ardaspear commited on
Commit
9eefd19
·
verified ·
1 Parent(s): c9b961d

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:314e2f05004aba05c68159ac12e33602684a2a27702e3110d39986dd0f6b75e9
3
  size 93608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de90b06656cb43604c02ff20d30aaa31f4306ef4870f7553d2858b386b3269a3
3
  size 93608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:147a6378959bdec09ff513e8244a9b9eb6cc103e8e69e3f2979baf91d45fb650
3
  size 197158
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2563daf0d86395180570724ab672d924012d19f22e1484ecf6fa9208e4984c5
3
  size 197158
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:870bff235260a948396f89eba7aa8360caaf7dcd6a760faaaac5c6a1a745f7f5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
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": 0.0898876404494382,
5
  "eval_steps": 5,
6
- "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,28 @@
30
  "eval_samples_per_second": 95.766,
31
  "eval_steps_per_second": 24.451,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 47003074560.0,
53
  "train_batch_size": 4,
54
  "trial_name": null,
55
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1797752808988764,
5
  "eval_steps": 5,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
30
  "eval_samples_per_second": 95.766,
31
  "eval_steps_per_second": 24.451,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.10786516853932585,
36
+ "grad_norm": 0.1660546213388443,
37
+ "learning_rate": 6e-05,
38
+ "loss": 11.9306,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.16179775280898875,
43
+ "grad_norm": 0.18455131351947784,
44
+ "learning_rate": 9e-05,
45
+ "loss": 11.9286,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.1797752808988764,
50
+ "eval_loss": 11.927314758300781,
51
+ "eval_runtime": 0.9797,
52
+ "eval_samples_per_second": 95.952,
53
+ "eval_steps_per_second": 24.498,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 94006149120.0,
75
  "train_batch_size": 4,
76
  "trial_name": null,
77
  "trial_params": null