VERSIL91 commited on
Commit
444b36a
·
verified ·
1 Parent(s): 7756eb9

Training in progress, step 4, 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:b6ec7c5a71332e50e803c5fb16bbe674dfbebc6c8a6e725a26ef67c76cc5211f
3
  size 5327744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6288f156f2311c628fd7f61707c9201b9f88320db35cb41280d7216186941b5f
3
  size 5327744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e00ae065131051227ac53894e738c97c6f5493c5606d6c8a82fce337e0b46da
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54fc4f2cc5227f86c28d8e9f8d7c8c97157f3d58250a61acde7c9028c2d9f1c0
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4dcca6a6804999e27755bbf6858c570aac8b5e53137849f476743d052cec0a5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e8b75f46108a8385b07ab00c0a73727d1192361f19a8799fb8bb1730dbee54a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
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": 0.96,
5
  "eval_steps": 1,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,21 @@
52
  "eval_samples_per_second": 64.457,
53
  "eval_steps_per_second": 32.229,
54
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 1,
@@ -66,12 +81,12 @@
66
  "should_evaluate": false,
67
  "should_log": false,
68
  "should_save": true,
69
- "should_training_stop": false
70
  },
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 25475413966848.0,
75
  "train_batch_size": 2,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.28,
5
  "eval_steps": 1,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 64.457,
53
  "eval_steps_per_second": 32.229,
54
  "step": 3
55
+ },
56
+ {
57
+ "epoch": 1.28,
58
+ "grad_norm": 217.41184997558594,
59
+ "learning_rate": 4e-05,
60
+ "loss": 99.4062,
61
+ "step": 4
62
+ },
63
+ {
64
+ "epoch": 1.28,
65
+ "eval_loss": 6.104166507720947,
66
+ "eval_runtime": 0.0866,
67
+ "eval_samples_per_second": 69.303,
68
+ "eval_steps_per_second": 34.651,
69
+ "step": 4
70
  }
71
  ],
72
  "logging_steps": 1,
 
81
  "should_evaluate": false,
82
  "should_log": false,
83
  "should_save": true,
84
+ "should_training_stop": true
85
  },
86
  "attributes": {}
87
  }
88
  },
89
+ "total_flos": 33701849726976.0,
90
  "train_batch_size": 2,
91
  "trial_name": null,
92
  "trial_params": null