "learning_rate": 0.0004814792406683762,
52859
+ "loss": 14.3015,
52860
+ "step": 75500
52861
+ },
52862
+ {
52863
+ "epoch": 0.11185407272662634,
52864
+ "grad_norm": 6.0625,
52865
+ "learning_rate": 0.0004814767712008724,
52866
+ "loss": 14.2982,
52867
+ "step": 75510
52868
+ },
52869
+ {
52870
+ "epoch": 0.11186888587359053,
52871
+ "grad_norm": 6.65625,
52872
+ "learning_rate": 0.00048147430173336867,
52873
+ "loss": 14.3616,
52874
+ "step": 75520
52875
+ },
52876
+ {
52877
+ "epoch": 0.11188369902055473,
52878
+ "grad_norm": 5.6875,
52879
+ "learning_rate": 0.00048147183226586487,
52880
+ "loss": 14.2431,
52881
+ "step": 75530
52882
+ },
52883
+ {
52884
+ "epoch": 0.11189851216751892,
52885
+ "grad_norm": 5.8125,
52886
+ "learning_rate": 0.00048146936279836106,
52887
+ "loss": 14.2885,
52888
+ "step": 75540
52889
+ },
52890
+ {
52891
+ "epoch": 0.11191332531448311,
52892
+ "grad_norm": 5.625,
52893
+ "learning_rate": 0.0004814668933308573,
52894
+ "loss": 14.3599,
52895
+ "step": 75550
52896
+ },
52897
+ {
52898
+ "epoch": 0.11192813846144731,
52899
+ "grad_norm": 5.6875,
52900
+ "learning_rate": 0.0004814644238633535,
52901
+ "loss": 14.3303,
52902
+ "step": 75560
52903
+ },
52904
+ {
52905
+ "epoch": 0.1119429516084115,
52906
+ "grad_norm": 7.28125,
52907
+ "learning_rate": 0.0004814619543958497,
52908
+ "loss": 14.2985,
52909
+ "step": 75570
52910
+ },
52911
+ {
52912
+ "epoch": 0.1119577647553757,
52913
+ "grad_norm": 7.0,
52914
+ "learning_rate": 0.00048145948492834596,
52915
+ "loss": 14.2463,
52916
+ "step": 75580
52917
+ },
52918
+ {
52919
+ "epoch": 0.11197257790233989,
52920
+ "grad_norm": 6.59375,
52921
+ "learning_rate": 0.00048145701546084216,
52922
+ "loss": 14.3136,
52923
+ "step": 75590
52924
+ },
52925
+ {
52926
+ "epoch": 0.11198739104930408,
52927
+ "grad_norm": 7.375,
52928
+ "learning_rate": 0.00048145454599333835,
52929
+ "loss": 14.2133,
52930
+ "step": 75600
52931
+ },
52932
+ {
52933
+ "epoch": 0.11200220419626827,
52934
+ "grad_norm": 6.09375,
52935
+ "learning_rate": 0.0004814520765258346,
52936
+ "loss": 14.2702,
52937
+ "step": 75610
52938
+ },
52939
+ {
52940
+ "epoch": 0.11201701734323247,
52941
+ "grad_norm": 82.0,
52942
+ "learning_rate": 0.0004814496070583308,
52943
+ "loss": 14.297,
52944
+ "step": 75620
52945
+ },
52946
+ {
52947
+ "epoch": 0.11203183049019666,
52948
+ "grad_norm": 6.125,
52949
+ "learning_rate": 0.00048144713759082705,
52950
+ "loss": 14.3539,
52951
+ "step": 75630
52952
+ },
52953
+ {
52954
+ "epoch": 0.11204664363716085,
52955
+ "grad_norm": 6.5625,
52956
+ "learning_rate": 0.0004814446681233232,
52957
+ "loss": 14.3088,
52958
+ "step": 75640
52959
+ },
52960
+ {
52961
+ "epoch": 0.11206145678412505,
52962
+ "grad_norm": 6.3125,
52963
+ "learning_rate": 0.00048144219865581944,
52964
+ "loss": 14.3281,
52965
+ "step": 75650
52966
+ },
52967
+ {
52968
+ "epoch": 0.11207626993108924,
52969
+ "grad_norm": 7.0625,
52970
+ "learning_rate": 0.0004814397291883157,
52971
+ "loss": 14.2247,
52972
+ "step": 75660
52973
+ },
52974
+ {
52975
+ "epoch": 0.11209108307805343,
52976
+ "grad_norm": 29.375,
52977
+ "learning_rate": 0.0004814372597208119,
52978
+ "loss": 14.2418,
52979
+ "step": 75670
52980
+ },
52981
+ {
52982
+ "epoch": 0.11210589622501763,
52983
+ "grad_norm": 6.40625,
52984
+ "learning_rate": 0.0004814347902533081,
52985
+ "loss": 14.2366,
52986
+ "step": 75680
52987
+ },
52988
+ {
52989
+ "epoch": 0.11212070937198182,
52990
+ "grad_norm": 6.40625,
52991
+ "learning_rate": 0.00048143232078580434,
52992
+ "loss": 14.2976,
52993
