tuanna08go commited on
Commit
6cbc356
·
verified ·
1 Parent(s): a219898

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 sha256:096bf84e4ab16e018e67084d857c23a35cb6e3c84a9b6e86ae9aaf9cb4addcd3
3
  size 28348936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:563077ad449d8d91d209fcd9f226014b76be72e7db2fe8609a4ffa3d9b483cf9
3
  size 28348936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e314750c0e108338abecb2f54c497a33facd085346825bd0dec5a775fef7b58b
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6930d4ceb3274f34b4fe8e972311ea998019e60e082632604206f46271b02ef3
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9df2dc131c7fe6d7c61a634cdf0a9db6d593c4e5b5da2dea5c4aed0556b01768
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12842ce095b0e2610c386ef94711d2850ceaa47b98aab11f80858505283ff76e
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": 0.03004043905257077,
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": 28.619,
46
  "eval_steps_per_second": 3.578,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 2.485852845165773e+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": 0.045060658578856154,
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": 28.619,
46
  "eval_steps_per_second": 3.578,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.03466204506065858,
51
+ "grad_norm": 1.285149097442627,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 1.6201,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.03466204506065858,
58
+ "eval_loss": 1.2765699625015259,
59
+ "eval_runtime": 203.7198,
60
+ "eval_samples_per_second": 28.623,
61
+ "eval_steps_per_second": 3.578,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 3.735269745151181e+16,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null