VERSIL91 commited on
Commit
c73cade
·
verified ·
1 Parent(s): 80387c6

Training in progress, step 4, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:895a12ff53e8065e99b232b4f04634bd661debb735b34afcae2c0361466b6a8a
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f5697ec13e3acc69308daae7c8374e571a6df565b399c8149d56bf76c6515d
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b15188ee33064b7296b6ccc4930bbcee5b258136e1d2dc91c1b3590dc45c2416
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21d2383923e834a9801b89a23b16a046aeb25da4365a83c888cb15d2821e4e28
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
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": 0.001251417621524383,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 26.731,
38
  "eval_steps_per_second": 13.366,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1479651398516736.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002502835243048766,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 26.731,
38
  "eval_steps_per_second": 13.366,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0018771264322865746,
43
+ "grad_norm": 3.2327237129211426,
44
+ "learning_rate": 3e-05,
45
+ "loss": 2.207,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.002502835243048766,
50
+ "grad_norm": 2.9982106685638428,
51
+ "learning_rate": 4e-05,
52
+ "loss": 2.0214,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.002502835243048766,
57
+ "eval_loss": 2.208998441696167,
58
+ "eval_runtime": 109.5929,
59
+ "eval_samples_per_second": 24.564,
60
+ "eval_steps_per_second": 12.282,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2959302797033472.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null