tuanna08go commited on
Commit
65e34a8
·
verified ·
1 Parent(s): 86afaf4

Training in progress, step 26, 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:a363b5f2bc1dd46765e15f138e5c5059f897b129ffa42d11b4a5bc46228be72e
3
  size 30026872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2892c14bf9734ea5d122b19b3cbd92bd1147b965e8afd5aa1b41a41858005d72
3
  size 30026872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0b8e7b1b57345c29e156ac92ddec455ee25bc31897b005a6b81206d8e3badff
3
  size 15611412
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9171d80ce84a7f004447a33c6066f222100b365e866156df4d49915dfc8e4e0
3
  size 15611412
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cada282df88fa872ae241f328070b3d154b7f83d7651e8c9b3eb27f30d23c8fe
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42cb77af00767f27e14a12c87356445647f0198691d2d77b67b9ee285576828b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
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": 0.0003913658668753951,
5
  "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 26.799,
38
  "eval_steps_per_second": 13.401,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 814697183969280.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0007827317337507902,
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,
 
37
  "eval_samples_per_second": 26.799,
38
  "eval_steps_per_second": 13.401,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.0004515760002408405,
43
+ "grad_norm": 0.2420434206724167,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 2.0589,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.0006021013336544541,
50
+ "grad_norm": 0.2056291550397873,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 2.0933,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.0006021013336544541,
57
+ "eval_loss": 2.048297882080078,
58
+ "eval_runtime": 522.1362,
59
+ "eval_samples_per_second": 26.788,
60
+ "eval_steps_per_second": 13.395,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.0007526266670680675,
65
+ "grad_norm": 0.24101394414901733,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 2.0368,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 1629394367938560.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null