DylanJHJ commited on
Commit
f64ab17
·
1 Parent(s): f842e8d

move the flatten on to the separate one

Browse files
Files changed (36) hide show
  1. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/config.json +0 -45
  2. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/model.safetensors +0 -3
  3. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/optimizer.pt +0 -3
  4. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/rng_state_0.pth +0 -3
  5. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/rng_state_1.pth +0 -3
  6. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/rng_state_2.pth +0 -3
  7. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/rng_state_3.pth +0 -3
  8. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/scheduler.pt +0 -3
  9. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/trainer_state.json +0 -0
  10. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/training_args.bin +0 -3
  11. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-15000/removed_as_it_was_not_better_than10k +0 -0
  12. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-20000/removed_as_it_was_not_better_than10k +0 -0
  13. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/config.json +0 -45
  14. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/model.safetensors +0 -3
  15. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/optimizer.pt +0 -3
  16. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/rng_state_0.pth +0 -3
  17. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/rng_state_1.pth +0 -3
  18. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/rng_state_2.pth +0 -3
  19. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/rng_state_3.pth +0 -3
  20. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/scheduler.pt +0 -3
  21. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/trainer_state.json +0 -3859
  22. modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/training_args.bin +0 -3
  23. modernbert-crux-researchy-flatten.b64_n512.1e-4/config.json +0 -45
  24. modernbert-crux-researchy-flatten.b64_n512.1e-4/model.safetensors +0 -3
  25. modernbert-crux-researchy-flatten.b64_n512.1e-4/optimizer.pt +0 -3
  26. modernbert-crux-researchy-flatten.b64_n512.1e-4/rng_state_0.pth +0 -3
  27. modernbert-crux-researchy-flatten.b64_n512.1e-4/rng_state_1.pth +0 -3
  28. modernbert-crux-researchy-flatten.b64_n512.1e-4/rng_state_2.pth +0 -3
  29. modernbert-crux-researchy-flatten.b64_n512.1e-4/rng_state_3.pth +0 -3
  30. modernbert-crux-researchy-flatten.b64_n512.1e-4/runs/Dec09_23-49-04_nid005106/events.out.tfevents.1765316992.nid005106.127904.0 +0 -3
  31. modernbert-crux-researchy-flatten.b64_n512.1e-4/scheduler.pt +0 -3
  32. modernbert-crux-researchy-flatten.b64_n512.1e-4/special_tokens_map.json +0 -37
  33. modernbert-crux-researchy-flatten.b64_n512.1e-4/tokenizer.json +0 -0
  34. modernbert-crux-researchy-flatten.b64_n512.1e-4/tokenizer_config.json +0 -945
  35. modernbert-crux-researchy-flatten.b64_n512.1e-4/trainer_state.json +0 -0
  36. modernbert-crux-researchy-flatten.b64_n512.1e-4/training_args.bin +0 -3
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/config.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "architectures": [
3
- "ModernBertModel"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 50281,
8
- "classifier_activation": "gelu",
9
- "classifier_bias": false,
10
- "classifier_dropout": 0.0,
11
- "classifier_pooling": "mean",
12
- "cls_token_id": 50281,
13
- "decoder_bias": true,
14
- "deterministic_flash_attn": false,
15
- "embedding_dropout": 0.0,
16
- "eos_token_id": 50282,
17
- "global_attn_every_n_layers": 3,
18
- "global_rope_theta": 160000.0,
19
- "gradient_checkpointing": false,
20
- "hidden_activation": "gelu",
21
- "hidden_size": 768,
22
- "initializer_cutoff_factor": 2.0,
23
- "initializer_range": 0.02,
24
- "intermediate_size": 1152,
25
- "layer_norm_eps": 1e-05,
26
- "local_attention": 128,
27
- "local_rope_theta": 10000.0,
28
- "max_position_embeddings": 8192,
29
- "mlp_bias": false,
30
- "mlp_dropout": 0.0,
31
- "model_type": "modernbert",
32
- "norm_bias": false,
33
- "norm_eps": 1e-05,
34
- "num_attention_heads": 12,
35
- "num_hidden_layers": 22,
36
- "pad_token_id": 50283,
37
- "position_embedding_type": "absolute",
38
- "repad_logits_with_grad": false,
39
- "sep_token_id": 50282,
40
- "sparse_pred_ignore_index": -100,
41
- "sparse_prediction": false,
42
- "torch_dtype": "bfloat16",
43
- "transformers_version": "4.53.0",
44
- "vocab_size": 50368
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2442b3cc24983ddcf31753c8fa56ab2fad6afb650c632ed25b776997797ed613
3
- size 298041696
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b67a1ed701ca39e8801c50d2e045472cac648267a09099521a862e0bb963eef
3
- size 596170443
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:18bb6b6e7da6250d22c25b95c64287be4aea598d9d97ef67b0fd69b9be869ed7
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cff16289615ba210b601be2162794d1949cb1d62132099a4cf62330c43649a5
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6caa3980c911491b74ec2e96e48a78cd7c3365dd32116c61642a4b6839a2da1
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e93d0d6464a92d227e9235c134b2224cf28ea45ba375cf82e6949c632e2b0d5
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1dc55d852ef70868b0961034622da0948eee9b7cd3b727c465e6777f6956438
3
- size 1465
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-10000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:205393de77a05f484db2377ef40c55556ef0de4b97d04fcaeb594ddb2a92de2c
3
- size 6033
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-15000/removed_as_it_was_not_better_than10k DELETED
File without changes
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-20000/removed_as_it_was_not_better_than10k DELETED
File without changes
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/config.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "architectures": [
3
- "ModernBertModel"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 50281,
8
- "classifier_activation": "gelu",
9
- "classifier_bias": false,
10
- "classifier_dropout": 0.0,
11
- "classifier_pooling": "mean",
12
- "cls_token_id": 50281,
13
- "decoder_bias": true,
14
- "deterministic_flash_attn": false,
15
- "embedding_dropout": 0.0,
16
- "eos_token_id": 50282,
17
- "global_attn_every_n_layers": 3,
18
- "global_rope_theta": 160000.0,
19
- "gradient_checkpointing": false,
20
- "hidden_activation": "gelu",
21
- "hidden_size": 768,
22
- "initializer_cutoff_factor": 2.0,
23
- "initializer_range": 0.02,
24
- "intermediate_size": 1152,
25
- "layer_norm_eps": 1e-05,
26
- "local_attention": 128,
27
- "local_rope_theta": 10000.0,
28
- "max_position_embeddings": 8192,
29
- "mlp_bias": false,
30
- "mlp_dropout": 0.0,
31
- "model_type": "modernbert",
32
- "norm_bias": false,
33
- "norm_eps": 1e-05,
34
- "num_attention_heads": 12,
35
- "num_hidden_layers": 22,
36
- "pad_token_id": 50283,
37
- "position_embedding_type": "absolute",
38
- "repad_logits_with_grad": false,
39
- "sep_token_id": 50282,
40
- "sparse_pred_ignore_index": -100,
41
- "sparse_prediction": false,
42
- "torch_dtype": "bfloat16",
43
- "transformers_version": "4.53.0",
44
- "vocab_size": 50368
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f549d22a6a470b7569e8227f818199fa8caca8f7fa42a87714eed88c40998ffd
3
- size 298041696
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b04a684bd4e9cc9a662d38fa7af49dfea5a10a1184ec2a2b5771603dd529776a
3
- size 596170443
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3044a568f2c48f55afab6e63cf0c046d3586784e77e39b1af825abecfb2cdba8
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b50176e6a2e04d27f26849df53fc28c50b0357c3f1bc26ca6b6bb8848991144
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbda571d0d08add9abed7e3b3b11bb38b8d472a92fd8409d00660f44b646db10
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5ce74a6352b774e1ca5b1ca2e8b3e684a2cc29987576c968c710783e2b33305
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b23fa07612480bb6aa3030f51e1c016c1312deccd8f5d909640a64afcadcf8ce
3
- size 1465
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/trainer_state.json DELETED
@@ -1,3859 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.6019744762822057,
6
- "eval_steps": 1000.0,
7
- "global_step": 5000,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0,
14
- "eval/nano_beir.arguana": 0.5201586889046041,
15
- "step": 0
16
- },
17
- {
18
- "epoch": 0,
19
- "eval/nano_beir.climate_fever": 0.23997409265084552,
20
- "step": 0
21
- },
22
- {
23
- "epoch": 0,
24
- "eval/nano_beir.dbpedia_entity": 0.34286887314902237,
25
- "step": 0
26
- },
27
- {
28
- "epoch": 0,
29
- "eval/nano_beir.fever": 0.6213496755517833,
30
- "step": 0
31
- },
32
- {
33
- "epoch": 0,
34
- "eval/nano_beir.fiqa": 0.4542903465876373,
35
- "step": 0
36
- },
37
- {
38
- "epoch": 0,
39
- "eval/nano_beir.hotpotqa": 0.6560051657630788,
40
- "step": 0
41
- },
42
- {
43
- "epoch": 0,
44
- "eval/nano_beir.nfcorpus": 0.3328835143785305,
45
- "step": 0
46
- },
47
- {
48
- "epoch": 0,
49
- "eval/nano_beir.nq": 0.4570725655218753,
50
- "step": 0
51
- },
52
- {
53
- "epoch": 0,
54
- "eval/nano_beir.quora": 0.832098944676056,
55
- "step": 0
56
- },
57
- {
58
- "epoch": 0,
59
- "eval/nano_beir.scidocs": 0.25908236715595256,
60
- "step": 0
61
- },
62
- {
63
- "epoch": 0,
64
- "eval/nano_beir.scifact": 0.7391066781087818,
65
- "step": 0
66
- },
67
- {
68
- "epoch": 0,
69
- "eval/nano_beir.webis_touche2020": 0.30431141846717047,
70
- "step": 0
71
- },
72
- {
73
- "epoch": 0,
74
- "eval/avg": 0.4799335275762782,
75
- "step": 0
76
- },
77
- {
78
- "epoch": 0.0012039489525644113,
79
- "grad_norm": 9.375,
80
- "learning_rate": 4.5e-07,
81
- "loss": 1.2124,
82
- "step": 10
83
- },
84
- {
85
- "epoch": 0.0024078979051288226,
86
- "grad_norm": 11.625,
87
- "learning_rate": 9.5e-07,
88
- "loss": 1.2431,
89
- "step": 20
90
- },
91
- {
92
- "epoch": 0.003611846857693234,
93
- "grad_norm": 12.9375,
94
- "learning_rate": 1.45e-06,
95
- "loss": 1.2449,
96
- "step": 30
97
- },
98
- {
99
- "epoch": 0.004815795810257645,
100
- "grad_norm": 10.25,
101
- "learning_rate": 1.95e-06,
102
- "loss": 1.3433,
103
- "step": 40
104
- },
105
- {
106
- "epoch": 0.006019744762822056,
107
- "grad_norm": 11.375,
108
- "learning_rate": 2.4500000000000003e-06,
109
- "loss": 1.3456,
110
- "step": 50
111
- },
112
- {
113
- "epoch": 0.007223693715386468,
114
- "grad_norm": 12.125,
115
- "learning_rate": 2.95e-06,
116
- "loss": 1.3311,
117
- "step": 60
118
- },
119
- {
120
- "epoch": 0.00842764266795088,
121
- "grad_norm": 10.75,
122
- "learning_rate": 3.4500000000000004e-06,
123
- "loss": 1.2169,
124
- "step": 70
125
- },
126
- {
127
- "epoch": 0.00963159162051529,
128
- "grad_norm": 19.125,
129
- "learning_rate": 3.95e-06,
130
- "loss": 1.4157,
131
- "step": 80
132
- },
133
- {
134
- "epoch": 0.010835540573079701,
135
- "grad_norm": 12.1875,
136
- "learning_rate": 4.45e-06,
137
- "loss": 1.1054,
138
- "step": 90
139
- },
140
- {
141
- "epoch": 0.012039489525644112,
142
- "grad_norm": 9.0,
143
- "learning_rate": 4.950000000000001e-06,
144
- "loss": 1.1525,
145
- "step": 100
146
- },
147
- {
148
- "epoch": 0.013243438478208525,
149
- "grad_norm": 9.625,
150
- "learning_rate": 5.45e-06,
151
- "loss": 1.2883,
152
- "step": 110
153
- },
154
- {
155
- "epoch": 0.014447387430772935,
156
- "grad_norm": 11.25,
157
- "learning_rate": 5.95e-06,
158
- "loss": 1.2931,
159
- "step": 120
160
- },
161
- {
162
- "epoch": 0.015651336383337346,
163
- "grad_norm": 11.4375,
164
- "learning_rate": 6.45e-06,
165
- "loss": 1.3545,
166
- "step": 130
167
- },
168
- {
169
- "epoch": 0.01685528533590176,
170
- "grad_norm": 15.1875,
171
- "learning_rate": 6.950000000000001e-06,
172
- "loss": 1.3885,
173
- "step": 140
174
- },
175
- {
176
- "epoch": 0.018059234288466168,
177
- "grad_norm": 10.9375,
178
- "learning_rate": 7.45e-06,
179
- "loss": 1.1764,
180
- "step": 150
181
- },
182
- {
183
- "epoch": 0.01926318324103058,
184
- "grad_norm": 12.0625,
185
- "learning_rate": 7.95e-06,
186
- "loss": 1.3003,
187
- "step": 160
188
- },
189
- {
190
- "epoch": 0.020467132193594993,
191
- "grad_norm": 12.3125,
192
- "learning_rate": 8.45e-06,
193
- "loss": 1.5038,
194
- "step": 170
195
- },
196
- {
197
- "epoch": 0.021671081146159402,
198
- "grad_norm": 10.9375,
199
- "learning_rate": 8.95e-06,
200
- "loss": 1.1602,
201
- "step": 180
202
- },
203
- {
204
- "epoch": 0.022875030098723815,
205
- "grad_norm": 10.5625,
206
- "learning_rate": 9.450000000000001e-06,
207
- "loss": 1.1491,
208
- "step": 190
209
- },
210
- {
211
- "epoch": 0.024078979051288224,
212
- "grad_norm": 11.375,
213
- "learning_rate": 9.950000000000001e-06,
214
- "loss": 1.3445,
215
- "step": 200
216
- },
217
- {
218
- "epoch": 0.025282928003852637,
219
- "grad_norm": 9.125,
220
- "learning_rate": 1.045e-05,
221
- "loss": 1.2298,
222
- "step": 210
223
- },
224
- {
225
- "epoch": 0.02648687695641705,
226
- "grad_norm": 10.3125,
227
- "learning_rate": 1.095e-05,
228
- "loss": 1.2853,
