Hugging Face's logo

Spaces:
Fas1
/
capybara_fas_ai
Running

App Files Community
Fas1 commited on
Commit
f278544
·
1 Parent(s): 3825b18

Add Space config for Hugging Face6

Browse files
Files changed (35) hide show
  1. .DS_Store +0 -0
  2. capybara-finetuned/.DS_Store +0 -0
  3. capybara-finetuned/adapter_config.json +3 -3
  4. capybara-finetuned/adapter_model.safetensors +1 -1
  5. capybara-finetuned/{checkpoint-193 → checkpoint-1479}/README.md +0 -0
  6. capybara-finetuned/{checkpoint-386 → checkpoint-1479}/adapter_config.json +3 -3
  7. capybara-finetuned/{checkpoint-386 → checkpoint-1479}/adapter_model.safetensors +1 -1
  8. capybara-finetuned/{checkpoint-386 → checkpoint-1479}/optimizer.pt +1 -1
  9. capybara-finetuned/{checkpoint-193 → checkpoint-1479}/rng_state.pth +1 -1
  10. capybara-finetuned/{checkpoint-386 → checkpoint-1479}/scaler.pt +1 -1
  11. capybara-finetuned/{checkpoint-386 → checkpoint-1479}/scheduler.pt +1 -1
  12. capybara-finetuned/checkpoint-1479/trainer_state.json +1063 -0
  13. capybara-finetuned/{checkpoint-386 → checkpoint-1479}/training_args.bin +1 -1
  14. capybara-finetuned/checkpoint-193/trainer_state.json +0 -167
  15. capybara-finetuned/checkpoint-386/trainer_state.json +0 -300
  16. capybara-finetuned/{checkpoint-386 → checkpoint-493}/README.md +0 -0
  17. capybara-finetuned/{checkpoint-193 → checkpoint-493}/adapter_config.json +3 -3
  18. capybara-finetuned/{checkpoint-579 → checkpoint-493}/adapter_model.safetensors +1 -1
  19. capybara-finetuned/{checkpoint-579 → checkpoint-493}/optimizer.pt +1 -1
  20. capybara-finetuned/{checkpoint-386 → checkpoint-493}/rng_state.pth +1 -1
  21. capybara-finetuned/{checkpoint-193 → checkpoint-493}/scaler.pt +1 -1
  22. capybara-finetuned/{checkpoint-579 → checkpoint-493}/scheduler.pt +1 -1
  23. capybara-finetuned/checkpoint-493/trainer_state.json +377 -0
  24. capybara-finetuned/{checkpoint-579 → checkpoint-493}/training_args.bin +1 -1
  25. capybara-finetuned/checkpoint-579/trainer_state.json +0 -433
  26. capybara-finetuned/{checkpoint-579 → checkpoint-986}/README.md +0 -0
  27. capybara-finetuned/{checkpoint-579 → checkpoint-986}/adapter_config.json +3 -3
  28. capybara-finetuned/{checkpoint-193 → checkpoint-986}/adapter_model.safetensors +1 -1
  29. capybara-finetuned/{checkpoint-193 → checkpoint-986}/optimizer.pt +1 -1
  30. capybara-finetuned/{checkpoint-579 → checkpoint-986}/rng_state.pth +1 -1
  31. capybara-finetuned/{checkpoint-579 → checkpoint-986}/scaler.pt +1 -1
  32. capybara-finetuned/{checkpoint-193 → checkpoint-986}/scheduler.pt +1 -1
  33. capybara-finetuned/checkpoint-986/trainer_state.json +720 -0
  34. capybara-finetuned/{checkpoint-193 → checkpoint-986}/training_args.bin +1 -1
  35. capybara-finetuned/training_args.bin +1 -1
.DS_Store CHANGED
Binary files a/.DS_Store and b/.DS_Store differ
 
capybara-finetuned/.DS_Store DELETED
Binary file (6.15 kB)
 
capybara-finetuned/adapter_config.json CHANGED
@@ -23,10 +23,10 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "k_proj",
27
- "o_proj",
28
  "q_proj",
29
- "v_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "q_proj",
27
+ "o_proj",
28
+ "v_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
capybara-finetuned/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c3e58810019f8c2423473124d01849395572ed748ab106aff696e68fe511594
3
  size 41977424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d956286b4baf5ad527917ee4315382460a321bc5c35187b469209b71f29584c8
3
  size 41977424
capybara-finetuned/{checkpoint-193 → checkpoint-1479}/README.md RENAMED
File without changes
capybara-finetuned/{checkpoint-386 → checkpoint-1479}/adapter_config.json RENAMED
@@ -23,10 +23,10 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "k_proj",
27
- "o_proj",
28
  "q_proj",
29
- "v_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "q_proj",
27
+ "o_proj",
28
+ "v_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
capybara-finetuned/{checkpoint-386 → checkpoint-1479}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c48baf1611005f53c51a539c229cfaf642e73bf8e0bd31de3a6fdc5137c2bf4
3
  size 41977424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d956286b4baf5ad527917ee4315382460a321bc5c35187b469209b71f29584c8
3
  size 41977424
capybara-finetuned/{checkpoint-386 → checkpoint-1479}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a7ae2f56bbb3d9d1eddcce3fe03c531162565f3bf8fade6f62694e71b727cdd
3
  size 84100858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e9fac9edec8200cf9dd58dc315696cd7f825de37a9a67eadd022f032af8c98
3
  size 84100858
capybara-finetuned/{checkpoint-193 → checkpoint-1479}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5875d8cc785fd3e6c6b01f2be69f2dcb4892851d4e48f50fde2b99e161c32ac5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea8d3323abee0c52f328f1d8230ac754e21c91ae89da92b5d060aef98445862
3
  size 14244
capybara-finetuned/{checkpoint-386 → checkpoint-1479}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:280ca9c9355adf4466a41f2ee36bbca8aa427ac79a7ddbfe9392315c33de41ad
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279ea1725d739ca68aed3759f755c3c7bc8593733e4304533b3e527c8e313468
3
  size 988
capybara-finetuned/{checkpoint-386 → checkpoint-1479}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b59b3a2a0fed8bd1d0e2c1ff88569235401e51bccb1720c6a789060b38d11fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6a4571359d3dd332f354307bc26c3b894989ab83f33243568076b49f114226
3
  size 1064
capybara-finetuned/checkpoint-1479/trainer_state.json ADDED
@@ -0,0 +1,1063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1479,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02028397565922921,
14
+ "grad_norm": 1.1712552309036255,
15
+ "learning_rate": 0.0001993238674780257,
16
+ "loss": 14.4092,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.04056795131845842,
21
+ "grad_norm": 0.48309916257858276,
22
+ "learning_rate": 0.0001979716024340771,
23
+ "loss": 0.2359,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.060851926977687626,
28
+ "grad_norm": 0.2885732352733612,
29
+ "learning_rate": 0.00019661933739012849,
30
+ "loss": 0.1483,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.08113590263691683,
35
+ "grad_norm": 0.2794722318649292,
36
+ "learning_rate": 0.00019526707234617988,
37
+ "loss": 0.1758,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.10141987829614604,
42
+ "grad_norm": 0.21984700858592987,
43
+ "learning_rate": 0.00019391480730223125,
44
+ "loss": 0.248,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.12170385395537525,
49
+ "grad_norm": 0.32381802797317505,
50
+ "learning_rate": 0.00019256254225828262,
51
+ "loss": 0.1618,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.14198782961460446,
56
+ "grad_norm": 0.28723254799842834,
57
+ "learning_rate": 0.00019121027721433401,
58
+ "loss": 0.1171,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.16227180527383367,
63
+ "grad_norm": 0.2172032743692398,
64
+ "learning_rate": 0.0001898580121703854,
65
+ "loss": 0.1621,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.18255578093306288,
70
+ "grad_norm": 0.23619882762432098,
71
+ "learning_rate": 0.00018850574712643678,
72
+ "loss": 0.1198,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.2028397565922921,
77
+ "grad_norm": 0.22938676178455353,
78
+ "learning_rate": 0.00018715348208248818,
79
+ "loss": 0.1546,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2231237322515213,
84
+ "grad_norm": 0.30202436447143555,
85
+ "learning_rate": 0.00018580121703853957,
86
+ "loss": 0.0521,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.2434077079107505,
91
+ "grad_norm": 0.9085210561752319,
92
+ "learning_rate": 0.00018444895199459097,
93
+ "loss": 0.1844,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.26369168356997974,
98
+ "grad_norm": 0.33736127614974976,
99
+ "learning_rate": 0.00018309668695064234,
100
+ "loss": 0.0827,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.2839756592292089,
105
+ "grad_norm": 0.13767044246196747,
106
+ "learning_rate": 0.00018174442190669373,
107
+ "loss": 0.1092,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.30425963488843816,
112
+ "grad_norm": 0.2765495181083679,
113
+ "learning_rate": 0.0001803921568627451,
114
+ "loss": 0.1144,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.32454361054766734,
119
+ "grad_norm": 0.13134893774986267,
120
+ "learning_rate": 0.0001790398918187965,
121
+ "loss": 0.0914,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3448275862068966,
126
+ "grad_norm": 0.15877078473567963,
127
+ "learning_rate": 0.00017768762677484786,
128
+ "loss": 0.0787,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.36511156186612576,
133
+ "grad_norm": 0.11392869800329208,
134
+ "learning_rate": 0.00017633536173089926,
135
+ "loss": 0.0483,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.385395537525355,
140
+ "grad_norm": 0.230561301112175,
141
+ "learning_rate": 0.00017498309668695066,
142
+ "loss": 0.0601,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.4056795131845842,
147
+ "grad_norm": 0.20257052779197693,
148
+ "learning_rate": 0.00017363083164300205,
149
+ "loss": 0.1253,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.4259634888438134,
154
+ "grad_norm": 0.25743618607521057,
155
+ "learning_rate": 0.00017227856659905342,
156
+ "loss": 0.0684,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.4462474645030426,
161
+ "grad_norm": 0.4015647768974304,
162
+ "learning_rate": 0.00017092630155510482,
163
+ "loss": 0.0734,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.4665314401622718,
168
+ "grad_norm": 1.1545509099960327,
169
+ "learning_rate": 0.00016957403651115619,
170
+ "loss": 0.1491,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.486815415821501,
175
+ "grad_norm": 0.3187839984893799,
176
+ "learning_rate": 0.00016822177146720758,
177
+ "loss": 0.101,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5070993914807302,
182
+ "grad_norm": 0.1046043112874031,
183
+ "learning_rate": 0.00016686950642325895,
184
+ "loss": 0.0917,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.5273833671399595,
189
+ "grad_norm": 0.13540491461753845,
190
+ "learning_rate": 0.00016551724137931035,
191
+ "loss": 0.0516,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.5476673427991886,
196
+ "grad_norm": 0.33530837297439575,
197
+ "learning_rate": 0.00016416497633536174,
198
+ "loss": 0.1529,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.5679513184584178,
203
+ "grad_norm": 0.7428917288780212,
204
+ "learning_rate": 0.00016281271129141314,
205
+ "loss": 0.1771,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5882352941176471,
210
+ "grad_norm": 0.11154314875602722,
211
+ "learning_rate": 0.0001614604462474645,
212
+ "loss": 0.0386,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.6085192697768763,
217
+ "grad_norm": 0.09267372637987137,
218
+ "learning_rate": 0.0001601081812035159,
219
+ "loss": 0.0625,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.6288032454361054,
