ardaspear commited on
Commit
0d47d77
·
verified ·
1 Parent(s): 36ab561

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:a69d4b13e965a3c836107b9098733b9a91c9a3f0b464cd9a9cc7321aa806efdb
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92adfd72e84aecd68d40f936b5fa9d2ccb282c3831b7297c7ff64670c3de44ae
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfadffdc10f43bbdd3c0cebd302f1e75d95eaaf101eb405c45f31b7addf36c68
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:119379ba78824bc2ef19fabec56af995ff9e1efbe6b573a978bde74a12a1dffb
3
  size 159641092
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b858b78f36c65303cc43c5895026eba72df7985e2a9ad8127cc9604564de326b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed104dfedc6618e2b40c9ea106808ac60ea59288a0c132678bbda3edf9b3c3bf
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": 0.0028269383668541475,
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": 27.586,
248
  "eval_steps_per_second": 6.896,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 1.4582792117551104e+16,
270
  "train_batch_size": 4,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.003180305662710916,
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": 27.586,
248
  "eval_steps_per_second": 6.896,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.0029447274654730705,
253
+ "grad_norm": 3.209977876394987e-05,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 0.0,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.003062516564091993,
260
+ "grad_norm": 2.9874341635149904e-05,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 0.0,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.003180305662710916,
267
+ "grad_norm": 3.113800266874023e-05,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 0.0,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.003180305662710916,
274
+ "eval_loss": 0.0005310006672516465,
275
+ "eval_runtime": 777.5014,
276
+ "eval_samples_per_second": 27.586,
277
+ "eval_steps_per_second": 6.896,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 1.6405641132244992e+16,
299
  "train_batch_size": 4,
300
  "trial_name": null,
301
  "trial_params": null