ardaspear commited on
Commit
7aa8494
·
verified ·
1 Parent(s): 7d829f7

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 sha256:49f30c4c505b6bc2fa9b9c9032c3de34fe90603c1c788bce24bdba7d93c78ada
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a5a8fd74b8fa36949c6c85f6bf7536f39c3fae50357aeb05ee427e9f519ddd
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dc0d66eb2dbcef0d88c488dea0aa5d0ab96543623260fb168804101deab5325
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ca33750c8c901afb3d92362b9af0c219f62c7b56aeed68e6e7875a3cffac07
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d78fb67a36a8ef685bd85c725b53ceb6959fc211f83739a3ee60241ff56c81f4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ed823756481de62e690edd754f7f54a40e9e3e0ac2be069841e8f5c60b2c76c
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": 0.2701688555347092,
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": 13.658,
248
  "eval_steps_per_second": 3.46,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 5.118799267233792e+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": 0.30393996247654786,
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": 13.658,
248
  "eval_steps_per_second": 3.46,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.28142589118198874,
253
+ "grad_norm": 0.008015623316168785,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 0.0002,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.2926829268292683,
260
+ "grad_norm": 0.09628616273403168,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 0.001,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.30393996247654786,
267
+ "grad_norm": 0.019364288076758385,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 0.0024,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.30393996247654786,
274
+ "eval_loss": 0.0014989529736340046,
275
+ "eval_runtime": 16.4648,
276
+ "eval_samples_per_second": 13.666,
277
+ "eval_steps_per_second": 3.462,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 5.758649175638016e+16,
299
  "train_batch_size": 4,
300
  "trial_name": null,
301
  "trial_params": null