224
+ "grad_norm": 0.24139204621315002,
225
+ "learning_rate": 0.0001587559161595673,
226
+ "loss": 0.1699,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.6490872210953347,
231
+ "grad_norm": 0.6370412111282349,
232
+ "learning_rate": 0.00015740365111561867,
233
+ "loss": 0.1857,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.6693711967545639,
238
+ "grad_norm": 0.07758647203445435,
239
+ "learning_rate": 0.00015605138607167004,
240
+ "loss": 0.1178,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.6896551724137931,
245
+ "grad_norm": 0.2090945690870285,
246
+ "learning_rate": 0.00015469912102772143,
247
+ "loss": 0.1247,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.7099391480730223,
252
+ "grad_norm": 0.24821089208126068,
253
+ "learning_rate": 0.00015334685598377283,
254
+ "loss": 0.1128,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.7302231237322515,
259
+ "grad_norm": 0.123480886220932,
260
+ "learning_rate": 0.00015199459093982422,
261
+ "loss": 0.1625,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.7505070993914807,
266
+ "grad_norm": 0.3176027238368988,
267
+ "learning_rate": 0.0001506423258958756,
268
+ "loss": 0.1215,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.77079107505071,
273
+ "grad_norm": 0.17533642053604126,
274
+ "learning_rate": 0.000149290060851927,
275
+ "loss": 0.1062,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.7910750507099391,
280
+ "grad_norm": 0.2660926878452301,
281
+ "learning_rate": 0.00014793779580797838,
282
+ "loss": 0.0877,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.8113590263691683,
287
+ "grad_norm": 0.5134332180023193,
288
+ "learning_rate": 0.00014658553076402975,
289
+ "loss": 0.0596,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.8316430020283976,
294
+ "grad_norm": 0.09723437577486038,
295
+ "learning_rate": 0.00014523326572008115,
296
+ "loss": 0.0448,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.8519269776876268,
301
+ "grad_norm": 0.40922313928604126,
302
+ "learning_rate": 0.00014388100067613252,
303
+ "loss": 0.0898,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.8722109533468559,
308
+ "grad_norm": 0.14394080638885498,
309
+ "learning_rate": 0.0001425287356321839,
310
+ "loss": 0.1304,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.8924949290060852,
315
+ "grad_norm": 0.578838050365448,
316
+ "learning_rate": 0.0001411764705882353,
317
+ "loss": 0.1038,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.9127789046653144,
322
+ "grad_norm": 0.46690645813941956,
323
+ "learning_rate": 0.00013982420554428668,
324
+ "loss": 0.2278,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.9330628803245437,
329
+ "grad_norm": 0.29226213693618774,
330
+ "learning_rate": 0.00013847194050033807,
331
+ "loss": 0.0747,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.9533468559837728,
336
+ "grad_norm": 0.14866693317890167,
337
+ "learning_rate": 0.00013711967545638947,
338
+ "loss": 0.1133,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.973630831643002,
343
+ "grad_norm": 0.08057406544685364,
344
+ "learning_rate": 0.00013576741041244087,
345
+ "loss": 0.0955,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.9939148073022313,
350
+ "grad_norm": 0.0708722174167633,
351
+ "learning_rate": 0.00013441514536849223,
352
+ "loss": 0.1018,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.0141987829614605,
357
+ "grad_norm": 0.07880403101444244,
358
+ "learning_rate": 0.0001330628803245436,
359
+ "loss": 0.1211,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.0344827586206897,
364
+ "grad_norm": 0.07375513017177582,
365
+ "learning_rate": 0.000131710615280595,
366
+ "loss": 0.0326,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.054766734279919,
371
+ "grad_norm": 0.1140335202217102,
372
+ "learning_rate": 0.0001303583502366464,
373
+ "loss": 0.0457,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.075050709939148,
378
+ "grad_norm": 0.4876038730144501,
379
+ "learning_rate": 0.00012900608519269776,
380
+ "loss": 0.0891,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.0953346855983772,
385
+ "grad_norm": 0.09218205511569977,
386
+ "learning_rate": 0.00012765382014874916,
387
+ "loss": 0.0633,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.1156186612576064,
392
+ "grad_norm": 0.23562578856945038,
393
+ "learning_rate": 0.00012630155510480055,
394
+ "loss": 0.0847,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.1359026369168357,
399
+ "grad_norm": 0.09944804757833481,
400
+ "learning_rate": 0.00012494929006085195,
401
+ "loss": 0.1096,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.156186612576065,
406
+ "grad_norm": 0.08697320520877838,
407
+ "learning_rate": 0.00012359702501690332,
408
+ "loss": 0.1171,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.1764705882352942,
413
+ "grad_norm": 0.34820541739463806,
414
+ "learning_rate": 0.00012224475997295472,
415
+ "loss": 0.0568,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.1967545638945234,
420
+ "grad_norm": 0.06811130791902542,
421
+ "learning_rate": 0.0001208924949290061,
422
+ "loss": 0.0846,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.2170385395537526,
427
+ "grad_norm": 0.3093971610069275,
428
+ "learning_rate": 0.00011954022988505748,
429
+ "loss": 0.1313,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.2373225152129819,
434
+ "grad_norm": 0.15817512571811676,
435
+ "learning_rate": 0.00011818796484110886,
436
+ "loss": 0.0341,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.2576064908722109,
441
+ "grad_norm": 0.6901296973228455,
442
+ "learning_rate": 0.00011683569979716024,
443
+ "loss": 0.1554,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 1.2778904665314401,
448
+ "grad_norm": 0.09194931387901306,
449
+ "learning_rate": 0.00011548343475321164,
450
+ "loss": 0.0733,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 1.2981744421906694,
455
+ "grad_norm": 0.059262920171022415,
456
+ "learning_rate": 0.00011413116970926304,
457
+ "loss": 0.0938,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.3184584178498986,
462
+ "grad_norm": 0.10133162140846252,
463
+ "learning_rate": 0.0001127789046653144,
464
+ "loss": 0.077,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.3387423935091278,
469
+ "grad_norm": 0.653348445892334,
470
+ "learning_rate": 0.00011142663962136579,
471
+ "loss": 0.1019,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.359026369168357,
476
+ "grad_norm": 0.28535157442092896,
477
+ "learning_rate": 0.00011007437457741718,
478
+ "loss": 0.0586,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.3793103448275863,
483
+ "grad_norm": 0.17364345490932465,
484
+ "learning_rate": 0.00010872210953346858,
485
+ "loss": 0.074,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.3995943204868153,
490
+ "grad_norm": 0.7617247700691223,
491
+ "learning_rate": 0.00010736984448951995,
492
+ "loss": 0.0855,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.4198782961460445,
497
+ "grad_norm": 0.2110460251569748,
498
+ "learning_rate": 0.00010601757944557133,
499
+ "loss": 0.1028,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.4401622718052738,
504
+ "grad_norm": 0.2486834079027176,
505
+ "learning_rate": 0.00010466531440162273,
506
+ "loss": 0.0612,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.460446247464503,
511
+ "grad_norm": 0.06596266478300095,
512
+ "learning_rate": 0.00010331304935767412,
513
+ "loss": 0.1176,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.4807302231237323,
518
+ "grad_norm": 0.23579204082489014,
519
+ "learning_rate": 0.00010196078431372549,
520
+ "loss": 0.0426,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.5010141987829615,
525
+ "grad_norm": 0.08997461199760437,
526
+ "learning_rate": 0.00010060851926977689,
527
+ "loss": 0.1211,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.5212981744421907,
532
+ "grad_norm": 0.08905690163373947,
533
+ "learning_rate": 9.925625422582827e-05,
534
+ "loss": 0.0583,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.5415821501014197,
539
+ "grad_norm": 0.16227023303508759,
540
+ "learning_rate": 9.790398918187965e-05,
541
+ "loss": 0.0546,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.5618661257606492,
546
+ "grad_norm": 0.10101054608821869,
547
+ "learning_rate": 9.655172413793105e-05,
548
+ "loss": 0.0993,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.5821501014198782,
553
+ "grad_norm": 0.36903953552246094,
554
+ "learning_rate": 9.519945909398243e-05,
555
+ "loss": 0.0603,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 1.6024340770791075,
560
+ "grad_norm": 0.4635933041572571,
561
+ "learning_rate": 9.384719405003381e-05,
562
+ "loss": 0.0524,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 1.6227180527383367,
567
+ "grad_norm": 0.19389425218105316,
568
+ "learning_rate": 9.24949290060852e-05,
569
+ "loss": 0.0509,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.643002028397566,
574
+ "grad_norm": 0.40768980979919434,
575
+ "learning_rate": 9.114266396213659e-05,
576
+ "loss": 0.045,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.6632860040567952,
581
+ "grad_norm": 0.37976548075675964,
582
+ "learning_rate": 8.979039891818797e-05,
583
+ "loss": 0.0349,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 1.6835699797160242,
588
+ "grad_norm": 0.15103350579738617,
589
+ "learning_rate": 8.843813387423935e-05,
590
+ "loss": 0.0381,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 1.7038539553752536,
595
+ "grad_norm": 0.0796438679099083,
596
+ "learning_rate": 8.708586883029074e-05,
597
+ "loss": 0.1125,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 1.7241379310344827,
602
+ "grad_norm": 0.2372894436120987,
603
+ "learning_rate": 8.573360378634213e-05,
604
+ "loss": 0.0524,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 1.744421906693712,
609
+ "grad_norm": 0.06453035771846771,
610
+ "learning_rate": 8.438133874239351e-05,
611
+ "loss": 0.0628,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 1.7647058823529411,
616
+ "grad_norm": 0.08101903647184372,
617
+ "learning_rate": 8.302907369844491e-05,
618
+ "loss": 0.0932,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 1.7849898580121704,
623
+ "grad_norm": 0.19378355145454407,
624
+ "learning_rate": 8.167680865449628e-05,
625
+ "loss": 0.0514,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 1.8052738336713996,
630
+ "grad_norm": 0.19586940109729767,
631
+ "learning_rate": 8.032454361054767e-05,
632
+ "loss": 0.0883,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 1.8255578093306288,
637
+ "grad_norm": 0.297462522983551,
638
+ "learning_rate": 7.897227856659906e-05,
639
+ "loss": 0.1196,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 1.845841784989858,
644
+ "grad_norm": 0.36705586314201355,
645
+ "learning_rate": 7.762001352265045e-05,
646
+ "loss": 0.0719,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 1.866125760649087,
651
+ "grad_norm": 0.6795341372489929,
652
