auxyus commited on
Commit
1131cd5
·
verified ·
1 Parent(s): 5b972b5

Training in progress, step 81, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97804f9f09cf0ecf88bfca955046ad34c2c2c59beaced40aee860d24a1e80e0a
3
  size 17425352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adca24c088ae3064673c96e464b0b5eb9253b21ef141b878b97e9ed5b2923d64
3
  size 17425352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab64cd401a8783cd9b2229082cef6286302bda815d67d8690a2032ae42437ad7
3
  size 10251668
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8f03d74e8beff9335eededd2325c1935f7078a5eedb5b1ea5a64dd7efa36d6
3
  size 10251668
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f397bae6af9e9ebb0562210f7bedbff739d13eeefe074a6c9b7198b1e7bbf338
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac564aab16c172e33ed70be43603bd16c90e9919ba57413e6141b17ae5103921
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
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": 0.16744186046511628,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 69.678,
248
  "eval_steps_per_second": 8.758,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 4515366394920960.0,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1883720930232558,
5
  "eval_steps": 9,
6
+ "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
247
  "eval_samples_per_second": 69.678,
248
  "eval_steps_per_second": 8.758,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.1744186046511628,
253
+ "grad_norm": 0.94745934009552,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 3.7317,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.1813953488372093,
260
+ "grad_norm": 0.8033557534217834,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 3.7478,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.1883720930232558,
267
+ "grad_norm": 0.942162036895752,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 3.4858,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.1883720930232558,
274
+ "eval_loss": 3.5632054805755615,
275
+ "eval_runtime": 10.3798,
276
+ "eval_samples_per_second": 69.751,
277
+ "eval_steps_per_second": 8.767,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 5079787194286080.0,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null