ccore commited on
Commit
55ff938
·
verified ·
1 Parent(s): c0fcbc1

Training in progress, epoch 4, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e09b2888c55226003d1777f8e74624ba24b23e653122bda72249d07cea5cc534
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:843cba4b3e81054050c1c8b16fe3d72610de13da96a25cfd3a66da50db03ba19
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7b43b9be14768ed562cc56fbceb4e4c212eff27a8bced56a087b2aaf2fed8a7
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e65a2ebeb383e088f82c4048574d61facefce2da766775b042bce0e395aa527
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:376d7899996a3d8015fb5b3439bc1391f1ffa20289c9f6ee4d9dd26e8beaf425
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a713c54e84cd48df8f7467fb50d1ee9fbe2656c83e7b41aac5e97a0c0dbebd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e0d537959189cef256eb23e89b5091772521a8ab26abc843e67a86264df692a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ee1e582342ae1078e771a171c799cb711145cb11265428051f9e7562adbe8b0
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.5381864309310913,
3
- "best_model_checkpoint": "./opt_trained3/checkpoint-45",
4
- "epoch": 3.0,
5
  "eval_steps": 500,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -31,6 +31,14 @@
31
  "eval_samples_per_second": 50.158,
32
  "eval_steps_per_second": 12.539,
33
  "step": 45
 
 
 
 
 
 
 
 
34
  }
35
  ],
36
  "logging_steps": 500,
@@ -50,7 +58,7 @@
50
  "attributes": {}
51
  }
52
  },
53
- "total_flos": 1669816840320000.0,
54
  "train_batch_size": 24,
55
  "trial_name": null,
56
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5374372005462646,
3
+ "best_model_checkpoint": "./opt_trained3/checkpoint-60",
4
+ "epoch": 4.0,
5
  "eval_steps": 500,
6
+ "global_step": 60,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
31
  "eval_samples_per_second": 50.158,
32
  "eval_steps_per_second": 12.539,
33
  "step": 45
34
+ },
35
+ {
36
+ "epoch": 4.0,
37
+ "eval_loss": 0.5374372005462646,
38
+ "eval_runtime": 5.9965,
39
+ "eval_samples_per_second": 50.03,
40
+ "eval_steps_per_second": 12.507,
41
+ "step": 60
42
  }
43
  ],
44
  "logging_steps": 500,
 
58
  "attributes": {}
59
  }
60
  },
61
+ "total_flos": 2226422453760000.0,
62
  "train_batch_size": 24,
63
  "trial_name": null,
64
  "trial_params": null