Nexspear commited on
Commit
67b8ed0
·
verified ·
1 Parent(s): 0c20285

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:ac3e4db9fe589ca7a9bb0078e4d1cf407d2e5b9e5eb7a3b0241cef97c117a3f9
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2944cf54ed544d1176a4e30b9ed7399ec23f6ab42fb847c01bd83e717832f376
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3008b4382c85a11a1ebd842e4512fb07da03db097dd2d3e0f9864eda4631d1e
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2673ae1fc9e1717a7293559e63bdcc598a1ce77a628ce2a1a7ca8dcd4f96417f
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20ae40147066520ba06d8488dffecb1617761bf0f5a71e5b8f891ada27bea484
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd93ad71d1e4da2e65f4e2c9390e9d7b7bc2ea6079b0f1bd60a10893bb8881fb
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": 0.012539184952978056,
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": 13.54,
31
  "eval_steps_per_second": 1.692,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 6728838021120000.0,
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": 0.025078369905956112,
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": 13.54,
31
  "eval_steps_per_second": 1.692,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.015047021943573668,
36
+ "grad_norm": 1.2794967889785767,
37
+ "learning_rate": 6e-05,
38
+ "loss": 2.2497,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.0225705329153605,
43
+ "grad_norm": 0.7042816281318665,
44
+ "learning_rate": 9e-05,
45
+ "loss": 1.9238,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.025078369905956112,
50
+ "eval_loss": 1.7871791124343872,
51
+ "eval_runtime": 49.7536,
52
+ "eval_samples_per_second": 13.507,
53
+ "eval_steps_per_second": 1.688,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 1.345767604224e+16,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null