tuanna08go commited on
Commit
57c4260
·
verified ·
1 Parent(s): a2dac59

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 sha256:4eb4db1254e95d05b36fdd88ecdf3440798ce5a906d95e11a3c0cfefcdfe2e36
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6da9ca2c82e2d5a51b45ac8503df9308e5162295f8269fdb68662a2f381bbc5
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01ce5987b10140859574e59e0021f2b9be23d72c2126438b37f844d921f60c4c
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe988cd336e4443db062b7f4193dce676068006f5cf7ae1487aa561188555554
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf20bdab1b91ba0de7f42ffa2f7eeead82681a87bd55df37cb18e7649b55f4c9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802e2a756dc35873fc0503119c69f55b5b07fa04fa3b56ba920bb985b5865d0f
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": 0.07567764235037293,
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": 11.134,
46
  "eval_steps_per_second": 1.395,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1.2899566436430643e+17,
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": 0.1135164635255594,
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": 11.134,
46
  "eval_steps_per_second": 1.395,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.0873203565581226,
51
+ "grad_norm": 0.09768923372030258,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 1.0214,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0873203565581226,
58
+ "eval_loss": 1.0394461154937744,
59
+ "eval_runtime": 207.9758,
60
+ "eval_samples_per_second": 11.131,
61
+ "eval_steps_per_second": 1.394,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1.9349349654645965e+17,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null