kostiantynk commited on
Commit
135b9dc
·
verified ·
1 Parent(s): cc43006

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:518c97cdfdf406e95bc06a63faf220b3c1d9f96c2f0f1babe9451f66e36afa18
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46230c7c909d034101eec830a509aec8a5bf96bb4c8d9b0bb565d5930356e60
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e02ec1d2c68943d4a3aad2bfffd726bcb887c63c6fe4e1901275c164032652ea
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5ec7a268648259fb5e8cefdf0a5f029edda0d5d72cbe6140391077ce731263c
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0e15b3ab42be987bdd5bb4aa2698ef604bdca6308e2d2d3c011ae026c96d55b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15d0423e9e22fc76257d4cfd834ba47d448c60a34365551f418a8285a28705b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.0148204446133384,
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,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 47.729,
61
  "eval_steps_per_second": 23.864,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1280978121129984.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.019000570017100513,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 47.729,
61
  "eval_steps_per_second": 23.864,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.01520045601368041,
66
+ "grad_norm": 0.8656594157218933,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.4262,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.019000570017100513,
73
+ "grad_norm": 0.9576824903488159,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.4131,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1637706205495296.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null