duyphu commited on
Commit
1eb31c0
·
verified ·
1 Parent(s): e93f3bc

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 sha256:68bce30b614f83a643f0741359170685dff02f80338af5e654726ff360bf455e
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32702dfd484bc765aeb465bf1514f6d0e84712974e344f76fcb0803a33c49348
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a18697cb7228c9e6b36d188b7d97c5e2d87673644dc4fb2eda14a02ca20be05
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573831a19be3f41de1ce0144799764603604b0a9f75621718110ea56f695da24
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:f92ff5a5b676a9b8b9f1a4521e56d6a9c9ca74b909b133a54f52c8e597e8f5a1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2677b6aaa3bc5404a10ef02bc234e7931913f63936664f48afa6077a1812ff8
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": 0.0006475232236694644,
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": 31.449,
38
  "eval_steps_per_second": 15.724,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 351713970094080.0,
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": 0.0012950464473389287,
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": 31.449,
38
  "eval_steps_per_second": 15.724,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.0007471421811570742,
43
+ "grad_norm": 1.5504509210586548,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 1.0723,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.000996189574876099,
50
+ "grad_norm": 1.3867547512054443,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 1.1504,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.000996189574876099,
57
+ "eval_loss": 1.0666918754577637,
58
+ "eval_runtime": 267.8435,
59
+ "eval_samples_per_second": 31.563,
60
+ "eval_steps_per_second": 15.782,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.0012452369685951236,
65
+ "grad_norm": 1.2634857892990112,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 1.1064,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 684243541819392.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null