229
- "step": 220
230
- },
231
- {
232
- "epoch": 0.02769082590898146,
233
- "grad_norm": 9.8125,
234
- "learning_rate": 1.145e-05,
235
- "loss": 1.2399,
236
- "step": 230
237
- },
238
- {
239
- "epoch": 0.02889477486154587,
240
- "grad_norm": 8.5625,
241
- "learning_rate": 1.195e-05,
242
- "loss": 1.281,
243
- "step": 240
244
- },
245
- {
246
- "epoch": 0.03009872381411028,
247
- "grad_norm": 12.5,
248
- "learning_rate": 1.2450000000000001e-05,
249
- "loss": 1.1571,
250
- "step": 250
251
- },
252
- {
253
- "epoch": 0.03130267276667469,
254
- "grad_norm": 11.0625,
255
- "learning_rate": 1.2950000000000001e-05,
256
- "loss": 1.2818,
257
- "step": 260
258
- },
259
- {
260
- "epoch": 0.032506621719239105,
261
- "grad_norm": 10.0,
262
- "learning_rate": 1.3450000000000002e-05,
263
- "loss": 1.0802,
264
- "step": 270
265
- },
266
- {
267
- "epoch": 0.03371057067180352,
268
- "grad_norm": 15.9375,
269
- "learning_rate": 1.3950000000000002e-05,
270
- "loss": 1.1303,
271
- "step": 280
272
- },
273
- {
274
- "epoch": 0.03491451962436792,
275
- "grad_norm": 11.5625,
276
- "learning_rate": 1.4449999999999999e-05,
277
- "loss": 1.086,
278
- "step": 290
279
- },
280
- {
281
- "epoch": 0.036118468576932336,
282
- "grad_norm": 11.75,
283
- "learning_rate": 1.4950000000000001e-05,
284
- "loss": 1.1996,
285
- "step": 300
286
- },
287
- {
288
- "epoch": 0.03732241752949675,
289
- "grad_norm": 7.5625,
290
- "learning_rate": 1.545e-05,
291
- "loss": 1.0982,
292
- "step": 310
293
- },
294
- {
295
- "epoch": 0.03852636648206116,
296
- "grad_norm": 9.5,
297
- "learning_rate": 1.595e-05,
298
- "loss": 1.0364,
299
- "step": 320
300
- },
301
- {
302
- "epoch": 0.039730315434625574,
303
- "grad_norm": 10.75,
304
- "learning_rate": 1.645e-05,
305
- "loss": 1.0967,
306
- "step": 330
307
- },
308
- {
309
- "epoch": 0.040934264387189986,
310
- "grad_norm": 9.3125,
311
- "learning_rate": 1.6950000000000002e-05,
312
- "loss": 1.1497,
313
- "step": 340
314
- },
315
- {
316
- "epoch": 0.04213821333975439,
317
- "grad_norm": 9.0625,
318
- "learning_rate": 1.745e-05,
319
- "loss": 1.1596,
320
- "step": 350
321
- },
322
- {
323
- "epoch": 0.043342162292318805,
324
- "grad_norm": 9.3125,
325
- "learning_rate": 1.795e-05,
326
- "loss": 1.0344,
327
- "step": 360
328
- },
329
- {
330
- "epoch": 0.04454611124488322,
331
- "grad_norm": 10.625,
332
- "learning_rate": 1.845e-05,
333
- "loss": 1.186,
334
- "step": 370
335
- },
336
- {
337
- "epoch": 0.04575006019744763,
338
- "grad_norm": 9.9375,
339
- "learning_rate": 1.895e-05,
340
- "loss": 0.9519,
341
- "step": 380
342
- },
343
- {
344
- "epoch": 0.04695400915001204,
345
- "grad_norm": 10.125,
346
- "learning_rate": 1.9450000000000002e-05,
347
- "loss": 1.1593,
348
- "step": 390
349
- },
350
- {
351
- "epoch": 0.04815795810257645,
352
- "grad_norm": 10.0,
353
- "learning_rate": 1.995e-05,
354
- "loss": 1.0437,
355
- "step": 400
356
- },
357
- {
358
- "epoch": 0.04936190705514086,
359
- "grad_norm": 10.5,
360
- "learning_rate": 2.045e-05,
361
- "loss": 1.1235,
362
- "step": 410
363
- },
364
- {
365
- "epoch": 0.05056585600770527,
366
- "grad_norm": 8.375,
367
- "learning_rate": 2.095e-05,
368
- "loss": 0.9802,
369
- "step": 420
370
- },
371
- {
372
- "epoch": 0.051769804960269686,
373
- "grad_norm": 11.125,
374
- "learning_rate": 2.145e-05,
375
- "loss": 1.1923,
376
- "step": 430
377
- },
378
- {
379
- "epoch": 0.0529737539128341,
380
- "grad_norm": 10.5625,
381
- "learning_rate": 2.195e-05,
382
- "loss": 1.0591,
383
- "step": 440
384
- },
385
- {
386
- "epoch": 0.054177702865398504,
387
- "grad_norm": 12.625,
388
- "learning_rate": 2.245e-05,
389
- "loss": 1.0929,
390
- "step": 450
391
- },
392
- {
393
- "epoch": 0.05538165181796292,
394
- "grad_norm": 7.4375,
395
- "learning_rate": 2.2950000000000002e-05,
396
- "loss": 0.8406,
397
- "step": 460
398
- },
399
- {
400
- "epoch": 0.05658560077052733,
401
- "grad_norm": 11.125,
402
- "learning_rate": 2.345e-05,
403
- "loss": 0.9958,
404
- "step": 470
405
- },
406
- {
407
- "epoch": 0.05778954972309174,
408
- "grad_norm": 9.9375,
409
- "learning_rate": 2.395e-05,
410
- "loss": 0.9885,
411
- "step": 480
412
- },
413
- {
414
- "epoch": 0.058993498675656154,
415
- "grad_norm": 9.625,
416
- "learning_rate": 2.445e-05,
417
- "loss": 1.0203,
418
- "step": 490
419
- },
420
- {
421
- "epoch": 0.06019744762822056,
422
- "grad_norm": 10.0,
423
- "learning_rate": 2.495e-05,
424
- "loss": 0.92,
425
- "step": 500
426
- },
427
- {
428
- "epoch": 0.06140139658078497,
429
- "grad_norm": 10.5625,
430
- "learning_rate": 2.5450000000000002e-05,
431
- "loss": 1.1444,
432
- "step": 510
433
- },
434
- {
435
- "epoch": 0.06260534553334939,
436
- "grad_norm": 11.75,
437
- "learning_rate": 2.595e-05,
438
- "loss": 0.9312,
439
- "step": 520
440
- },
441
- {
442
- "epoch": 0.0638092944859138,
443
- "grad_norm": 9.5,
444
- "learning_rate": 2.6450000000000003e-05,
445
- "loss": 1.0683,
446
- "step": 530
447
- },
448
- {
449
- "epoch": 0.06501324343847821,
450
- "grad_norm": 10.75,
451
- "learning_rate": 2.6950000000000005e-05,
452
- "loss": 0.9993,
453
- "step": 540
454
- },
455
- {
456
- "epoch": 0.06621719239104262,
457
- "grad_norm": 5.9375,
458
- "learning_rate": 2.7450000000000003e-05,
459
- "loss": 0.9648,
460
- "step": 550
461
- },
462
- {
463
- "epoch": 0.06742114134360704,
464
- "grad_norm": 10.25,
465
- "learning_rate": 2.7950000000000005e-05,
466
- "loss": 0.9591,
467
- "step": 560
468
- },
469
- {
470
- "epoch": 0.06862509029617145,
471
- "grad_norm": 9.6875,
472
- "learning_rate": 2.845e-05,
473
- "loss": 1.0011,
474
- "step": 570
475
- },
476
- {
477
- "epoch": 0.06982903924873585,
478
- "grad_norm": 8.9375,
479
- "learning_rate": 2.895e-05,
480
- "loss": 0.8669,
481
- "step": 580
482
- },
483
- {
484
- "epoch": 0.07103298820130026,
485
- "grad_norm": 8.8125,
486
- "learning_rate": 2.945e-05,
487
- "loss": 0.8381,
488
- "step": 590
489
- },
490
- {
491
- "epoch": 0.07223693715386467,
492
- "grad_norm": 7.9375,
493
- "learning_rate": 2.995e-05,
494
- "loss": 0.8767,
495
- "step": 600
496
- },
497
- {
498
- "epoch": 0.07344088610642908,
499
- "grad_norm": 7.75,
500
- "learning_rate": 3.045e-05,
501
- "loss": 0.7875,
502
- "step": 610
503
- },
504
- {
505
- "epoch": 0.0746448350589935,
506
- "grad_norm": 6.21875,
507
- "learning_rate": 3.095e-05,
508
- "loss": 0.8435,
509
- "step": 620
510
- },
511
- {
512
- "epoch": 0.07584878401155791,
513
- "grad_norm": 8.1875,
514
- "learning_rate": 3.145e-05,
515
- "loss": 0.8618,
516
- "step": 630
517
- },
518
- {
519
- "epoch": 0.07705273296412232,
520
- "grad_norm": 8.5,
521
- "learning_rate": 3.1950000000000004e-05,
522
- "loss": 0.8589,
523
- "step": 640
524
- },
525
- {
526
- "epoch": 0.07825668191668674,
527
- "grad_norm": 8.5,
528
- "learning_rate": 3.245e-05,
529
- "loss": 0.9605,
530
- "step": 650
531
- },
532
- {
533
- "epoch": 0.07946063086925115,
534
- "grad_norm": 7.4375,
535
- "learning_rate": 3.295e-05,
536
- "loss": 0.9085,
537
- "step": 660
538
- },
539
- {
540
- "epoch": 0.08066457982181556,
541
- "grad_norm": 6.71875,
542
- "learning_rate": 3.345000000000001e-05,
543
- "loss": 0.8026,
544
- "step": 670
545
- },
546
- {
547
- "epoch": 0.08186852877437997,
548
- "grad_norm": 10.0625,
549
- "learning_rate": 3.3950000000000005e-05,
550
- "loss": 0.8285,
551
- "step": 680
552
- },
553
- {
554
- "epoch": 0.08307247772694437,
555
- "grad_norm": 8.4375,
556
- "learning_rate": 3.445e-05,
557
- "loss": 0.8712,
558
- "step": 690
559
- },
560
- {
561
- "epoch": 0.08427642667950878,
562
- "grad_norm": 8.5,
563
- "learning_rate": 3.495e-05,
564
- "loss": 0.8366,
565
- "step": 700
566
- },
567
- {
568
- "epoch": 0.0854803756320732,
569
- "grad_norm": 9.3125,
570
- "learning_rate": 3.545e-05,
571
- "loss": 0.9514,
572
- "step": 710
573
- },
574
- {
575
- "epoch": 0.08668432458463761,
576
- "grad_norm": 7.34375,
577
- "learning_rate": 3.595e-05,
578
- "loss": 0.9519,
579
- "step": 720
580
- },
581
- {
582
- "epoch": 0.08788827353720202,
583
- "grad_norm": 7.03125,
584
- "learning_rate": 3.645e-05,
585
- "loss": 0.8114,
586
- "step": 730
587
- },
588
- {
589
- "epoch": 0.08909222248976643,
590
- "grad_norm": 8.3125,
591
- "learning_rate": 3.6950000000000004e-05,
592
- "loss": 0.8443,
593
- "step": 740
594
- },
595
- {
596
- "epoch": 0.09029617144233085,
597
- "grad_norm": 5.8125,
598
- "learning_rate": 3.745e-05,
599
- "loss": 0.815,
600
- "step": 750
601
- },
602
- {
603
- "epoch": 0.09150012039489526,
604
- "grad_norm": 7.125,
605
- "learning_rate": 3.795e-05,
606
- "loss": 0.8194,
607
- "step": 760
608
- },
609
- {
610
- "epoch": 0.09270406934745967,
611
- "grad_norm": 7.375,
612
- "learning_rate": 3.845e-05,
613
- "loss": 0.8795,
614
- "step": 770
615
- },
616
- {
617
- "epoch": 0.09390801830002408,
618
- "grad_norm": 6.125,
619
- "learning_rate": 3.8950000000000005e-05,
620
- "loss": 0.7941,
621
- "step": 780
622
- },
623
- {
624
- "epoch": 0.09511196725258848,
625
- "grad_norm": 6.65625,
626
- "learning_rate": 3.9450000000000003e-05,
627
- "loss": 0.9511,
628
- "step": 790
629
- },
630
- {
631
- "epoch": 0.0963159162051529,
632
- "grad_norm": 6.78125,
633
- "learning_rate": 3.995e-05,
634
- "loss": 0.9017,
635
- "step": 800
636
- },
637
- {
638
- "epoch": 0.09751986515771731,
639
- "grad_norm": 5.9375,
640
- "learning_rate": 4.045000000000001e-05,
641
- "loss": 0.8358,
642
- "step": 810
643
- },
644
- {
645
- "epoch": 0.09872381411028172,
646
- "grad_norm": 5.6875,
647
- "learning_rate": 4.095e-05,
648
- "loss": 0.8172,
649
- "step": 820
650
- },
651
- {
652
- "epoch": 0.09992776306284613,
653
- "grad_norm": 5.4375,
654
- "learning_rate": 4.145e-05,
655
- "loss": 0.9306,
656
- "step": 830
657
- },
658
- {
659
- "epoch": 0.10113171201541055,
660
- "grad_norm": 6.125,
661
- "learning_rate": 4.195e-05,
662
- "loss": 0.801,
663
- "step": 840
664
- },
665
- {
666
- "epoch": 0.10233566096797496,
667
- "grad_norm": 6.4375,
668
- "learning_rate": 4.245e-05,
669
- "loss": 0.793,
670
- "step": 850
671
- },
672
- {
673
- "epoch": 0.10353960992053937,
674
- "grad_norm": 5.25,
675
- "learning_rate": 4.295e-05,
676
- "loss": 0.7686,
677
- "step": 860
678
- },
679
- {
680
- "epoch": 0.10474355887310378,
681
- "grad_norm": 6.65625,
682
- "learning_rate": 4.345e-05,
683
- "loss": 0.8891,
684
- "step": 870
685
- },
686
- {
687
- "epoch": 0.1059475078256682,
688
- "grad_norm": 5.71875,
689
- "learning_rate": 4.3950000000000004e-05,
690
- "loss": 0.7847,
691
- "step": 880
692
- },
693
- {
694
- "epoch": 0.10715145677823261,
695
- "grad_norm": 6.78125,
696
- "learning_rate": 4.445e-05,
697
- "loss": 0.7822,
698
- "step": 890
699
- },
700
- {
701
- "epoch": 0.10835540573079701,
702
- "grad_norm": 6.15625,
703
- "learning_rate": 4.495e-05,
704
- "loss": 0.7343,
705
- "step": 900
706
- },
707
- {
708
- "epoch": 0.10955935468336142,
709
- "grad_norm": 5.78125,
710
- "learning_rate": 4.545000000000001e-05,
711
- "loss": 0.7725,
712
- "step": 910
713
- },
714
- {
715
- "epoch": 0.11076330363592583,
716
- "grad_norm": 6.625,
717
- "learning_rate": 4.5950000000000006e-05,
718
- "loss": 0.7744,
719
- "step": 920
720
- },
721
- {
722
- "epoch": 0.11196725258849025,
723
- "grad_norm": 10.4375,
724
- "learning_rate": 4.6450000000000004e-05,
725
- "loss": 0.72,
726
- "step": 930
727
- },
728
- {
729
- "epoch": 0.11317120154105466,
730
- "grad_norm": 6.5625,
731
- "learning_rate": 4.695e-05,
732
- "loss": 0.79,
733
- "step": 940
734
- },
735
- {
736
- "epoch": 0.11437515049361907,
737
- "grad_norm": 5.75,
738
- "learning_rate": 4.745e-05,
739
- "loss": 0.8084,
740
- "step": 950
741
- },
742
- {
743
- "epoch": 0.11557909944618348,
744
- "grad_norm": 7.71875,
745
- "learning_rate": 4.795e-05,
746
- "loss": 0.7332,
747
- "step": 960
748
- },
749
- {
750
- "epoch": 0.1167830483987479,
751
- "grad_norm": 6.875,
752
- "learning_rate": 4.845e-05,
753
- "loss": 0.827,
754
- "step": 970
755
- },
756
- {
757
- "epoch": 0.11798699735131231,
758
- "grad_norm": 6.375,
759
- "learning_rate": 4.8950000000000004e-05,
760
- "loss": 0.8598,
761
- "step": 980
762
- },
763
- {
764
- "epoch": 0.11919094630387672,
765
- "grad_norm": 6.5625,
766
- "learning_rate": 4.945e-05,
767
- "loss": 0.8785,
768
- "step": 990
769
- },
770
- {
771
- "epoch": 0.12039489525644112,
772
- "grad_norm": 6.5,
773
- "learning_rate": 4.995e-05,
774
- "loss": 0.7385,
775
- "step": 1000
776
- },
777
- {
778
- "epoch": 0.12039489525644112,
779
- "eval/nano_beir.arguana": 0.4762374986283534,
780
- "step": 1000
781
- },
782
- {
783
- "epoch": 0.12039489525644112,
784
- "eval/nano_beir.climate_fever": 0.233898612493137,
785
- "step": 1000
786
- },
787
- {
788
- "epoch": 0.12039489525644112,
789
- "eval/nano_beir.dbpedia_entity": 0.3310615619837843,
790
- "step": 1000
791
- },
792
- {
793
- "epoch": 0.12039489525644112,
794
- "eval/nano_beir.fever": 0.6534142202824448,
795
- "step": 1000
796
- },
797
- {
798
- "epoch": 0.12039489525644112,
799
- "eval/nano_beir.fiqa": 0.44285036968778174,
800
- "step": 1000
801
- },
802
- {
803
- "epoch": 0.12039489525644112,
804
- "eval/nano_beir.hotpotqa": 0.6857747415442759,