+ "step": 75690
52994
+ },
52995
+ {
52996
+ "epoch": 0.11213552251894601,
52997
+ "grad_norm": 8.3125,
52998
+ "learning_rate": 0.00048142985131830054,
52999
+ "loss": 14.2993,
53000
+ "step": 75700
53001
+ },
53002
+ {
53003
+ "epoch": 0.1121503356659102,
53004
+ "grad_norm": 7.5,
53005
+ "learning_rate": 0.0004814273818507968,
53006
+ "loss": 14.3212,
53007
+ "step": 75710
53008
+ },
53009
+ {
53010
+ "epoch": 0.1121651488128744,
53011
+ "grad_norm": 6.21875,
53012
+ "learning_rate": 0.000481424912383293,
53013
+ "loss": 14.2308,
53014
+ "step": 75720
53015
+ },
53016
+ {
53017
+ "epoch": 0.11217996195983859,
53018
+ "grad_norm": 7.6875,
53019
+ "learning_rate": 0.0004814224429157892,
53020
+ "loss": 14.3475,
53021
+ "step": 75730
53022
+ },
53023
+ {
53024
+ "epoch": 0.11219477510680279,
53025
+ "grad_norm": 7.5625,
53026
+ "learning_rate": 0.00048141997344828543,
53027
+ "loss": 14.3303,
53028
+ "step": 75740
53029
+ },
53030
+ {
53031
+ "epoch": 0.11220958825376698,
53032
+ "grad_norm": 5.9375,
53033
+ "learning_rate": 0.0004814175039807816,
53034
+ "loss": 14.2898,
53035
+ "step": 75750
53036
+ },
53037
+ {
53038
+ "epoch": 0.11222440140073117,
53039
+ "grad_norm": 5.78125,
53040
+ "learning_rate": 0.0004814150345132778,
53041
+ "loss": 14.1977,
53042
+ "step": 75760
53043
+ },
53044
+ {
53045
+ "epoch": 0.11223921454769537,
53046
+ "grad_norm": 5.6875,
53047
+ "learning_rate": 0.0004814125650457741,
53048
+ "loss": 14.1474,
53049
+ "step": 75770
53050
+ },
53051
+ {
53052
+ "epoch": 0.11225402769465956,
53053
+ "grad_norm": 15.4375,
53054
+ "learning_rate": 0.0004814100955782703,
53055
+ "loss": 14.1729,
53056
+ "step": 75780
53057
+ },
53058
+ {
53059
+ "epoch": 0.11226884084162375,
53060
+ "grad_norm": 22.75,
53061
+ "learning_rate": 0.00048140762611076647,
53062
+ "loss": 14.2655,
53063
+ "step": 75790
53064
+ },
53065
+ {
53066
+ "epoch": 0.11228365398858794,
53067
+ "grad_norm": 6.34375,
53068
+ "learning_rate": 0.0004814051566432627,
53069
+ "loss": 14.3214,
53070
+ "step": 75800
53071
+ },
53072
+ {
53073
+ "epoch": 0.11229846713555215,
53074
+ "grad_norm": 6.0,
53075
+ "learning_rate": 0.0004814026871757589,
53076
+ "loss": 14.2248,
53077
+ "step": 75810
53078
+ },
53079
+ {
53080
+ "epoch": 0.11231328028251635,
53081
+ "grad_norm": 5.9375,
53082
+ "learning_rate": 0.00048140021770825517,
53083
+ "loss": 14.3127,
53084
+ "step": 75820
53085
+ },
53086
+ {
53087
+ "epoch": 0.11232809342948054,
53088
+ "grad_norm": 5.71875,
53089
+ "learning_rate": 0.00048139774824075137,
53090
+ "loss": 14.2397,
53091
+ "step": 75830
53092
+ },
53093
+ {
53094
+ "epoch": 0.11234290657644473,
53095
+ "grad_norm": 6.375,
53096
+ "learning_rate": 0.00048139527877324756,
53097
+ "loss": 14.197,
53098
+ "step": 75840
53099
+ },
53100
+ {
53101
+ "epoch": 0.11235771972340892,
53102
+ "grad_norm": 7.53125,
53103
+ "learning_rate": 0.0004813928093057438,
53104
+ "loss": 14.2269,
53105
+ "step": 75850
53106
+ },
53107
+ {
53108
+ "epoch": 0.11237253287037312,
53109
+ "grad_norm": 6.53125,
53110
+ "learning_rate": 0.00048139033983824,
53111
+ "loss": 14.2153,
53112
+ "step": 75860
53113
+ },
53114
+ {
53115
+ "epoch": 0.11238734601733731,
53116
+ "grad_norm": 5.78125,
53117
+ "learning_rate": 0.0004813878703707362,
53118
+ "loss": 14.2859,
53119
+ "step": 75870
53120
+ },
53121
+ {
53122
+ "epoch": 0.1124021591643015,
53123
+ "grad_norm": 6.09375,
53124
+ "learning_rate": 0.00048138540090323246,
53125
+ "loss": 14.2697,
53126
+ "step": 75880
53127
+ },
53128
+ {
53129
+ "epoch": 0.1124169723112657,
