cwaud commited on
Commit
b9e55ce
1 Parent(s): d49c2e3

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:e8f2a3ec9a2f64974453d7855fbfb4abb009693e899dcaa45edbf4f593851df0
3
  size 194563400
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebb50374a1cb309c96bf57bc1194e3d0487c4f31e0c4e5552d43039b6577d8d1
3
  size 194563400
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f2e5938ddd3b5b0380bf72f97b10a2cd2a458620a7a30033139f20f833c9e49
3
  size 99235764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb78abc4c3f812a3c51c009c4b8fadc191c4e7a124fca258ba9efb778945d7be
3
  size 99235764
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5816aa6c6cca42d90fc09c9d5fa09e83b849abc67a0b62bacae6a45943753d68
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea54d2c350a4b2f8ad7efc6a9086ec6f77e8edbe147b48c2a3617b9ad41af6c
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": 0.8,
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": 2.812,
23
  "eval_steps_per_second": 2.812,
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": 563748884447232.0,
45
  "train_batch_size": 2,
46
  "trial_name": null,
47
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.6,
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": 2.812,
23
  "eval_steps_per_second": 2.812,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 1.6,
28
+ "grad_norm": 0.9447022080421448,
29
+ "learning_rate": 4e-05,
30
+ "loss": 1.2703,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 1.6,
35
+ "eval_loss": 0.5292582511901855,
36
+ "eval_runtime": 0.3756,
37
+ "eval_samples_per_second": 2.662,
38
+ "eval_steps_per_second": 2.662,
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": 1057029158338560.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null