samoline commited on
Commit
db0007a
·
verified ·
1 Parent(s): 380330e

Training in progress, step 2, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66b7ee507081a733f207d5c74679a7efc1ad4bb333a290af8814618c70925ee2
3
  size 42002136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a2e942e1d436697cdddbec2b8a6d4f7c4a13c6b37309e76823d6b6454e3314
3
  size 42002136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce8b1eb1b5d4d376157194fd53abe121ef1194e1b026448a3e976ead662ef960
3
  size 21822612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd9079b7c0f4618a44538786a2ee14cbe638a8b5d6064ef09190318f051a2899
3
  size 21822612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f426b342f25de604001541a885e78348759a59b4cb5058936159c11a91c2bdd3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfc0556259ed5f7f0740f29a24049b40f9eb0f41ca8118f9bad2867bd9b36d59
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
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": 2.966830831305999e-06,
5
  "eval_steps": 1,
6
- "global_step": 1,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -22,6 +22,21 @@
22
  "eval_samples_per_second": 3.229,
23
  "eval_steps_per_second": 3.229,
24
  "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 1,
@@ -36,12 +51,12 @@
36
  "should_evaluate": false,
37
  "should_log": false,
38
  "should_save": true,
39
- "should_training_stop": false
40
  },
41
  "attributes": {}
42
  }
43
  },
44
- "total_flos": 46174681694208.0,
45
  "train_batch_size": 1,
46
  "trial_name": null,
47
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.933661662611998e-06,
5
  "eval_steps": 1,
6
+ "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 3.229,
23
  "eval_steps_per_second": 3.229,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 5.933661662611998e-06,
28
+ "grad_norm": 0.6276322603225708,
29
+ "learning_rate": 4e-05,
30
+ "loss": 1.1349,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 5.933661662611998e-06,
35
+ "eval_loss": 1.2181776762008667,
36
+ "eval_runtime": 5436.3595,
37
+ "eval_samples_per_second": 3.263,
38
+ "eval_steps_per_second": 3.263,
39
+ "step": 2
40
  }
41
  ],
42
  "logging_steps": 1,
 
51
  "should_evaluate": false,
52
  "should_log": false,
53
  "should_save": true,
54
+ "should_training_stop": true
55
  },
56
  "attributes": {}
57
  }
58
  },
59
+ "total_flos": 92349363388416.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null