pilotj commited on
Commit
afc2edc
·
verified ·
1 Parent(s): 80e692b

Training in progress, step 20313, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d861f1c50b4babeb0ddfe9f4020bcb3a996a9eb9d7a41ad0576af16e2c79fd8
3
  size 267906392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faf59f0ceef9d6c6a8e1aae52b1676cc70b5f73ebc82fb606ba168ea0edf18ba
3
  size 267906392
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13be2966720ba7ce0917ac84fc7970ac5972585de122eecab46a2a797f56f02b
3
  size 535874874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1c31b7e9dd5cc43389500ab26330d1c4e37b796731b18f04fe714d2ac0b909
3
  size 535874874
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba7e8f705c23164d5593ce6d42004b8dd0f6ac10452a22909c826fec1f8a5f6d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a02b7af990d61d8bd7a78e7e63d0963a06c28b6f029475a54945285d842b8a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67909ecb00418f832a3d7b80fc531337432dc34bd11aad10d0c49e76cd1ab91f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4eadf56e31ad52d563a55cb98432ed46602e0c5ea9f425ff126fdfa6b4b403c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.4073016345500946,
3
  "best_model_checkpoint": "/kaggle/working/results/checkpoint-20000",
4
- "epoch": 0.9845911485255747,
5
  "eval_steps": 2000,
6
- "global_step": 20000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -381,12 +381,12 @@
381
  "should_evaluate": false,
382
  "should_log": false,
383
  "should_save": true,
384
- "should_training_stop": false
385
  },
386
  "attributes": {}
387
  }
388
  },
389
- "total_flos": 8.481542111232e+16,
390
  "train_batch_size": 32,
391
  "trial_name": null,
392
  "trial_params": null
 
1
  {
2
  "best_metric": 0.4073016345500946,
3
  "best_model_checkpoint": "/kaggle/working/results/checkpoint-20000",
4
+ "epoch": 1.0,
5
  "eval_steps": 2000,
6
+ "global_step": 20313,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
381
  "should_evaluate": false,
382
  "should_log": false,
383
  "should_save": true,
384
+ "should_training_stop": true
385
  },
386
  "attributes": {}
387
  }
388
  },
389
+ "total_flos": 8.61406620672e+16,
390
  "train_batch_size": 32,
391
  "trial_name": null,
392
  "trial_params": null