kostiantynk-out commited on
Commit
fa283e9
·
verified ·
1 Parent(s): 788842d

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 sha256:673576a52c5de8cff7ba6beb68601bdbf9193ae28e7078aa5dcc404571eef7e2
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dcf7fe44d0a182e81092e5c09949ae17f7105f9679aed760b9a4a272fff4e77
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:def4849ccf312a49d2af5e45ba0277ddc527cbb775cf6e3acfd0309b19a497f7
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af4a892d87105189ab391fd452ead783cfe7819acf7bb48ccf607191ddeea87d
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:ae2be3b7bc5de30f888aa7806ac10f8ac5d98cac9fed1e3f02f3349c405f5610
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d48e35f5c526296adaa10e9d66469e5e182a3bb6ac3751b2fc0413eae9601e
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": 0.0031699585466959277,
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": 28.839,
61
  "eval_steps_per_second": 14.425,
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": 3298217215131648.0,
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": 0.004064049418840933,
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": 28.839,
61
  "eval_steps_per_second": 14.425,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0032512395350727465,
66
+ "grad_norm": 2.1857964992523193,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 2.4931,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.004064049418840933,
73
+ "grad_norm": 2.205508232116699,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.668,
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": 4234748029304832.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null