leixa commited on
Commit
43022fc
·
verified ·
1 Parent(s): c20c42b

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 sha256:4a894cabd4a8f489eef0f1bbc5d0696ce157e9e253f93b59baeed7527ea81ef6
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd81b5143a2851467ee237e4b1aae743ef67cbb140678d87678837d18724d0c1
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2243fce557d8288822f52fa134f7728184d68adb65a139a33abb545e6879aba1
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c6a6f648698cd3455ec070fd03d54c2ca5075daafcf8d88087dcffc0390d2fd
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8127c1bda6b25f0e4f316ed7261d647723fa030e6c0023340fc8bc711b03a601
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74b86d52620cc1ca6c6ad3d1937f9ecd5813650698788b10f41a3d7f093677d1
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": 0.008223944330222995,
5
  "eval_steps": 13,
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": 13.101,
38
  "eval_steps_per_second": 6.55,
39
  "step": 13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 4530853719834624.0,
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": 0.01644788866044599,
5
  "eval_steps": 13,
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": 13.101,
38
  "eval_steps_per_second": 6.55,
39
  "step": 13
40
+ },
41
+ {
42
+ "epoch": 0.009489166534872686,
43
+ "grad_norm": 0.25495731830596924,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 0.7955,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.012652222046496917,
50
+ "grad_norm": 0.3009412884712219,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 0.7136,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.015815277558121146,
57
+ "grad_norm": 0.28066885471343994,
58
+ "learning_rate": 6.91341716182545e-05,
59
+ "loss": 0.659,
60
+ "step": 25
61
+ },
62
+ {
63
+ "epoch": 0.01644788866044599,
64
+ "eval_loss": 0.6159524917602539,
65
+ "eval_runtime": 51.1075,
66
+ "eval_samples_per_second": 13.031,
67
+ "eval_steps_per_second": 6.516,
68
+ "step": 26
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 9061707439669248.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null