ardaspear commited on
Commit
83cdbce
·
verified ·
1 Parent(s): 7cad6c7

Training in progress, step 15, 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:de90b06656cb43604c02ff20d30aaa31f4306ef4870f7553d2858b386b3269a3
3
  size 93608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a3a7cbf677bcaa3d09bbf754f3ef38d7d58607818fa57a01123ee7c0f18917
3
  size 93608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2563daf0d86395180570724ab672d924012d19f22e1484ecf6fa9208e4984c5
3
  size 197158
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b3292ce93c0d19d6ed4fc537b2aad230e2d79b999c094e5706e198a420ef239
3
  size 197158
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8d9358611d5238c19c59fb3aa3eac2040cbac245a7cfcfe56e1467f677e36cf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372c9c91189dafe7a0013b948ff9907e60fc7ad4b32cc7ac3bccb3f603cf2268
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
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": 0.1797752808988764,
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,
@@ -52,6 +52,28 @@
52
  "eval_samples_per_second": 95.952,
53
  "eval_steps_per_second": 24.498,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +93,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 94006149120.0,
75
  "train_batch_size": 4,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.2696629213483146,
5
  "eval_steps": 5,
6
+ "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 95.952,
53
  "eval_steps_per_second": 24.498,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.2157303370786517,
58
+ "grad_norm": 0.22720609605312347,
59
+ "learning_rate": 9.938441702975689e-05,
60
+ "loss": 11.9266,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.2696629213483146,
65
+ "grad_norm": 0.28416040539741516,
66
+ "learning_rate": 9.619397662556435e-05,
67
+ "loss": 11.9244,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.2696629213483146,
72
+ "eval_loss": 11.922819137573242,
73
+ "eval_runtime": 0.9826,
74
+ "eval_samples_per_second": 95.669,
75
+ "eval_steps_per_second": 24.426,
76
+ "step": 15
77
  }
78
  ],
79
  "logging_steps": 3,
 
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 142214430720.0,
97
  "train_batch_size": 4,
98
  "trial_name": null,
99
  "trial_params": null