tuanna08go commited on
Commit
2207a0b
·
verified ·
1 Parent(s): d9452b2

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 sha256:3aa765bd4ba448071fb5280d8b7811f7c9a08c03fe98614bc90194f4dc800e99
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:400620106b3cff5b4b4142e9edb9768eca7dd9bdd4789cc77df819575c281147
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af5bedeee2c45881ea31da03f11ff4e04a8e3c50404fa47bcb6b89adfe27eca6
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0be69b04aa6a670c840461092f23685be402d2fd625ecec061d5088d921536eb
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:971d18b1498661ca2e478d94cee70958977c8629bc91870f6a60546d5625409b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfcfd5e133f2f2340612d67096d68f4b96d6e485041671364e214a08c01caf7c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
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": 0.13273771537970644,
5
  "eval_steps": 10,
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": 38.39,
46
  "eval_steps_per_second": 4.799,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 2.128189259041997e+16,
68
  "train_batch_size": 8,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.19910657306955967,
5
  "eval_steps": 10,
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": 38.39,
46
  "eval_steps_per_second": 4.799,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.15315890236119975,
51
+ "grad_norm": 0.07069219648838043,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 0.5459,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.15315890236119975,
58
+ "eval_loss": 0.5473927855491638,
59
+ "eval_runtime": 34.3812,
60
+ "eval_samples_per_second": 38.393,
61
+ "eval_steps_per_second": 4.799,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 3.192283888562995e+16,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null