805
- "step": 1000
806
- },
807
- {
808
- "epoch": 0.12039489525644112,
809
- "eval/nano_beir.nfcorpus": 0.32960913350288634,
810
- "step": 1000
811
- },
812
- {
813
- "epoch": 0.12039489525644112,
814
- "eval/nano_beir.nq": 0.4234776162530602,
815
- "step": 1000
816
- },
817
- {
818
- "epoch": 0.12039489525644112,
819
- "eval/nano_beir.quora": 0.815858322680335,
820
- "step": 1000
821
- },
822
- {
823
- "epoch": 0.12039489525644112,
824
- "eval/nano_beir.scidocs": 0.2474366934846326,
825
- "step": 1000
826
- },
827
- {
828
- "epoch": 0.12039489525644112,
829
- "eval/nano_beir.scifact": 0.7414771066794785,
830
- "step": 1000
831
- },
832
- {
833
- "epoch": 0.12039489525644112,
834
- "eval/nano_beir.webis_touche2020": 0.29723028397312157,
835
- "step": 1000
836
- },
837
- {
838
- "epoch": 0.12039489525644112,
839
- "eval/avg": 0.47319384676610765,
840
- "step": 1000
841
- },
842
- {
843
- "epoch": 0.12159884420900553,
844
- "grad_norm": 6.28125,
845
- "learning_rate": 5.045e-05,
846
- "loss": 0.8105,
847
- "step": 1010
848
- },
849
- {
850
- "epoch": 0.12280279316156995,
851
- "grad_norm": 6.15625,
852
- "learning_rate": 5.095e-05,
853
- "loss": 0.773,
854
- "step": 1020
855
- },
856
- {
857
- "epoch": 0.12400674211413436,
858
- "grad_norm": 7.125,
859
- "learning_rate": 5.145e-05,
860
- "loss": 0.7829,
861
- "step": 1030
862
- },
863
- {
864
- "epoch": 0.12521069106669877,
865
- "grad_norm": 7.0,
866
- "learning_rate": 5.1949999999999996e-05,
867
- "loss": 0.7485,
868
- "step": 1040
869
- },
870
- {
871
- "epoch": 0.1264146400192632,
872
- "grad_norm": 6.1875,
873
- "learning_rate": 5.245e-05,
874
- "loss": 0.7062,
875
- "step": 1050
876
- },
877
- {
878
- "epoch": 0.1276185889718276,
879
- "grad_norm": 6.1875,
880
- "learning_rate": 5.295e-05,
881
- "loss": 0.8668,
882
- "step": 1060
883
- },
884
- {
885
- "epoch": 0.128822537924392,
886
- "grad_norm": 8.4375,
887
- "learning_rate": 5.345e-05,
888
- "loss": 0.7711,
889
- "step": 1070
890
- },
891
- {
892
- "epoch": 0.13002648687695642,
893
- "grad_norm": 6.0,
894
- "learning_rate": 5.3950000000000004e-05,
895
- "loss": 0.788,
896
- "step": 1080
897
- },
898
- {
899
- "epoch": 0.13123043582952082,
900
- "grad_norm": 5.59375,
901
- "learning_rate": 5.445e-05,
902
- "loss": 0.7042,
903
- "step": 1090
904
- },
905
- {
906
- "epoch": 0.13243438478208525,
907
- "grad_norm": 5.25,
908
- "learning_rate": 5.495e-05,
909
- "loss": 0.7907,
910
- "step": 1100
911
- },
912
- {
913
- "epoch": 0.13363833373464964,
914
- "grad_norm": 5.4375,
915
- "learning_rate": 5.545e-05,
916
- "loss": 0.7463,
917
- "step": 1110
918
- },
919
- {
920
- "epoch": 0.13484228268721407,
921
- "grad_norm": 4.71875,
922
- "learning_rate": 5.5950000000000005e-05,
923
- "loss": 0.7524,
924
- "step": 1120
925
- },
926
- {
927
- "epoch": 0.13604623163977847,
928
- "grad_norm": 3.671875,
929
- "learning_rate": 5.645e-05,
930
- "loss": 0.6886,
931
- "step": 1130
932
- },
933
- {
934
- "epoch": 0.1372501805923429,
935
- "grad_norm": 5.34375,
936
- "learning_rate": 5.695e-05,
937
- "loss": 0.796,
938
- "step": 1140
939
- },
940
- {
941
- "epoch": 0.1384541295449073,
942
- "grad_norm": 9.9375,
943
- "learning_rate": 5.745e-05,
944
- "loss": 0.7372,
945
- "step": 1150
946
- },
947
- {
948
- "epoch": 0.1396580784974717,
949
- "grad_norm": 8.75,
950
- "learning_rate": 5.7950000000000006e-05,
951
- "loss": 0.7826,
952
- "step": 1160
953
- },
954
- {
955
- "epoch": 0.14086202745003612,
956
- "grad_norm": 6.03125,
957
- "learning_rate": 5.8450000000000005e-05,
958
- "loss": 0.938,
959
- "step": 1170
960
- },
961
- {
962
- "epoch": 0.14206597640260052,
963
- "grad_norm": 6.71875,
964
- "learning_rate": 5.895e-05,
965
- "loss": 0.7121,
966
- "step": 1180
967
- },
968
- {
969
- "epoch": 0.14326992535516495,
970
- "grad_norm": 5.6875,
971
- "learning_rate": 5.945000000000001e-05,
972
- "loss": 0.7018,
973
- "step": 1190
974
- },
975
- {
976
- "epoch": 0.14447387430772934,
977
- "grad_norm": 5.40625,
978
- "learning_rate": 5.995000000000001e-05,
979
- "loss": 0.7568,
980
- "step": 1200
981
- },
982
- {
983
- "epoch": 0.14567782326029377,
984
- "grad_norm": 5.625,
985
- "learning_rate": 6.0450000000000006e-05,
986
- "loss": 0.7159,
987
- "step": 1210
988
- },
989
- {
990
- "epoch": 0.14688177221285817,
991
- "grad_norm": 5.71875,
992
- "learning_rate": 6.0950000000000004e-05,
993
- "loss": 0.7932,
994
- "step": 1220
995
- },
996
- {
997
- "epoch": 0.1480857211654226,
998
- "grad_norm": 6.53125,
999
- "learning_rate": 6.145e-05,
1000
- "loss": 0.6287,
1001
- "step": 1230
1002
- },
1003
- {
1004
- "epoch": 0.149289670117987,
1005
- "grad_norm": 6.625,
1006
- "learning_rate": 6.195e-05,
1007
- "loss": 0.8986,
1008
- "step": 1240
1009
- },
1010
- {
1011
- "epoch": 0.15049361907055142,
1012
- "grad_norm": 5.96875,
1013
- "learning_rate": 6.245000000000001e-05,
1014
- "loss": 0.681,
1015
- "step": 1250
1016
- },
1017
- {
1018
- "epoch": 0.15169756802311582,
1019
- "grad_norm": 6.65625,
1020
- "learning_rate": 6.295e-05,
1021
- "loss": 0.7139,
1022
- "step": 1260
1023
- },
1024
- {
1025
- "epoch": 0.15290151697568022,
1026
- "grad_norm": 6.75,
1027
- "learning_rate": 6.345e-05,
1028
- "loss": 0.72,
1029
- "step": 1270
1030
- },
1031
- {
1032
- "epoch": 0.15410546592824464,
1033
- "grad_norm": 5.71875,
1034
- "learning_rate": 6.395e-05,
1035
- "loss": 0.7386,
1036
- "step": 1280
1037
- },
1038
- {
1039
- "epoch": 0.15530941488080904,
1040
- "grad_norm": 5.6875,
1041
- "learning_rate": 6.445e-05,
1042
- "loss": 0.769,
1043
- "step": 1290
1044
- },
1045
- {
1046
- "epoch": 0.15651336383337347,
1047
- "grad_norm": 6.0625,
1048
- "learning_rate": 6.494999999999999e-05,
1049
- "loss": 0.7968,
1050
- "step": 1300
1051
- },
1052
- {
1053
- "epoch": 0.15771731278593787,
1054
- "grad_norm": 6.625,
1055
- "learning_rate": 6.545e-05,
1056
- "loss": 0.6689,
1057
- "step": 1310
1058
- },
1059
- {
1060
- "epoch": 0.1589212617385023,
1061
- "grad_norm": 6.6875,
1062
- "learning_rate": 6.595e-05,
1063
- "loss": 0.6724,
1064
- "step": 1320
1065
- },
1066
- {
1067
- "epoch": 0.1601252106910667,
1068
- "grad_norm": 7.46875,
1069
- "learning_rate": 6.645e-05,
1070
- "loss": 0.7493,
1071
- "step": 1330
1072
- },
1073
- {
1074
- "epoch": 0.16132915964363112,
1075
- "grad_norm": 5.25,
1076
- "learning_rate": 6.695e-05,
1077
- "loss": 0.7919,
1078
- "step": 1340
1079
- },
1080
- {
1081
- "epoch": 0.16253310859619552,
1082
- "grad_norm": 8.3125,
1083
- "learning_rate": 6.745e-05,
1084
- "loss": 0.6997,
1085
- "step": 1350
1086
- },
1087
- {
1088
- "epoch": 0.16373705754875995,
1089
- "grad_norm": 5.375,
1090
- "learning_rate": 6.795e-05,
1091
- "loss": 0.8986,
1092
- "step": 1360
1093
- },
1094
- {
1095
- "epoch": 0.16494100650132434,
1096
- "grad_norm": 5.5,
1097
- "learning_rate": 6.845e-05,
1098
- "loss": 0.6123,
1099
- "step": 1370
1100
- },
1101
- {
1102
- "epoch": 0.16614495545388874,
1103
- "grad_norm": 5.5,
1104
- "learning_rate": 6.895000000000001e-05,
1105
- "loss": 0.7185,
1106
- "step": 1380
1107
- },
1108
- {
1109
- "epoch": 0.16734890440645317,
1110
- "grad_norm": 4.625,
1111
- "learning_rate": 6.945000000000001e-05,
1112
- "loss": 0.6719,
1113
- "step": 1390
1114
- },
1115
- {
1116
- "epoch": 0.16855285335901757,
1117
- "grad_norm": 6.59375,
1118
- "learning_rate": 6.995e-05,
1119
- "loss": 0.8054,
1120
- "step": 1400
1121
- },
1122
- {
1123
- "epoch": 0.169756802311582,
1124
- "grad_norm": 5.28125,
1125
- "learning_rate": 7.045e-05,
1126
- "loss": 0.7182,
1127
- "step": 1410
1128
- },
1129
- {
1130
- "epoch": 0.1709607512641464,
1131
- "grad_norm": 5.0625,
1132
- "learning_rate": 7.095e-05,
1133
- "loss": 0.6471,
1134
- "step": 1420
1135
- },
1136
- {
1137
- "epoch": 0.17216470021671082,
1138
- "grad_norm": 4.5625,
1139
- "learning_rate": 7.145e-05,
1140
- "loss": 0.6292,
1141
- "step": 1430
1142
- },
1143
- {
1144
- "epoch": 0.17336864916927522,
1145
- "grad_norm": 6.875,
1146
- "learning_rate": 7.195e-05,
1147
- "loss": 0.7815,
1148
- "step": 1440
1149
- },
1150
- {
1151
- "epoch": 0.17457259812183964,
1152
- "grad_norm": 5.25,
1153
- "learning_rate": 7.245000000000001e-05,
1154
- "loss": 0.6529,
1155
- "step": 1450
1156
- },
1157
- {
1158
- "epoch": 0.17577654707440404,
1159
- "grad_norm": 6.59375,
1160
- "learning_rate": 7.295000000000001e-05,
1161
- "loss": 0.7466,
1162
- "step": 1460
1163
- },
1164
- {
1165
- "epoch": 0.17698049602696847,
1166
- "grad_norm": 4.84375,
1167
- "learning_rate": 7.345000000000001e-05,
1168
- "loss": 0.7231,
1169
- "step": 1470
1170
- },
1171
- {
1172
- "epoch": 0.17818444497953287,
1173
- "grad_norm": 4.90625,
1174
- "learning_rate": 7.395000000000001e-05,
1175
- "loss": 0.6796,
1176
- "step": 1480
1177
- },
1178
- {
1179
- "epoch": 0.17938839393209727,
1180
- "grad_norm": 4.96875,
1181
- "learning_rate": 7.445000000000001e-05,
1182
- "loss": 0.7144,
1183
- "step": 1490
1184
- },
1185
- {
1186
- "epoch": 0.1805923428846617,
1187
- "grad_norm": 6.03125,
1188
- "learning_rate": 7.495e-05,
1189
- "loss": 0.6959,
1190
- "step": 1500
1191
- },
1192
- {
1193
- "epoch": 0.1817962918372261,
1194
- "grad_norm": 5.84375,
1195
- "learning_rate": 7.545e-05,
1196
- "loss": 0.7335,
1197
- "step": 1510
1198
- },
1199
- {
1200
- "epoch": 0.18300024078979052,
1201
- "grad_norm": 6.125,
1202
- "learning_rate": 7.595e-05,
1203
- "loss": 0.6612,
1204
- "step": 1520
1205
- },
1206
- {
1207
- "epoch": 0.18420418974235492,
1208
- "grad_norm": 4.71875,
1209
- "learning_rate": 7.645e-05,
1210
- "loss": 0.7597,
1211
- "step": 1530
1212
- },
1213
- {
1214
- "epoch": 0.18540813869491934,
1215
- "grad_norm": 5.71875,
1216
- "learning_rate": 7.695e-05,
1217
- "loss": 0.639,
1218
- "step": 1540
1219
- },
1220
- {
1221
- "epoch": 0.18661208764748374,
1222
- "grad_norm": 6.375,
1223
- "learning_rate": 7.745e-05,
1224
- "loss": 0.6398,
1225
- "step": 1550
1226
- },
1227
- {
1228
- "epoch": 0.18781603660004817,
1229
- "grad_norm": 6.5625,
1230
- "learning_rate": 7.795e-05,
1231
- "loss": 0.7311,
1232
- "step": 1560
1233
- },
1234
- {
1235
- "epoch": 0.18901998555261257,
1236
- "grad_norm": 6.28125,
1237
- "learning_rate": 7.845e-05,
1238
- "loss": 0.7353,
1239
- "step": 1570
1240
- },
1241
- {
1242
- "epoch": 0.19022393450517697,
1243
- "grad_norm": 4.5625,
1244
- "learning_rate": 7.895000000000001e-05,
1245
- "loss": 0.6926,
1246
- "step": 1580
1247
- },
1248
- {
1249
- "epoch": 0.1914278834577414,
1250
- "grad_norm": 5.875,
1251
- "learning_rate": 7.945e-05,
1252
- "loss": 0.7124,
1253
- "step": 1590
1254
- },
1255
- {
1256
- "epoch": 0.1926318324103058,
1257
- "grad_norm": 5.15625,
1258
- "learning_rate": 7.995e-05,
1259
- "loss": 0.758,
1260
- "step": 1600
1261
- },
1262
- {
1263
- "epoch": 0.19383578136287022,
1264
- "grad_norm": 4.625,
1265
- "learning_rate": 8.045e-05,
1266
- "loss": 0.6659,
1267
- "step": 1610
1268
- },
1269
- {
1270
- "epoch": 0.19503973031543462,
1271
- "grad_norm": 5.0625,
1272
- "learning_rate": 8.095e-05,
1273
- "loss": 0.6103,
1274
- "step": 1620
1275
- },
1276
- {
1277
- "epoch": 0.19624367926799904,
1278
- "grad_norm": 5.96875,
1279
- "learning_rate": 8.145e-05,
1280
- "loss": 0.7149,
1281
- "step": 1630
1282
- },
1283
- {
1284
- "epoch": 0.19744762822056344,
1285
- "grad_norm": 5.875,
1286
- "learning_rate": 8.195e-05,
1287
- "loss": 0.686,
1288
- "step": 1640
1289
- },
1290
- {
1291
- "epoch": 0.19865157717312787,
1292
- "grad_norm": 6.75,
1293
- "learning_rate": 8.245e-05,
1294
- "loss": 0.7359,
1295
- "step": 1650
1296
- },
1297
- {
1298
- "epoch": 0.19985552612569227,
1299
- "grad_norm": 4.90625,
1300
- "learning_rate": 8.295000000000001e-05,
1301
- "loss": 0.7223,
1302
- "step": 1660
1303
- },
1304
- {
1305
- "epoch": 0.2010594750782567,
1306
- "grad_norm": 5.84375,
1307
- "learning_rate": 8.345000000000001e-05,
1308
- "loss": 0.7182,
1309
- "step": 1670
1310
- },
1311
- {
1312
- "epoch": 0.2022634240308211,
1313
- "grad_norm": 4.875,
1314
- "learning_rate": 8.395000000000001e-05,
1315
- "loss": 0.7124,
1316
- "step": 1680
1317
- },
1318
- {
1319
- "epoch": 0.2034673729833855,
1320
- "grad_norm": 4.875,
1321
- "learning_rate": 8.445e-05,
1322
- "loss": 0.6543,
1323
- "step": 1690
1324
- },
1325
- {
1326
- "epoch": 0.20467132193594992,
1327
- "grad_norm": 4.3125,
1328
- "learning_rate": 8.495e-05,
1329
- "loss": 0.6369,
1330
- "step": 1700
1331
- },
1332
- {
1333
- "epoch": 0.20587527088851432,
1334
- "grad_norm": 6.6875,
1335
- "learning_rate": 8.545e-05,
1336
- "loss": 0.7942,
1337
- "step": 1710
1338
- },
1339
- {
1340
- "epoch": 0.20707921984107874,
1341
- "grad_norm": 6.9375,
1342
- "learning_rate": 8.595e-05,
1343
- "loss": 0.7056,
1344
- "step": 1720
1345
- },
1346
- {
1347
- "epoch": 0.20828316879364314,
1348
- "grad_norm": 7.90625,
1349
- "learning_rate": 8.645000000000001e-05,
1350
- "loss": 0.6661,
1351
- "step": 1730
1352
- },
1353
- {
1354
- "epoch": 0.20948711774620757,
1355
- "grad_norm": 5.40625,
1356
- "learning_rate": 8.695000000000001e-05,
1357
- "loss": 0.7553,
1358
- "step": 1740
1359
- },
1360
- {
1361
- "epoch": 0.21069106669877197,
1362
