kostiantynk1205 commited on
Commit
5eec412
·
verified ·
1 Parent(s): 51afae8

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 sha256:25a03aa4f6e901f0a9b434909fd30fbdff576106963afb1ce10f90d64f948c37
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b4a723ab169ef62a8b0db96f53d1931426c2fad463eaa0a8a3f4d4ee6d1594
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:002255a7925410cbe54d306702c76c247ec5986dcb8b45bc3ffec4da3b7dfd9e
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dc79bf8ce3cd61380d7e411d929287c79222d7261c2caf0ada03f1924636255
3
  size 33424212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:157f0b38a83b3746dd7a07fdaa1bfaddd05a6863135cff06f7445a1aa2497e82
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1497e53506b7c7510e6e14b6e50b7d3f046b534f9e7664814ec7a9094516f156
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": 0.003368821128555078,
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": 21.338,
61
  "eval_steps_per_second": 10.671,
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": 1.2488456935047168e+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": 0.004319001446865485,
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": 21.338,
61
  "eval_steps_per_second": 10.671,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.003455201157492388,
66
+ "grad_norm": 2.3207147121429443,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 8.7712,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.004319001446865485,
73
+ "grad_norm": 2.3708016872406006,
74
+ "learning_rate": 0.0,
75
+ "loss": 8.5769,
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": 1.5998284701106176e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null