nathanialhunt commited on
Commit
df06362
·
verified ·
1 Parent(s): 33a877d

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:e406461ae0603a87f8c431640b35d701e88dda6a3650bdfe4511449afeb65879
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ee84a7cf148435ec287dde80eb584ee57ca44e5d430c3c7cbbb994405227cc
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37f96c1f1759e1fb751303641d948f8e7a62b2fb13d6a4e02e3a832e6db15a8a
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a7a598005777a9f9744c3fe31d5035976a1bcea825a32159a0eac7fd09eb0ab
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a202ffbaa01015117a9f9ebe123d1662aac2af45b7ed9c72946f6c35b3ed409b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b29aef03c991f6bab85ca61524ae5fbc2dacc16323d80f5f5b89b12d9af90c
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": 0.00422661139559457,
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": 28.869,
46
  "eval_steps_per_second": 14.44,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 4397622953508864.0,
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": 0.0063399170933918555,
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": 28.869,
46
  "eval_steps_per_second": 14.44,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.00487685930260912,
51
+ "grad_norm": 1.642345905303955,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 5.1682,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0063399170933918555,
58
+ "eval_loss": 1.2337496280670166,
59
+ "eval_runtime": 89.7814,
60
+ "eval_samples_per_second": 28.859,
61
+ "eval_steps_per_second": 14.435,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 6677871892365312.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null