- "grad_norm": 5.40625,
1363
- "learning_rate": 8.745000000000001e-05,
1364
- "loss": 0.5773,
1365
- "step": 1750
1366
- },
1367
- {
1368
- "epoch": 0.2118950156513364,
1369
- "grad_norm": 6.875,
1370
- "learning_rate": 8.795e-05,
1371
- "loss": 0.6403,
1372
- "step": 1760
1373
- },
1374
- {
1375
- "epoch": 0.2130989646039008,
1376
- "grad_norm": 5.21875,
1377
- "learning_rate": 8.845e-05,
1378
- "loss": 0.6805,
1379
- "step": 1770
1380
- },
1381
- {
1382
- "epoch": 0.21430291355646522,
1383
- "grad_norm": 6.34375,
1384
- "learning_rate": 8.895e-05,
1385
- "loss": 0.6963,
1386
- "step": 1780
1387
- },
1388
- {
1389
- "epoch": 0.21550686250902962,
1390
- "grad_norm": 5.6875,
1391
- "learning_rate": 8.945e-05,
1392
- "loss": 0.6754,
1393
- "step": 1790
1394
- },
1395
- {
1396
- "epoch": 0.21671081146159402,
1397
- "grad_norm": 4.875,
1398
- "learning_rate": 8.995e-05,
1399
- "loss": 0.6748,
1400
- "step": 1800
1401
- },
1402
- {
1403
- "epoch": 0.21791476041415844,
1404
- "grad_norm": 5.1875,
1405
- "learning_rate": 9.045e-05,
1406
- "loss": 0.6637,
1407
- "step": 1810
1408
- },
1409
- {
1410
- "epoch": 0.21911870936672284,
1411
- "grad_norm": 5.46875,
1412
- "learning_rate": 9.095e-05,
1413
- "loss": 0.6794,
1414
- "step": 1820
1415
- },
1416
- {
1417
- "epoch": 0.22032265831928727,
1418
- "grad_norm": 5.90625,
1419
- "learning_rate": 9.145e-05,
1420
- "loss": 0.6713,
1421
- "step": 1830
1422
- },
1423
- {
1424
- "epoch": 0.22152660727185167,
1425
- "grad_norm": 5.90625,
1426
- "learning_rate": 9.195e-05,
1427
- "loss": 0.6591,
1428
- "step": 1840
1429
- },
1430
- {
1431
- "epoch": 0.2227305562244161,
1432
- "grad_norm": 5.84375,
1433
- "learning_rate": 9.245e-05,
1434
- "loss": 0.6735,
1435
- "step": 1850
1436
- },
1437
- {
1438
- "epoch": 0.2239345051769805,
1439
- "grad_norm": 5.21875,
1440
- "learning_rate": 9.295000000000001e-05,
1441
- "loss": 0.6405,
1442
- "step": 1860
1443
- },
1444
- {
1445
- "epoch": 0.22513845412954492,
1446
- "grad_norm": 6.75,
1447
- "learning_rate": 9.345000000000001e-05,
1448
- "loss": 0.855,
1449
- "step": 1870
1450
- },
1451
- {
1452
- "epoch": 0.22634240308210932,
1453
- "grad_norm": 4.65625,
1454
- "learning_rate": 9.395000000000001e-05,
1455
- "loss": 0.6795,
1456
- "step": 1880
1457
- },
1458
- {
1459
- "epoch": 0.22754635203467374,
1460
- "grad_norm": 5.53125,
1461
- "learning_rate": 9.445e-05,
1462
- "loss": 0.7027,
1463
- "step": 1890
1464
- },
1465
- {
1466
- "epoch": 0.22875030098723814,
1467
- "grad_norm": 5.71875,
1468
- "learning_rate": 9.495e-05,
1469
- "loss": 0.6272,
1470
- "step": 1900
1471
- },
1472
- {
1473
- "epoch": 0.22995424993980254,
1474
- "grad_norm": 5.28125,
1475
- "learning_rate": 9.545e-05,
1476
- "loss": 0.6486,
1477
- "step": 1910
1478
- },
1479
- {
1480
- "epoch": 0.23115819889236697,
1481
- "grad_norm": 7.75,
1482
- "learning_rate": 9.595e-05,
1483
- "loss": 0.6701,
1484
- "step": 1920
1485
- },
1486
- {
1487
- "epoch": 0.23236214784493137,
1488
- "grad_norm": 5.8125,
1489
- "learning_rate": 9.645000000000001e-05,
1490
- "loss": 0.6247,
1491
- "step": 1930
1492
- },
1493
- {
1494
- "epoch": 0.2335660967974958,
1495
- "grad_norm": 6.25,
1496
- "learning_rate": 9.695000000000001e-05,
1497
- "loss": 0.5737,
1498
- "step": 1940
1499
- },
1500
- {
1501
- "epoch": 0.2347700457500602,
1502
- "grad_norm": 5.6875,
1503
- "learning_rate": 9.745000000000001e-05,
1504
- "loss": 0.6458,
1505
- "step": 1950
1506
- },
1507
- {
1508
- "epoch": 0.23597399470262462,
1509
- "grad_norm": 5.75,
1510
- "learning_rate": 9.795000000000001e-05,
1511
- "loss": 0.6185,
1512
- "step": 1960
1513
- },
1514
- {
1515
- "epoch": 0.23717794365518902,
1516
- "grad_norm": 5.03125,
1517
- "learning_rate": 9.845000000000001e-05,
1518
- "loss": 0.6793,
1519
- "step": 1970
1520
- },
1521
- {
1522
- "epoch": 0.23838189260775344,
1523
- "grad_norm": 4.8125,
1524
- "learning_rate": 9.895e-05,
1525
- "loss": 0.6427,
1526
- "step": 1980
1527
- },
1528
- {
1529
- "epoch": 0.23958584156031784,
1530
- "grad_norm": 6.4375,
1531
- "learning_rate": 9.945e-05,
1532
- "loss": 0.5906,
1533
- "step": 1990
1534
- },
1535
- {
1536
- "epoch": 0.24078979051288224,
1537
- "grad_norm": 4.875,
1538
- "learning_rate": 9.995e-05,
1539
- "loss": 0.722,
1540
- "step": 2000
1541
- },
1542
- {
1543
- "epoch": 0.24078979051288224,
1544
- "eval/nano_beir.arguana": 0.4525611780495533,
1545
- "step": 2000
1546
- },
1547
- {
1548
- "epoch": 0.24078979051288224,
1549
- "eval/nano_beir.climate_fever": 0.2570101915834051,
1550
- "step": 2000
1551
- },
1552
- {
1553
- "epoch": 0.24078979051288224,
1554
- "eval/nano_beir.dbpedia_entity": 0.32066621016721925,
1555
- "step": 2000
1556
- },
1557
- {
1558
- "epoch": 0.24078979051288224,
1559
- "eval/nano_beir.fever": 0.6653091674586123,
1560
- "step": 2000
1561
- },
1562
- {
1563
- "epoch": 0.24078979051288224,
1564
- "eval/nano_beir.fiqa": 0.4363959457519276,
1565
- "step": 2000
1566
- },
1567
- {
1568
- "epoch": 0.24078979051288224,
1569
- "eval/nano_beir.hotpotqa": 0.6777722196406764,
1570
- "step": 2000
1571
- },
1572
- {
1573
- "epoch": 0.24078979051288224,
1574
- "eval/nano_beir.nfcorpus": 0.34079846618923787,
1575
- "step": 2000
1576
- },
1577
- {
1578
- "epoch": 0.24078979051288224,
1579
- "eval/nano_beir.nq": 0.4250588398489226,
1580
- "step": 2000
1581
- },
1582
- {
1583
- "epoch": 0.24078979051288224,
1584
- "eval/nano_beir.quora": 0.8267157890689902,
1585
- "step": 2000
1586
- },
1587
- {
1588
- "epoch": 0.24078979051288224,
1589
- "eval/nano_beir.scidocs": 0.2523924791841879,
1590
- "step": 2000
1591
- },
1592
- {
1593
- "epoch": 0.24078979051288224,
1594
- "eval/nano_beir.scifact": 0.7454362051377628,
1595
- "step": 2000
1596
- },
1597
- {
1598
- "epoch": 0.24078979051288224,
1599
- "eval/nano_beir.webis_touche2020": 0.2983187434961579,
1600
- "step": 2000
1601
- },
1602
- {
1603
- "epoch": 0.24078979051288224,
1604
- "eval/avg": 0.47486961963138774,
1605
- "step": 2000
1606
- },
1607
- {
1608
- "epoch": 0.24199373946544667,
1609
- "grad_norm": 4.90625,
1610
- "learning_rate": 9.999993831498517e-05,
1611
- "loss": 0.629,
1612
- "step": 2010
1613
- },
1614
- {
1615
- "epoch": 0.24319768841801107,
1616
- "grad_norm": 5.15625,
1617
- "learning_rate": 9.999972508303057e-05,
1618
- "loss": 0.6816,
1619
- "step": 2020
1620
- },
1621
- {
1622
- "epoch": 0.2444016373705755,
1623
- "grad_norm": 4.3125,
1624
- "learning_rate": 9.999935954324219e-05,
1625
- "loss": 0.6942,
1626
- "step": 2030
1627
- },
1628
- {
1629
- "epoch": 0.2456055863231399,
1630
- "grad_norm": 4.40625,
1631
- "learning_rate": 9.999884169673351e-05,
1632
- "loss": 0.6213,
1633
- "step": 2040
1634
- },
1635
- {
1636
- "epoch": 0.24680953527570432,
1637
- "grad_norm": 6.375,
1638
- "learning_rate": 9.9998171545082e-05,
1639
- "loss": 0.7049,
1640
- "step": 2050
1641
- },
1642
- {
1643
- "epoch": 0.24801348422826872,
1644
- "grad_norm": 6.40625,
1645
- "learning_rate": 9.999734909032906e-05,
1646
- "loss": 0.6177,
1647
- "step": 2060
1648
- },
1649
- {
1650
- "epoch": 0.24921743318083314,
1651
- "grad_norm": 5.71875,
1652
- "learning_rate": 9.999637433497999e-05,
1653
- "loss": 0.674,
1654
- "step": 2070
1655
- },
1656
- {
1657
- "epoch": 0.25042138213339754,
1658
- "grad_norm": 5.25,
1659
- "learning_rate": 9.999524728200411e-05,
1660
- "loss": 0.5632,
1661
- "step": 2080
1662
- },
1663
- {
1664
- "epoch": 0.25162533108596197,
1665
- "grad_norm": 5.96875,
1666
- "learning_rate": 9.999396793483462e-05,
1667
- "loss": 0.6868,
1668
- "step": 2090
1669
- },
1670
- {
1671
- "epoch": 0.2528292800385264,
1672
- "grad_norm": 7.125,
1673
- "learning_rate": 9.99925362973686e-05,
1674
- "loss": 0.6709,
1675
- "step": 2100
1676
- },
1677
- {
1678
- "epoch": 0.25403322899109076,
1679
- "grad_norm": 4.5,
1680
- "learning_rate": 9.999095237396707e-05,
1681
- "loss": 0.6105,
1682
- "step": 2110
1683
- },
1684
- {
1685
- "epoch": 0.2552371779436552,
1686
- "grad_norm": 6.09375,
1687
- "learning_rate": 9.998921616945498e-05,
1688
- "loss": 0.7128,
1689
- "step": 2120
1690
- },
1691
- {
1692
- "epoch": 0.2564411268962196,
1693
- "grad_norm": 5.5,
1694
- "learning_rate": 9.998732768912104e-05,
1695
- "loss": 0.6496,
1696
- "step": 2130
1697
- },
1698
- {
1699
- "epoch": 0.257645075848784,
1700
- "grad_norm": 4.90625,
1701
- "learning_rate": 9.998528693871796e-05,
1702
- "loss": 0.7465,
1703
- "step": 2140
1704
- },
1705
- {
1706
- "epoch": 0.2588490248013484,
1707
- "grad_norm": 6.09375,
1708
- "learning_rate": 9.998309392446217e-05,
1709
- "loss": 0.6041,
1710
- "step": 2150
1711
- },
1712
- {
1713
- "epoch": 0.26005297375391284,
1714
- "grad_norm": 5.15625,
1715
- "learning_rate": 9.998074865303399e-05,
1716
- "loss": 0.6091,
1717
- "step": 2160
1718
- },
1719
- {
1720
- "epoch": 0.26125692270647727,
1721
- "grad_norm": 4.4375,
1722
- "learning_rate": 9.997825113157753e-05,
1723
- "loss": 0.7457,
1724
- "step": 2170
1725
- },
1726
- {
1727
- "epoch": 0.26246087165904164,
1728
- "grad_norm": 4.8125,
1729
- "learning_rate": 9.997560136770065e-05,
1730
- "loss": 0.6663,
1731
- "step": 2180
1732
- },
1733
- {
1734
- "epoch": 0.26366482061160607,
1735
- "grad_norm": 4.21875,
1736
- "learning_rate": 9.997279936947502e-05,
1737
- "loss": 0.7311,
1738
- "step": 2190
1739
- },
1740
- {
1741
- "epoch": 0.2648687695641705,
1742
- "grad_norm": 5.5625,
1743
- "learning_rate": 9.996984514543598e-05,
1744
- "loss": 0.5879,
1745
- "step": 2200
1746
- },
1747
- {
1748
- "epoch": 0.26607271851673486,
1749
- "grad_norm": 4.96875,
1750
- "learning_rate": 9.996673870458264e-05,
1751
- "loss": 0.7008,
1752
- "step": 2210
1753
- },
1754
- {
1755
- "epoch": 0.2672766674692993,
1756
- "grad_norm": 5.09375,
1757
- "learning_rate": 9.996348005637775e-05,
1758
- "loss": 0.5099,
1759
- "step": 2220
1760
- },
1761
- {
1762
- "epoch": 0.2684806164218637,
1763
- "grad_norm": 6.6875,
1764
- "learning_rate": 9.99600692107477e-05,
1765
- "loss": 0.6186,
1766
- "step": 2230
1767
- },
1768
- {
1769
- "epoch": 0.26968456537442814,
1770
- "grad_norm": 5.15625,
1771
- "learning_rate": 9.995650617808252e-05,
1772
- "loss": 0.6839,
1773
- "step": 2240
1774
- },
1775
- {
1776
- "epoch": 0.2708885143269925,
1777
- "grad_norm": 3.90625,
1778
- "learning_rate": 9.995279096923585e-05,
1779
- "loss": 0.6287,
1780
- "step": 2250
1781
- },
1782
- {
1783
- "epoch": 0.27209246327955694,
1784
- "grad_norm": 3.921875,
1785
- "learning_rate": 9.994892359552483e-05,
1786
- "loss": 0.5221,
1787
- "step": 2260
1788
- },
1789
- {
1790
- "epoch": 0.27329641223212137,
1791
- "grad_norm": 6.4375,
1792
- "learning_rate": 9.994490406873019e-05,
1793
- "loss": 0.6728,
1794
- "step": 2270
1795
- },
1796
- {
1797
- "epoch": 0.2745003611846858,
1798
- "grad_norm": 4.375,
1799
- "learning_rate": 9.994073240109606e-05,
1800
- "loss": 0.5306,
1801
- "step": 2280
1802
- },
1803
- {
1804
- "epoch": 0.27570431013725016,
1805
- "grad_norm": 5.65625,
1806
- "learning_rate": 9.993640860533009e-05,
1807
- "loss": 0.6765,
1808
- "step": 2290
1809
- },
1810
- {
1811
- "epoch": 0.2769082590898146,
1812
- "grad_norm": 5.09375,
1813
- "learning_rate": 9.99319326946033e-05,
1814
- "loss": 0.5858,
1815
- "step": 2300
1816
- },
1817
- {
1818
- "epoch": 0.278112208042379,
1819
- "grad_norm": 6.0625,
1820
- "learning_rate": 9.992730468255011e-05,
1821
- "loss": 0.6345,
1822
- "step": 2310
1823
- },
1824
- {
1825
- "epoch": 0.2793161569949434,
1826
- "grad_norm": 4.9375,
1827
- "learning_rate": 9.992252458326823e-05,
1828
- "loss": 0.5993,
1829
- "step": 2320
1830
- },
1831
- {
1832
- "epoch": 0.2805201059475078,
1833
- "grad_norm": 4.65625,
1834
- "learning_rate": 9.991759241131869e-05,
1835
- "loss": 0.7848,
1836
- "step": 2330
1837
- },
1838
- {
1839
- "epoch": 0.28172405490007224,
1840
- "grad_norm": 4.5625,
1841
- "learning_rate": 9.99125081817257e-05,
1842
- "loss": 0.565,
1843
- "step": 2340
1844
- },
1845
- {
1846
- "epoch": 0.28292800385263667,
1847
- "grad_norm": 3.796875,
1848
- "learning_rate": 9.990727190997674e-05,
1849
- "loss": 0.5264,
1850
- "step": 2350
1851
- },
1852
- {
1853
- "epoch": 0.28413195280520104,
1854
- "grad_norm": 4.21875,
1855
- "learning_rate": 9.99018836120224e-05,
1856
- "loss": 0.6909,
1857
- "step": 2360
1858
- },
1859
- {
1860
- "epoch": 0.28533590175776546,
1861
- "grad_norm": 4.0,
1862
- "learning_rate": 9.989634330427636e-05,
1863
- "loss": 0.6056,
1864
- "step": 2370
1865
- },
1866
- {
1867
- "epoch": 0.2865398507103299,
1868
- "grad_norm": 5.9375,
1869
- "learning_rate": 9.989065100361536e-05,
1870
- "loss": 0.6339,
1871
- "step": 2380
1872
- },
1873
- {
1874
- "epoch": 0.2877437996628943,
1875
- "grad_norm": 5.84375,
1876
- "learning_rate": 9.988480672737915e-05,
1877
- "loss": 0.6631,
1878
- "step": 2390
1879
- },
1880
- {
1881
- "epoch": 0.2889477486154587,
1882
- "grad_norm": 4.03125,
1883
- "learning_rate": 9.987881049337037e-05,
1884
- "loss": 0.6711,
1885
- "step": 2400
1886
- },
1887
- {
1888
- "epoch": 0.2901516975680231,
1889
- "grad_norm": 4.65625,
1890
- "learning_rate": 9.987266231985462e-05,
1891
- "loss": 0.6853,
1892
- "step": 2410
1893
- },
