Nexspear commited on
Commit
54f8ba5
·
verified ·
1 Parent(s): e921763

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 sha256:9f27d84eceb462f04bda1fe847d5e6498b14d2013a23ba9a4295592da3e82eac
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0b736ae7a9e8b7d666739556b9d6bf5ea2955250af69c59d19bd5b527ae0f39
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8beda06226b4f2101bdd96a860be2463276fd44a0965d7e107cbfedea8eeec9a
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853f7c31f307d3c64a7de01d9081ae67aabf9de6b21ce393ebdb5b1f4f411392
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": 0.03577817531305903,
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": 11.09,
31
  "eval_steps_per_second": 1.41,
32
  "step": 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 3,
@@ -49,7 +71,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 6652543295815680.0,
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": 0.07155635062611806,
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": 11.09,
31
  "eval_steps_per_second": 1.41,
32
  "step": 5
33
+ },
34
+ {
35
+ "epoch": 0.04293381037567084,
36
+ "grad_norm": 59.01460647583008,
37
+ "learning_rate": 6e-05,
38
+ "loss": 29.5122,
39
+ "step": 6
40
+ },
41
+ {
42
+ "epoch": 0.06440071556350627,
43
+ "grad_norm": 31.912750244140625,
44
+ "learning_rate": 9e-05,
45
+ "loss": 15.7048,
46
+ "step": 9
47
+ },
48
+ {
49
+ "epoch": 0.07155635062611806,
50
+ "eval_loss": 1.4119746685028076,
51
+ "eval_runtime": 21.3324,
52
+ "eval_samples_per_second": 11.063,
53
+ "eval_steps_per_second": 1.406,
54
+ "step": 10
55
  }
56
  ],
57
  "logging_steps": 3,
 
71
  "attributes": {}
72
  }
73
  },
74
+ "total_flos": 1.330508659163136e+16,
75
  "train_batch_size": 8,
76
  "trial_name": null,
77
  "trial_params": null