+ "learning_rate": 7.626774847870182e-05,
653
+ "loss": 0.0981,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 1.8864097363083165,
658
+ "grad_norm": 0.25088199973106384,
659
+ "learning_rate": 7.491548343475322e-05,
660
+ "loss": 0.0941,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 1.9066937119675456,
665
+ "grad_norm": 0.0679168701171875,
666
+ "learning_rate": 7.35632183908046e-05,
667
+ "loss": 0.0841,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.9269776876267748,
672
+ "grad_norm": 0.11561597138643265,
673
+ "learning_rate": 7.2210953346856e-05,
674
+ "loss": 0.046,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.947261663286004,
679
+ "grad_norm": 0.07672413438558578,
680
+ "learning_rate": 7.085868830290738e-05,
681
+ "loss": 0.1174,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.9675456389452333,
686
+ "grad_norm": 0.2567373216152191,
687
+ "learning_rate": 6.950642325895876e-05,
688
+ "loss": 0.0489,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.9878296146044625,
693
+ "grad_norm": 0.2821916937828064,
694
+ "learning_rate": 6.815415821501014e-05,
695
+ "loss": 0.0578,
696
+ "step": 980
697
+ },
698
+ {
699
+ "epoch": 2.0081135902636915,
700
+ "grad_norm": 0.2148137390613556,
701
+ "learning_rate": 6.680189317106154e-05,
702
+ "loss": 0.07,
703
+ "step": 990
704
+ },
705
+ {
706
+ "epoch": 2.028397565922921,
707
+ "grad_norm": 0.5325772762298584,
708
+ "learning_rate": 6.544962812711292e-05,
709
+ "loss": 0.0471,
710
+ "step": 1000
711
+ },
712
+ {
713
+ "epoch": 2.04868154158215,
714
+ "grad_norm": 0.07029282301664352,
715
+ "learning_rate": 6.40973630831643e-05,
716
+ "loss": 0.0348,
717
+ "step": 1010
718
+ },
719
+ {
720
+ "epoch": 2.0689655172413794,
721
+ "grad_norm": 0.7373214364051819,
722
+ "learning_rate": 6.274509803921569e-05,
723
+ "loss": 0.0292,
724
+ "step": 1020
725
+ },
726
+ {
727
+ "epoch": 2.0892494929006085,
728
+ "grad_norm": 0.12320854514837265,
729
+ "learning_rate": 6.139283299526708e-05,
730
+ "loss": 0.0539,
731
+ "step": 1030
732
+ },
733
+ {
734
+ "epoch": 2.109533468559838,
735
+ "grad_norm": 0.33340805768966675,
736
+ "learning_rate": 6.0040567951318463e-05,
737
+ "loss": 0.0642,
738
+ "step": 1040
739
+ },
740
+ {
741
+ "epoch": 2.129817444219067,
742
+ "grad_norm": 0.19844286143779755,
743
+ "learning_rate": 5.868830290736985e-05,
744
+ "loss": 0.088,
745
+ "step": 1050
746
+ },
747
+ {
748
+ "epoch": 2.150101419878296,
749
+ "grad_norm": 0.08252275735139847,
750
+ "learning_rate": 5.7336037863421235e-05,
751
+ "loss": 0.0808,
752
+ "step": 1060
753
+ },
754
+ {
755
+ "epoch": 2.1703853955375254,
756
+ "grad_norm": 0.2959117889404297,
757
+ "learning_rate": 5.5983772819472624e-05,
758
+ "loss": 0.0541,
759
+ "step": 1070
760
+ },
761
+ {
762
+ "epoch": 2.1906693711967544,
763
+ "grad_norm": 0.09467535465955734,
764
+ "learning_rate": 5.4631507775524006e-05,
765
+ "loss": 0.0849,
766
+ "step": 1080
767
+ },
768
+ {
769
+ "epoch": 2.210953346855984,
770
+ "grad_norm": 0.3499992787837982,
771
+ "learning_rate": 5.3279242731575395e-05,
772
+ "loss": 0.0627,
773
+ "step": 1090
774
+ },
775
+ {
776
+ "epoch": 2.231237322515213,
777
+ "grad_norm": 1.0827431678771973,
778
+ "learning_rate": 5.192697768762678e-05,
779
+ "loss": 0.068,
780
+ "step": 1100
781
+ },
782
+ {
783
+ "epoch": 2.2515212981744424,
784
+ "grad_norm": 0.13049522042274475,
785
+ "learning_rate": 5.057471264367817e-05,
786
+ "loss": 0.0465,
787
+ "step": 1110
788
+ },
789
+ {
790
+ "epoch": 2.2718052738336714,
791
+ "grad_norm": 0.34500986337661743,
792
+ "learning_rate": 4.922244759972955e-05,
793
+ "loss": 0.0605,
794
+ "step": 1120
795
+ },
796
+ {
797
+ "epoch": 2.292089249492901,
798
+ "grad_norm": 0.8774737119674683,
799
+ "learning_rate": 4.787018255578094e-05,
800
+ "loss": 0.0548,
801
+ "step": 1130
802
+ },
803
+ {
804
+ "epoch": 2.31237322515213,
805
+ "grad_norm": 0.2063056379556656,
806
+ "learning_rate": 4.651791751183232e-05,
807
+ "loss": 0.0567,
808
+ "step": 1140
809
+ },
810
+ {
811
+ "epoch": 2.332657200811359,
812
+ "grad_norm": 0.17436668276786804,
813
+ "learning_rate": 4.516565246788371e-05,
814
+ "loss": 0.0651,
815
+ "step": 1150
816
+ },
817
+ {
818
+ "epoch": 2.3529411764705883,
819
+ "grad_norm": 0.2623351812362671,
820
+ "learning_rate": 4.381338742393509e-05,
821
+ "loss": 0.0415,
822
+ "step": 1160
823
+ },
824
+ {
825
+ "epoch": 2.3732251521298173,
826
+ "grad_norm": 0.47244420647621155,
827
+ "learning_rate": 4.246112237998648e-05,
828
+ "loss": 0.0572,
829
+ "step": 1170
830
+ },
831
+ {
832
+ "epoch": 2.393509127789047,
833
+ "grad_norm": 0.11136631667613983,
834
+ "learning_rate": 4.110885733603786e-05,
835
+ "loss": 0.0552,
836
+ "step": 1180
837
+ },
838
+ {
839
+ "epoch": 2.413793103448276,
840
+ "grad_norm": 0.08631566911935806,
841
+ "learning_rate": 3.975659229208925e-05,
842
+ "loss": 0.0667,
843
+ "step": 1190
844
+ },
845
+ {
846
+ "epoch": 2.4340770791075053,
847
+ "grad_norm": 0.4146149456501007,
848
+ "learning_rate": 3.8404327248140634e-05,
849
+ "loss": 0.0536,
850
+ "step": 1200
851
+ },
852
+ {
853
+ "epoch": 2.4543610547667343,
854
+ "grad_norm": 0.18690726161003113,
855
+ "learning_rate": 3.7052062204192023e-05,
856
+ "loss": 0.0355,
857
+ "step": 1210
858
+ },
859
+ {
860
+ "epoch": 2.4746450304259637,
861
+ "grad_norm": 0.09517161548137665,
862
+ "learning_rate": 3.5699797160243406e-05,
863
+ "loss": 0.0616,
864
+ "step": 1220
865
+ },
866
+ {
867
+ "epoch": 2.4949290060851927,
868
+ "grad_norm": 0.18913179636001587,
869
+ "learning_rate": 3.4347532116294795e-05,
870
+ "loss": 0.0414,
871
+ "step": 1230
872
+ },
873
+ {
874
+ "epoch": 2.5152129817444218,
875
+ "grad_norm": 0.08904486149549484,
876
+ "learning_rate": 3.2995267072346184e-05,
877
+ "loss": 0.0265,
878
+ "step": 1240
879
+ },
880
+ {
881
+ "epoch": 2.535496957403651,
882
+ "grad_norm": 0.07549070566892624,
883
+ "learning_rate": 3.1643002028397566e-05,
884
+ "loss": 0.0164,
885
+ "step": 1250
886
+ },
887
+ {
888
+ "epoch": 2.5557809330628802,
889
+ "grad_norm": 0.2816295325756073,
890
+ "learning_rate": 3.0290736984448952e-05,
891
+ "loss": 0.0755,
892
+ "step": 1260
893
+ },
894
+ {
895
+ "epoch": 2.5760649087221097,
896
+ "grad_norm": 0.07601668685674667,
897
+ "learning_rate": 2.8938471940500338e-05,
898
+ "loss": 0.0381,
899
+ "step": 1270
900
+ },
901
+ {
902
+ "epoch": 2.5963488843813387,
903
+ "grad_norm": 0.07386976480484009,
904
+ "learning_rate": 2.7586206896551727e-05,
905
+ "loss": 0.0326,
906
+ "step": 1280
907
+ },
908
+ {
909
+ "epoch": 2.6166328600405677,
910
+ "grad_norm": 0.12348837405443192,
911
+ "learning_rate": 2.6233941852603112e-05,
912
+ "loss": 0.0336,
913
+ "step": 1290
914
+ },
915
+ {
916
+ "epoch": 2.636916835699797,
917
+ "grad_norm": 0.09142586588859558,
918
+ "learning_rate": 2.4881676808654498e-05,
919
+ "loss": 0.0637,
920
+ "step": 1300
921
+ },
922
+ {
923
+ "epoch": 2.6572008113590266,
924
+ "grad_norm": 0.09933874011039734,
925
+ "learning_rate": 2.3529411764705884e-05,
926
+ "loss": 0.0356,
927
+ "step": 1310
928
+ },
929
+ {
930
+ "epoch": 2.6774847870182557,
931
+ "grad_norm": 0.07997220754623413,
932
+ "learning_rate": 2.217714672075727e-05,
933
+ "loss": 0.0655,
934
+ "step": 1320
935
+ },
936
+ {
937
+ "epoch": 2.6977687626774847,
938
+ "grad_norm": 0.4215179681777954,
939
+ "learning_rate": 2.0824881676808655e-05,
940
+ "loss": 0.0602,
941
+ "step": 1330
942
+ },
943
+ {
944
+ "epoch": 2.718052738336714,
945
+ "grad_norm": 0.09120413661003113,
946
+ "learning_rate": 1.947261663286004e-05,
947
+ "loss": 0.0466,
948
+ "step": 1340
949
+ },
950
+ {
951
+ "epoch": 2.738336713995943,
952
+ "grad_norm": 0.19115319848060608,
953
+ "learning_rate": 1.8120351588911426e-05,
954
+ "loss": 0.0425,
955
+ "step": 1350
956
+ },
957
+ {
958
+ "epoch": 2.7586206896551726,
959
+ "grad_norm": 0.2734648883342743,
960
+ "learning_rate": 1.6768086544962812e-05,
961
+ "loss": 0.0404,
962
+ "step": 1360
963
+ },
964
+ {
965
+ "epoch": 2.7789046653144016,
966
+ "grad_norm": 0.18521787226200104,
967
+ "learning_rate": 1.5415821501014198e-05,
968
+ "loss": 0.0557,
969
+ "step": 1370
970
+ },
971
+ {
972
+ "epoch": 2.7991886409736306,
973
+ "grad_norm": 0.21627341210842133,
974
+ "learning_rate": 1.4063556457065585e-05,
975
+ "loss": 0.0462,
976
+ "step": 1380
977
+ },
978
+ {
979
+ "epoch": 2.81947261663286,
980
+ "grad_norm": 0.3548518121242523,
981
+ "learning_rate": 1.271129141311697e-05,
982
+ "loss": 0.0365,
983
+ "step": 1390
984
+ },
985
+ {
986
+ "epoch": 2.839756592292089,
987
+ "grad_norm": 0.1926935911178589,
988
+ "learning_rate": 1.1359026369168358e-05,
989
+ "loss": 0.0312,
990
+ "step": 1400
991
+ },
992
+ {
993
+ "epoch": 2.8600405679513186,
994
+ "grad_norm": 0.119568832218647,
995
+ "learning_rate": 1.0006761325219744e-05,
996
+ "loss": 0.0852,
997
+ "step": 1410
998
+ },
999
+ {
1000
+ "epoch": 2.8803245436105476,
1001
+ "grad_norm": 0.13755157589912415,
1002
+ "learning_rate": 8.65449628127113e-06,
1003
+ "loss": 0.0504,
1004
+ "step": 1420
1005
+ },
1006
+ {
1007
+ "epoch": 2.900608519269777,
1008
+ "grad_norm": 0.07374096661806107,
1009
+ "learning_rate": 7.302231237322515e-06,
1010
+ "loss": 0.0477,
1011
+ "step": 1430
1012
+ },
1013
+ {
1014
+ "epoch": 2.920892494929006,
1015
+ "grad_norm": 0.6795891523361206,
1016
+ "learning_rate": 5.949966193373902e-06,
1017
+ "loss": 0.0989,
1018
+ "step": 1440
1019
+ },
1020
+ {
1021
+ "epoch": 2.9411764705882355,
1022
+ "grad_norm": 0.13575242459774017,
1023
+ "learning_rate": 4.5977011494252875e-06,
1024
+ "loss": 0.0635,
1025
+ "step": 1450
1026
+ },
1027
+ {
1028
+ "epoch": 2.9614604462474645,
1029
+ "grad_norm": 0.05683169886469841,
1030
+ "learning_rate": 3.2454361054766736e-06,
1031
+ "loss": 0.0944,
1032
+ "step": 1460
1033
+ },
1034
+ {
1035
+ "epoch": 2.9817444219066935,
1036
+ "grad_norm": 0.07545312494039536,
1037
+ "learning_rate": 1.8931710615280595e-06,
1038
+ "loss": 0.072,
1039
+ "step": 1470
1040
+ }
1041
+ ],
1042
+ "logging_steps": 10,
1043
+ "max_steps": 1479,
1044
+ "num_input_tokens_seen": 0,
1045
+ "num_train_epochs": 3,
1046
+ "save_steps": 500,
1047
+ "stateful_callbacks": {
1048
+ "TrainerControl": {
1049
+ "args": {
1050
+ "should_epoch_stop": false,
1051
+ "should_evaluate": false,
1052
+ "should_log": false,
1053
+ "should_save": true,
1054
+ "should_training_stop": true
1055
+ },
1056
+ "attributes": {}
1057
+ }
1058
+ },
1059
+ "total_flos": 2.432720434102272e+16,
1060
+ "train_batch_size": 1,
1061
+ "trial_name": null,
1062
+ "trial_params": null
1063
+ }
capybara-finetuned/{checkpoint-386 → checkpoint-1479}/training_args.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb5dfa95d8bedc071d0ca429ace88a97d08b4e6c0549993636c23bd1392d3f9
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2100089ad10458b37c0f5f32a5e01b69d497af008f5f732e686747ea1860ac98
3
  size 5304
capybara-finetuned/checkpoint-193/trainer_state.json DELETED
@@ -1,167 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 1.0,
6
- "eval_steps": 500,
7