1894
- {
1895
- "epoch": 0.29135564652058754,
1896
- "grad_norm": 5.5625,
1897
- "learning_rate": 9.986636222556032e-05,
1898
- "loss": 0.593,
1899
- "step": 2420
1900
- },
1901
- {
1902
- "epoch": 0.2925595954731519,
1903
- "grad_norm": 5.40625,
1904
- "learning_rate": 9.98599102296786e-05,
1905
- "loss": 0.5731,
1906
- "step": 2430
1907
- },
1908
- {
1909
- "epoch": 0.29376354442571634,
1910
- "grad_norm": 4.21875,
1911
- "learning_rate": 9.985330635186341e-05,
1912
- "loss": 0.5369,
1913
- "step": 2440
1914
- },
1915
- {
1916
- "epoch": 0.29496749337828077,
1917
- "grad_norm": 5.1875,
1918
- "learning_rate": 9.984655061223126e-05,
1919
- "loss": 0.6457,
1920
- "step": 2450
1921
- },
1922
- {
1923
- "epoch": 0.2961714423308452,
1924
- "grad_norm": 4.6875,
1925
- "learning_rate": 9.983964303136133e-05,
1926
- "loss": 0.482,
1927
- "step": 2460
1928
- },
1929
- {
1930
- "epoch": 0.29737539128340956,
1931
- "grad_norm": 6.5,
1932
- "learning_rate": 9.983258363029531e-05,
1933
- "loss": 0.6507,
1934
- "step": 2470
1935
- },
1936
- {
1937
- "epoch": 0.298579340235974,
1938
- "grad_norm": 3.875,
1939
- "learning_rate": 9.982537243053737e-05,
1940
- "loss": 0.5553,
1941
- "step": 2480
1942
- },
1943
- {
1944
- "epoch": 0.2997832891885384,
1945
- "grad_norm": 5.21875,
1946
- "learning_rate": 9.981800945405403e-05,
1947
- "loss": 0.5712,
1948
- "step": 2490
1949
- },
1950
- {
1951
- "epoch": 0.30098723814110284,
1952
- "grad_norm": 4.875,
1953
- "learning_rate": 9.981049472327426e-05,
1954
- "loss": 0.6483,
1955
- "step": 2500
1956
- },
1957
- {
1958
- "epoch": 0.3021911870936672,
1959
- "grad_norm": 4.15625,
1960
- "learning_rate": 9.980282826108918e-05,
1961
- "loss": 0.5455,
1962
- "step": 2510
1963
- },
1964
- {
1965
- "epoch": 0.30339513604623164,
1966
- "grad_norm": 5.09375,
1967
- "learning_rate": 9.979501009085219e-05,
1968
- "loss": 0.7318,
1969
- "step": 2520
1970
- },
1971
- {
1972
- "epoch": 0.30459908499879607,
1973
- "grad_norm": 5.78125,
1974
- "learning_rate": 9.978704023637878e-05,
1975
- "loss": 0.6642,
1976
- "step": 2530
1977
- },
1978
- {
1979
- "epoch": 0.30580303395136044,
1980
- "grad_norm": 6.71875,
1981
- "learning_rate": 9.97789187219465e-05,
1982
- "loss": 0.6208,
1983
- "step": 2540
1984
- },
1985
- {
1986
- "epoch": 0.30700698290392486,
1987
- "grad_norm": 4.90625,
1988
- "learning_rate": 9.977064557229492e-05,
1989
- "loss": 0.6076,
1990
- "step": 2550
1991
- },
1992
- {
1993
- "epoch": 0.3082109318564893,
1994
- "grad_norm": 6.09375,
1995
- "learning_rate": 9.976222081262545e-05,
1996
- "loss": 0.5148,
1997
- "step": 2560
1998
- },
1999
- {
2000
- "epoch": 0.3094148808090537,
2001
- "grad_norm": 4.78125,
2002
- "learning_rate": 9.975364446860142e-05,
2003
- "loss": 0.642,
2004
- "step": 2570
2005
- },
2006
- {
2007
- "epoch": 0.3106188297616181,
2008
- "grad_norm": 5.0625,
2009
- "learning_rate": 9.974491656634782e-05,
2010
- "loss": 0.6305,
2011
- "step": 2580
2012
- },
2013
- {
2014
- "epoch": 0.3118227787141825,
2015
- "grad_norm": 4.5625,
2016
- "learning_rate": 9.973603713245135e-05,
2017
- "loss": 0.6977,
2018
- "step": 2590
2019
- },
2020
- {
2021
- "epoch": 0.31302672766674694,
2022
- "grad_norm": 5.0,
2023
- "learning_rate": 9.972700619396033e-05,
2024
- "loss": 0.6351,
2025
- "step": 2600
2026
- },
2027
- {
2028
- "epoch": 0.31423067661931137,
2029
- "grad_norm": 4.8125,
2030
- "learning_rate": 9.971782377838457e-05,
2031
- "loss": 0.6461,
2032
- "step": 2610
2033
- },
2034
- {
2035
- "epoch": 0.31543462557187574,
2036
- "grad_norm": 4.53125,
2037
- "learning_rate": 9.970848991369529e-05,
2038
- "loss": 0.6827,
2039
- "step": 2620
2040
- },
2041
- {
2042
- "epoch": 0.31663857452444016,
2043
- "grad_norm": 3.890625,
2044
- "learning_rate": 9.969900462832505e-05,
2045
- "loss": 0.6179,
2046
- "step": 2630
2047
- },
2048
- {
2049
- "epoch": 0.3178425234770046,
2050
- "grad_norm": 4.90625,
2051
- "learning_rate": 9.968936795116768e-05,
2052
- "loss": 0.5521,
2053
- "step": 2640
2054
- },
2055
- {
2056
- "epoch": 0.31904647242956896,
2057
- "grad_norm": 4.59375,
2058
- "learning_rate": 9.967957991157817e-05,
2059
- "loss": 0.6362,
2060
- "step": 2650
2061
- },
2062
- {
2063
- "epoch": 0.3202504213821334,
2064
- "grad_norm": 5.46875,
2065
- "learning_rate": 9.96696405393726e-05,
2066
- "loss": 0.7081,
2067
- "step": 2660
2068
- },
2069
- {
2070
- "epoch": 0.3214543703346978,
2071
- "grad_norm": 4.125,
2072
- "learning_rate": 9.965954986482799e-05,
2073
- "loss": 0.6079,
2074
- "step": 2670
2075
- },
2076
- {
2077
- "epoch": 0.32265831928726224,
2078
- "grad_norm": 4.625,
2079
- "learning_rate": 9.964930791868233e-05,
2080
- "loss": 0.6601,
2081
- "step": 2680
2082
- },
2083
- {
2084
- "epoch": 0.3238622682398266,
2085
- "grad_norm": 4.4375,
2086
- "learning_rate": 9.963891473213431e-05,
2087
- "loss": 0.4889,
2088
- "step": 2690
2089
- },
2090
- {
2091
- "epoch": 0.32506621719239104,
2092
- "grad_norm": 5.84375,
2093
- "learning_rate": 9.962837033684343e-05,
2094
- "loss": 0.5751,
2095
- "step": 2700
2096
- },
2097
- {
2098
- "epoch": 0.32627016614495546,
2099
- "grad_norm": 5.875,
2100
- "learning_rate": 9.96176747649297e-05,
2101
- "loss": 0.5564,
2102
- "step": 2710
2103
- },
2104
- {
2105
- "epoch": 0.3274741150975199,
2106
- "grad_norm": 3.8125,
2107
- "learning_rate": 9.960682804897372e-05,
2108
- "loss": 0.6049,
2109
- "step": 2720
2110
- },
2111
- {
2112
- "epoch": 0.32867806405008426,
2113
- "grad_norm": 5.0625,
2114
- "learning_rate": 9.959583022201647e-05,
2115
- "loss": 0.6224,
2116
- "step": 2730
2117
- },
2118
- {
2119
- "epoch": 0.3298820130026487,
2120
- "grad_norm": 4.9375,
2121
- "learning_rate": 9.958468131755923e-05,
2122
- "loss": 0.6209,
2123
- "step": 2740
2124
- },
2125
- {
2126
- "epoch": 0.3310859619552131,
2127
- "grad_norm": 5.09375,
2128
- "learning_rate": 9.957338136956347e-05,
2129
- "loss": 0.6223,
2130
- "step": 2750
2131
- },
2132
- {
2133
- "epoch": 0.3322899109077775,
2134
- "grad_norm": 4.625,
2135
- "learning_rate": 9.956193041245084e-05,
2136
- "loss": 0.5007,
2137
- "step": 2760
2138
- },
2139
- {
2140
- "epoch": 0.3334938598603419,
2141
- "grad_norm": 5.125,
2142
- "learning_rate": 9.955032848110288e-05,
2143
- "loss": 0.7128,
2144
- "step": 2770
2145
- },
2146
- {
2147
- "epoch": 0.33469780881290634,
2148
- "grad_norm": 3.765625,
2149
- "learning_rate": 9.953857561086115e-05,
2150
- "loss": 0.6118,
2151
- "step": 2780
2152
- },
2153
- {
2154
- "epoch": 0.33590175776547077,
2155
- "grad_norm": 4.5,
2156
- "learning_rate": 9.952667183752689e-05,
2157
- "loss": 0.6389,
2158
- "step": 2790
2159
- },
2160
- {
2161
- "epoch": 0.33710570671803514,
2162
- "grad_norm": 5.40625,
2163
- "learning_rate": 9.951461719736109e-05,
2164
- "loss": 0.6104,
2165
- "step": 2800
2166
- },
2167
- {
2168
- "epoch": 0.33830965567059956,
2169
- "grad_norm": 5.65625,
2170
- "learning_rate": 9.950241172708423e-05,
2171
- "loss": 0.5951,
2172
- "step": 2810
2173
- },
2174
- {
2175
- "epoch": 0.339513604623164,
2176
- "grad_norm": 4.375,
2177
- "learning_rate": 9.949005546387631e-05,
2178
- "loss": 0.719,
2179
- "step": 2820
2180
- },
2181
- {
2182
- "epoch": 0.3407175535757284,
2183
- "grad_norm": 6.0,
2184
- "learning_rate": 9.947754844537666e-05,
2185
- "loss": 0.5546,
2186
- "step": 2830
2187
- },
2188
- {
2189
- "epoch": 0.3419215025282928,
2190
- "grad_norm": 5.0,
2191
- "learning_rate": 9.946489070968383e-05,
2192
- "loss": 0.6485,
2193
- "step": 2840
2194
- },
2195
- {
2196
- "epoch": 0.3431254514808572,
2197
- "grad_norm": 5.4375,
2198
- "learning_rate": 9.945208229535548e-05,
2199
- "loss": 0.4833,
2200
- "step": 2850
2201
- },
2202
- {
2203
- "epoch": 0.34432940043342164,
2204
- "grad_norm": 4.6875,
2205
- "learning_rate": 9.943912324140823e-05,
2206
- "loss": 0.6452,
2207
- "step": 2860
2208
- },
2209
- {
2210
- "epoch": 0.345533349385986,
2211
- "grad_norm": 7.78125,
2212
- "learning_rate": 9.942601358731762e-05,
2213
- "loss": 0.6203,
2214
- "step": 2870
2215
- },
2216
- {
2217
- "epoch": 0.34673729833855044,
2218
- "grad_norm": 5.78125,
2219
- "learning_rate": 9.941275337301796e-05,
2220
- "loss": 0.5906,
2221
- "step": 2880
2222
- },
2223
- {
2224
- "epoch": 0.34794124729111486,
2225
- "grad_norm": 3.578125,
2226
- "learning_rate": 9.939934263890213e-05,
2227
- "loss": 0.6033,
2228
- "step": 2890
2229
- },
2230
- {
2231
- "epoch": 0.3491451962436793,
2232
- "grad_norm": 4.21875,
2233
- "learning_rate": 9.938578142582155e-05,
2234
- "loss": 0.5577,
2235
- "step": 2900
2236
- },
2237
- {
2238
- "epoch": 0.35034914519624366,
2239
- "grad_norm": 5.1875,
2240
- "learning_rate": 9.937206977508604e-05,
2241
- "loss": 0.584,
2242
- "step": 2910
2243
- },
2244
- {
2245
- "epoch": 0.3515530941488081,
2246
- "grad_norm": 5.65625,
2247
- "learning_rate": 9.935820772846367e-05,
2248
- "loss": 0.6395,
2249
- "step": 2920
2250
- },
2251
- {
2252
- "epoch": 0.3527570431013725,
2253
- "grad_norm": 4.9375,
2254
- "learning_rate": 9.934419532818063e-05,
2255
- "loss": 0.6887,
2256
- "step": 2930
2257
- },
2258
- {
2259
- "epoch": 0.35396099205393694,
2260
- "grad_norm": 3.515625,
2261
- "learning_rate": 9.933003261692113e-05,
2262
- "loss": 0.6007,
2263
- "step": 2940
2264
- },
2265
- {
2266
- "epoch": 0.3551649410065013,
2267
- "grad_norm": 3.765625,
2268
- "learning_rate": 9.931571963782721e-05,
2269
- "loss": 0.5343,
2270
- "step": 2950
2271
- },
2272
- {
2273
- "epoch": 0.35636888995906574,
2274
- "grad_norm": 6.625,
2275
- "learning_rate": 9.930125643449875e-05,
2276
- "loss": 0.6603,
2277
- "step": 2960
2278
- },
2279
- {
2280
- "epoch": 0.35757283891163016,
2281
- "grad_norm": 5.78125,
2282
- "learning_rate": 9.928664305099314e-05,
2283
- "loss": 0.6181,
2284
- "step": 2970
2285
- },
2286
- {
2287
- "epoch": 0.35877678786419454,
2288
- "grad_norm": 5.46875,
2289
- "learning_rate": 9.927187953182525e-05,
2290
- "loss": 0.6866,
2291
- "step": 2980
2292
- },
2293
- {
2294
- "epoch": 0.35998073681675896,
2295
- "grad_norm": 5.3125,
2296
- "learning_rate": 9.925696592196736e-05,
2297
- "loss": 0.6638,
2298
- "step": 2990
2299
- },
2300
- {
2301
- "epoch": 0.3611846857693234,
2302
- "grad_norm": 4.65625,
2303
- "learning_rate": 9.92419022668489e-05,
2304
- "loss": 0.6748,
2305
- "step": 3000
2306
- },
2307
- {
2308
- "epoch": 0.3611846857693234,
2309
- "eval/nano_beir.arguana": 0.43364873258121056,
2310
- "step": 3000
2311
- },
2312
- {
2313
- "epoch": 0.3611846857693234,
2314
- "eval/nano_beir.climate_fever": 0.2460637609555945,
2315
- "step": 3000
2316
- },
2317
- {
2318
- "epoch": 0.3611846857693234,
2319
- "eval/nano_beir.dbpedia_entity": 0.3159084412902975,
2320
- "step": 3000
2321
- },
2322
- {
2323
- "epoch": 0.3611846857693234,
2324
- "eval/nano_beir.fever": 0.6561861919849862,
2325
- "step": 3000
2326
- },
2327
- {
2328
- "epoch": 0.3611846857693234,
2329
- "eval/nano_beir.fiqa": 0.4461917273661319,
2330
- "step": 3000
2331
- },
2332
- {
2333
- "epoch": 0.3611846857693234,
2334
- "eval/nano_beir.hotpotqa": 0.6787641908210825,
2335
- "step": 3000
2336
- },
2337
- {
2338
- "epoch": 0.3611846857693234,
2339
- "eval/nano_beir.nfcorpus": 0.3435535179091152,
2340
- "step": 3000
2341
- },
2342
- {
2343
- "epoch": 0.3611846857693234,
2344
- "eval/nano_beir.nq": 0.4301288631476355,
2345
- "step": 3000
2346
- },
2347
- {
2348
- "epoch": 0.3611846857693234,
2349
- "eval/nano_beir.quora": 0.840867288047918,
2350
- "step": 3000
2351
- },
2352
- {
2353
- "epoch": 0.3611846857693234,
2354
- "eval/nano_beir.scidocs": 0.2483700409338938,
2355
- "step": 3000
2356
- },
2357
- {
2358
- "epoch": 0.3611846857693234,
2359
- "eval/nano_beir.scifact": 0.7407091437249231,
2360
- "step": 3000
2361
- },
2362
- {
2363
- "epoch": 0.3611846857693234,
2364
- "eval/nano_beir.webis_touche2020": 0.2932674650458427,
2365
- "step": 3000
2366
- },
2367
- {
2368
- "epoch": 0.3611846857693234,
2369
- "eval/avg": 0.4728049469840527,
2370
- "step": 3000
2371
- },
2372
- {
2373
- "epoch": 0.3623886347218878,
2374
- "grad_norm": 4.21875,
2375
- "learning_rate": 9.92266886123564e-05,
2376
- "loss": 0.6107,
2377
- "step": 3010
2378
- },
2379
- {
2380
- "epoch": 0.3635925836744522,
2381
- "grad_norm": 5.875,
2382
- "learning_rate": 9.921132500483325e-05,
2383
- "loss": 0.6822,
2384
- "step": 3020
2385
- },
2386
- {
2387
- "epoch": 0.3647965326270166,
2388
- "grad_norm": 5.1875,
2389
- "learning_rate": 9.919581149107968e-05,
2390
- "loss": 0.6194,
2391
- "step": 3030
2392
- },
2393
- {
2394
- "epoch": 0.36600048157958104,
2395
- "grad_norm": 3.5,
2396
- "learning_rate": 9.918014811835254e-05,
2397
- "loss": 0.5776,
2398
- "step": 3040
2399
- },
2400
- {
2401
- "epoch": 0.3672044305321454,
2402
- "grad_norm": 6.84375,
2403
- "learning_rate": 9.91643349343652e-05,
2404
- "loss": 0.6947,
2405
- "step": 3050
2406
- },
2407
- {
2408
- "epoch": 0.36840837948470984,
2409
- "grad_norm": 5.25,
2410
- "learning_rate": 9.914837198728733e-05,
2411
- "loss": 0.5273,
2412
- "step": 3060
2413
- },
2414
- {
2415
- "epoch": 0.36961232843727426,
2416
- "grad_norm": 6.25,
2417
- "learning_rate": 9.913225932574486e-05,