53130
+ "grad_norm": 5.9375,
53131
+ "learning_rate": 0.00048138293143572866,
53132
+ "loss": 14.2928,
53133
+ "step": 75890
53134
+ },
53135
+ {
53136
+ "epoch": 0.11243178545822989,
53137
+ "grad_norm": 11.375,
53138
+ "learning_rate": 0.0004813804619682249,
53139
+ "loss": 14.2692,
53140
+ "step": 75900
53141
+ },
53142
+ {
53143
+ "epoch": 0.11244659860519408,
53144
+ "grad_norm": 6.84375,
53145
+ "learning_rate": 0.0004813779925007211,
53146
+ "loss": 14.3065,
53147
+ "step": 75910
53148
+ },
53149
+ {
53150
+ "epoch": 0.11246141175215828,
53151
+ "grad_norm": 6.875,
53152
+ "learning_rate": 0.0004813755230332173,
53153
+ "loss": 14.2375,
53154
+ "step": 75920
53155
+ },
53156
+ {
53157
+ "epoch": 0.11247622489912247,
53158
+ "grad_norm": 6.75,
53159
+ "learning_rate": 0.00048137305356571355,
53160
+ "loss": 14.2619,
53161
+ "step": 75930
53162
+ },
53163
+ {
53164
+ "epoch": 0.11249103804608666,
53165
+ "grad_norm": 6.28125,
53166
+ "learning_rate": 0.0004813705840982097,
53167
+ "loss": 14.2412,
53168
+ "step": 75940
53169
+ },
53170
+ {
53171
+ "epoch": 0.11250585119305086,
53172
+ "grad_norm": 6.46875,
53173
+ "learning_rate": 0.00048136811463070595,
53174
+ "loss": 14.3294,
53175
+ "step": 75950
53176
+ },
53177
+ {
53178
+ "epoch": 0.11252066434001505,
53179
+ "grad_norm": 5.71875,
53180
+ "learning_rate": 0.0004813656451632022,
53181
+ "loss": 14.2541,
53182
+ "step": 75960
53183
+ },
53184
+ {
53185
+ "epoch": 0.11253547748697924,
53186
+ "grad_norm": 5.8125,
53187
+ "learning_rate": 0.0004813631756956984,
53188
+ "loss": 14.2392,
53189
+ "step": 75970
53190
+ },
53191
+ {
53192
+ "epoch": 0.11255029063394344,
53193
+ "grad_norm": 5.6875,
53194
+ "learning_rate": 0.0004813607062281946,
53195
+ "loss": 14.2,
53196
+ "step": 75980
53197
+ },
53198
+ {
53199
+ "epoch": 0.11256510378090763,
53200
+ "grad_norm": 5.78125,
53201
+ "learning_rate": 0.00048135823676069084,
53202
+ "loss": 14.2877,
53203
+ "step": 75990
53204
+ },
53205
+ {
53206
+ "epoch": 0.11257991692787182,
53207
+ "grad_norm": 6.09375,
53208
+ "learning_rate": 0.00048135576729318704,
53209
+ "loss": 14.2944,
53210
+ "step": 76000
53211
+ },
53212
+ {
53213
+ "epoch": 0.11259473007483602,
53214
+ "grad_norm": 7.34375,
53215
+ "learning_rate": 0.0004813532978256833,
53216
+ "loss": 14.3311,
53217
+ "step": 76010
53218
+ },
53219
+ {
53220
+ "epoch": 0.11260954322180021,
53221
+ "grad_norm": 9.25,
53222
+ "learning_rate": 0.0004813508283581795,
53223
+ "loss": 14.3216,
53224
+ "step": 76020
53225
+ },
53226
+ {
53227
+ "epoch": 0.1126243563687644,
53228
+ "grad_norm": 5.875,
53229
+ "learning_rate": 0.0004813483588906757,
53230
+ "loss": 14.3309,
53231
+ "step": 76030
53232
+ },
53233
+ {
53234
+ "epoch": 0.1126391695157286,
53235
+ "grad_norm": 6.1875,
53236
+ "learning_rate": 0.00048134588942317193,
53237
+ "loss": 14.3306,
53238
+ "step": 76040
53239
+ },
53240
+ {
53241
+ "epoch": 0.11265398266269279,
53242
+ "grad_norm": 6.25,
53243
+ "learning_rate": 0.00048134341995566813,
53244
+ "loss": 14.3626,
53245
+ "step": 76050
53246
+ },
53247
+ {
53248
+ "epoch": 0.11266879580965698,
53249
+ "grad_norm": 6.03125,
53250
+ "learning_rate": 0.0004813409504881643,
53251
+ "loss": 14.3068,
53252
+ "step": 76060
53253
+ },
53254
+ {
53255
+ "epoch": 0.11268360895662118,
53256
+ "grad_norm": 12.125,
53257
+ "learning_rate": 0.0004813384810206606,
53258
+ "loss": 14.2034,
53259
+ "step": 76070
53260
+ },
53261
+ {
53262
+ "epoch": 0.11269842210358537,
53263
+ "grad_norm": 6.3125,
53264
+ "learning_rate": 0.0004813360115531568,
