ardaspear commited on
Commit
956bb0c
·
verified ·
1 Parent(s): d47a2eb

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:a65e8ce83131fe626769bc95afa2f1787b2ad53bfc84619e75739bf1988b3813
3
  size 162933396
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9107fafa3feb2315c0bfdcc6cc8ec2c735d37487a11022c7e2850cf0e953e4d7
3
  size 162933396
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dbb49bef08cf8288b1bc9f3b6e725c48f9cb02ec3c5f7649f37de04fbffc476
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4225b533e4e9dd54d7aa3f270f10463a965c47e914701f2f60fa9f7dcf3dd1
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": 0.3146067415730337,
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": 7.145,
149
  "eval_steps_per_second": 1.824,
150
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  }
152
  ],
153
  "logging_steps": 3,
@@ -167,7 +189,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 4.420978277665997e+16,
171
  "train_batch_size": 4,
172
  "trial_name": null,
173
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3595505617977528,
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": 7.145,
149
  "eval_steps_per_second": 1.824,
150
  "step": 35
151
+ },
152
+ {
153
+ "epoch": 0.3235955056179775,
154
+ "grad_norm": NaN,
155
+ "learning_rate": 2.7300475013022663e-05,
156
+ "loss": 0.0,
157
+ "step": 36
158
+ },
159
+ {
160
+ "epoch": 0.350561797752809,
161
+ "grad_norm": NaN,
162
+ "learning_rate": 1.7527597583490822e-05,
163
+ "loss": 0.0,
164
+ "step": 39
165
+ },
166
+ {
167
+ "epoch": 0.3595505617977528,
168
+ "eval_loss": NaN,
169
+ "eval_runtime": 13.1422,
170
+ "eval_samples_per_second": 7.153,
171
+ "eval_steps_per_second": 1.826,
172
+ "step": 40
173
  }
174
  ],
175
  "logging_steps": 3,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 5.061937953610138e+16,
193
  "train_batch_size": 4,
194
  "trial_name": null,
195
  "trial_params": null