leixa commited on
Commit
f9f5a0d
·
verified ·
1 Parent(s): a5f3c91

Training in progress, step 10, 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:d7507f4477a4e3ed81af29798a350297eae988bcfbe641c11a310fd126adf435
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c725c39d410e1cc86077d7037eccfb1be8bb11272ac6e5efd6875bdedc89021
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a85fa7e1ae57f4ae9da65f18b9ff09a5bd63db989e084c5bf7ff8fece767c51
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f66edb06bd47771e6d9d855e27d846d8f6ad27273a7f3a5f599e5a946407406b
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:047151db14ffede0730de92127fdfa1a36439a819f9b11e3446f30afa10ac216
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd50a23e6f0664128e73c6e676519a860b8250545aa786d69bfea11d765b5b5e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
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": 0.006749915626054675,
5
  "eval_steps": 5,
6
- "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,28 @@
30
  "eval_samples_per_second": 4.335,
31
  "eval_steps_per_second": 0.542,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 1.2972459426840576e+16,
53
  "train_batch_size": 8,
54
  "trial_name": null,
55
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.01349983125210935,
5
  "eval_steps": 5,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
30
  "eval_samples_per_second": 4.335,
31
  "eval_steps_per_second": 0.542,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.00809989875126561,
36
+ "grad_norm": 14.753717422485352,
37
+ "learning_rate": 6e-05,
38
+ "loss": 16.8055,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.012149848126898413,
43
+ "grad_norm": 19.439973831176758,
44
+ "learning_rate": 9e-05,
45
+ "loss": 15.2762,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.01349983125210935,
50
+ "eval_loss": 2.515470027923584,
51
+ "eval_runtime": 287.8629,
52
+ "eval_samples_per_second": 4.335,
53
+ "eval_steps_per_second": 0.542,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 2.6277546018471936e+16,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null