53265
+ "loss": 14.3568,
53266
+ "step": 76080
53267
+ },
53268
+ {
53269
+ "epoch": 0.11271323525054956,
53270
+ "grad_norm": 36.75,
53271
+ "learning_rate": 0.00048133354208565297,
53272
+ "loss": 14.3241,
53273
+ "step": 76090
53274
+ },
53275
+ {
53276
+ "epoch": 0.11272804839751376,
53277
+ "grad_norm": 7.5,
53278
+ "learning_rate": 0.0004813310726181492,
53279
+ "loss": 14.2845,
53280
+ "step": 76100
53281
+ },
53282
+ {
53283
+ "epoch": 0.11274286154447795,
53284
+ "grad_norm": 6.34375,
53285
+ "learning_rate": 0.0004813286031506454,
53286
+ "loss": 14.3303,
53287
+ "step": 76110
53288
+ },
53289
+ {
53290
+ "epoch": 0.11275767469144214,
53291
+ "grad_norm": 7.28125,
53292
+ "learning_rate": 0.00048132613368314167,
53293
+ "loss": 14.2115,
53294
+ "step": 76120
53295
+ },
53296
+ {
53297
+ "epoch": 0.11277248783840635,
53298
+ "grad_norm": 7.78125,
53299
+ "learning_rate": 0.00048132366421563787,
53300
+ "loss": 14.1719,
53301
+ "step": 76130
53302
+ },
53303
+ {
53304
+ "epoch": 0.11278730098537054,
53305
+ "grad_norm": 6.0,
53306
+ "learning_rate": 0.00048132119474813406,
53307
+ "loss": 14.2165,
53308
+ "step": 76140
53309
+ },
53310
+ {
53311
+ "epoch": 0.11280211413233474,
53312
+ "grad_norm": 6.1875,
53313
+ "learning_rate": 0.0004813187252806303,
53314
+ "loss": 14.3187,
53315
+ "step": 76150
53316
+ },
53317
+ {
53318
+ "epoch": 0.11281692727929893,
53319
+ "grad_norm": 6.875,
53320
+ "learning_rate": 0.0004813162558131265,
53321
+ "loss": 14.2172,
53322
+ "step": 76160
53323
+ },
53324
+ {
53325
+ "epoch": 0.11283174042626312,
53326
+ "grad_norm": 5.9375,
53327
+ "learning_rate": 0.0004813137863456227,
53328
+ "loss": 14.301,
53329
+ "step": 76170
53330
+ },
53331
+ {
53332
+ "epoch": 0.11284655357322732,
53333
+ "grad_norm": 6.0625,
53334
+ "learning_rate": 0.00048131131687811896,
53335
+ "loss": 14.2381,
53336
+ "step": 76180
53337
+ },
53338
+ {
53339
+ "epoch": 0.11286136672019151,
53340
+ "grad_norm": 6.21875,
53341
+ "learning_rate": 0.00048130884741061516,
53342
+ "loss": 14.3047,
53343
+ "step": 76190
53344
+ },
53345
+ {
53346
+ "epoch": 0.1128761798671557,
53347
+ "grad_norm": 5.875,
53348
+ "learning_rate": 0.0004813063779431114,
53349
+ "loss": 14.2807,
53350
+ "step": 76200
53351
+ },
53352
+ {
53353
+ "epoch": 0.1128909930141199,
53354
+ "grad_norm": 7.4375,
53355
+ "learning_rate": 0.0004813039084756076,
53356
+ "loss": 14.2668,
53357
+ "step": 76210
53358
+ },
53359
+ {
53360
+ "epoch": 0.11290580616108409,
53361
+ "grad_norm": 6.4375,
53362
+ "learning_rate": 0.0004813014390081038,
53363
+ "loss": 14.2441,
53364
+ "step": 76220
53365
+ },
53366
+ {
53367
+ "epoch": 0.11292061930804828,
53368
+ "grad_norm": 9.625,
53369
+ "learning_rate": 0.00048129896954060005,
53370
+ "loss": 14.2955,
53371
+ "step": 76230
53372
+ },
53373
+ {
53374
+ "epoch": 0.11293543245501247,
53375
+ "grad_norm": 7.46875,
53376
+ "learning_rate": 0.00048129650007309625,
53377
+ "loss": 14.2896,
53378
+ "step": 76240
53379
+ },
53380
+ {
53381
+ "epoch": 0.11295024560197667,
53382
+ "grad_norm": 5.71875,
53383
+ "learning_rate": 0.00048129403060559245,
53384
+ "loss": 14.2628,
53385
+ "step": 76250
53386
+ },
53387
+ {
53388
+ "epoch": 0.11296505874894086,
53389
+ "grad_norm": 7.65625,
53390
+ "learning_rate": 0.0004812915611380887,
53391
+ "loss": 14.2738,
53392
+ "step": 76260
53393
+ },
53394
+ {
53395
+ "epoch": 0.11297987189590505,
53396
+ "grad_norm": 6.8125,
53397
+ "learning_rate": 0.0004812890916705849,
53398
+ "loss": 14.1957,
53399
+ "step": 76270
53400
+ },
53401
