kostiantynk-out commited on
Commit
794078d
·
verified ·
1 Parent(s): 3272691

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:affca13cfbfe909b932e193a4cbdb3e5fb41d8ec4ea31ea2bd64bc1f6941902f
3
  size 15182728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d21612bd9bece6a24af4e7f026890f7cda9694ae7e62209e3cded38e0ccc29
3
  size 15182728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5101afc240b60930906a9ac0c09cd783b83d47ff269dcd1d116e89b9d826c05
3
  size 8075796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:757cd338f0e1b1ad5115f5877a1a7098003a834ec161083fc21a76bf99413290
3
  size 8075796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb33172a4788405b593512374238eaf3a5470f2ea3c1bb3fe44e557aaedc787c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7814f4d14289bd54bda1535e05889ad87883f16c404df295dc987b23bef2da0
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": 0.031604538087520256,
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": 60.086,
61
  "eval_steps_per_second": 30.043,
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": 180300936118272.0,
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": 0.04051863857374392,
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": 60.086,
61
  "eval_steps_per_second": 30.043,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.03241491085899514,
66
+ "grad_norm": 2.0714833736419678,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 3.3757,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.04051863857374392,
73
+ "grad_norm": 1.009650468826294,
74
+ "learning_rate": 0.0,
75
+ "loss": 3.2078,
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": 232089502875648.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null