2418
- "loss": 0.655,
2419
- "step": 3070
2420
- },
2421
- {
2422
- "epoch": 0.3708162773898387,
2423
- "grad_norm": 6.46875,
2424
- "learning_rate": 9.911599699881974e-05,
2425
- "loss": 0.659,
2426
- "step": 3080
2427
- },
2428
- {
2429
- "epoch": 0.37202022634240306,
2430
- "grad_norm": 5.09375,
2431
- "learning_rate": 9.909958505604984e-05,
2432
- "loss": 0.6164,
2433
- "step": 3090
2434
- },
2435
- {
2436
- "epoch": 0.3732241752949675,
2437
- "grad_norm": 5.90625,
2438
- "learning_rate": 9.908302354742878e-05,
2439
- "loss": 0.6318,
2440
- "step": 3100
2441
- },
2442
- {
2443
- "epoch": 0.3744281242475319,
2444
- "grad_norm": 3.859375,
2445
- "learning_rate": 9.906631252340578e-05,
2446
- "loss": 0.541,
2447
- "step": 3110
2448
- },
2449
- {
2450
- "epoch": 0.37563207320009634,
2451
- "grad_norm": 5.40625,
2452
- "learning_rate": 9.904945203488554e-05,
2453
- "loss": 0.5854,
2454
- "step": 3120
2455
- },
2456
- {
2457
- "epoch": 0.3768360221526607,
2458
- "grad_norm": 5.6875,
2459
- "learning_rate": 9.903244213322802e-05,
2460
- "loss": 0.6657,
2461
- "step": 3130
2462
- },
2463
- {
2464
- "epoch": 0.37803997110522514,
2465
- "grad_norm": 5.78125,
2466
- "learning_rate": 9.901528287024833e-05,
2467
- "loss": 0.5835,
2468
- "step": 3140
2469
- },
2470
- {
2471
- "epoch": 0.37924392005778956,
2472
- "grad_norm": 4.875,
2473
- "learning_rate": 9.899797429821656e-05,
2474
- "loss": 0.6369,
2475
- "step": 3150
2476
- },
2477
- {
2478
- "epoch": 0.38044786901035393,
2479
- "grad_norm": 5.84375,
2480
- "learning_rate": 9.898051646985762e-05,
2481
- "loss": 0.5991,
2482
- "step": 3160
2483
- },
2484
- {
2485
- "epoch": 0.38165181796291836,
2486
- "grad_norm": 5.3125,
2487
- "learning_rate": 9.896290943835109e-05,
2488
- "loss": 0.5792,
2489
- "step": 3170
2490
- },
2491
- {
2492
- "epoch": 0.3828557669154828,
2493
- "grad_norm": 4.34375,
2494
- "learning_rate": 9.894515325733103e-05,
2495
- "loss": 0.635,
2496
- "step": 3180
2497
- },
2498
- {
2499
- "epoch": 0.3840597158680472,
2500
- "grad_norm": 3.859375,
2501
- "learning_rate": 9.892724798088586e-05,
2502
- "loss": 0.7034,
2503
- "step": 3190
2504
- },
2505
- {
2506
- "epoch": 0.3852636648206116,
2507
- "grad_norm": 5.03125,
2508
- "learning_rate": 9.890919366355816e-05,
2509
- "loss": 0.658,
2510
- "step": 3200
2511
- },
2512
- {
2513
- "epoch": 0.386467613773176,
2514
- "grad_norm": 5.1875,
2515
- "learning_rate": 9.889099036034451e-05,
2516
- "loss": 0.5952,
2517
- "step": 3210
2518
- },
2519
- {
2520
- "epoch": 0.38767156272574044,
2521
- "grad_norm": 5.46875,
2522
- "learning_rate": 9.88726381266953e-05,
2523
- "loss": 0.6666,
2524
- "step": 3220
2525
- },
2526
- {
2527
- "epoch": 0.38887551167830486,
2528
- "grad_norm": 5.5,
2529
- "learning_rate": 9.885413701851464e-05,
2530
- "loss": 0.7236,
2531
- "step": 3230
2532
- },
2533
- {
2534
- "epoch": 0.39007946063086923,
2535
- "grad_norm": 5.4375,
2536
- "learning_rate": 9.883548709216013e-05,
2537
- "loss": 0.6152,
2538
- "step": 3240
2539
- },
2540
- {
2541
- "epoch": 0.39128340958343366,
2542
- "grad_norm": 5.71875,
2543
- "learning_rate": 9.881668840444265e-05,
2544
- "loss": 0.6167,
2545
- "step": 3250
2546
- },
2547
- {
2548
- "epoch": 0.3924873585359981,
2549
- "grad_norm": 4.46875,
2550
- "learning_rate": 9.879774101262627e-05,
2551
- "loss": 0.5904,
2552
- "step": 3260
2553
- },
2554
- {
2555
- "epoch": 0.39369130748856246,
2556
- "grad_norm": 4.0,
2557
- "learning_rate": 9.877864497442804e-05,
2558
- "loss": 0.5288,
2559
- "step": 3270
2560
- },
2561
- {
2562
- "epoch": 0.3948952564411269,
2563
- "grad_norm": 5.25,
2564
- "learning_rate": 9.87594003480178e-05,
2565
- "loss": 0.6141,
2566
- "step": 3280
2567
- },
2568
- {
2569
- "epoch": 0.3960992053936913,
2570
- "grad_norm": 6.0625,
2571
- "learning_rate": 9.874000719201804e-05,
2572
- "loss": 0.7486,
2573
- "step": 3290
2574
- },
2575
- {
2576
- "epoch": 0.39730315434625574,
2577
- "grad_norm": 5.1875,
2578
- "learning_rate": 9.872046556550363e-05,
2579
- "loss": 0.6557,
2580
- "step": 3300
2581
- },
2582
- {
2583
- "epoch": 0.3985071032988201,
2584
- "grad_norm": 5.25,
2585
- "learning_rate": 9.870077552800179e-05,
2586
- "loss": 0.6125,
2587
- "step": 3310
2588
- },
2589
- {
2590
- "epoch": 0.39971105225138454,
2591
- "grad_norm": 5.0625,
2592
- "learning_rate": 9.868093713949178e-05,
2593
- "loss": 0.5268,
2594
- "step": 3320
2595
- },
2596
- {
2597
- "epoch": 0.40091500120394896,
2598
- "grad_norm": 4.96875,
2599
- "learning_rate": 9.866095046040478e-05,
2600
- "loss": 0.6483,
2601
- "step": 3330
2602
- },
2603
- {
2604
- "epoch": 0.4021189501565134,
2605
- "grad_norm": 4.90625,
2606
- "learning_rate": 9.864081555162366e-05,
2607
- "loss": 0.7377,
2608
- "step": 3340
2609
- },
2610
- {
2611
- "epoch": 0.40332289910907776,
2612
- "grad_norm": 5.34375,
2613
- "learning_rate": 9.862053247448286e-05,
2614
- "loss": 0.5641,
2615
- "step": 3350
2616
- },
2617
- {
2618
- "epoch": 0.4045268480616422,
2619
- "grad_norm": 4.5625,
2620
- "learning_rate": 9.860010129076813e-05,
2621
- "loss": 0.6322,
2622
- "step": 3360
2623
- },
2624
- {
2625
- "epoch": 0.4057307970142066,
2626
- "grad_norm": 5.25,
2627
- "learning_rate": 9.857952206271643e-05,
2628
- "loss": 0.614,
2629
- "step": 3370
2630
- },
2631
- {
2632
- "epoch": 0.406934745966771,
2633
- "grad_norm": 5.3125,
2634
- "learning_rate": 9.855879485301564e-05,
2635
- "loss": 0.5311,
2636
- "step": 3380
2637
- },
2638
- {
2639
- "epoch": 0.4081386949193354,
2640
- "grad_norm": 4.46875,
2641
- "learning_rate": 9.853791972480445e-05,
2642
- "loss": 0.6266,
2643
- "step": 3390
2644
- },
2645
- {
2646
- "epoch": 0.40934264387189984,
2647
- "grad_norm": 5.40625,
2648
- "learning_rate": 9.85168967416721e-05,
2649
- "loss": 0.5445,
2650
- "step": 3400
2651
- },
2652
- {
2653
- "epoch": 0.41054659282446426,
2654
- "grad_norm": 5.1875,
2655
- "learning_rate": 9.849572596765826e-05,
2656
- "loss": 0.6219,
2657
- "step": 3410
2658
- },
2659
- {
2660
- "epoch": 0.41175054177702863,
2661
- "grad_norm": 6.0,
2662
- "learning_rate": 9.847440746725275e-05,
2663
- "loss": 0.6091,
2664
- "step": 3420
2665
- },
2666
- {
2667
- "epoch": 0.41295449072959306,
2668
- "grad_norm": 6.03125,
2669
- "learning_rate": 9.845294130539546e-05,
2670
- "loss": 0.5503,
2671
- "step": 3430
2672
- },
2673
- {
2674
- "epoch": 0.4141584396821575,
2675
- "grad_norm": 3.953125,
2676
- "learning_rate": 9.8431327547476e-05,
2677
- "loss": 0.5049,
2678
- "step": 3440
2679
- },
2680
- {
2681
- "epoch": 0.4153623886347219,
2682
- "grad_norm": 4.40625,
2683
- "learning_rate": 9.840956625933367e-05,
2684
- "loss": 0.6165,
2685
- "step": 3450
2686
- },
2687
- {
2688
- "epoch": 0.4165663375872863,
2689
- "grad_norm": 5.78125,
2690
- "learning_rate": 9.838765750725709e-05,
2691
- "loss": 0.6076,
2692
- "step": 3460
2693
- },
2694
- {
2695
- "epoch": 0.4177702865398507,
2696
- "grad_norm": 5.9375,
2697
- "learning_rate": 9.836560135798415e-05,
2698
- "loss": 0.6464,
2699
- "step": 3470
2700
- },
2701
- {
2702
- "epoch": 0.41897423549241514,
2703
- "grad_norm": 4.53125,
2704
- "learning_rate": 9.834339787870166e-05,
2705
- "loss": 0.5661,
2706
- "step": 3480
2707
- },
2708
- {
2709
- "epoch": 0.4201781844449795,
2710
- "grad_norm": 4.25,
2711
- "learning_rate": 9.832104713704531e-05,
2712
- "loss": 0.5922,
2713
- "step": 3490
2714
- },
2715
- {
2716
- "epoch": 0.42138213339754393,
2717
- "grad_norm": 4.40625,
2718
- "learning_rate": 9.829854920109934e-05,
2719
- "loss": 0.5543,
2720
- "step": 3500
2721
- },
2722
- {
2723
- "epoch": 0.42258608235010836,
2724
- "grad_norm": 5.78125,
2725
- "learning_rate": 9.827590413939632e-05,
2726
- "loss": 0.5931,
2727
- "step": 3510
2728
- },
2729
- {
2730
- "epoch": 0.4237900313026728,
2731
- "grad_norm": 5.375,
2732
- "learning_rate": 9.825311202091707e-05,
2733
- "loss": 0.7203,
2734
- "step": 3520
2735
- },
2736
- {
2737
- "epoch": 0.42499398025523716,
2738
- "grad_norm": 5.96875,
2739
- "learning_rate": 9.823017291509034e-05,
2740
- "loss": 0.6172,
2741
- "step": 3530
2742
- },
2743
- {
2744
- "epoch": 0.4261979292078016,
2745
- "grad_norm": 5.71875,
2746
- "learning_rate": 9.820708689179259e-05,
2747
- "loss": 0.5939,
2748
- "step": 3540
2749
- },
2750
- {
2751
- "epoch": 0.427401878160366,
2752
- "grad_norm": 5.71875,
2753
- "learning_rate": 9.818385402134788e-05,
2754
- "loss": 0.5387,
2755
- "step": 3550
2756
- },
2757
- {
2758
- "epoch": 0.42860582711293044,
2759
- "grad_norm": 4.75,
2760
- "learning_rate": 9.816047437452757e-05,
2761
- "loss": 0.6173,
2762
- "step": 3560
2763
- },
2764
- {
2765
- "epoch": 0.4298097760654948,
2766
- "grad_norm": 6.1875,
2767
- "learning_rate": 9.81369480225501e-05,
2768
- "loss": 0.5851,
2769
- "step": 3570
2770
- },
2771
- {
2772
- "epoch": 0.43101372501805923,
2773
- "grad_norm": 5.71875,
2774
- "learning_rate": 9.811327503708081e-05,
2775
- "loss": 0.5655,
2776
- "step": 3580
2777
- },
2778
- {
2779
- "epoch": 0.43221767397062366,
2780
- "grad_norm": 5.09375,
2781
- "learning_rate": 9.808945549023174e-05,
2782
- "loss": 0.5661,
2783
- "step": 3590
2784
- },
2785
- {
2786
- "epoch": 0.43342162292318803,
2787
- "grad_norm": 4.84375,
2788
- "learning_rate": 9.806548945456134e-05,
2789
- "loss": 0.7306,
2790
- "step": 3600
2791
- },
2792
- {
2793
- "epoch": 0.43462557187575246,
2794
- "grad_norm": 3.953125,
2795
- "learning_rate": 9.804137700307434e-05,
2796
- "loss": 0.5806,
2797
- "step": 3610
2798
- },
2799
- {
2800
- "epoch": 0.4358295208283169,
2801
- "grad_norm": 3.765625,
2802
- "learning_rate": 9.801711820922142e-05,
2803
- "loss": 0.6206,
2804
- "step": 3620
2805
- },
2806
- {
2807
- "epoch": 0.4370334697808813,
2808
- "grad_norm": 5.75,
2809
- "learning_rate": 9.799271314689908e-05,
2810
- "loss": 0.6145,
2811
- "step": 3630
2812
- },
2813
- {
2814
- "epoch": 0.4382374187334457,
2815
- "grad_norm": 4.21875,
2816
- "learning_rate": 9.796816189044939e-05,
2817
- "loss": 0.5976,
2818
- "step": 3640
2819
- },
2820
- {
2821
- "epoch": 0.4394413676860101,
2822
- "grad_norm": 4.46875,
2823
- "learning_rate": 9.794346451465972e-05,
2824
- "loss": 0.7035,
2825
- "step": 3650
2826
- },
2827
- {
2828
- "epoch": 0.44064531663857454,
2829
- "grad_norm": 5.96875,
2830
- "learning_rate": 9.791862109476257e-05,
2831
- "loss": 0.5378,
2832
- "step": 3660
2833
- },
2834
- {
2835
- "epoch": 0.44184926559113896,
2836
- "grad_norm": 4.90625,
2837
- "learning_rate": 9.789363170643528e-05,
2838
- "loss": 0.5624,
2839
- "step": 3670
2840
- },
2841
- {
2842
- "epoch": 0.44305321454370333,
2843
- "grad_norm": 4.75,
2844
- "learning_rate": 9.786849642579989e-05,
2845
- "loss": 0.613,
2846
- "step": 3680
2847
- },
2848
- {
2849
- "epoch": 0.44425716349626776,
2850
- "grad_norm": 5.5625,
2851
- "learning_rate": 9.784321532942282e-05,
2852
- "loss": 0.5219,
2853
- "step": 3690
2854
- },
2855
- {
2856
- "epoch": 0.4454611124488322,
2857
- "grad_norm": 4.34375,
2858
- "learning_rate": 9.781778849431464e-05,
2859
- "loss": 0.6854,
2860
- "step": 3700
2861
- },
2862
- {
2863
- "epoch": 0.44666506140139656,
2864
- "grad_norm": 6.40625,
2865
- "learning_rate": 9.779221599792995e-05,
2866
- "loss": 0.5974,
2867
- "step": 3710
2868
- },
2869
- {
2870
- "epoch": 0.447869010353961,
2871
- "grad_norm": 5.96875,
2872
- "learning_rate": 9.776649791816698e-05,
2873
- "loss": 0.6709,
2874
- "step": 3720
2875
- },
2876
- {
2877
- "epoch": 0.4490729593065254,
2878
- "grad_norm": 5.25,
2879
- "learning_rate": 9.774063433336746e-05,
2880
- "loss": 0.6575,
2881
- "step": 3730
2882
- },
2883
- {
2884
- "epoch": 0.45027690825908984,
2885
- "grad_norm": 4.3125,
2886
- "learning_rate": 9.771462532231635e-05,
2887
- "loss": 0.5585,
2888
- "step": 3740
2889
- },
2890
- {
2891
- "epoch": 0.4514808572116542,
2892
- "grad_norm": 4.34375,
2893
- "learning_rate": 9.768847096424164e-05,
2894
- "loss": 0.5921,
2895
- "step": 3750
2896
- },
2897
- {
2898
- "epoch": 0.45268480616421863,
2899
- "grad_norm": 4.96875,
2900
- "learning_rate": 9.7662171338814e-05,
2901
- "loss": 0.5416,
2902
- "step": 3760
2903
- },
2904
- {
2905
- "epoch": 0.45388875511678306,
2906
- "grad_norm": 6.46875,
2907
- "learning_rate": 9.763572652614668e-05,
2908
- "loss": 0.5491,
2909
- "step": 3770
2910
- },
2911
- {
2912
- "epoch": 0.4550927040693475,
2913
- "grad_norm": 4.15625,
2914
- "learning_rate": 9.760913660679515e-05,
2915
- "loss": 0.5819,
2916
- "step": 3780
2917
- },
2918
- {
2919
- "epoch": 0.45629665302191186,
2920
- "grad_norm": 5.75,
2921
- "learning_rate": 9.758240166175692e-05,
2922
- "loss": 0.6891,
2923
- "step": 3790
2924
- },
2925
- {
2926
- "epoch": 0.4575006019744763,
2927
- "grad_norm": 5.28125,
2928
- "learning_rate": 9.755552177247127e-05,
2929
- "loss": 0.631,
2930
- "step": 3800
2931
- },
2932
- {
2933
- "epoch": 0.4587045509270407,
2934
- "grad_norm": 5.25,
2935
- "learning_rate": 9.752849702081901e-05,
2936
- "loss": 0.5935,
2937
- "step": 3810
2938
- },
2939
- {
2940
- "epoch": 0.4599084998796051,
2941
- "grad_norm": 4.3125,
2942
- "learning_rate": 9.750132748912219e-05,
2943
- "loss": 0.5239,
2944
