ardaspear commited on
Commit
8648fe9
·
verified ·
1 Parent(s): e2ad754

Training in progress, step 99, 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:ca6fcfc317190b3c10bb6483b2408ef2a0b29f64cf246465d8551432dbb2fa9a
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b8535ce5de58dd63f34b8043d253eeac9eea5e3907f45acf97c126b39d2a6c
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3022a3ace88562cdb896a3843a04b79fae0674fa5890d40062c5670eca79d5f6
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8533a3faf3630f31cddd9760b4819aa442d238ffe008399be37b5917a97f6a1
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:cffb28af98bf98a8ea3309520e1b6df275194f6bbb1c206aba0a187dfbac832d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22f2fda467cd25026edf60d16b6556f10fde836c761f4769abd354d0b3232d3e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
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": 0.0035336729585676847,
5
  "eval_steps": 9,
6
- "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -305,6 +305,35 @@
305
  "eval_samples_per_second": 27.586,
306
  "eval_steps_per_second": 6.896,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.822849014693888e+16,
328
  "train_batch_size": 4,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.003887040254424453,
5
  "eval_steps": 9,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
305
  "eval_samples_per_second": 27.586,
306
  "eval_steps_per_second": 6.896,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.0036514620571866073,
311
+ "grad_norm": 2.96364141831873e-05,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 0.0,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.0037692511558055303,
318
+ "grad_norm": 3.082916373386979e-05,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 0.0,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.003887040254424453,
325
+ "grad_norm": 2.8683465643553063e-05,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 0.0,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.003887040254424453,
332
+ "eval_loss": 0.0005314745358191431,
333
+ "eval_runtime": 777.4915,
334
+ "eval_samples_per_second": 27.586,
335
+ "eval_steps_per_second": 6.897,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 2.005133916163277e+16,
357
  "train_batch_size": 4,
358
  "trial_name": null,
359
  "trial_params": null