brixeus commited on
Commit
7491e0f
·
verified ·
1 Parent(s): 8231360

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:f7420e4d3e2ee017d4692df8503f0eef13833bbd25c970cd6556f64c55109287
3
  size 100697728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:537f6c2732e69b0507534e3171d3d688087f420322b3b0d3556836734372e899
3
  size 100697728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2edfdd5bc8e58ca9a7b2f29febdce69a4e711bfca8e65819b4e662302828c5b1
3
  size 51418196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f729d0a910a7c462e6f7d1de699303aec58fd25312e08ec4051433d4cab90076
3
  size 51418196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5207043c5b33c602de04e5de247689e035286894ab3238d36305921eebfde0b2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56950fd55c0f052c78b8d8c2a9db7ac6e2db75faed414b2f06069e908055f19f
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": 0.005183436042158613,
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": 21.837,
306
  "eval_steps_per_second": 2.73,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 6.797317665875558e+16,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0057017796463744745,
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": 21.837,
306
  "eval_steps_per_second": 2.73,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.0053562172435639,
311
+ "grad_norm": 0.9962571859359741,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 9.2092,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.005528998444969188,
318
+ "grad_norm": 1.0119867324829102,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 9.5268,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.0057017796463744745,
325
+ "grad_norm": 1.0774887800216675,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 9.4073,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.0057017796463744745,
332
+ "eval_loss": 2.4344372749328613,
333
+ "eval_runtime": 1338.1241,
334
+ "eval_samples_per_second": 21.854,
335
+ "eval_steps_per_second": 2.732,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 7.460470608887808e+16,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null