ardaspear commited on
Commit
cc08b9b
·
verified ·
1 Parent(s): 94a37e4

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:dcde46922143049b9245734529a5e64c31f2f7305532314b1ac55ed3baa635cc
3
  size 247936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb3391cc964032c4f7bbececa19b46ffa89526608f10dc32217bf61d3203c27c
3
  size 247936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6639522835626391eb5b4f47e0a41c4cb163b7913c17c522755321d98cbcfc80
3
  size 263024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e05c54bd7d150324fee7fb367dbf0999cb0f7383c79b063e43a7dea0435733e9
3
  size 263024
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12002707d6533b4858bef1387878cda57708ad78dd95cf4b6295e0d81c054e61
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e60026f80fd7f1a2958d0aa771127ff3ac2eee272a3f23e35c58ef19e35fd09
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": 0.08184143222506395,
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": 155.753,
248
  "eval_steps_per_second": 39.096,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 643246325760.0,
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": 0.09207161125319693,
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": 155.753,
248
  "eval_steps_per_second": 39.096,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.08525149190110827,
253
+ "grad_norm": 1.064352035522461,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 43.7996,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.0886615515771526,
260
+ "grad_norm": 0.9701411128044128,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 43.8023,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.09207161125319693,
267
+ "grad_norm": 1.058826208114624,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 43.8552,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.09207161125319693,
274
+ "eval_loss": 10.935081481933594,
275
+ "eval_runtime": 4.232,
276
+ "eval_samples_per_second": 175.096,
277
+ "eval_steps_per_second": 43.951,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 719774023680.0,
299
  "train_batch_size": 4,
300
  "trial_name": null,
301
  "trial_params": null