nathanialhunt commited on
Commit
c060628
·
verified ·
1 Parent(s): 74f5cfa

Training in progress, step 39, 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:efdc05da2e14ea12f11d6f5af7e672107482cdd9be3419593a91a7afd8417557
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2d6f9dd100d02d60cda9ea2e62dcd89bec3232de82a2d61d2d1062c6105bb4
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fba74470b0bda4543c54ed70923767eef5e56ad08890992e871ffe8a1b21ff29
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb6f866b6cffe38a24f34ed45c9cd1e315934404c8024f845b56921933e256c
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.0948905109489051,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 286.785,
46
  "eval_steps_per_second": 143.393,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 3072196608.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.14233576642335766,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 286.785,
46
  "eval_steps_per_second": 143.393,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.10948905109489052,
51
+ "grad_norm": 0.008942769840359688,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 11.9365,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.14233576642335766,
58
+ "eval_loss": 11.936768531799316,
59
+ "eval_runtime": 0.4038,
60
+ "eval_samples_per_second": 287.298,
61
+ "eval_steps_per_second": 143.649,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 4608294912.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null