VERSIL91 commited on
Commit
df54a5d
·
verified ·
1 Parent(s): cab104c

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 sha256:92475182f8fb1ed7a5d5ed49fe9eb3a030a7721a9b8d9c861c30cf112ccf89f1
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67c5b7ae63a3b539b94f7289128e6338295caff2aba10e498ccc03408e8318a7
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe05c54d5fc9ed78454c7ae48a2a5d787ce0b099eb7d51702eaa908f121b985b
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42fa34b8dbfceff65894ec1b12469678676fc40452dd349c8f646df1b749023f
3
  size 819770
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": 0.05186385737439222,
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": 282.296,
38
  "eval_steps_per_second": 143.319,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 524468355072.0,
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": 0.10372771474878444,
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": 282.296,
38
  "eval_steps_per_second": 143.319,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.07779578606158834,
43
+ "grad_norm": 8.418513298034668,
44
+ "learning_rate": 3e-05,
45
+ "loss": 9.3496,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.10372771474878444,
50
+ "grad_norm": 8.357897758483887,
51
+ "learning_rate": 4e-05,
52
+ "loss": 9.5666,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.10372771474878444,
57
+ "eval_loss": 9.41639232635498,
58
+ "eval_runtime": 0.2451,
59
+ "eval_samples_per_second": 265.15,
60
+ "eval_steps_per_second": 134.614,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 1048936710144.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null