kostiantynk-out commited on
Commit
06bc525
·
verified ·
1 Parent(s): 27eb53f

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:ae968c97883ef3942e72ca7ec821aca836b7d85644455f3c4c6d019bdc618af1
3
  size 104902272
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12a62f9ba54a52b0e9a067117466084dd03f556d584b160eaed0d6b294a9f12f
3
  size 104902272
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91b18a953e8c22bc4317953d421e29caba7d02998f4a66abd8a5281070d1d6b6
3
  size 53622996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e82c9b1cb2c0458499ab1f754ec4d7375b7c50cc92500e90e5f91464d981aa
3
  size 53622996
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3818e95074faa0d9cd258190f04acef580a83fcaa738e0b748c985ee478a8f7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7718a1d01c91dc6fa09a030f5942f5aea9ab54e5cf06ea621fd017f2fab042
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": 0.0011017260374586854,
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": 13.516,
61
  "eval_steps_per_second": 6.759,
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": 1.200026862747648e+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": 0.0014124692787931862,
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": 13.516,
61
  "eval_steps_per_second": 6.759,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.001129975423034549,
66
+ "grad_norm": 1.1995586156845093,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 3.2732,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0014124692787931862,
73
+ "grad_norm": 1.5555026531219482,
74
+ "learning_rate": 0.0,
75
+ "loss": 3.1901,
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": 1.537289314369536e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null