RoyJoy commited on
Commit
09b1c39
·
verified ·
1 Parent(s): 40a4be3

Training in progress, step 26, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:954ac47ac3c5d06fcb48111b9491adc8aa9b51a62b3d8b47b4dcbc8be2493468
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83dc4a29e9fad91afb04b519bb068889f5562fa8cb33f3105b8a5ebc63e375aa
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87ed46ad6c5b345164df5482e6f48f824f494f99358d99ee8ac4fe305f2d4150
3
  size 18810036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d9b0a631533c00609f474655b03a16ae3902a7acc9767684d28ae4ebb97948a
3
  size 18810036
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20a6ef3006adf5f9e602883e224336641c549072267eea9b4e8df3bf07dbedbb
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6216dc83f24b17415976279736a88142c79dbe0c54e5abb8dfeed35308a890c
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:577c789f4d54f97c7a38bb2a12f37b5f6bf2e502ba76bfd0eedeefec1792f673
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd34f63e44f9069fae7082f243a54db35fc68a432ae6aa527241e906af3957c
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2052023e8e722171e8f41e2880af14679ce70e2959744c18745d7107a34b3dcb
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9403c85bf61e63b29aa17f85d67574a6719cd35ddf4bafac4bd64d6b0f040e46
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4308aefcd7175d37a3da6ddc92e7aa879f2a597238c78e55cc1f665f24fd72ae
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:813a3607511b244d531aecd7484e78d5c8539b61749ecd7598b1f17679fac19c
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.1951219512195122,
5
  "eval_steps": 13,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -114,6 +114,105 @@
114
  "eval_samples_per_second": 111.684,
115
  "eval_steps_per_second": 14.178,
116
  "step": 13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
117
  }
118
  ],
119
  "logging_steps": 1,
@@ -133,7 +232,7 @@
133
  "attributes": {}
134
  }
135
  },
136
- "total_flos": 1.499584945717248e+16,
137
  "train_batch_size": 2,
138
  "trial_name": null,
139
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3902439024390244,
5
  "eval_steps": 13,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
114
  "eval_samples_per_second": 111.684,
115
  "eval_steps_per_second": 14.178,
116
  "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.2101313320825516,
120
+ "grad_norm": 6.852001667022705,
121
+ "learning_rate": 9.755282581475769e-05,
122
+ "loss": 0.8059,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.225140712945591,
127
+ "grad_norm": 15.55766487121582,
128
+ "learning_rate": 9.619397662556435e-05,
129
+ "loss": 0.7977,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.2401500938086304,
134
+ "grad_norm": 6.66907262802124,
135
+ "learning_rate": 9.45503262094184e-05,
136
+ "loss": 0.7264,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.2551594746716698,
141
+ "grad_norm": 6.188997745513916,
142
+ "learning_rate": 9.263200821770461e-05,
143
+ "loss": 0.7352,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.2701688555347092,
148
+ "grad_norm": 2.3706018924713135,
149
+ "learning_rate": 9.045084971874738e-05,
150
+ "loss": 0.719,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.2851782363977486,
155
+ "grad_norm": 5.199508190155029,
156
+ "learning_rate": 8.802029828000156e-05,
157
+ "loss": 0.755,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.300187617260788,
162
+ "grad_norm": 2.7987897396087646,
163
+ "learning_rate": 8.535533905932738e-05,
164
+ "loss": 0.7206,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.3151969981238274,
169
+ "grad_norm": 3.605015516281128,
170
+ "learning_rate": 8.247240241650918e-05,
171
+ "loss": 0.7075,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.3302063789868668,
176
+ "grad_norm": 1.987611174583435,
177
+ "learning_rate": 7.938926261462366e-05,
178
+ "loss": 0.7034,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.3452157598499062,
183
+ "grad_norm": 2.15010666847229,
184
+ "learning_rate": 7.612492823579745e-05,
185
+ "loss": 0.698,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.3602251407129456,
190
+ "grad_norm": 2.248389959335327,
191
+ "learning_rate": 7.269952498697734e-05,
192
+ "loss": 0.717,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.37523452157598497,
197
+ "grad_norm": 1.4804418087005615,
198
+ "learning_rate": 6.91341716182545e-05,
199
+ "loss": 0.707,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.3902439024390244,
204
+ "grad_norm": 3.2395734786987305,
205
+ "learning_rate": 6.545084971874738e-05,
206
+ "loss": 0.708,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.3902439024390244,
211
+ "eval_loss": 0.6942992806434631,
212
+ "eval_runtime": 4.0219,
213
+ "eval_samples_per_second": 111.638,
214
+ "eval_steps_per_second": 14.172,
215
+ "step": 26
216
  }
217
  ],
218
  "logging_steps": 1,
 
232
  "attributes": {}
233
  }
234
  },
235
+ "total_flos": 2.999169891434496e+16,
236
  "train_batch_size": 2,
237
  "trial_name": null,
238
  "trial_params": null