Paladiso commited on
Commit
1a1bb36
·
verified ·
1 Parent(s): e3cbbfb

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 sha256:0aaf2e9dd92a54c116d18274ce25d8ee0a9e86993a5c220c974405920efb9f5f
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb7a241eb975ae50d4a58abceb1f9181e0c8efdac70ba539852857cc87cf7e9
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed1a5bdfa465078bf4941a45535575daf09f606ccf03e0dfbad917677f4ba868
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a684cb2e047a6d54a96ca90ef5605f1a7fc954625a6749de826c5680533d739
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9872a72847429cc558d5cf26bb80538beabca5c1276ec308e19b2b498c2a911
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c1b87f8654c8017ee20bafb0743e5a5c10d15bcd99fdd912d066afaa342d7d
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": 0.00299625468164794,
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": 17.41,
37
  "eval_steps_per_second": 8.705,
38
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
40
  ],
41
  "logging_steps": 1,
@@ -55,7 +84,7 @@
55
  "attributes": {}
56
  }
57
  },
58
- "total_flos": 246014599495680.0,
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": 0.00599250936329588,
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": 17.41,
37
  "eval_steps_per_second": 8.705,
38
  "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.003995006242197253,
42
+ "grad_norm": 0.3317357003688812,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.9,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.004993757802746567,
49
+ "grad_norm": 0.3528467118740082,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.9682,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.00599250936329588,
56
+ "grad_norm": 0.45743900537490845,
57
+ "learning_rate": 0.00012,
58
+ "loss": 1.1032,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.00599250936329588,
63
+ "eval_loss": 1.039202094078064,
64
+ "eval_runtime": 22.8981,
65
+ "eval_samples_per_second": 18.429,
66
+ "eval_steps_per_second": 9.215,
67
+ "step": 6
68
  }
69
  ],
70
  "logging_steps": 1,
 
84
  "attributes": {}
85
  }
86
  },
87
+ "total_flos": 492029198991360.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null