ardaspear commited on
Commit
a773ec1
·
verified ·
1 Parent(s): 070843d

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 sha256:96ae921e895bcd8204a64656686dafacd5b789b4cc44388ec452082c1b0961a1
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5dab9574c2b6d235b2ee6f10756f7cfdfc52f332a9b58f3eca2b86a1cfda1cb
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4e897ab2d964ac8f8076065575d25846b306ddccd8c181c45365480a8ce10bf
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8643a05f710ab8e087e407667bb1956cccbed5c666bceb85abd407d3211981d7
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:599b9972ee45f3a6b4a0614ff019c3d8d9975b9f24af949c6d4998026461b28b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f79a1e31a322b1a2e29b8aea291d95f55115db82ac310645decbdf92e040800
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": 0.6371681415929203,
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": 7.762,
248
  "eval_steps_per_second": 1.961,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 1.0400790686466048e+17,
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": 0.7168141592920354,
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": 7.762,
248
  "eval_steps_per_second": 1.961,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.6637168141592921,
253
+ "grad_norm": 4.825639189220965e-05,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 0.0,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.6902654867256637,
260
+ "grad_norm": 0.0025355853140354156,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 0.0,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.7168141592920354,
267
+ "grad_norm": 6.508089427370578e-05,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 0.0,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.7168141592920354,
274
+ "eval_loss": 2.18654548689301e-07,
275
+ "eval_runtime": 12.2613,
276
+ "eval_samples_per_second": 7.748,
277
+ "eval_steps_per_second": 1.957,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 1.1785416071970816e+17,
299
  "train_batch_size": 4,
300
  "trial_name": null,
301
  "trial_params": null