kostiantynk commited on
Commit
fe82721
·
verified ·
1 Parent(s): 3c5bc47

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:e56e26718e24e1b0252069e7aedd866f99f9b987ba36328b8e7788d94656a8d3
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54095a97b4c9af011db02b130355b3a283a62aa7b4194d5a5ed2e3d2b4cd1ed5
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa6a68b4ae1fcb92434871a463e68769d72810b55846eafcf9b7684f9e9ee3a1
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3249a8688fb4ac00d8532dd52dd88afe48a9c8ae2bec2917630b0d595fc0e36f
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:717799f0aa3afaa98d8da58b6052182c4c98ad2734be77edcecb8e4d26dc8077
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b85b9bc41fe584a03a587a2c59a5970998bc1ae863da72a13715a6ff0bfcf01
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": 0.040880503144654086,
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": 18.598,
61
  "eval_steps_per_second": 9.299,
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": 1.0866552672878592e+16,
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": 0.05241090146750524,
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": 18.598,
61
  "eval_steps_per_second": 9.299,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.041928721174004195,
66
+ "grad_norm": 18.513267517089844,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 6.1619,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.05241090146750524,
73
+ "grad_norm": 14.252823829650879,
74
+ "learning_rate": 0.0,
75
+ "loss": 6.2404,
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": 1.4065175032233984e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null