+ {
53402
+ "epoch": 0.11299468504286925,
53403
+ "grad_norm": 8.6875,
53404
+ "learning_rate": 0.0004812866222030811,
53405
+ "loss": 14.1696,
53406
+ "step": 76280
53407
+ },
53408
+ {
53409
+ "epoch": 0.11300949818983344,
53410
+ "grad_norm": 6.59375,
53411
+ "learning_rate": 0.00048128415273557734,
53412
+ "loss": 14.2516,
53413
+ "step": 76290
53414
+ },
53415
+ {
53416
+ "epoch": 0.11302431133679763,
53417
+ "grad_norm": 6.53125,
53418
+ "learning_rate": 0.00048128168326807354,
53419
+ "loss": 14.1725,
53420
+ "step": 76300
53421
+ },
53422
+ {
53423
+ "epoch": 0.11303912448376183,
53424
+ "grad_norm": 6.8125,
53425
+ "learning_rate": 0.0004812792138005698,
53426
+ "loss": 14.3749,
53427
+ "step": 76310
53428
+ },
53429
+ {
53430
+ "epoch": 0.11305393763072602,
53431
+ "grad_norm": 6.46875,
53432
+ "learning_rate": 0.000481276744333066,
53433
+ "loss": 14.2899,
53434
+ "step": 76320
53435
+ },
53436
+ {
53437
+ "epoch": 0.11306875077769021,
53438
+ "grad_norm": 6.53125,
53439
+ "learning_rate": 0.0004812742748655622,
53440
+ "loss": 14.2117,
53441
+ "step": 76330
53442
+ },
53443
+ {
53444
+ "epoch": 0.1130835639246544,
53445
+ "grad_norm": 7.5625,
53446
+ "learning_rate": 0.00048127180539805843,
53447
+ "loss": 14.269,
53448
+ "step": 76340
53449
+ },
53450
+ {
53451
+ "epoch": 0.1130983770716186,
53452
+ "grad_norm": 6.0,
53453
+ "learning_rate": 0.00048126933593055463,
53454
+ "loss": 14.2377,
53455
+ "step": 76350
53456
+ },
53457
+ {
53458
+ "epoch": 0.1131131902185828,
53459
+ "grad_norm": 6.8125,
53460
+ "learning_rate": 0.0004812668664630508,
53461
+ "loss": 14.2324,
53462
+ "step": 76360
53463
+ },
53464
+ {
53465
+ "epoch": 0.11312800336554699,
53466
+ "grad_norm": 6.53125,
53467
+ "learning_rate": 0.0004812643969955471,
53468
+ "loss": 14.1774,
53469
+ "step": 76370
53470
+ },
53471
+ {
53472
+ "epoch": 0.11314281651251118,
53473
+ "grad_norm": 6.59375,
53474
+ "learning_rate": 0.0004812619275280433,
53475
+ "loss": 14.3132,
53476
+ "step": 76380
53477
+ },
53478
+ {
53479
+ "epoch": 0.11315762965947537,
53480
+ "grad_norm": 6.0625,
53481
+ "learning_rate": 0.0004812594580605395,
53482
+ "loss": 14.2157,
53483
+ "step": 76390
53484
+ },
53485
+ {
53486
+ "epoch": 0.11317244280643957,
53487
+ "grad_norm": 10.0,
53488
+ "learning_rate": 0.0004812569885930357,
53489
+ "loss": 14.3112,
53490
+ "step": 76400
53491
+ },
53492
+ {
53493
+ "epoch": 0.11318725595340376,
53494
+ "grad_norm": 7.375,
53495
+ "learning_rate": 0.0004812545191255319,
53496
+ "loss": 14.2281,
53497
+ "step": 76410
53498
+ },
53499
+ {
53500
+ "epoch": 0.11320206910036795,
53501
+ "grad_norm": 6.8125,
53502
+ "learning_rate": 0.00048125204965802817,
53503
+ "loss": 14.2651,
53504
+ "step": 76420
53505
+ },
53506
+ {
53507
+ "epoch": 0.11321688224733215,
53508
+ "grad_norm": 6.0625,
53509
+ "learning_rate": 0.00048124958019052437,
53510
+ "loss": 14.249,
53511
+ "step": 76430
53512
+ },
53513
+ {
53514
+ "epoch": 0.11323169539429635,
53515
+ "grad_norm": 6.03125,
53516
+ "learning_rate": 0.00048124711072302056,
53517
+ "loss": 14.2616,
53518
+ "step": 76440
53519
+ },
53520
+ {
53521
+ "epoch": 0.11324650854126055,
53522
+ "grad_norm": 6.34375,
53523
+ "learning_rate": 0.0004812446412555168,
53524
+ "loss": 14.3167,
53525
+ "step": 76450
53526
+ },
53527
+ {
53528
+ "epoch": 0.11326132168822474,
53529
+ "grad_norm": 6.125,
53530
+ "learning_rate": 0.000481242171788013,
53531
+ "loss": 14.2566,
53532
+ "step": 76460
53533
+ },
53534
+ {
53535
+ "epoch": 0.11327613483518893,
53536
+ "grad_norm": 5.59375,