- "step": 3820
2945
- },
2946
- {
2947
- "epoch": 0.4611124488321695,
2948
- "grad_norm": 5.90625,
2949
- "learning_rate": 9.747401326014395e-05,
2950
- "loss": 0.6117,
2951
- "step": 3830
2952
- },
2953
- {
2954
- "epoch": 0.46231639778473393,
2955
- "grad_norm": 5.84375,
2956
- "learning_rate": 9.744655441708818e-05,
2957
- "loss": 0.5105,
2958
- "step": 3840
2959
- },
2960
- {
2961
- "epoch": 0.46352034673729836,
2962
- "grad_norm": 5.96875,
2963
- "learning_rate": 9.741895104359924e-05,
2964
- "loss": 0.5531,
2965
- "step": 3850
2966
- },
2967
- {
2968
- "epoch": 0.46472429568986273,
2969
- "grad_norm": 4.9375,
2970
- "learning_rate": 9.739120322376181e-05,
2971
- "loss": 0.5423,
2972
- "step": 3860
2973
- },
2974
- {
2975
- "epoch": 0.46592824464242716,
2976
- "grad_norm": 4.65625,
2977
- "learning_rate": 9.736331104210056e-05,
2978
- "loss": 0.6987,
2979
- "step": 3870
2980
- },
2981
- {
2982
- "epoch": 0.4671321935949916,
2983
- "grad_norm": 5.0625,
2984
- "learning_rate": 9.733527458357992e-05,
2985
- "loss": 0.6308,
2986
- "step": 3880
2987
- },
2988
- {
2989
- "epoch": 0.468336142547556,
2990
- "grad_norm": 4.1875,
2991
- "learning_rate": 9.730709393360378e-05,
2992
- "loss": 0.6365,
2993
- "step": 3890
2994
- },
2995
- {
2996
- "epoch": 0.4695400915001204,
2997
- "grad_norm": 5.125,
2998
- "learning_rate": 9.72787691780153e-05,
2999
- "loss": 0.6731,
3000
- "step": 3900
3001
- },
3002
- {
3003
- "epoch": 0.4707440404526848,
3004
- "grad_norm": 4.4375,
3005
- "learning_rate": 9.725030040309662e-05,
3006
- "loss": 0.589,
3007
- "step": 3910
3008
- },
3009
- {
3010
- "epoch": 0.47194798940524924,
3011
- "grad_norm": 4.0625,
3012
- "learning_rate": 9.722168769556854e-05,
3013
- "loss": 0.5825,
3014
- "step": 3920
3015
- },
3016
- {
3017
- "epoch": 0.4731519383578136,
3018
- "grad_norm": 6.0,
3019
- "learning_rate": 9.719293114259033e-05,
3020
- "loss": 0.5556,
3021
- "step": 3930
3022
- },
3023
- {
3024
- "epoch": 0.47435588731037803,
3025
- "grad_norm": 6.4375,
3026
- "learning_rate": 9.716403083175946e-05,
3027
- "loss": 0.6386,
3028
- "step": 3940
3029
- },
3030
- {
3031
- "epoch": 0.47555983626294246,
3032
- "grad_norm": 6.34375,
3033
- "learning_rate": 9.713498685111128e-05,
3034
- "loss": 0.6426,
3035
- "step": 3950
3036
- },
3037
- {
3038
- "epoch": 0.4767637852155069,
3039
- "grad_norm": 4.3125,
3040
- "learning_rate": 9.710579928911876e-05,
3041
- "loss": 0.5251,
3042
- "step": 3960
3043
- },
3044
- {
3045
- "epoch": 0.47796773416807126,
3046
- "grad_norm": 5.46875,
3047
- "learning_rate": 9.707646823469232e-05,
3048
- "loss": 0.5381,
3049
- "step": 3970
3050
- },
3051
- {
3052
- "epoch": 0.4791716831206357,
3053
- "grad_norm": 5.5625,
3054
- "learning_rate": 9.704699377717941e-05,
3055
- "loss": 0.6042,
3056
- "step": 3980
3057
- },
3058
- {
3059
- "epoch": 0.4803756320732001,
3060
- "grad_norm": 5.6875,
3061
- "learning_rate": 9.701737600636436e-05,
3062
- "loss": 0.5149,
3063
- "step": 3990
3064
- },
3065
- {
3066
- "epoch": 0.4815795810257645,
3067
- "grad_norm": 4.5625,
3068
- "learning_rate": 9.698761501246801e-05,
3069
- "loss": 0.4981,
3070
- "step": 4000
3071
- },
3072
- {
3073
- "epoch": 0.4815795810257645,
3074
- "eval/nano_beir.arguana": 0.4533164648115519,
3075
- "step": 4000
3076
- },
3077
- {
3078
- "epoch": 0.4815795810257645,
3079
- "eval/nano_beir.climate_fever": 0.2415330766300153,
3080
- "step": 4000
3081
- },
3082
- {
3083
- "epoch": 0.4815795810257645,
3084
- "eval/nano_beir.dbpedia_entity": 0.3267307232969415,
3085
- "step": 4000
3086
- },
3087
- {
3088
- "epoch": 0.4815795810257645,
3089
- "eval/nano_beir.fever": 0.6627993781769471,
3090
- "step": 4000
3091
- },
3092
- {
3093
- "epoch": 0.4815795810257645,
3094
- "eval/nano_beir.fiqa": 0.44257400247946427,
3095
- "step": 4000
3096
- },
3097
- {
3098
- "epoch": 0.4815795810257645,
3099
- "eval/nano_beir.hotpotqa": 0.6918069318835383,
3100
- "step": 4000
3101
- },
3102
- {
3103
- "epoch": 0.4815795810257645,
3104
- "eval/nano_beir.nfcorpus": 0.34324706059190796,
3105
- "step": 4000
3106
- },
3107
- {
3108
- "epoch": 0.4815795810257645,
3109
- "eval/nano_beir.nq": 0.43319148909889377,
3110
- "step": 4000
3111
- },
3112
- {
3113
- "epoch": 0.4815795810257645,
3114
- "eval/nano_beir.quora": 0.8358698300981718,
3115
- "step": 4000
3116
- },
3117
- {
3118
- "epoch": 0.4815795810257645,
3119
- "eval/nano_beir.scidocs": 0.25506900118184184,
3120
- "step": 4000
3121
- },
3122
- {
3123
- "epoch": 0.4815795810257645,
3124
- "eval/nano_beir.scifact": 0.7542598352338724,
3125
- "step": 4000
3126
- },
3127
- {
3128
- "epoch": 0.4815795810257645,
3129
- "eval/nano_beir.webis_touche2020": 0.2901138539973763,
3130
- "step": 4000
3131
- },
3132
- {
3133
- "epoch": 0.4815795810257645,
3134
- "eval/avg": 0.47754263729004354,
3135
- "step": 4000
3136
- },
3137
- {
3138
- "epoch": 0.4827835299783289,
3139
- "grad_norm": 5.0,
3140
- "learning_rate": 9.695771088614753e-05,
3141
- "loss": 0.6134,
3142
- "step": 4010
3143
- },
3144
- {
3145
- "epoch": 0.48398747893089333,
3146
- "grad_norm": 4.40625,
3147
- "learning_rate": 9.692766371849606e-05,
3148
- "loss": 0.5217,
3149
- "step": 4020
3150
- },
3151
- {
3152
- "epoch": 0.48519142788345776,
3153
- "grad_norm": 4.875,
3154
- "learning_rate": 9.689747360104252e-05,
3155
- "loss": 0.6753,
3156
- "step": 4030
3157
- },
3158
- {
3159
- "epoch": 0.48639537683602213,
3160
- "grad_norm": 4.53125,
3161
- "learning_rate": 9.686714062575118e-05,
3162
- "loss": 0.5712,
3163
- "step": 4040
3164
- },
3165
- {
3166
- "epoch": 0.48759932578858656,
3167
- "grad_norm": 4.75,
3168
- "learning_rate": 9.683666488502158e-05,
3169
- "loss": 0.5574,
3170
- "step": 4050
3171
- },
3172
- {
3173
- "epoch": 0.488803274741151,
3174
- "grad_norm": 5.125,
3175
- "learning_rate": 9.680604647168813e-05,
3176
- "loss": 0.6066,
3177
- "step": 4060
3178
- },
3179
- {
3180
- "epoch": 0.4900072236937154,
3181
- "grad_norm": 5.21875,
3182
- "learning_rate": 9.677528547901981e-05,
3183
- "loss": 0.5138,
3184
- "step": 4070
3185
- },
3186
- {
3187
- "epoch": 0.4912111726462798,
3188
- "grad_norm": 3.671875,
3189
- "learning_rate": 9.674438200071991e-05,
3190
- "loss": 0.5157,
3191
- "step": 4080
3192
- },
3193
- {
3194
- "epoch": 0.4924151215988442,
3195
- "grad_norm": 4.84375,
3196
- "learning_rate": 9.671333613092583e-05,
3197
- "loss": 0.5865,
3198
- "step": 4090
3199
- },
3200
- {
3201
- "epoch": 0.49361907055140863,
3202
- "grad_norm": 6.4375,
3203
- "learning_rate": 9.668214796420866e-05,
3204
- "loss": 0.5833,
3205
- "step": 4100
3206
- },
3207
- {
3208
- "epoch": 0.494823019503973,
3209
- "grad_norm": 6.09375,
3210
- "learning_rate": 9.665081759557295e-05,
3211
- "loss": 0.5759,
3212
- "step": 4110
3213
- },
3214
- {
3215
- "epoch": 0.49602696845653743,
3216
- "grad_norm": 5.8125,
3217
- "learning_rate": 9.661934512045644e-05,
3218
- "loss": 0.5217,
3219
- "step": 4120
3220
- },
3221
- {
3222
- "epoch": 0.49723091740910186,
3223
- "grad_norm": 6.0625,
3224
- "learning_rate": 9.658773063472975e-05,
3225
- "loss": 0.6464,
3226
- "step": 4130
3227
- },
3228
- {
3229
- "epoch": 0.4984348663616663,
3230
- "grad_norm": 5.09375,
3231
- "learning_rate": 9.655597423469609e-05,
3232
- "loss": 0.5918,
3233
- "step": 4140
3234
- },
3235
- {
3236
- "epoch": 0.49963881531423066,
3237
- "grad_norm": 5.5625,
3238
- "learning_rate": 9.652407601709096e-05,
3239
- "loss": 0.5892,
3240
- "step": 4150
3241
- },
3242
- {
3243
- "epoch": 0.5008427642667951,
3244
- "grad_norm": 6.0625,
3245
- "learning_rate": 9.649203607908187e-05,
3246
- "loss": 0.6439,
3247
- "step": 4160
3248
- },
3249
- {
3250
- "epoch": 0.5020467132193595,
3251
- "grad_norm": 5.09375,
3252
- "learning_rate": 9.645985451826803e-05,
3253
- "loss": 0.5668,
3254
- "step": 4170
3255
- },
3256
- {
3257
- "epoch": 0.5032506621719239,
3258
- "grad_norm": 5.28125,
3259
- "learning_rate": 9.642753143268002e-05,
3260
- "loss": 0.6326,
3261
- "step": 4180
3262
- },
3263
- {
3264
- "epoch": 0.5044546111244883,
3265
- "grad_norm": 5.28125,
3266
- "learning_rate": 9.63950669207796e-05,
3267
- "loss": 0.561,
3268
- "step": 4190
3269
- },
3270
- {
3271
- "epoch": 0.5056585600770528,
3272
- "grad_norm": 6.4375,
3273
- "learning_rate": 9.636246108145929e-05,
3274
- "loss": 0.6184,
3275
- "step": 4200
3276
- },
3277
- {
3278
- "epoch": 0.5068625090296172,
3279
- "grad_norm": 5.09375,
3280
- "learning_rate": 9.632971401404214e-05,
3281
- "loss": 0.5612,
3282
- "step": 4210
3283
- },
3284
- {
3285
- "epoch": 0.5080664579821815,
3286
- "grad_norm": 6.21875,
3287
- "learning_rate": 9.62968258182814e-05,
3288
- "loss": 0.6528,
3289
- "step": 4220
3290
- },
3291
- {
3292
- "epoch": 0.509270406934746,
3293
- "grad_norm": 5.53125,
3294
- "learning_rate": 9.626379659436017e-05,
3295
- "loss": 0.6768,
3296
- "step": 4230
3297
- },
3298
- {
3299
- "epoch": 0.5104743558873104,
3300
- "grad_norm": 3.75,
3301
- "learning_rate": 9.623062644289127e-05,
3302
- "loss": 0.5089,
3303
- "step": 4240
3304
- },
3305
- {
3306
- "epoch": 0.5116783048398748,
3307
- "grad_norm": 6.1875,
3308
- "learning_rate": 9.61973154649167e-05,
3309
- "loss": 0.5932,
3310
- "step": 4250
3311
- },
3312
- {
3313
- "epoch": 0.5128822537924392,
3314
- "grad_norm": 5.28125,
3315
- "learning_rate": 9.616386376190745e-05,
3316
- "loss": 0.6448,
3317
- "step": 4260
3318
- },
3319
- {
3320
- "epoch": 0.5140862027450036,
3321
- "grad_norm": 5.75,
3322
- "learning_rate": 9.613027143576325e-05,
3323
- "loss": 0.5775,
3324
- "step": 4270
3325
- },
3326
- {
3327
- "epoch": 0.515290151697568,
3328
- "grad_norm": 3.625,
3329
- "learning_rate": 9.609653858881211e-05,
3330
- "loss": 0.5966,
3331
- "step": 4280
3332
- },
3333
- {
3334
- "epoch": 0.5164941006501325,
3335
- "grad_norm": 5.28125,
3336
- "learning_rate": 9.606266532381018e-05,
3337
- "loss": 0.5776,
3338
- "step": 4290
3339
- },
3340
- {
3341
- "epoch": 0.5176980496026968,
3342
- "grad_norm": 5.875,
3343
- "learning_rate": 9.602865174394127e-05,
3344
- "loss": 0.5759,
3345
- "step": 4300
3346
- },
3347
- {
3348
- "epoch": 0.5189019985552613,
3349
- "grad_norm": 4.5625,
3350
- "learning_rate": 9.599449795281662e-05,
3351
- "loss": 0.6263,
3352
- "step": 4310
3353
- },
3354
- {
3355
- "epoch": 0.5201059475078257,
3356
- "grad_norm": 4.34375,
3357
- "learning_rate": 9.596020405447466e-05,
3358
- "loss": 0.578,
3359
- "step": 4320
3360
- },
3361
- {
3362
- "epoch": 0.52130989646039,
3363
- "grad_norm": 5.71875,
3364
- "learning_rate": 9.592577015338051e-05,
3365
- "loss": 0.5554,
3366
- "step": 4330
3367
- },
3368
- {
3369
- "epoch": 0.5225138454129545,
3370
- "grad_norm": 5.78125,
3371
- "learning_rate": 9.589119635442582e-05,
3372
- "loss": 0.6189,
3373
- "step": 4340
3374
- },
3375
- {
3376
- "epoch": 0.5237177943655189,
3377
- "grad_norm": 4.4375,
3378
- "learning_rate": 9.585648276292836e-05,
3379
- "loss": 0.6218,
3380
- "step": 4350
3381
- },
3382
- {
3383
- "epoch": 0.5249217433180833,
3384
- "grad_norm": 5.25,
3385
- "learning_rate": 9.582162948463177e-05,
3386
- "loss": 0.5972,
3387
- "step": 4360
3388
- },
3389
- {
3390
- "epoch": 0.5261256922706478,
3391
- "grad_norm": 5.96875,
3392
- "learning_rate": 9.578663662570518e-05,
3393
- "loss": 0.6237,
3394
- "step": 4370
3395
- },
3396
- {
3397
- "epoch": 0.5273296412232121,
3398
- "grad_norm": 5.03125,
3399
- "learning_rate": 9.575150429274287e-05,
3400
- "loss": 0.5754,
3401
- "step": 4380
3402
- },
3403
- {
3404
- "epoch": 0.5285335901757765,
3405
- "grad_norm": 3.46875,
3406
- "learning_rate": 9.571623259276408e-05,
3407
- "loss": 0.5525,
3408
- "step": 4390
3409
- },
3410
- {
3411
- "epoch": 0.529737539128341,
3412
- "grad_norm": 3.84375,
3413
- "learning_rate": 9.568082163321247e-05,
3414
- "loss": 0.5924,
3415
- "step": 4400
3416
- },
3417
- {
3418
- "epoch": 0.5309414880809054,
3419
- "grad_norm": 4.1875,
3420
- "learning_rate": 9.5645271521956e-05,
3421
- "loss": 0.5747,
3422
- "step": 4410
3423
- },
3424
- {
3425
- "epoch": 0.5321454370334697,
3426
- "grad_norm": 5.0625,
3427
- "learning_rate": 9.560958236728646e-05,
3428
- "loss": 0.681,
3429
- "step": 4420
3430
- },
3431
- {
3432
- "epoch": 0.5333493859860342,
3433
- "grad_norm": 5.03125,
3434
- "learning_rate": 9.557375427791919e-05,
3435
- "loss": 0.5728,
3436
- "step": 4430
3437
- },
3438
- {
3439
- "epoch": 0.5345533349385986,
3440
- "grad_norm": 4.75,
3441
- "learning_rate": 9.553778736299279e-05,
3442
- "loss": 0.5402,
3443
- "step": 4440
3444
- },
3445
- {
3446
- "epoch": 0.5357572838911631,
3447
- "grad_norm": 5.375,
3448
- "learning_rate": 9.550168173206873e-05,
3449
- "loss": 0.6011,
3450
- "step": 4450
3451
- },
3452
- {
3453
- "epoch": 0.5369612328437274,
3454
- "grad_norm": 4.84375,
3455
- "learning_rate": 9.546543749513096e-05,
3456
- "loss": 0.6079,
3457
- "step": 4460
3458
- },
3459
- {
3460
- "epoch": 0.5381651817962918,
3461
- "grad_norm": 4.375,
3462
- "learning_rate": 9.54290547625858e-05,
3463
- "loss": 0.6335,
3464
- "step": 4470
3465
- },
3466
- {
3467
- "epoch": 0.5393691307488563,
3468
- "grad_norm": 4.5625,
3469
- "learning_rate": 9.539253364526128e-05,