- "global_step": 193,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.05181347150259067,
14
- "grad_norm": 0.8095124363899231,
15
- "learning_rate": 0.00019792746113989637,
16
- "loss": 12.3719,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.10362694300518134,
21
- "grad_norm": 0.2720714509487152,
22
- "learning_rate": 0.00019447322970639035,
23
- "loss": 0.2877,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.15544041450777202,
28
- "grad_norm": 0.3335513770580292,
29
- "learning_rate": 0.0001910189982728843,
30
- "loss": 0.3723,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.20725388601036268,
35
- "grad_norm": 0.21196776628494263,
36
- "learning_rate": 0.00018756476683937825,
37
- "loss": 0.1598,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.25906735751295334,
42
- "grad_norm": 0.41250184178352356,
43
- "learning_rate": 0.0001841105354058722,
44
- "loss": 0.1899,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.31088082901554404,
49
- "grad_norm": 0.2743557095527649,
50
- "learning_rate": 0.00018065630397236614,
51
- "loss": 0.3541,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.3626943005181347,
56
- "grad_norm": 0.28188714385032654,
57
- "learning_rate": 0.00017720207253886012,
58
- "loss": 0.1689,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.41450777202072536,
63
- "grad_norm": 0.3063858151435852,
64
- "learning_rate": 0.00017374784110535407,
65
- "loss": 0.2957,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.46632124352331605,
70
- "grad_norm": 0.24155083298683167,
71
- "learning_rate": 0.00017029360967184802,
72
- "loss": 0.2411,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.5181347150259067,
77
- "grad_norm": 0.3580751121044159,
78
- "learning_rate": 0.00016683937823834197,
79
- "loss": 0.2035,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.5699481865284974,
84
- "grad_norm": 0.32368239760398865,
85
- "learning_rate": 0.00016338514680483594,
86
- "loss": 0.2863,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 0.6217616580310881,
91
- "grad_norm": 0.31771329045295715,
92
- "learning_rate": 0.0001599309153713299,
93
- "loss": 0.2815,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 0.6735751295336787,
98
- "grad_norm": 0.1532900333404541,
99
- "learning_rate": 0.00015647668393782384,
100
- "loss": 0.1949,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 0.7253886010362695,
105
- "grad_norm": 0.41243669390678406,
106
- "learning_rate": 0.0001530224525043178,
107
- "loss": 0.1595,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 0.7772020725388601,
112
- "grad_norm": 0.10424460470676422,
113
- "learning_rate": 0.00014956822107081174,
114
- "loss": 0.1694,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 0.8290155440414507,
119
- "grad_norm": 0.2025623470544815,
120
- "learning_rate": 0.0001461139896373057,
121
- "loss": 0.2369,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 0.8808290155440415,
126
- "grad_norm": 0.1760733723640442,
127
- "learning_rate": 0.00014265975820379966,
128
- "loss": 0.3239,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 0.9326424870466321,
133
- "grad_norm": 0.10223771631717682,
134
- "learning_rate": 0.0001392055267702936,
135
- "loss": 0.1242,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 0.9844559585492227,
140
- "grad_norm": 0.4485471844673157,
141
- "learning_rate": 0.00013575129533678756,
142
- "loss": 0.3755,
143
- "step": 190
144
- }
145
- ],
146
- "logging_steps": 10,
147
- "max_steps": 579,
148
- "num_input_tokens_seen": 0,
149
- "num_train_epochs": 3,
150
- "save_steps": 500,
151
- "stateful_callbacks": {
152
- "TrainerControl": {
153
- "args": {
154
- "should_epoch_stop": false,
155
- "should_evaluate": false,
156
- "should_log": false,
157
- "should_save": true,
158
- "should_training_stop": false
159
- },
160
- "attributes": {}
161
- }
162
- },
163
- "total_flos": 3174543906570240.0,
164
- "train_batch_size": 1,
165
- "trial_name": null,
166
- "trial_params": null
167
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
capybara-finetuned/checkpoint-386/trainer_state.json DELETED
@@ -1,300 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 2.0,
6
- "eval_steps": 500,
7
- "global_step": 386,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.05181347150259067,
14
- "grad_norm": 0.8095124363899231,
15
- "learning_rate": 0.00019792746113989637,
16
- "loss": 12.3719,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.10362694300518134,
21
- "grad_norm": 0.2720714509487152,
22
- "learning_rate": 0.00019447322970639035,
23
- "loss": 0.2877,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.15544041450777202,
28
- "grad_norm": 0.3335513770580292,
29
- "learning_rate": 0.0001910189982728843,
30
- "loss": 0.3723,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.20725388601036268,
35
- "grad_norm": 0.21196776628494263,
36
- "learning_rate": 0.00018756476683937825,
37
- "loss": 0.1598,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.25906735751295334,
42
- "grad_norm": 0.41250184178352356,
43
- "learning_rate": 0.0001841105354058722,
44
- "loss": 0.1899,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.31088082901554404,
49
- "grad_norm": 0.2743557095527649,
50
- "learning_rate": 0.00018065630397236614,
51
- "loss": 0.3541,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.3626943005181347,
56
- "grad_norm": 0.28188714385032654,
57
- "learning_rate": 0.00017720207253886012,
58
- "loss": 0.1689,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.41450777202072536,
63
- "grad_norm": 0.3063858151435852,
64
- "learning_rate": 0.00017374784110535407,
65
- "loss": 0.2957,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.46632124352331605,
70
- "grad_norm": 0.24155083298683167,
71
- "learning_rate": 0.00017029360967184802,
72
- "loss": 0.2411,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.5181347150259067,
77
- "grad_norm": 0.3580751121044159,
78
- "learning_rate": 0.00016683937823834197,
79
- "loss": 0.2035,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.5699481865284974,
84
- "grad_norm": 0.32368239760398865,
85
- "learning_rate": 0.00016338514680483594,
86
- "loss": 0.2863,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 0.6217616580310881,
91
- "grad_norm": 0.31771329045295715,
92
- "learning_rate": 0.0001599309153713299,
93
- "loss": 0.2815,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 0.6735751295336787,
98
- "grad_norm": 0.1532900333404541,
99
- "learning_rate": 0.00015647668393782384,
100
- "loss": 0.1949,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 0.7253886010362695,
105
- "grad_norm": 0.41243669390678406,
106
- "learning_rate": 0.0001530224525043178,
107
- "loss": 0.1595,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 0.7772020725388601,
112
- "grad_norm": 0.10424460470676422,
113
- "learning_rate": 0.00014956822107081174,
114
- "loss": 0.1694,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 0.8290155440414507,
119
- "grad_norm": 0.2025623470544815,
120
- "learning_rate": 0.0001461139896373057,
121
- "loss": 0.2369,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 0.8808290155440415,
126
- "grad_norm": 0.1760733723640442,
127
- "learning_rate": 0.00014265975820379966,
128
- "loss": 0.3239,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 0.9326424870466321,
133
- "grad_norm": 0.10223771631717682,
134
- "learning_rate": 0.0001392055267702936,
135
- "loss": 0.1242,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 0.9844559585492227,
140
- "grad_norm": 0.4485471844673157,
141
- "learning_rate": 0.00013575129533678756,
142
- "loss": 0.3755,
143
- "step": 190
144
- },
145
- {
146
- "epoch": 1.0362694300518134,
147
- "grad_norm": 0.39652231335639954,
148
- "learning_rate": 0.0001322970639032815,
149
- "loss": 0.2445,
150
- "step": 200
151
- },
152
- {
153
- "epoch": 1.0880829015544042,
154
- "grad_norm": 0.36412283778190613,
155
- "learning_rate": 0.00012884283246977548,
156
- "loss": 0.2351,
157
- "step": 210
158
- },
159
- {
160
- "epoch": 1.1398963730569949,
161
- "grad_norm": 0.21277184784412384,
162
- "learning_rate": 0.00012538860103626943,
163
- "loss": 0.1115,
164
- "step": 220
165
- },
166
- {
167
- "epoch": 1.1917098445595855,
168
- "grad_norm": 0.4270087480545044,
169
- "learning_rate": 0.00012193436960276338,
170
- "loss": 0.1656,
171
- "step": 230
172
- },
173
- {
174
- "epoch": 1.2435233160621761,
175
- "grad_norm": 0.35429275035858154,
176
- "learning_rate": 0.00011848013816925734,
177
- "loss": 0.2019,
178
- "step": 240
179
- },
180
- {
181
- "epoch": 1.2953367875647668,
182
- "grad_norm": 0.5731873512268066,
183
- "learning_rate": 0.0001150259067357513,
184
- "loss": 0.193,
185
- "step": 250
186
- },
187
- {
188
- "epoch": 1.3471502590673574,
189
- "grad_norm": 0.18436703085899353,
190
- "learning_rate": 0.00011157167530224525,
191
- "loss": 0.2204,
192
- "step": 260
193
- },
194
- {
195
- "epoch": 1.3989637305699483,
196
- "grad_norm": 0.6231918334960938,
197
- "learning_rate": 0.0001081174438687392,
198
- "loss": 0.2204,
199
- "step": 270
200
- },
201
- {
202
- "epoch": 1.450777202072539,
203
- "grad_norm": 0.27956509590148926,
204
- "learning_rate": 0.00010466321243523317,
205
- "loss": 0.1864,
206
- "step": 280
207
- },
208
- {
209
- "epoch": 1.5025906735751295,
210
- "grad_norm": 0.24223612248897552,
211
- "learning_rate": 0.00010120898100172711,
212
- "loss": 0.1985,
213
- "step": 290
214
- },
215
- {
216
- "epoch": 1.5544041450777202,
217
- "grad_norm": 0.28999006748199463,
218
- "learning_rate": 9.775474956822108e-05,
219
- "loss": 0.1322,
220
- "step": 300
221
- },
222
- {
223
- "epoch": 1.6062176165803108,
224
- "grad_norm": 0.505622923374176,
225
- "learning_rate": 9.430051813471503e-05,
226
- "loss": 0.1745,
227
- "step": 310
228
- },
229
- {
230
- "epoch": 1.6580310880829017,
231
- "grad_norm": 0.17805594205856323,
232
- "learning_rate": 9.084628670120899e-05,
233
- "loss": 0.229,
234
- "step": 320
235
- },
236
- {
237
- "epoch": 1.709844559585492,
238
- "grad_norm": 0.8911346197128296,
239
- "learning_rate": 8.739205526770295e-05,
240
- "loss": 0.2056,
241
- "step": 330
242
- },
243
- {
244
- "epoch": 1.761658031088083,
245
- "grad_norm": 0.2521348297595978,
246
- "learning_rate": 8.39378238341969e-05,
247
- "loss": 0.2274,
248
- "step": 340
249
- },
250
- {
251
- "epoch": 1.8134715025906736,
252
- "grad_norm": 0.1958165019750595,
253
- "learning_rate": 8.048359240069086e-05,
254
- "loss": 0.1346,
255
- "step": 350
256
- },
257
- {
258
- "epoch": 1.8652849740932642,
259
- "grad_norm": 0.43222665786743164,
260
- "learning_rate": 7.702936096718481e-05,
261
- "loss": 0.1926,
262
- "step": 360
263
- },
264
- {
265
- "epoch": 1.917098445595855,
266
- "grad_norm": 0.28354278206825256,
267
- "learning_rate": 7.357512953367876e-05,
268
- "loss": 0.1491,
269
- "step": 370
270
- },
271
- {
272
- "epoch": 1.9689119170984455,
273
- "grad_norm": 0.30970773100852966,
274
- "learning_rate": 7.012089810017272e-05,
275
- "loss": 0.1939,
276
- "step": 380
277
