nathanialhunt commited on
Commit
88a741f
·
verified ·
1 Parent(s): e1df8c8

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 sha256:9fd048f0630b46361686b799d59963ada0d72048b88fd4a0e1b33927f1a66a18
3
  size 104902272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b75629105030a1363742d6131a0f7d9d66a1c434a2f2cf985238b6664b038cb
3
  size 104902272
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e3a6618c0df9de34cd5ad38e7addc8259b680fe330a5c727a760bd97d271d79
3
  size 53622996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1eb580d3db46b29295490d32ba801046f5ee9308c371a505bad4dfabd85574ce
3
  size 53622996
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a92bd0f72c29115d8fa8b7500a902c8a38f91c88a3e970fc06f5f8ffb40a0b5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c67a3447d55006c2777019c4d6c4c7c5f9aa8bb2d7d1d12706ce84756770d0a
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": 0.005194545726986664,
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": 15.386,
46
  "eval_steps_per_second": 7.693,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 1.41179630911488e+16,
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": 0.007791818590479996,
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": 15.386,
46
  "eval_steps_per_second": 7.693,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.005993706608061536,
51
+ "grad_norm": 1.7101911306381226,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 1.6937,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.007791818590479996,
58
+ "eval_loss": 0.3522377610206604,
59
+ "eval_runtime": 137.2429,
60
+ "eval_samples_per_second": 15.36,
61
+ "eval_steps_per_second": 7.68,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 2.172597653471232e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null