Aivesa commited on
Commit
06f7f3a
·
verified ·
1 Parent(s): 05e2641

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96640492e4eebb3782897966308daf45674659a3403ce942316d7a2728a772a3
3
  size 1579352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e24d8977b04ed67f3e015b0698d712f57cd266bee8f38861e9360a3b45f969
3
  size 1579352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dd20387b993a09a924375a817be7f70889c6f6a25985329df203e8496eea17b
3
  size 857338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67889d205fe0466c783c12df8fb4c612f8da52de233b455e1bb5f8f7fbe9af4b
3
  size 857338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffdc96db1ec9a670058701dd0308bfdfe068878d06160a9778f803fae41380ee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd910d4cf35c746d41dd642c825d4de369b0bdac6b91d822ac300a0dbd53f5f6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.00011652408649971354,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -36,6 +36,35 @@
36
  "eval_samples_per_second": 41.507,
37
  "eval_steps_per_second": 20.755,
38
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
40
  ],
41
  "logging_steps": 1,
@@ -55,7 +84,7 @@
55
  "attributes": {}
56
  }
57
  },
58
- "total_flos": 5537487912960.0,
59
  "train_batch_size": 2,
60
  "trial_name": null,
61
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0002330481729994271,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
36
  "eval_samples_per_second": 41.507,
37
  "eval_steps_per_second": 20.755,
38
  "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.00015536544866628474,
42
+ "grad_norm": 1267.2216796875,
43
+ "learning_rate": 8e-05,
44
+ "loss": 43.4303,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.0001942068108328559,
49
+ "grad_norm": 1062.40234375,
50
+ "learning_rate": 0.0001,
51
+ "loss": 33.3487,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.0002330481729994271,
56
+ "grad_norm": 1249.7735595703125,
57
+ "learning_rate": 0.00012,
58
+ "loss": 41.8347,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.0002330481729994271,
63
+ "eval_loss": 11.542579650878906,
64
+ "eval_runtime": 259.9141,
65
+ "eval_samples_per_second": 41.71,
66
+ "eval_steps_per_second": 20.857,
67
+ "step": 6
68
  }
69
  ],
70
  "logging_steps": 1,
 
84
  "attributes": {}
85
  }
86
  },
87
+ "total_flos": 11628724617216.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null