53537
+ "learning_rate": 0.0004812397023205092,
53538
+ "loss": 14.2231,
53539
+ "step": 76470
53540
+ },
53541
+ {
53542
+ "epoch": 0.11329094798215313,
53543
+ "grad_norm": 6.71875,
53544
+ "learning_rate": 0.00048123723285300546,
53545
+ "loss": 14.2224,
53546
+ "step": 76480
53547
+ },
53548
+ {
53549
+ "epoch": 0.11330576112911732,
53550
+ "grad_norm": 6.25,
53551
+ "learning_rate": 0.00048123476338550166,
53552
+ "loss": 14.2313,
53553
+ "step": 76490
53554
+ },
53555
+ {
53556
+ "epoch": 0.11332057427608151,
53557
+ "grad_norm": 6.25,
53558
+ "learning_rate": 0.0004812322939179979,
53559
+ "loss": 14.3768,
53560
+ "step": 76500
53561
+ },
53562
+ {
53563
+ "epoch": 0.1133353874230457,
53564
+ "grad_norm": 5.875,
53565
+ "learning_rate": 0.0004812298244504941,
53566
+ "loss": 14.2302,
53567
+ "step": 76510
53568
+ },
53569
+ {
53570
+ "epoch": 0.1133502005700099,
53571
+ "grad_norm": 6.375,
53572
+ "learning_rate": 0.0004812273549829903,
53573
+ "loss": 14.2672,
53574
+ "step": 76520
53575
+ },
53576
+ {
53577
+ "epoch": 0.11336501371697409,
53578
+ "grad_norm": 6.40625,
53579
+ "learning_rate": 0.00048122488551548655,
53580
+ "loss": 14.2666,
53581
+ "step": 76530
53582
+ },
53583
+ {
53584
+ "epoch": 0.11337982686393829,
53585
+ "grad_norm": 6.71875,
53586
+ "learning_rate": 0.00048122241604798275,
53587
+ "loss": 14.2527,
53588
+ "step": 76540
53589
+ },
53590
+ {
53591
+ "epoch": 0.11339464001090248,
53592
+ "grad_norm": 8.125,
53593
+ "learning_rate": 0.00048121994658047895,
53594
+ "loss": 14.2752,
53595
+ "step": 76550
53596
+ },
53597
+ {
53598
+ "epoch": 0.11340945315786667,
53599
+ "grad_norm": 42.5,
53600
+ "learning_rate": 0.0004812174771129752,
53601
+ "loss": 14.2521,
53602
+ "step": 76560
53603
+ },
53604
+ {
53605
+ "epoch": 0.11342426630483086,
53606
+ "grad_norm": 5.90625,
53607
+ "learning_rate": 0.0004812150076454714,
53608
+ "loss": 14.3064,
53609
+ "step": 76570
53610
+ },
53611
+ {
53612
+ "epoch": 0.11343907945179506,
53613
+ "grad_norm": 6.53125,
53614
+ "learning_rate": 0.00048121253817796764,
53615
+ "loss": 14.2165,
53616
+ "step": 76580
53617
+ },
53618
+ {
53619
+ "epoch": 0.11345389259875925,
53620
+ "grad_norm": 12.0,
53621
+ "learning_rate": 0.00048121006871046384,
53622
+ "loss": 14.2153,
53623
+ "step": 76590
53624
+ },
53625
+ {
53626
+ "epoch": 0.11346870574572344,
53627
+ "grad_norm": 5.96875,
53628
+ "learning_rate": 0.00048120759924296004,
53629
+ "loss": 14.337,
53630
+ "step": 76600
53631
+ },
53632
+ {
53633
+ "epoch": 0.11348351889268764,
53634
+ "grad_norm": 6.21875,
53635
+ "learning_rate": 0.0004812051297754563,
53636
+ "loss": 14.1815,
53637
+ "step": 76610
53638
+ },
53639
+ {
53640
+ "epoch": 0.11349833203965183,
53641
+ "grad_norm": 6.78125,
53642
+ "learning_rate": 0.0004812026603079525,
53643
+ "loss": 14.2926,
53644
+ "step": 76620
53645
+ },
53646
+ {
53647
+ "epoch": 0.11351314518661602,
53648
+ "grad_norm": 5.84375,
53649
+ "learning_rate": 0.0004812001908404487,
53650
+ "loss": 14.2356,
53651
+ "step": 76630
53652
+ },
53653
+ {
53654
+ "epoch": 0.11352795833358022,
53655
+ "grad_norm": 7.71875,
53656
+ "learning_rate": 0.00048119772137294493,
53657
+ "loss": 14.2212,
53658
+ "step": 76640
53659
+ },
53660
+ {
53661
+ "epoch": 0.11354277148054441,
53662
+ "grad_norm": 6.65625,
53663
+ "learning_rate": 0.00048119525190544113,
53664
+ "loss": 14.2676,
53665
+ "step": 76650
53666
+ },
53667
+ {
53668
+ "epoch": 0.1135575846275086,
53669
+ "grad_norm": 6.40625,
53670
+ "learning_rate": 0.00048119278243793733,
53671
+ "loss": 14.3445,