3470
- "loss": 0.6007,
3471
- "step": 4480
3472
- },
3473
- {
3474
- "epoch": 0.5405730797014207,
3475
- "grad_norm": 4.40625,
3476
- "learning_rate": 9.535587425440712e-05,
3477
- "loss": 0.5092,
3478
- "step": 4490
3479
- },
3480
- {
3481
- "epoch": 0.541777028653985,
3482
- "grad_norm": 3.671875,
3483
- "learning_rate": 9.531907670169415e-05,
3484
- "loss": 0.5609,
3485
- "step": 4500
3486
- },
3487
- {
3488
- "epoch": 0.5429809776065495,
3489
- "grad_norm": 5.3125,
3490
- "learning_rate": 9.52821410992141e-05,
3491
- "loss": 0.5731,
3492
- "step": 4510
3493
- },
3494
- {
3495
- "epoch": 0.5441849265591139,
3496
- "grad_norm": 5.6875,
3497
- "learning_rate": 9.524506755947921e-05,
3498
- "loss": 0.6179,
3499
- "step": 4520
3500
- },
3501
- {
3502
- "epoch": 0.5453888755116783,
3503
- "grad_norm": 3.640625,
3504
- "learning_rate": 9.520785619542196e-05,
3505
- "loss": 0.5156,
3506
- "step": 4530
3507
- },
3508
- {
3509
- "epoch": 0.5465928244642427,
3510
- "grad_norm": 5.46875,
3511
- "learning_rate": 9.517050712039456e-05,
3512
- "loss": 0.6161,
3513
- "step": 4540
3514
- },
3515
- {
3516
- "epoch": 0.5477967734168071,
3517
- "grad_norm": 4.46875,
3518
- "learning_rate": 9.51330204481688e-05,
3519
- "loss": 0.5739,
3520
- "step": 4550
3521
- },
3522
- {
3523
- "epoch": 0.5490007223693716,
3524
- "grad_norm": 5.3125,
3525
- "learning_rate": 9.509539629293558e-05,
3526
- "loss": 0.6028,
3527
- "step": 4560
3528
- },
3529
- {
3530
- "epoch": 0.550204671321936,
3531
- "grad_norm": 5.0625,
3532
- "learning_rate": 9.50576347693046e-05,
3533
- "loss": 0.6909,
3534
- "step": 4570
3535
- },
3536
- {
3537
- "epoch": 0.5514086202745003,
3538
- "grad_norm": 3.703125,
3539
- "learning_rate": 9.5019735992304e-05,
3540
- "loss": 0.6186,
3541
- "step": 4580
3542
- },
3543
- {
3544
- "epoch": 0.5526125692270648,
3545
- "grad_norm": 4.0625,
3546
- "learning_rate": 9.498170007738005e-05,
3547
- "loss": 0.5563,
3548
- "step": 4590
3549
- },
3550
- {
3551
- "epoch": 0.5538165181796292,
3552
- "grad_norm": 4.09375,
3553
- "learning_rate": 9.494352714039674e-05,
3554
- "loss": 0.535,
3555
- "step": 4600
3556
- },
3557
- {
3558
- "epoch": 0.5550204671321936,
3559
- "grad_norm": 4.46875,
3560
- "learning_rate": 9.490521729763542e-05,
3561
- "loss": 0.5516,
3562
- "step": 4610
3563
- },
3564
- {
3565
- "epoch": 0.556224416084758,
3566
- "grad_norm": 4.40625,
3567
- "learning_rate": 9.486677066579456e-05,
3568
- "loss": 0.6259,
3569
- "step": 4620
3570
- },
3571
- {
3572
- "epoch": 0.5574283650373224,
3573
- "grad_norm": 4.78125,
3574
- "learning_rate": 9.482818736198925e-05,
3575
- "loss": 0.5551,
3576
- "step": 4630
3577
- },
3578
- {
3579
- "epoch": 0.5586323139898868,
3580
- "grad_norm": 5.28125,
3581
- "learning_rate": 9.478946750375092e-05,
3582
- "loss": 0.6171,
3583
- "step": 4640
3584
- },
3585
- {
3586
- "epoch": 0.5598362629424513,
3587
- "grad_norm": 5.40625,
3588
- "learning_rate": 9.475061120902698e-05,
3589
- "loss": 0.5887,
3590
- "step": 4650
3591
- },
3592
- {
3593
- "epoch": 0.5610402118950156,
3594
- "grad_norm": 5.6875,
3595
- "learning_rate": 9.471161859618045e-05,
3596
- "loss": 0.5992,
3597
- "step": 4660
3598
- },
3599
- {
3600
- "epoch": 0.5622441608475801,
3601
- "grad_norm": 4.9375,
3602
- "learning_rate": 9.467248978398957e-05,
3603
- "loss": 0.61,
3604
- "step": 4670
3605
- },
3606
- {
3607
- "epoch": 0.5634481098001445,
3608
- "grad_norm": 5.53125,
3609
- "learning_rate": 9.46332248916475e-05,
3610
- "loss": 0.5746,
3611
- "step": 4680
3612
- },
3613
- {
3614
- "epoch": 0.5646520587527089,
3615
- "grad_norm": 5.75,
3616
- "learning_rate": 9.459382403876192e-05,
3617
- "loss": 0.5999,
3618
- "step": 4690
3619
- },
3620
- {
3621
- "epoch": 0.5658560077052733,
3622
- "grad_norm": 6.28125,
3623
- "learning_rate": 9.455428734535463e-05,
3624
- "loss": 0.5727,
3625
- "step": 4700
3626
- },
3627
- {
3628
- "epoch": 0.5670599566578377,
3629
- "grad_norm": 4.65625,
3630
- "learning_rate": 9.451461493186129e-05,
3631
- "loss": 0.6048,
3632
- "step": 4710
3633
- },
3634
- {
3635
- "epoch": 0.5682639056104021,
3636
- "grad_norm": 5.125,
3637
- "learning_rate": 9.447480691913094e-05,
3638
- "loss": 0.575,
3639
- "step": 4720
3640
- },
3641
- {
3642
- "epoch": 0.5694678545629666,
3643
- "grad_norm": 5.25,
3644
- "learning_rate": 9.443486342842569e-05,
3645
- "loss": 0.5623,
3646
- "step": 4730
3647
- },
3648
- {
3649
- "epoch": 0.5706718035155309,
3650
- "grad_norm": 5.65625,
3651
- "learning_rate": 9.439478458142033e-05,
3652
- "loss": 0.6507,
3653
- "step": 4740
3654
- },
3655
- {
3656
- "epoch": 0.5718757524680953,
3657
- "grad_norm": 5.53125,
3658
- "learning_rate": 9.435457050020198e-05,
3659
- "loss": 0.6093,
3660
- "step": 4750
3661
- },
3662
- {
3663
- "epoch": 0.5730797014206598,
3664
- "grad_norm": 5.09375,
3665
- "learning_rate": 9.431422130726973e-05,
3666
- "loss": 0.5577,
3667
- "step": 4760
3668
- },
3669
- {
3670
- "epoch": 0.5742836503732242,
3671
- "grad_norm": 4.21875,
3672
- "learning_rate": 9.42737371255342e-05,
3673
- "loss": 0.6243,
3674
- "step": 4770
3675
- },
3676
- {
3677
- "epoch": 0.5754875993257886,
3678
- "grad_norm": 5.625,
3679
- "learning_rate": 9.423311807831723e-05,
3680
- "loss": 0.5395,
3681
- "step": 4780
3682
- },
3683
- {
3684
- "epoch": 0.576691548278353,
3685
- "grad_norm": 6.03125,
3686
- "learning_rate": 9.419236428935147e-05,
3687
- "loss": 0.6082,
3688
- "step": 4790
3689
- },
3690
- {
3691
- "epoch": 0.5778954972309174,
3692
- "grad_norm": 7.4375,
3693
- "learning_rate": 9.415147588278005e-05,
3694
- "loss": 0.6082,
3695
- "step": 4800
3696
- },
3697
- {
3698
- "epoch": 0.5790994461834819,
3699
- "grad_norm": 4.3125,
3700
- "learning_rate": 9.411045298315614e-05,
3701
- "loss": 0.6097,
3702
- "step": 4810
3703
- },
3704
- {
3705
- "epoch": 0.5803033951360462,
3706
- "grad_norm": 4.78125,
3707
- "learning_rate": 9.406929571544261e-05,
3708
- "loss": 0.5135,
3709
- "step": 4820
3710
- },
3711
- {
3712
- "epoch": 0.5815073440886106,
3713
- "grad_norm": 4.40625,
3714
- "learning_rate": 9.402800420501164e-05,
3715
- "loss": 0.5316,
3716
- "step": 4830
3717
- },
3718
- {
3719
- "epoch": 0.5827112930411751,
3720
- "grad_norm": 4.21875,
3721
- "learning_rate": 9.398657857764431e-05,
3722
- "loss": 0.5902,
3723
- "step": 4840
3724
- },
3725
- {
3726
- "epoch": 0.5839152419937395,
3727
- "grad_norm": 5.25,
3728
- "learning_rate": 9.394501895953026e-05,
3729
- "loss": 0.6585,
3730
- "step": 4850
3731
- },
3732
- {
3733
- "epoch": 0.5851191909463038,
3734
- "grad_norm": 5.96875,
3735
- "learning_rate": 9.390332547726733e-05,
3736
- "loss": 0.6581,
3737
- "step": 4860
3738
- },
3739
- {
3740
- "epoch": 0.5863231398988683,
3741
- "grad_norm": 6.53125,
3742
- "learning_rate": 9.386149825786108e-05,
3743
- "loss": 0.6056,
3744
- "step": 4870
3745
- },
3746
- {
3747
- "epoch": 0.5875270888514327,
3748
- "grad_norm": 4.40625,
3749
- "learning_rate": 9.381953742872447e-05,
3750
- "loss": 0.6065,
3751
- "step": 4880
3752
- },
3753
- {
3754
- "epoch": 0.5887310378039972,
3755
- "grad_norm": 4.6875,
3756
- "learning_rate": 9.377744311767746e-05,
3757
- "loss": 0.5369,
3758
- "step": 4890
3759
- },
3760
- {
3761
- "epoch": 0.5899349867565615,
3762
- "grad_norm": 6.4375,
3763
- "learning_rate": 9.373521545294663e-05,
3764
- "loss": 0.5646,
3765
- "step": 4900
3766
- },
3767
- {
3768
- "epoch": 0.5911389357091259,
3769
- "grad_norm": 4.9375,
3770
- "learning_rate": 9.369285456316479e-05,
3771
- "loss": 0.5593,
3772
- "step": 4910
3773
- },
3774
- {
3775
- "epoch": 0.5923428846616904,
3776
- "grad_norm": 5.09375,
3777
- "learning_rate": 9.36503605773705e-05,
3778
- "loss": 0.6057,
3779
- "step": 4920
3780
- },
3781
- {
3782
- "epoch": 0.5935468336142548,
3783
- "grad_norm": 4.40625,
3784
- "learning_rate": 9.360773362500787e-05,
3785
- "loss": 0.532,
3786
- "step": 4930
3787
- },
3788
- {
3789
- "epoch": 0.5947507825668191,
3790
- "grad_norm": 5.71875,
3791
- "learning_rate": 9.356497383592596e-05,
3792
- "loss": 0.5265,
3793
- "step": 4940
3794
- },
3795
- {
3796
- "epoch": 0.5959547315193836,
3797
- "grad_norm": 4.75,
3798
- "learning_rate": 9.352208134037851e-05,
3799
- "loss": 0.5161,
3800
- "step": 4950
3801
- },
3802
- {
3803
- "epoch": 0.597158680471948,
3804
- "grad_norm": 5.90625,
3805
- "learning_rate": 9.347905626902349e-05,
3806
- "loss": 0.5466,
3807
- "step": 4960
3808
- },
3809
- {
3810
- "epoch": 0.5983626294245123,
3811
- "grad_norm": 4.75,
3812
- "learning_rate": 9.343589875292274e-05,
3813
- "loss": 0.5735,
3814
- "step": 4970
3815
- },
3816
- {
3817
- "epoch": 0.5995665783770768,
3818
- "grad_norm": 4.34375,
3819
- "learning_rate": 9.339260892354153e-05,
3820
- "loss": 0.5381,
3821
- "step": 4980
3822
- },
3823
- {
3824
- "epoch": 0.6007705273296412,
3825
- "grad_norm": 5.34375,
3826
- "learning_rate": 9.334918691274818e-05,
3827
- "loss": 0.5387,
3828
- "step": 4990
3829
- },
3830
- {
3831
- "epoch": 0.6019744762822057,
3832
- "grad_norm": 4.84375,
3833
- "learning_rate": 9.330563285281371e-05,
3834
- "loss": 0.5521,
3835
- "step": 5000
3836
- }
3837
- ],
3838
- "logging_steps": 10,
3839
- "max_steps": 20000,
3840
- "num_input_tokens_seen": 0,
3841
- "num_train_epochs": 3,
3842
- "save_steps": 5000,
3843
- "stateful_callbacks": {
3844
- "TrainerControl": {
3845
- "args": {
3846
- "should_epoch_stop": false,
3847
- "should_evaluate": false,
3848
- "should_log": false,
3849
- "should_save": true,
3850
- "should_training_stop": false
3851
- },
3852
- "attributes": {}
3853
- }
3854
- },
3855
- "total_flos": 0.0,
3856
- "train_batch_size": 16,
3857
- "trial_name": null,
3858
- "trial_params": null
3859
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/checkpoint-5000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:205393de77a05f484db2377ef40c55556ef0de4b97d04fcaeb594ddb2a92de2c
3
- size 6033
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/config.json DELETED
@@ -1,45 +0,0 @@
1
- {
2
- "architectures": [
3
- "ModernBertModel"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 50281,
8
- "classifier_activation": "gelu",
9
- "classifier_bias": false,
10
- "classifier_dropout": 0.0,
11
- "classifier_pooling": "mean",
12
- "cls_token_id": 50281,
13
- "decoder_bias": true,
14
- "deterministic_flash_attn": false,
15
- "embedding_dropout": 0.0,
16
- "eos_token_id": 50282,
17
- "global_attn_every_n_layers": 3,
18
- "global_rope_theta": 160000.0,
19
- "gradient_checkpointing": false,
20
- "hidden_activation": "gelu",
21
- "hidden_size": 768,
22
- "initializer_cutoff_factor": 2.0,
23
- "initializer_range": 0.02,
24
- "intermediate_size": 1152,
25
- "layer_norm_eps": 1e-05,
26
- "local_attention": 128,
27
- "local_rope_theta": 10000.0,
28
- "max_position_embeddings": 8192,
29
- "mlp_bias": false,
30
- "mlp_dropout": 0.0,
31
- "model_type": "modernbert",
32
- "norm_bias": false,
33
- "norm_eps": 1e-05,
34
- "num_attention_heads": 12,
35
- "num_hidden_layers": 22,
36
- "pad_token_id": 50283,
37
- "position_embedding_type": "absolute",
38
- "repad_logits_with_grad": false,
39
- "sep_token_id": 50282,
40
- "sparse_pred_ignore_index": -100,
41
- "sparse_prediction": false,
42
- "torch_dtype": "bfloat16",
43
- "transformers_version": "4.53.0",
44
- "vocab_size": 50368
45
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2442b3cc24983ddcf31753c8fa56ab2fad6afb650c632ed25b776997797ed613
3
- size 298041696
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b67a1ed701ca39e8801c50d2e045472cac648267a09099521a862e0bb963eef
3
- size 596170443
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:18bb6b6e7da6250d22c25b95c64287be4aea598d9d97ef67b0fd69b9be869ed7
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cff16289615ba210b601be2162794d1949cb1d62132099a4cf62330c43649a5
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6caa3980c911491b74ec2e96e48a78cd7c3365dd32116c61642a4b6839a2da1
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e93d0d6464a92d227e9235c134b2224cf28ea45ba375cf82e6949c632e2b0d5
3
- size 15365
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/runs/Dec09_23-49-04_nid005106/events.out.tfevents.1765316992.nid005106.127904.0 DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf8a8d73aeaaf6ea133e1fe8d9307045e4b5066f778aed66090980ec0ada69dd
3
- size 459937
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1dc55d852ef70868b0961034622da0948eee9b7cd3b727c465e6777f6956438
3
- size 1465
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/special_tokens_map.json DELETED
@@ -1,37 +0,0 @@
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/tokenizer_config.json DELETED
@@ -1,945 +0,0 @@
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": 1000000000000000019884624838656,
941
- "pad_token": "[PAD]",
942
- "sep_token": "[SEP]",
943
- "tokenizer_class": "PreTrainedTokenizerFast",
944
- "unk_token": "[UNK]"
945
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
modernbert-crux-researchy-flatten.b64_n512.1e-4/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:205393de77a05f484db2377ef40c55556ef0de4b97d04fcaeb594ddb2a92de2c
3
- size 6033