oldiday commited on
Commit
9f5f300
·
verified ·
1 Parent(s): 3c9dd50

Training in progress, step 54, 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:a2c6e0fa1fe23124e957d30d9dd4a4888ad417d78d5d5b86df0ad3407c1a3a34
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ea403b9e05fa7f5f11fe5cf5b8f41e8b49a755b6e7442ced9b8db5a869580f
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4063bb97ee3e64b28ed94b0c443d63755fca0f23da0be53e7351204ea8b682c8
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b0900d270d90df98b84180d3dd7df5c1a4f78bd87338f3b2c6d691bb45139ea
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05de074c39f85666a0a560cfe9d1a3cb4d0dea668ee250ea7d270dcd0130b7ff
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:534e7c453aeda04ef26a9783b095419e7223ca9b7e276c9ec61094ca16162658
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
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": 0.10465116279069768,
5
  "eval_steps": 9,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -160,6 +160,35 @@
160
  "eval_samples_per_second": 36.406,
161
  "eval_steps_per_second": 4.576,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 1.175641953140736e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.12558139534883722,
5
  "eval_steps": 9,
6
+ "global_step": 54,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
160
  "eval_samples_per_second": 36.406,
161
  "eval_steps_per_second": 4.576,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.11162790697674418,
166
+ "grad_norm": 3.60516095161438,
167
+ "learning_rate": 3.104804738999169e-05,
168
+ "loss": 2.7192,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.1186046511627907,
173
+ "grad_norm": 3.239312171936035,
174
+ "learning_rate": 2.8479327524001636e-05,
175
+ "loss": 2.7269,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.12558139534883722,
180
+ "grad_norm": 2.7312939167022705,
181
+ "learning_rate": 2.587248741756253e-05,
182
+ "loss": 2.6379,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.12558139534883722,
187
+ "eval_loss": 2.7178566455841064,
188
+ "eval_runtime": 19.8989,
189
+ "eval_samples_per_second": 36.384,
190
+ "eval_steps_per_second": 4.573,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 1.4107703437688832e+16,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null