leixa commited on
Commit
ac63052
·
verified ·
1 Parent(s): 9525518

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 sha256:43ab75bb9becb657d610f76874db111c38a9d91f73fe8db02640659faac13c5e
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716c95d71d14195f7609f2b47b8cd394054c201c713778941a925565eb5c9fbe
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2132d0e55c326e0c24a8e138aae528acad3593299a4827e25e96118c3232c7e5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1d95bf1a292ea4a2936184a69f8c3dce438a13419e0bcc2bef40ba98d756d8
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": 0.10050251256281408,
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": 64.76,
149
  "eval_steps_per_second": 8.164,
150
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  }
152
  ],
153
  "logging_steps": 3,
@@ -167,7 +189,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 2704968851128320.0,
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": 0.11486001435750179,
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": 64.76,
149
  "eval_steps_per_second": 8.164,
150
  "step": 35
151
+ },
152
+ {
153
+ "epoch": 0.10337401292175162,
154
+ "grad_norm": NaN,
155
+ "learning_rate": 2.7300475013022663e-05,
156
+ "loss": 0.0,
157
+ "step": 36
158
+ },
159
+ {
160
+ "epoch": 0.11198851399856424,
161
+ "grad_norm": NaN,
162
+ "learning_rate": 1.7527597583490822e-05,
163
+ "loss": 0.0,
164
+ "step": 39
165
+ },
166
+ {
167
+ "epoch": 0.11486001435750179,
168
+ "eval_loss": NaN,
169
+ "eval_runtime": 9.0704,
170
+ "eval_samples_per_second": 64.716,
171
+ "eval_steps_per_second": 8.158,
172
+ "step": 40
173
  }
174
  ],
175
  "logging_steps": 3,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 3091392972718080.0,
193
  "train_batch_size": 8,
194
  "trial_name": null,
195
  "trial_params": null