- }
278
- ],
279
- "logging_steps": 10,
280
- "max_steps": 579,
281
- "num_input_tokens_seen": 0,
282
- "num_train_epochs": 3,
283
- "save_steps": 500,
284
- "stateful_callbacks": {
285
- "TrainerControl": {
286
- "args": {
287
- "should_epoch_stop": false,
288
- "should_evaluate": false,
289
- "should_log": false,
290
- "should_save": true,
291
- "should_training_stop": false
292
- },
293
- "attributes": {}
294
- }
295
- },
296
- "total_flos": 6349087813140480.0,
297
- "train_batch_size": 1,
298
- "trial_name": null,
299
- "trial_params": null
300
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
capybara-finetuned/{checkpoint-386 → checkpoint-493}/README.md RENAMED
File without changes
capybara-finetuned/{checkpoint-193 → checkpoint-493}/adapter_config.json RENAMED
@@ -23,10 +23,10 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "k_proj",
27
- "o_proj",
28
  "q_proj",
29
- "v_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "q_proj",
27
+ "o_proj",
28
+ "v_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
capybara-finetuned/{checkpoint-579 → checkpoint-493}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c3e58810019f8c2423473124d01849395572ed748ab106aff696e68fe511594
3
  size 41977424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:347fb3092f0a80971aae3b64ef58ccd7d2eb1ce119843502c07a7b867d0cf5a5
3
  size 41977424
capybara-finetuned/{checkpoint-579 → checkpoint-493}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ae81316b6c06fe5011bed6387e38d2e9e6d59b269947e0e98a135f250e53431
3
  size 84100858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fcafd5a996027f6e6275b9eb28f25705c528ee43d6ce5a632d48e165211eab3
3
  size 84100858
capybara-finetuned/{checkpoint-386 → checkpoint-493}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fe550639dad04133d303c68a9bec2bc782de93b44e018edd8ecc0eb84989821
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4434a5acd90ba05c6d3867a16f2de4083738b8c5352639c8385a33b8312526
3
  size 14244
capybara-finetuned/{checkpoint-193 → checkpoint-493}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d83b6a26d96339cdb88224ae8d6de87f5142e8f652dddb69b9d2ad537cd43ce1
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ddfe0293f7f24495853182cf5394dca1ef50bb90484a993d2f3c5cca2b86da
3
  size 988
capybara-finetuned/{checkpoint-579 → checkpoint-493}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:180e243f8de76fb954da6fdb3fad5a9f4cc7a2aa5ac46cf1ccaa53c9bb3946ef
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f311460affa935ad3b9db7683ef981a3f5fa7f746895182fcd28a309f42ecfcc
3
  size 1064
capybara-finetuned/checkpoint-493/trainer_state.json ADDED
@@ -0,0 +1,377 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 493,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02028397565922921,
14
+ "grad_norm": 1.1712552309036255,
15
+ "learning_rate": 0.0001993238674780257,
16
+ "loss": 14.4092,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.04056795131845842,
21
+ "grad_norm": 0.48309916257858276,
22
+ "learning_rate": 0.0001979716024340771,
23
+ "loss": 0.2359,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.060851926977687626,
28
+ "grad_norm": 0.2885732352733612,
29
+ "learning_rate": 0.00019661933739012849,
30
+ "loss": 0.1483,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.08113590263691683,
35
+ "grad_norm": 0.2794722318649292,
36
+ "learning_rate": 0.00019526707234617988,
37
+ "loss": 0.1758,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.10141987829614604,
42
+ "grad_norm": 0.21984700858592987,
43
+ "learning_rate": 0.00019391480730223125,
44
+ "loss": 0.248,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.12170385395537525,
49
+ "grad_norm": 0.32381802797317505,
50
+ "learning_rate": 0.00019256254225828262,
51
+ "loss": 0.1618,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.14198782961460446,
56
+ "grad_norm": 0.28723254799842834,
57
+ "learning_rate": 0.00019121027721433401,
58
+ "loss": 0.1171,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.16227180527383367,
63
+ "grad_norm": 0.2172032743692398,
64
+ "learning_rate": 0.0001898580121703854,
65
+ "loss": 0.1621,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.18255578093306288,
70
+ "grad_norm": 0.23619882762432098,
71
+ "learning_rate": 0.00018850574712643678,
72
+ "loss": 0.1198,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.2028397565922921,
77
+ "grad_norm": 0.22938676178455353,
78
+ "learning_rate": 0.00018715348208248818,
79
+ "loss": 0.1546,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2231237322515213,
84
+ "grad_norm": 0.30202436447143555,
85
+ "learning_rate": 0.00018580121703853957,
86
+ "loss": 0.0521,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.2434077079107505,
91
+ "grad_norm": 0.9085210561752319,
92
+ "learning_rate": 0.00018444895199459097,
93
+ "loss": 0.1844,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.26369168356997974,
98
+ "grad_norm": 0.33736127614974976,
99
+ "learning_rate": 0.00018309668695064234,
100
+ "loss": 0.0827,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.2839756592292089,
105
+ "grad_norm": 0.13767044246196747,
106
+ "learning_rate": 0.00018174442190669373,
107
+ "loss": 0.1092,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.30425963488843816,
112
+ "grad_norm": 0.2765495181083679,
113
+ "learning_rate": 0.0001803921568627451,
114
+ "loss": 0.1144,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.32454361054766734,
119
+ "grad_norm": 0.13134893774986267,
120
+ "learning_rate": 0.0001790398918187965,
121
+ "loss": 0.0914,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3448275862068966,
126
+ "grad_norm": 0.15877078473567963,
127
+ "learning_rate": 0.00017768762677484786,
128
+ "loss": 0.0787,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.36511156186612576,
133
+ "grad_norm": 0.11392869800329208,
134
+ "learning_rate": 0.00017633536173089926,
135
+ "loss": 0.0483,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.385395537525355,
140
+ "grad_norm": 0.230561301112175,
141
+ "learning_rate": 0.00017498309668695066,
142
+ "loss": 0.0601,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.4056795131845842,
147
+ "grad_norm": 0.20257052779197693,
148
+ "learning_rate": 0.00017363083164300205,
149
+ "loss": 0.1253,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.4259634888438134,
154
+ "grad_norm": 0.25743618607521057,
155
+ "learning_rate": 0.00017227856659905342,
156
+ "loss": 0.0684,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.4462474645030426,
161
+ "grad_norm": 0.4015647768974304,
162
+ "learning_rate": 0.00017092630155510482,
163
+ "loss": 0.0734,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.4665314401622718,
168
+ "grad_norm": 1.1545509099960327,
169
+ "learning_rate": 0.00016957403651115619,
170
+ "loss": 0.1491,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.486815415821501,
175
+ "grad_norm": 0.3187839984893799,
176
+ "learning_rate": 0.00016822177146720758,
177
+ "loss": 0.101,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5070993914807302,
182
+ "grad_norm": 0.1046043112874031,
183
+ "learning_rate": 0.00016686950642325895,
184
+ "loss": 0.0917,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.5273833671399595,
189
+ "grad_norm": 0.13540491461753845,
190
+ "learning_rate": 0.00016551724137931035,
191
+ "loss": 0.0516,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.5476673427991886,
196
+ "grad_norm": 0.33530837297439575,
197
+ "learning_rate": 0.00016416497633536174,
198
+ "loss": 0.1529,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.5679513184584178,
203
+ "grad_norm": 0.7428917288780212,
204
+ "learning_rate": 0.00016281271129141314,
205
+ "loss": 0.1771,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5882352941176471,
210
+ "grad_norm": 0.11154314875602722,
211
+ "learning_rate": 0.0001614604462474645,
212
+ "loss": 0.0386,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.6085192697768763,
217
+ "grad_norm": 0.09267372637987137,
218
+ "learning_rate": 0.0001601081812035159,
219
+ "loss": 0.0625,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.6288032454361054,
224
+ "grad_norm": 0.24139204621315002,
225
+ "learning_rate": 0.0001587559161595673,
226
+ "loss": 0.1699,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.6490872210953347,
231
+ "grad_norm": 0.6370412111282349,
232
+ "learning_rate": 0.00015740365111561867,
233
+ "loss": 0.1857,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.6693711967545639,
238
+ "grad_norm": 0.07758647203445435,
239
+ "learning_rate": 0.00015605138607167004,
240
+ "loss": 0.1178,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.6896551724137931,
245
+ "grad_norm": 0.2090945690870285,
246
+ "learning_rate": 0.00015469912102772143,
247
+ "loss": 0.1247,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.7099391480730223,
252
+ "grad_norm": 0.24821089208126068,
253
+ "learning_rate": 0.00015334685598377283,
254
+ "loss": 0.1128,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.7302231237322515,
259
+ "grad_norm": 0.123480886220932,
260
+ "learning_rate": 0.00015199459093982422,
261
+ "loss": 0.1625,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.7505070993914807,
266
+ "grad_norm": 0.3176027238368988,
267
+ "learning_rate": 0.0001506423258958756,
268
+ "loss": 0.1215,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.77079107505071,
273
+ "grad_norm": 0.17533642053604126,
274
+ "learning_rate": 0.000149290060851927,
275
+ "loss": 0.1062,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.7910750507099391,
280
+ "grad_norm": 0.2660926878452301,
281
+ "learning_rate": 0.00014793779580797838,
282
+ "loss": 0.0877,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.8113590263691683,
287
+ "grad_norm": 0.5134332180023193,
288
+ "learning_rate": 0.00014658553076402975,
289
+ "loss": 0.0596,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.8316430020283976,
294
+ "grad_norm": 0.09723437577486038,
295
+ "learning_rate": 0.00014523326572008115,
296
+ "loss": 0.0448,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.8519269776876268,
301
+ "grad_norm": 0.40922313928604126,
302
+ "learning_rate": 0.00014388100067613252,
303
+ "loss": 0.0898,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.8722109533468559,
308
+ "grad_norm": 0.14394080638885498,
309
+ "learning_rate": 0.0001425287356321839,
310
+ "loss": 0.1304,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.8924949290060852,
315
+ "grad_norm": 0.578838050365448,
316
+ "learning_rate": 0.0001411764705882353,
317
+ "loss": 0.1038,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.9127789046653144,
322
+ "grad_norm": 0.46690645813941956,
323
+ "learning_rate": 0.00013982420554428668,
324
+ "loss": 0.2278,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.9330628803245437,
329
+ "grad_norm": 0.29226213693618774,
330
+ "learning_rate": 0.00013847194050033807,
331
+ "loss": 0.0747,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.9533468559837728,
336