53672
+ "step": 76660
53673
+ },
53674
+ {
53675
+ "epoch": 0.1135723977744728,
53676
+ "grad_norm": 6.625,
53677
+ "learning_rate": 0.0004811903129704336,
53678
+ "loss": 14.2609,
53679
+ "step": 76670
53680
+ },
53681
+ {
53682
+ "epoch": 0.11358721092143699,
53683
+ "grad_norm": 5.78125,
53684
+ "learning_rate": 0.0004811878435029298,
53685
+ "loss": 14.229,
53686
+ "step": 76680
53687
+ },
53688
+ {
53689
+ "epoch": 0.11360202406840118,
53690
+ "grad_norm": 6.09375,
53691
+ "learning_rate": 0.000481185374035426,
53692
+ "loss": 14.2251,
53693
+ "step": 76690
53694
+ },
53695
+ {
53696
+ "epoch": 0.11361683721536538,
53697
+ "grad_norm": 6.5625,
53698
+ "learning_rate": 0.0004811829045679222,
53699
+ "loss": 14.2172,
53700
+ "step": 76700
53701
+ },
53702
+ {
53703
+ "epoch": 0.11363165036232957,
53704
+ "grad_norm": 5.6875,
53705
+ "learning_rate": 0.0004811804351004184,
53706
+ "loss": 14.2995,
53707
+ "step": 76710
53708
+ },
53709
+ {
53710
+ "epoch": 0.11364646350929376,
53711
+ "grad_norm": 6.34375,
53712
+ "learning_rate": 0.00048117796563291467,
53713
+ "loss": 14.2622,
53714
+ "step": 76720
53715
+ },
53716
+ {
53717
+ "epoch": 0.11366127665625796,
53718
+ "grad_norm": 6.78125,
53719
+ "learning_rate": 0.0004811754961654109,
53720
+ "loss": 14.1751,
53721
+ "step": 76730
53722
+ },
53723
+ {
53724
+ "epoch": 0.11367608980322215,
53725
+ "grad_norm": 6.0625,
53726
+ "learning_rate": 0.00048117302669790706,
53727
+ "loss": 14.2192,
53728
+ "step": 76740
53729
+ },
53730
+ {
53731
+ "epoch": 0.11369090295018634,
53732
+ "grad_norm": 6.46875,
53733
+ "learning_rate": 0.0004811705572304033,
53734
+ "loss": 14.3389,
53735
+ "step": 76750
53736
+ },
53737
+ {
53738
+ "epoch": 0.11370571609715055,
53739
+ "grad_norm": 6.625,
53740
+ "learning_rate": 0.0004811680877628995,
53741
+ "loss": 14.2331,
53742
+ "step": 76760
53743
+ },
53744
+ {
53745
+ "epoch": 0.11372052924411474,
53746
+ "grad_norm": 6.6875,
53747
+ "learning_rate": 0.0004811656182953957,
53748
+ "loss": 14.1758,
53749
+ "step": 76770
53750
+ },
53751
+ {
53752
+ "epoch": 0.11373534239107894,
53753
+ "grad_norm": 5.4375,
53754
+ "learning_rate": 0.00048116314882789196,
53755
+ "loss": 14.2328,
53756
+ "step": 76780
53757
+ },
53758
+ {
53759
+ "epoch": 0.11375015553804313,
53760
+ "grad_norm": 9.25,
53761
+ "learning_rate": 0.00048116067936038816,
53762
+ "loss": 14.2768,
53763
+ "step": 76790
53764
+ },
53765
+ {
53766
+ "epoch": 0.11376496868500732,
53767
+ "grad_norm": 6.1875,
53768
+ "learning_rate": 0.0004811582098928844,
53769
+ "loss": 14.3041,
53770
+ "step": 76800
53771
+ },
53772
+ {
53773
+ "epoch": 0.11377978183197152,
53774
+ "grad_norm": 7.5,
53775
+ "learning_rate": 0.0004811557404253806,
53776
+ "loss": 14.2251,
53777
+ "step": 76810
53778
+ },
53779
+ {
53780
+ "epoch": 0.11379459497893571,
53781
+ "grad_norm": 6.21875,
53782
+ "learning_rate": 0.0004811532709578768,
53783
+ "loss": 14.2144,
53784
+ "step": 76820
53785
+ },
53786
+ {
53787
+ "epoch": 0.1138094081258999,
53788
+ "grad_norm": 6.5,
53789
+ "learning_rate": 0.00048115080149037305,
53790
+ "loss": 14.1908,
53791
+ "step": 76830
53792
+ },
53793
+ {
53794
+ "epoch": 0.1138242212728641,
53795
+ "grad_norm": 7.875,
53796
+ "learning_rate": 0.00048114833202286925,
53797
+ "loss": 14.2018,
53798
+ "step": 76840
53799
+ },
53800
+ {
53801
+ "epoch": 0.11383903441982829,
53802
+ "grad_norm": 5.875,
53803
+ "learning_rate": 0.00048114586255536545,
53804
+ "loss": 14.2807,
53805
+ "step": 76850
53806
+ },
53807
+ {
53808
+ "epoch": 0.11385384756679248,
