ardaspear commited on
Commit
d4feaaf
·
verified ·
1 Parent(s): 7a95a3f

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 sha256:99f77011c2753a3764b3dcb336ff0b12ddc119e028e891a447e623435172b859
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc55f53855e0ad12c49455e02175feb614b48f2877c80cadb38dffb451f32e89
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61ce952228f10d7511a36ea2edf5a18940a1e3d0d4d4efdf305c0149a645b3eb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bf98a67c599286dab5162f19b7a37e68ecdaa1d1318df7d5427ad8fa0313846
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": 0.01038961038961039,
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": 13.368,
149
  "eval_steps_per_second": 1.673,
150
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  }
152
  ],
153
  "logging_steps": 3,
@@ -167,7 +189,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 5.089195621298995e+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": 0.011873840445269016,
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": 13.368,
149
  "eval_steps_per_second": 1.673,
150
  "step": 35
151
+ },
152
+ {
153
+ "epoch": 0.010686456400742115,
154
+ "grad_norm": NaN,
155
+ "learning_rate": 2.7300475013022663e-05,
156
+ "loss": 0.0,
157
+ "step": 36
158
+ },
159
+ {
160
+ "epoch": 0.01157699443413729,
161
+ "grad_norm": NaN,
162
+ "learning_rate": 1.7527597583490822e-05,
163
+ "loss": 0.0,
164
+ "step": 39
165
+ },
166
+ {
167
+ "epoch": 0.011873840445269016,
168
+ "eval_loss": NaN,
169
+ "eval_runtime": 424.5651,
170
+ "eval_samples_per_second": 13.364,
171
+ "eval_steps_per_second": 1.672,
172
+ "step": 40
173
  }
174
  ],
175
  "logging_steps": 3,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 5.854238100317798e+16,
193
  "train_batch_size": 8,
194
  "trial_name": null,
195
  "trial_params": null