+ "grad_norm": 0.14866693317890167,
337
+ "learning_rate": 0.00013711967545638947,
338
+ "loss": 0.1133,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.973630831643002,
343
+ "grad_norm": 0.08057406544685364,
344
+ "learning_rate": 0.00013576741041244087,
345
+ "loss": 0.0955,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.9939148073022313,
350
+ "grad_norm": 0.0708722174167633,
351
+ "learning_rate": 0.00013441514536849223,
352
+ "loss": 0.1018,
353
+ "step": 490
354
+ }
355
+ ],
356
+ "logging_steps": 10,
357
+ "max_steps": 1479,
358
+ "num_input_tokens_seen": 0,
359
+ "num_train_epochs": 3,
360
+ "save_steps": 500,
361
+ "stateful_callbacks": {
362
+ "TrainerControl": {
363
+ "args": {
364
+ "should_epoch_stop": false,
365
+ "should_evaluate": false,
366
+ "should_log": false,
367
+ "should_save": true,
368
+ "should_training_stop": false
369
+ },
370
+ "attributes": {}
371
+ }
372
+ },
373
+ "total_flos": 8109068113674240.0,
374
+ "train_batch_size": 1,
375
+ "trial_name": null,
376
+ "trial_params": null
377
+ }
capybara-finetuned/{checkpoint-579 → checkpoint-493}/training_args.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb5dfa95d8bedc071d0ca429ace88a97d08b4e6c0549993636c23bd1392d3f9
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2100089ad10458b37c0f5f32a5e01b69d497af008f5f732e686747ea1860ac98
3
  size 5304
capybara-finetuned/checkpoint-579/trainer_state.json DELETED
@@ -1,433 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 3.0,
6
- "eval_steps": 500,
7
- "global_step": 579,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "epoch": 0.05181347150259067,
14
- "grad_norm": 0.8095124363899231,
15
- "learning_rate": 0.00019792746113989637,
16
- "loss": 12.3719,
17
- "step": 10
18
- },
19
- {
20
- "epoch": 0.10362694300518134,
21
- "grad_norm": 0.2720714509487152,
22
- "learning_rate": 0.00019447322970639035,
23
- "loss": 0.2877,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 0.15544041450777202,
28
- "grad_norm": 0.3335513770580292,
29
- "learning_rate": 0.0001910189982728843,
30
- "loss": 0.3723,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 0.20725388601036268,
35
- "grad_norm": 0.21196776628494263,
36
- "learning_rate": 0.00018756476683937825,
37
- "loss": 0.1598,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 0.25906735751295334,
42
- "grad_norm": 0.41250184178352356,
43
- "learning_rate": 0.0001841105354058722,
44
- "loss": 0.1899,
45
- "step": 50
46
- },
47
- {
48
- "epoch": 0.31088082901554404,
49
- "grad_norm": 0.2743557095527649,
50
- "learning_rate": 0.00018065630397236614,
51
- "loss": 0.3541,
52
- "step": 60
53
- },
54
- {
55
- "epoch": 0.3626943005181347,
56
- "grad_norm": 0.28188714385032654,
57
- "learning_rate": 0.00017720207253886012,
58
- "loss": 0.1689,
59
- "step": 70
60
- },
61
- {
62
- "epoch": 0.41450777202072536,
63
- "grad_norm": 0.3063858151435852,
64
- "learning_rate": 0.00017374784110535407,
65
- "loss": 0.2957,
66
- "step": 80
67
- },
68
- {
69
- "epoch": 0.46632124352331605,
70
- "grad_norm": 0.24155083298683167,
71
- "learning_rate": 0.00017029360967184802,
72
- "loss": 0.2411,
73
- "step": 90
74
- },
75
- {
76
- "epoch": 0.5181347150259067,
77
- "grad_norm": 0.3580751121044159,
78
- "learning_rate": 0.00016683937823834197,
79
- "loss": 0.2035,
80
- "step": 100
81
- },
82
- {
83
- "epoch": 0.5699481865284974,
84
- "grad_norm": 0.32368239760398865,
85
- "learning_rate": 0.00016338514680483594,
86
- "loss": 0.2863,
87
- "step": 110
88
- },
89
- {
90
- "epoch": 0.6217616580310881,
91
- "grad_norm": 0.31771329045295715,
92
- "learning_rate": 0.0001599309153713299,
93
- "loss": 0.2815,
94
- "step": 120
95
- },
96
- {
97
- "epoch": 0.6735751295336787,
98
- "grad_norm": 0.1532900333404541,
99
- "learning_rate": 0.00015647668393782384,
100
- "loss": 0.1949,
101
- "step": 130
102
- },
103
- {
104
- "epoch": 0.7253886010362695,
105
- "grad_norm": 0.41243669390678406,
106
- "learning_rate": 0.0001530224525043178,
107
- "loss": 0.1595,
108
- "step": 140
109
- },
110
- {
111
- "epoch": 0.7772020725388601,
112
- "grad_norm": 0.10424460470676422,
113
- "learning_rate": 0.00014956822107081174,
114
- "loss": 0.1694,
115
- "step": 150
116
- },
117
- {
118
- "epoch": 0.8290155440414507,
119
- "grad_norm": 0.2025623470544815,
120
- "learning_rate": 0.0001461139896373057,
121
- "loss": 0.2369,
122
- "step": 160
123
- },
124
- {
125
- "epoch": 0.8808290155440415,
126
- "grad_norm": 0.1760733723640442,
127
- "learning_rate": 0.00014265975820379966,
128
- "loss": 0.3239,
129
- "step": 170
130
- },
131
- {
132
- "epoch": 0.9326424870466321,
133
- "grad_norm": 0.10223771631717682,
134
- "learning_rate": 0.0001392055267702936,
135
- "loss": 0.1242,
136
- "step": 180
137
- },
138
- {
139
- "epoch": 0.9844559585492227,
140
- "grad_norm": 0.4485471844673157,
141
- "learning_rate": 0.00013575129533678756,
142
- "loss": 0.3755,
143
- "step": 190
144
- },
145
- {
146
- "epoch": 1.0362694300518134,
147
- "grad_norm": 0.39652231335639954,
148
- "learning_rate": 0.0001322970639032815,
149
- "loss": 0.2445,
150
- "step": 200
151
- },
152
- {
153
- "epoch": 1.0880829015544042,
154
- "grad_norm": 0.36412283778190613,
155
- "learning_rate": 0.00012884283246977548,
156
- "loss": 0.2351,
157
- "step": 210
158
- },
159
- {
160
- "epoch": 1.1398963730569949,
161
- "grad_norm": 0.21277184784412384,
162
- "learning_rate": 0.00012538860103626943,
163
- "loss": 0.1115,
164
- "step": 220
165
- },
166
- {
167
- "epoch": 1.1917098445595855,
168
- "grad_norm": 0.4270087480545044,
169
- "learning_rate": 0.00012193436960276338,
170
- "loss": 0.1656,
171
- "step": 230
172
- },
173
- {
174
- "epoch": 1.2435233160621761,
175
- "grad_norm": 0.35429275035858154,
176
- "learning_rate": 0.00011848013816925734,
177
- "loss": 0.2019,
178
- "step": 240
179
- },
180
- {
181
- "epoch": 1.2953367875647668,
182
- "grad_norm": 0.5731873512268066,
183
- "learning_rate": 0.0001150259067357513,
184
- "loss": 0.193,
185
- "step": 250
186
- },
187
- {
188
- "epoch": 1.3471502590673574,
189
- "grad_norm": 0.18436703085899353,
190
- "learning_rate": 0.00011157167530224525,
191
- "loss": 0.2204,
192
- "step": 260
193
- },
194
- {
195
- "epoch": 1.3989637305699483,
196
- "grad_norm": 0.6231918334960938,
197
- "learning_rate": 0.0001081174438687392,
198
- "loss": 0.2204,
199
- "step": 270
200
- },
201
- {
202
- "epoch": 1.450777202072539,
203
- "grad_norm": 0.27956509590148926,
204
- "learning_rate": 0.00010466321243523317,
205
- "loss": 0.1864,
206
- "step": 280
207
- },
208
- {
209
- "epoch": 1.5025906735751295,
210
- "grad_norm": 0.24223612248897552,
211
- "learning_rate": 0.00010120898100172711,
212
- "loss": 0.1985,
213
- "step": 290
214
- },
215
- {
216
- "epoch": 1.5544041450777202,
217
- "grad_norm": 0.28999006748199463,
218
- "learning_rate": 9.775474956822108e-05,
219
- "loss": 0.1322,
220
- "step": 300
221
- },
222
- {
223
- "epoch": 1.6062176165803108,
224
- "grad_norm": 0.505622923374176,
225
- "learning_rate": 9.430051813471503e-05,
226
- "loss": 0.1745,
227
- "step": 310
228
- },
229
- {
230
- "epoch": 1.6580310880829017,
231
- "grad_norm": 0.17805594205856323,
232
- "learning_rate": 9.084628670120899e-05,
233
- "loss": 0.229,
234
- "step": 320
235
- },
236
- {
237
- "epoch": 1.709844559585492,
238
- "grad_norm": 0.8911346197128296,
239
- "learning_rate": 8.739205526770295e-05,
240
- "loss": 0.2056,
241
- "step": 330
242
- },
243
- {
244
- "epoch": 1.761658031088083,
245
- "grad_norm": 0.2521348297595978,
246
- "learning_rate": 8.39378238341969e-05,
247
- "loss": 0.2274,
248
- "step": 340
249
- },
250
- {
251
- "epoch": 1.8134715025906736,
252
- "grad_norm": 0.1958165019750595,
253
- "learning_rate": 8.048359240069086e-05,
254
- "loss": 0.1346,
255
- "step": 350
256
- },
257
- {
258
- "epoch": 1.8652849740932642,
259
- "grad_norm": 0.43222665786743164,
260
- "learning_rate": 7.702936096718481e-05,
261
- "loss": 0.1926,
262
- "step": 360
263
- },
264
- {
265
- "epoch": 1.917098445595855,
266
- "grad_norm": 0.28354278206825256,
267
- "learning_rate": 7.357512953367876e-05,
268
- "loss": 0.1491,
269
- "step": 370
270
- },
271
- {
272
- "epoch": 1.9689119170984455,
273
- "grad_norm": 0.30970773100852966,
274
- "learning_rate": 7.012089810017272e-05,
275
- "loss": 0.1939,
276
- "step": 380
277
- },
278
- {
279
- "epoch": 2.0207253886010363,
280
- "grad_norm": 0.23131532967090607,
281
- "learning_rate": 6.666666666666667e-05,
282
- "loss": 0.1619,
283
- "step": 390
284
- },
285
- {
286
- "epoch": 2.0725388601036268,
287
- "grad_norm": 0.6155455708503723,
288
- "learning_rate": 6.321243523316063e-05,
289
- "loss": 0.1383,
290
- "step": 400
291
- },
292
- {
293
- "epoch": 2.1243523316062176,
294
- "grad_norm": 0.4131735563278198,
295
- "learning_rate": 5.9758203799654574e-05,
296
- "loss": 0.1434,
297
- "step": 410
298
- },
299
- {
300
- "epoch": 2.1761658031088085,
301
- "grad_norm": 0.3871082365512848,
302
- "learning_rate": 5.6303972366148536e-05,
303
- "loss": 0.0827,
304
- "step": 420
305
- },
306
- {
307
- "epoch": 2.227979274611399,
308
- "grad_norm": 0.8619069457054138,
309
- "learning_rate": 5.284974093264249e-05,
310
- "loss": 0.161,
311
- "step": 430
312
- },
313
- {
314
- "epoch": 2.2797927461139897,
315
- "grad_norm": 0.3584190905094147,
316
- "learning_rate": 4.939550949913645e-05,
317
- "loss": 0.1341,
318
- "step": 440
319
- },
320
- {
321
- "epoch": 2.33160621761658,
322
- "grad_norm": 0.2826884090900421,
323
- "learning_rate": 4.59412780656304e-05,
324
- "loss": 0.1257,
325
- "step": 450
326
- },
327
- {
328
- "epoch": 2.383419689119171,
329
- "grad_norm": 0.4198673367500305,
330
- "learning_rate": 4.248704663212436e-05,
331
- "loss": 0.1216,
332
- "step": 460
333
- },
334
- {
335
- "epoch": 2.4352331606217614,
336
- "grad_norm": 0.582490086555481,
337
- "learning_rate": 3.9032815198618314e-05,
338
- "loss": 0.1325,
339
- "step": 470
340
- },
341
- {
342
- "epoch": 2.4870466321243523,
343
- "grad_norm": 0.7895885109901428,
344
- "learning_rate": 3.557858376511227e-05,
345
- "loss": 0.128,
346
- "step": 480
347
- },
348
- {
349
- "epoch": 2.538860103626943,
350
- "grad_norm": 0.24237169325351715,
351
- "learning_rate": 3.212435233160622e-05,
352
- "loss": 0.1391,
353
- "step": 490
354
- },
355
- {
356
- "epoch": 2.5906735751295336,
357
- "grad_norm": 0.46788838505744934,
358
- "learning_rate": 2.8670120898100174e-05,
359
- "loss": 0.1712,
360
- "step": 500
361
- },
362
- {
363
- "epoch": 2.6424870466321244,
364
- "grad_norm": 0.2091088891029358,
365
- "learning_rate": 2.521588946459413e-05,
366
- "loss": 0.1146,
367
- "step": 510
368
- },
369
- {
370
- "epoch": 2.694300518134715,
371
- "grad_norm": 0.3197329342365265,
372
- "learning_rate": 2.1761658031088085e-05,
373
- "loss": 0.1483,
374
- "step": 520
375
- },
376
- {
377
- "epoch": 2.7461139896373057,
378
- "grad_norm": 0.5090299844741821,
379
- "learning_rate": 1.830742659758204e-05,
380
- "loss": 0.1418,
381
- "step": 530
382
- },
383
- {
384
- "epoch": 2.7979274611398965,
385
- "grad_norm": 0.1630585491657257,