53809
+ "grad_norm": 6.71875,
53810
+ "learning_rate": 0.0004811433930878617,
53811
+ "loss": 14.2364,
53812
+ "step": 76860
53813
+ },
53814
+ {
53815
+ "epoch": 0.11386866071375668,
53816
+ "grad_norm": 6.25,
53817
+ "learning_rate": 0.0004811409236203579,
53818
+ "loss": 14.1742,
53819
+ "step": 76870
53820
+ },
53821
+ {
53822
+ "epoch": 0.11388347386072087,
53823
+ "grad_norm": 6.6875,
53824
+ "learning_rate": 0.00048113845415285414,
53825
+ "loss": 14.3333,
53826
+ "step": 76880
53827
+ },
53828
+ {
53829
+ "epoch": 0.11389828700768506,
53830
+ "grad_norm": 6.09375,
53831
+ "learning_rate": 0.00048113598468535034,
53832
+ "loss": 14.2396,
53833
+ "step": 76890
53834
+ },
53835
+ {
53836
+ "epoch": 0.11391310015464925,
53837
+ "grad_norm": 5.625,
53838
+ "learning_rate": 0.00048113351521784654,
53839
+ "loss": 14.2659,
53840
+ "step": 76900
53841
+ },
53842
+ {
53843
+ "epoch": 0.11392791330161345,
53844
+ "grad_norm": 13.3125,
53845
+ "learning_rate": 0.0004811310457503428,
53846
+ "loss": 14.1783,
53847
+ "step": 76910
53848
+ },
53849
+ {
53850
+ "epoch": 0.11394272644857764,
53851
+ "grad_norm": 6.09375,
53852
+ "learning_rate": 0.00048112857628283904,
53853
+ "loss": 14.3416,
53854
+ "step": 76920
53855
+ },
53856
+ {
53857
+ "epoch": 0.11395753959554183,
53858
+ "grad_norm": 11.0,
53859
+ "learning_rate": 0.0004811261068153352,
53860
+ "loss": 14.2827,
53861
+ "step": 76930
53862
+ },
53863
+ {
53864
+ "epoch": 0.11397235274250603,
53865
+ "grad_norm": 9.1875,
53866
+ "learning_rate": 0.00048112363734783143,
53867
+ "loss": 14.3132,
53868
+ "step": 76940
53869
+ },
53870
+ {
53871
+ "epoch": 0.11398716588947022,
53872
+ "grad_norm": 7.96875,
53873
+ "learning_rate": 0.00048112116788032763,
53874
+ "loss": 14.2937,
53875
+ "step": 76950
53876
+ },
53877
+ {
53878
+ "epoch": 0.11400197903643441,
53879
+ "grad_norm": 8.3125,
53880
+ "learning_rate": 0.00048111869841282383,
53881
+ "loss": 14.2692,
53882
+ "step": 76960
53883
+ },
53884
+ {
53885
+ "epoch": 0.11401679218339861,
53886
+ "grad_norm": 6.40625,
53887
+ "learning_rate": 0.0004811162289453201,
53888
+ "loss": 14.2134,
53889
+ "step": 76970
53890
+ },
53891
+ {
53892
+ "epoch": 0.1140316053303628,
53893
+ "grad_norm": 6.71875,
53894
+ "learning_rate": 0.0004811137594778163,
53895
+ "loss": 14.1841,
53896
+ "step": 76980
53897
+ },
53898
+ {
53899
+ "epoch": 0.114046418477327,
53900
+ "grad_norm": 7.78125,
53901
+ "learning_rate": 0.0004811112900103125,
53902
+ "loss": 14.1835,
53903
+ "step": 76990
53904
+ },
53905
+ {
53906
+ "epoch": 0.11406123162429119,
53907
+ "grad_norm": 7.71875,
53908
+ "learning_rate": 0.0004811088205428087,
53909
+ "loss": 14.2408,
53910
+ "step": 77000
53911
  }
53912
  ],
53913
  "logging_steps": 10,
 
53927
  "attributes": {}
53928
  }
53929
  },
53930
+ "total_flos": 1.664016501607781e+20,
53931
  "train_batch_size": 48,
53932
  "trial_name": null,
53933
  "trial_params": null
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50a9561c05504384f8a5358ec95beca3b2814433f472420dc733ce1dc363e842
3
  size 1032262338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c5e718e5fb652f04bf12e08e8623b730b6736e03622227a4c7a774463a05f7
3
  size 1032262338
runs/Sep21_22-35-48_nid006862/events.out.tfevents.1758486957.nid006862.27495.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ad8b8d13e4fdf23f8aaa7dd19ecd65b8076254f307ffc7f4923ad34e4c5c050
3
- size 91337
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd0b5224a81f242c5efe6246836ef4d749eb6af55b63432892b621256dfe649
3
+ size 198837