kk-aivio commited on
Commit
ab6ce32
·
verified ·
1 Parent(s): b27a166

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22a022465093b38b46720ff80c1af857a24b822fefd69c48186ee9c12a9d8d43
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46c61ea6d9e252af4783f6235260dd4108f7b5d5d971fad958a45b5f7ae0a72
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:439efe10746318bfc59bb3c7164c060dd5583055d36c140c5f2ed547d03380fa
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cc3feecca10946bb142fe6bbfd829c6a0e31bee9d6d20a066dc01d479ac72cd
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1524d6216e42e36e3ae993ad521ab277b184f833ce70f98c345e5a3bfe1d0cf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19fe7f4523f948a940f0c9bcc718353f7ff70e31ee7567f30f2aa6254ec62566
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.028392028392028392,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 10.62,
46
  "eval_steps_per_second": 5.31,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1.646426824114176e+16,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.042588042588042586,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 10.62,
46
  "eval_steps_per_second": 5.31,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.03276003276003276,
51
+ "grad_norm": 0.39251863956451416,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 2.0696,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.042588042588042586,
58
+ "eval_loss": 2.084362506866455,
59
+ "eval_runtime": 36.3334,
60
+ "eval_samples_per_second": 10.624,
61
+ "eval_steps_per_second": 5.312,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 2.469640236171264e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null