386
- "learning_rate": 1.4853195164075994e-05,
387
- "loss": 0.1563,
388
- "step": 540
389
- },
390
- {
391
- "epoch": 2.849740932642487,
392
- "grad_norm": 0.9052726626396179,
393
- "learning_rate": 1.139896373056995e-05,
394
- "loss": 0.1299,
395
- "step": 550
396
- },
397
- {
398
- "epoch": 2.901554404145078,
399
- "grad_norm": 0.21230316162109375,
400
- "learning_rate": 7.944732297063904e-06,
401
- "loss": 0.1496,
402
- "step": 560
403
- },
404
- {
405
- "epoch": 2.9533678756476682,
406
- "grad_norm": 0.4288373291492462,
407
- "learning_rate": 4.490500863557859e-06,
408
- "loss": 0.1735,
409
- "step": 570
410
- }
411
- ],
412
- "logging_steps": 10,
413
- "max_steps": 579,
414
- "num_input_tokens_seen": 0,
415
- "num_train_epochs": 3,
416
- "save_steps": 500,
417
- "stateful_callbacks": {
418
- "TrainerControl": {
419
- "args": {
420
- "should_epoch_stop": false,
421
- "should_evaluate": false,
422
- "should_log": false,
423
- "should_save": true,
424
- "should_training_stop": true
425
- },
426
- "attributes": {}
427
- }
428
- },
429
- "total_flos": 9523631719710720.0,
430
- "train_batch_size": 1,
431
- "trial_name": null,
432
- "trial_params": null
433
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
capybara-finetuned/{checkpoint-579 → checkpoint-986}/README.md RENAMED
File without changes
capybara-finetuned/{checkpoint-579 → checkpoint-986}/adapter_config.json RENAMED
@@ -23,10 +23,10 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "k_proj",
27
- "o_proj",
28
  "q_proj",
29
- "v_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "q_proj",
27
+ "o_proj",
28
+ "v_proj",
29
+ "k_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
capybara-finetuned/{checkpoint-193 → checkpoint-986}/adapter_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c1cffa05984bb9ec4cccf6fe24b4fa1e2f160a679abffee220de9914bf0b4f4
3
  size 41977424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f0f8c20dacc313aada2e293df5eb632737b3c5bea9d25f67e7445067d1d1e8
3
  size 41977424
capybara-finetuned/{checkpoint-193 → checkpoint-986}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de5346d830853d3585860a55a744ab7368789f3985ea18232bd4fc69de13e474
3
  size 84100858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c5b1a6d9e272451f5c1198229100d71285a195ada36e70b898cb09244d1b76
3
  size 84100858
capybara-finetuned/{checkpoint-579 → checkpoint-986}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9be5bd0f0585baf47114de4868010f1d69cccda30c0451f6ffa7a6656210a61c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:313233f0d6e57b81ba06b5d5049e34e2f422a32b13fe78b9c8de0f09ed7b336e
3
  size 14244
capybara-finetuned/{checkpoint-579 → checkpoint-986}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b70d513d90f98dc0b17bacf317603627627da3ea2748eb84b7ab7f4d8ec7a878
3
  size 988
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc4fb55b6c3b320d84c9c328fbb382686950dc6d91cd90671724184d20402a66
3
  size 988
capybara-finetuned/{checkpoint-193 → checkpoint-986}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1df4562b25749970667ca99578444d9238c0f6469c2aeca8d78f2e9cb3094c36
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48ea5101a00e3d9708af2ef3bbd7d7823b50b5697cfb4798bc3eb64312229aad
3
  size 1064
capybara-finetuned/checkpoint-986/trainer_state.json ADDED
@@ -0,0 +1,720 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 986,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02028397565922921,
14
+ "grad_norm": 1.1712552309036255,
15
+ "learning_rate": 0.0001993238674780257,
16
+ "loss": 14.4092,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.04056795131845842,
21
+ "grad_norm": 0.48309916257858276,
22
+ "learning_rate": 0.0001979716024340771,
23
+ "loss": 0.2359,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.060851926977687626,
28
+ "grad_norm": 0.2885732352733612,
29
+ "learning_rate": 0.00019661933739012849,
30
+ "loss": 0.1483,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.08113590263691683,
35
+ "grad_norm": 0.2794722318649292,
36
+ "learning_rate": 0.00019526707234617988,
37
+ "loss": 0.1758,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.10141987829614604,
42
+ "grad_norm": 0.21984700858592987,
43
+ "learning_rate": 0.00019391480730223125,
44
+ "loss": 0.248,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.12170385395537525,
49
+ "grad_norm": 0.32381802797317505,
50
+ "learning_rate": 0.00019256254225828262,
51
+ "loss": 0.1618,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.14198782961460446,
56
+ "grad_norm": 0.28723254799842834,
57
+ "learning_rate": 0.00019121027721433401,
58
+ "loss": 0.1171,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.16227180527383367,
63
+ "grad_norm": 0.2172032743692398,
64
+ "learning_rate": 0.0001898580121703854,
65
+ "loss": 0.1621,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.18255578093306288,
70
+ "grad_norm": 0.23619882762432098,
71
+ "learning_rate": 0.00018850574712643678,
72
+ "loss": 0.1198,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.2028397565922921,
77
+ "grad_norm": 0.22938676178455353,
78
+ "learning_rate": 0.00018715348208248818,
79
+ "loss": 0.1546,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.2231237322515213,
84
+ "grad_norm": 0.30202436447143555,
85
+ "learning_rate": 0.00018580121703853957,
86
+ "loss": 0.0521,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.2434077079107505,
91
+ "grad_norm": 0.9085210561752319,
92
+ "learning_rate": 0.00018444895199459097,
93
+ "loss": 0.1844,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.26369168356997974,
98
+ "grad_norm": 0.33736127614974976,
99
+ "learning_rate": 0.00018309668695064234,
100
+ "loss": 0.0827,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.2839756592292089,
105
+ "grad_norm": 0.13767044246196747,
106
+ "learning_rate": 0.00018174442190669373,
107
+ "loss": 0.1092,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.30425963488843816,
112
+ "grad_norm": 0.2765495181083679,
113
+ "learning_rate": 0.0001803921568627451,
114
+ "loss": 0.1144,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.32454361054766734,
119
+ "grad_norm": 0.13134893774986267,
120
+ "learning_rate": 0.0001790398918187965,
121
+ "loss": 0.0914,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3448275862068966,
126
+ "grad_norm": 0.15877078473567963,
127
+ "learning_rate": 0.00017768762677484786,
128
+ "loss": 0.0787,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.36511156186612576,
133
+ "grad_norm": 0.11392869800329208,
134
+ "learning_rate": 0.00017633536173089926,
135
+ "loss": 0.0483,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.385395537525355,
140
+ "grad_norm": 0.230561301112175,
141
+ "learning_rate": 0.00017498309668695066,
142
+ "loss": 0.0601,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.4056795131845842,
147
+ "grad_norm": 0.20257052779197693,
148
+ "learning_rate": 0.00017363083164300205,
149
+ "loss": 0.1253,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.4259634888438134,
154
+ "grad_norm": 0.25743618607521057,
155
+ "learning_rate": 0.00017227856659905342,
156
+ "loss": 0.0684,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.4462474645030426,
161
+ "grad_norm": 0.4015647768974304,
162
+ "learning_rate": 0.00017092630155510482,
163
+ "loss": 0.0734,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.4665314401622718,
168
+ "grad_norm": 1.1545509099960327,
169
+ "learning_rate": 0.00016957403651115619,
170
+ "loss": 0.1491,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.486815415821501,
175
+ "grad_norm": 0.3187839984893799,
176
+ "learning_rate": 0.00016822177146720758,
177
+ "loss": 0.101,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.5070993914807302,
182
+ "grad_norm": 0.1046043112874031,
183
+ "learning_rate": 0.00016686950642325895,
184
+ "loss": 0.0917,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.5273833671399595,
189
+ "grad_norm": 0.13540491461753845,
190
+ "learning_rate": 0.00016551724137931035,
191
+ "loss": 0.0516,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.5476673427991886,
196
+ "grad_norm": 0.33530837297439575,
197
+ "learning_rate": 0.00016416497633536174,
198
+ "loss": 0.1529,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.5679513184584178,
203
+ "grad_norm": 0.7428917288780212,
204
+ "learning_rate": 0.00016281271129141314,
205
+ "loss": 0.1771,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5882352941176471,
210
+ "grad_norm": 0.11154314875602722,
211
+ "learning_rate": 0.0001614604462474645,
212
+ "loss": 0.0386,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.6085192697768763,
217
+ "grad_norm": 0.09267372637987137,
218
+ "learning_rate": 0.0001601081812035159,
219
+ "loss": 0.0625,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.6288032454361054,
224
+ "grad_norm": 0.24139204621315002,
225
+ "learning_rate": 0.0001587559161595673,
226
+ "loss": 0.1699,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.6490872210953347,
231
+ "grad_norm": 0.6370412111282349,
232
+ "learning_rate": 0.00015740365111561867,
233
+ "loss": 0.1857,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.6693711967545639,
238
+ "grad_norm": 0.07758647203445435,
239
+ "learning_rate": 0.00015605138607167004,
240
+ "loss": 0.1178,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.6896551724137931,
245
+ "grad_norm": 0.2090945690870285,
246
+ "learning_rate": 0.00015469912102772143,
247
+ "loss": 0.1247,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.7099391480730223,
252
+ "grad_norm": 0.24821089208126068,
253
+ "learning_rate": 0.00015334685598377283,
254
+ "loss": 0.1128,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.7302231237322515,
259
+ "grad_norm": 0.123480886220932,
260
+ "learning_rate": 0.00015199459093982422,
261
+ "loss": 0.1625,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.7505070993914807,
266
+ "grad_norm": 0.3176027238368988,
267
+ "learning_rate": 0.0001506423258958756,
268
+ "loss": 0.1215,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.77079107505071,
273
+ "grad_norm": 0.17533642053604126,
274
+ "learning_rate": 0.000149290060851927,
275
+ "loss": 0.1062,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.7910750507099391,
280
+ "grad_norm": 0.2660926878452301,
281
+ "learning_rate": 0.00014793779580797838,
282
+ "loss": 0.0877,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.8113590263691683,
287
+ "grad_norm": 0.5134332180023193,
288
+ "learning_rate": 0.00014658553076402975,
289
+ "loss": 0.0596,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.8316430020283976,
294
+ "grad_norm": 0.09723437577486038,
295
+ "learning_rate": 0.00014523326572008115,
296
+ "loss": 0.0448,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.8519269776876268,
301
+ "grad_norm": 0.40922313928604126,
302
+ "learning_rate": 0.00014388100067613252,
303
+ "loss": 0.0898,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.8722109533468559,
308
+ "grad_norm": 0.14394080638885498,
309
