ardaspear commited on
Commit
06e3f29
·
verified ·
1 Parent(s): eec6280

Training in progress, step 40, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14d79aec87f25697b8cf04ac479bb9cdc2a09c6015a47112596f400eff01a54c
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4bca8dc6894e75279e93a96b36f4359e88ace00e60885863270ad773f3055e
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6c760e18afd0b6280aeb7d401fe56fa9e714d09b578fad90d37a6e9ad6827b0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42e4d0276ac2fb70e5c0593f417f2d935273357ff980559b410f61ea4ea09832
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
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": 0.006458458273746367,
5
  "eval_steps": 5,
6
- "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -148,6 +148,28 @@
148
  "eval_samples_per_second": 14.464,
149
  "eval_steps_per_second": 1.808,
150
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  }
152
  ],
153
  "logging_steps": 3,
@@ -167,7 +189,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 5.008493031456768e+16,
171
  "train_batch_size": 8,
172
  "trial_name": null,
173
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.007381095169995848,
5
  "eval_steps": 5,
6
+ "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
148
  "eval_samples_per_second": 14.464,
149
  "eval_steps_per_second": 1.808,
150
  "step": 35
151
+ },
152
+ {
153
+ "epoch": 0.0066429856529962635,
154
+ "grad_norm": NaN,
155
+ "learning_rate": 2.7300475013022663e-05,
156
+ "loss": 0.0,
157
+ "step": 36
158
+ },
159
+ {
160
+ "epoch": 0.007196567790745952,
161
+ "grad_norm": NaN,
162
+ "learning_rate": 1.7527597583490822e-05,
163
+ "loss": 0.0,
164
+ "step": 39
165
+ },
166
+ {
167
+ "epoch": 0.007381095169995848,
168
+ "eval_loss": NaN,
169
+ "eval_runtime": 630.8367,
170
+ "eval_samples_per_second": 14.468,
171
+ "eval_steps_per_second": 1.809,
172
+ "step": 40
173
  }
174
  ],
175
  "logging_steps": 3,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 5.723992035950592e+16,
193
  "train_batch_size": 8,
194
  "trial_name": null,
195
  "trial_params": null