oldiday commited on
Commit
029947c
·
verified ·
1 Parent(s): bc08440

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:e064a5d5d8aad1cb95c1b3520bd70d9302e1f36c9f93e3dfdae85d6f2e340f7a
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:297b38e69f29c26c634ac37317584ca6d05b2c37d4797c966e442a92c7ffefa3
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3174032e752723bbbca33f9601321b2b08cdbf096ac72cb23e87b56dd4066d1
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3b6a4089390339c40d8c6b6e9c6df0bde9061861f57763aaebf5fe3be34e89
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49324b9e90e4a3300216fe09ec318d103f16e5de8c543c825c0b873b9acee835
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d1dffd43c641606e054f7ea218bf8a83debf312b1baadbf2c3f507d6e23d65e
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": 0.8955223880597015,
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": 15.057,
161
  "eval_steps_per_second": 1.949,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 5.881123817127936e+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": 1.0746268656716418,
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": 15.057,
161
  "eval_steps_per_second": 1.949,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.9552238805970149,
166
+ "grad_norm": 0.5606002807617188,
167
+ "learning_rate": 3.104804738999169e-05,
168
+ "loss": 1.0615,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 1.0149253731343284,
173
+ "grad_norm": 1.186905860900879,
174
+ "learning_rate": 2.8479327524001636e-05,
175
+ "loss": 1.1214,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 1.0746268656716418,
180
+ "grad_norm": 0.5500369668006897,
181
+ "learning_rate": 2.587248741756253e-05,
182
+ "loss": 0.8825,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 1.0746268656716418,
187
+ "eval_loss": 1.0109927654266357,
188
+ "eval_runtime": 5.6371,
189
+ "eval_samples_per_second": 15.079,
190
+ "eval_steps_per_second": 1.951,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 7.053264466791629e+16,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null