+ "learning_rate": 0.0001425287356321839,
310
+ "loss": 0.1304,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.8924949290060852,
315
+ "grad_norm": 0.578838050365448,
316
+ "learning_rate": 0.0001411764705882353,
317
+ "loss": 0.1038,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.9127789046653144,
322
+ "grad_norm": 0.46690645813941956,
323
+ "learning_rate": 0.00013982420554428668,
324
+ "loss": 0.2278,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.9330628803245437,
329
+ "grad_norm": 0.29226213693618774,
330
+ "learning_rate": 0.00013847194050033807,
331
+ "loss": 0.0747,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.9533468559837728,
336
+ "grad_norm": 0.14866693317890167,
337
+ "learning_rate": 0.00013711967545638947,
338
+ "loss": 0.1133,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.973630831643002,
343
+ "grad_norm": 0.08057406544685364,
344
+ "learning_rate": 0.00013576741041244087,
345
+ "loss": 0.0955,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.9939148073022313,
350
+ "grad_norm": 0.0708722174167633,
351
+ "learning_rate": 0.00013441514536849223,
352
+ "loss": 0.1018,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 1.0141987829614605,
357
+ "grad_norm": 0.07880403101444244,
358
+ "learning_rate": 0.0001330628803245436,
359
+ "loss": 0.1211,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 1.0344827586206897,
364
+ "grad_norm": 0.07375513017177582,
365
+ "learning_rate": 0.000131710615280595,
366
+ "loss": 0.0326,
367
+ "step": 510
368
+ },
369
+ {
370
+ "epoch": 1.054766734279919,
371
+ "grad_norm": 0.1140335202217102,
372
+ "learning_rate": 0.0001303583502366464,
373
+ "loss": 0.0457,
374
+ "step": 520
375
+ },
376
+ {
377
+ "epoch": 1.075050709939148,
378
+ "grad_norm": 0.4876038730144501,
379
+ "learning_rate": 0.00012900608519269776,
380
+ "loss": 0.0891,
381
+ "step": 530
382
+ },
383
+ {
384
+ "epoch": 1.0953346855983772,
385
+ "grad_norm": 0.09218205511569977,
386
+ "learning_rate": 0.00012765382014874916,
387
+ "loss": 0.0633,
388
+ "step": 540
389
+ },
390
+ {
391
+ "epoch": 1.1156186612576064,
392
+ "grad_norm": 0.23562578856945038,
393
+ "learning_rate": 0.00012630155510480055,
394
+ "loss": 0.0847,
395
+ "step": 550
396
+ },
397
+ {
398
+ "epoch": 1.1359026369168357,
399
+ "grad_norm": 0.09944804757833481,
400
+ "learning_rate": 0.00012494929006085195,
401
+ "loss": 0.1096,
402
+ "step": 560
403
+ },
404
+ {
405
+ "epoch": 1.156186612576065,
406
+ "grad_norm": 0.08697320520877838,
407
+ "learning_rate": 0.00012359702501690332,
408
+ "loss": 0.1171,
409
+ "step": 570
410
+ },
411
+ {
412
+ "epoch": 1.1764705882352942,
413
+ "grad_norm": 0.34820541739463806,
414
+ "learning_rate": 0.00012224475997295472,
415
+ "loss": 0.0568,
416
+ "step": 580
417
+ },
418
+ {
419
+ "epoch": 1.1967545638945234,
420
+ "grad_norm": 0.06811130791902542,
421
+ "learning_rate": 0.0001208924949290061,
422
+ "loss": 0.0846,
423
+ "step": 590
424
+ },
425
+ {
426
+ "epoch": 1.2170385395537526,
427
+ "grad_norm": 0.3093971610069275,
428
+ "learning_rate": 0.00011954022988505748,
429
+ "loss": 0.1313,
430
+ "step": 600
431
+ },
432
+ {
433
+ "epoch": 1.2373225152129819,
434
+ "grad_norm": 0.15817512571811676,
435
+ "learning_rate": 0.00011818796484110886,
436
+ "loss": 0.0341,
437
+ "step": 610
438
+ },
439
+ {
440
+ "epoch": 1.2576064908722109,
441
+ "grad_norm": 0.6901296973228455,
442
+ "learning_rate": 0.00011683569979716024,
443
+ "loss": 0.1554,
444
+ "step": 620
445
+ },
446
+ {
447
+ "epoch": 1.2778904665314401,
448
+ "grad_norm": 0.09194931387901306,
449
+ "learning_rate": 0.00011548343475321164,
450
+ "loss": 0.0733,
451
+ "step": 630
452
+ },
453
+ {
454
+ "epoch": 1.2981744421906694,
455
+ "grad_norm": 0.059262920171022415,
456
+ "learning_rate": 0.00011413116970926304,
457
+ "loss": 0.0938,
458
+ "step": 640
459
+ },
460
+ {
461
+ "epoch": 1.3184584178498986,
462
+ "grad_norm": 0.10133162140846252,
463
+ "learning_rate": 0.0001127789046653144,
464
+ "loss": 0.077,
465
+ "step": 650
466
+ },
467
+ {
468
+ "epoch": 1.3387423935091278,
469
+ "grad_norm": 0.653348445892334,
470
+ "learning_rate": 0.00011142663962136579,
471
+ "loss": 0.1019,
472
+ "step": 660
473
+ },
474
+ {
475
+ "epoch": 1.359026369168357,
476
+ "grad_norm": 0.28535157442092896,
477
+ "learning_rate": 0.00011007437457741718,
478
+ "loss": 0.0586,
479
+ "step": 670
480
+ },
481
+ {
482
+ "epoch": 1.3793103448275863,
483
+ "grad_norm": 0.17364345490932465,
484
+ "learning_rate": 0.00010872210953346858,
485
+ "loss": 0.074,
486
+ "step": 680
487
+ },
488
+ {
489
+ "epoch": 1.3995943204868153,
490
+ "grad_norm": 0.7617247700691223,
491
+ "learning_rate": 0.00010736984448951995,
492
+ "loss": 0.0855,
493
+ "step": 690
494
+ },
495
+ {
496
+ "epoch": 1.4198782961460445,
497
+ "grad_norm": 0.2110460251569748,
498
+ "learning_rate": 0.00010601757944557133,
499
+ "loss": 0.1028,
500
+ "step": 700
501
+ },
502
+ {
503
+ "epoch": 1.4401622718052738,
504
+ "grad_norm": 0.2486834079027176,
505
+ "learning_rate": 0.00010466531440162273,
506
+ "loss": 0.0612,
507
+ "step": 710
508
+ },
509
+ {
510
+ "epoch": 1.460446247464503,
511
+ "grad_norm": 0.06596266478300095,
512
+ "learning_rate": 0.00010331304935767412,
513
+ "loss": 0.1176,
514
+ "step": 720
515
+ },
516
+ {
517
+ "epoch": 1.4807302231237323,
518
+ "grad_norm": 0.23579204082489014,
519
+ "learning_rate": 0.00010196078431372549,
520
+ "loss": 0.0426,
521
+ "step": 730
522
+ },
523
+ {
524
+ "epoch": 1.5010141987829615,
525
+ "grad_norm": 0.08997461199760437,
526
+ "learning_rate": 0.00010060851926977689,
527
+ "loss": 0.1211,
528
+ "step": 740
529
+ },
530
+ {
531
+ "epoch": 1.5212981744421907,
532
+ "grad_norm": 0.08905690163373947,
533
+ "learning_rate": 9.925625422582827e-05,
534
+ "loss": 0.0583,
535
+ "step": 750
536
+ },
537
+ {
538
+ "epoch": 1.5415821501014197,
539
+ "grad_norm": 0.16227023303508759,
540
+ "learning_rate": 9.790398918187965e-05,
541
+ "loss": 0.0546,
542
+ "step": 760
543
+ },
544
+ {
545
+ "epoch": 1.5618661257606492,
546
+ "grad_norm": 0.10101054608821869,
547
+ "learning_rate": 9.655172413793105e-05,
548
+ "loss": 0.0993,
549
+ "step": 770
550
+ },
551
+ {
552
+ "epoch": 1.5821501014198782,
553
+ "grad_norm": 0.36903953552246094,
554
+ "learning_rate": 9.519945909398243e-05,
555
+ "loss": 0.0603,
556
+ "step": 780
557
+ },
558
+ {
559
+ "epoch": 1.6024340770791075,
560
+ "grad_norm": 0.4635933041572571,
561
+ "learning_rate": 9.384719405003381e-05,
562
+ "loss": 0.0524,
563
+ "step": 790
564
+ },
565
+ {
566
+ "epoch": 1.6227180527383367,
567
+ "grad_norm": 0.19389425218105316,
568
+ "learning_rate": 9.24949290060852e-05,
569
+ "loss": 0.0509,
570
+ "step": 800
571
+ },
572
+ {
573
+ "epoch": 1.643002028397566,
574
+ "grad_norm": 0.40768980979919434,
575
+ "learning_rate": 9.114266396213659e-05,
576
+ "loss": 0.045,
577
+ "step": 810
578
+ },
579
+ {
580
+ "epoch": 1.6632860040567952,
581
+ "grad_norm": 0.37976548075675964,
582
+ "learning_rate": 8.979039891818797e-05,
583
+ "loss": 0.0349,
584
+ "step": 820
585
+ },
586
+ {
587
+ "epoch": 1.6835699797160242,
588
+ "grad_norm": 0.15103350579738617,
589
+ "learning_rate": 8.843813387423935e-05,
590
+ "loss": 0.0381,
591
+ "step": 830
592
+ },
593
+ {
594
+ "epoch": 1.7038539553752536,
595
+ "grad_norm": 0.0796438679099083,
596
+ "learning_rate": 8.708586883029074e-05,
597
+ "loss": 0.1125,
598
+ "step": 840
599
+ },
600
+ {
601
+ "epoch": 1.7241379310344827,
602
+ "grad_norm": 0.2372894436120987,
603
+ "learning_rate": 8.573360378634213e-05,
604
+ "loss": 0.0524,
605
+ "step": 850
606
+ },
607
+ {
608
+ "epoch": 1.744421906693712,
609
+ "grad_norm": 0.06453035771846771,
610
+ "learning_rate": 8.438133874239351e-05,
611
+ "loss": 0.0628,
612
+ "step": 860
613
+ },
614
+ {
615
+ "epoch": 1.7647058823529411,
616
+ "grad_norm": 0.08101903647184372,
617
+ "learning_rate": 8.302907369844491e-05,
618
+ "loss": 0.0932,
619
+ "step": 870
620
+ },
621
+ {
622
+ "epoch": 1.7849898580121704,
623
+ "grad_norm": 0.19378355145454407,
624
+ "learning_rate": 8.167680865449628e-05,
625
+ "loss": 0.0514,
626
+ "step": 880
627
+ },
628
+ {
629
+ "epoch": 1.8052738336713996,
630
+ "grad_norm": 0.19586940109729767,
631
+ "learning_rate": 8.032454361054767e-05,
632
+ "loss": 0.0883,
633
+ "step": 890
634
+ },
635
+ {
636
+ "epoch": 1.8255578093306288,
637
+ "grad_norm": 0.297462522983551,
638
+ "learning_rate": 7.897227856659906e-05,
639
+ "loss": 0.1196,
640
+ "step": 900
641
+ },
642
+ {
643
+ "epoch": 1.845841784989858,
644
+ "grad_norm": 0.36705586314201355,
645
+ "learning_rate": 7.762001352265045e-05,
646
+ "loss": 0.0719,
647
+ "step": 910
648
+ },
649
+ {
650
+ "epoch": 1.866125760649087,
651
+ "grad_norm": 0.6795341372489929,
652
+ "learning_rate": 7.626774847870182e-05,
653
+ "loss": 0.0981,
654
+ "step": 920
655
+ },
656
+ {
657
+ "epoch": 1.8864097363083165,
658
+ "grad_norm": 0.25088199973106384,
659
+ "learning_rate": 7.491548343475322e-05,
660
+ "loss": 0.0941,
661
+ "step": 930
662
+ },
663
+ {
664
+ "epoch": 1.9066937119675456,
665
+ "grad_norm": 0.0679168701171875,
666
+ "learning_rate": 7.35632183908046e-05,
667
+ "loss": 0.0841,
668
+ "step": 940
669
+ },
670
+ {
671
+ "epoch": 1.9269776876267748,
672
+ "grad_norm": 0.11561597138643265,
673
+ "learning_rate": 7.2210953346856e-05,
674
+ "loss": 0.046,
675
+ "step": 950
676
+ },
677
+ {
678
+ "epoch": 1.947261663286004,
679
+ "grad_norm": 0.07672413438558578,
680
+ "learning_rate": 7.085868830290738e-05,
681
+ "loss": 0.1174,
682
+ "step": 960
683
+ },
684
+ {
685
+ "epoch": 1.9675456389452333,
686
+ "grad_norm": 0.2567373216152191,
687
+ "learning_rate": 6.950642325895876e-05,
688
+ "loss": 0.0489,
689
+ "step": 970
690
+ },
691
+ {
692
+ "epoch": 1.9878296146044625,
693
+ "grad_norm": 0.2821916937828064,
694
+ "learning_rate": 6.815415821501014e-05,
695
+ "loss": 0.0578,
696
+ "step": 980
697
+ }
698
+ ],
699
+ "logging_steps": 10,
700
+ "max_steps": 1479,
701
+ "num_input_tokens_seen": 0,
702
+ "num_train_epochs": 3,
703
+ "save_steps": 500,
704
+ "stateful_callbacks": {
705
+ "TrainerControl": {
706
+ "args": {
707
+ "should_epoch_stop": false,
708
+ "should_evaluate": false,
709
+ "should_log": false,
710
+ "should_save": true,
711
+ "should_training_stop": false
712
+ },
713
+ "attributes": {}
714
+ }
715
+ },
716
+ "total_flos": 1.621813622734848e+16,
717
+ "train_batch_size": 1,
718
+ "trial_name": null,
719
+ "trial_params": null
720
+ }
capybara-finetuned/{checkpoint-193 → checkpoint-986}/training_args.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb5dfa95d8bedc071d0ca429ace88a97d08b4e6c0549993636c23bd1392d3f9
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2100089ad10458b37c0f5f32a5e01b69d497af008f5f732e686747ea1860ac98
3
  size 5304
capybara-finetuned/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb5dfa95d8bedc071d0ca429ace88a97d08b4e6c0549993636c23bd1392d3f9
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2100089ad10458b37c0f5f32a5e01b69d497af008f5f732e686747ea1860ac98
3
  size 5304