kostiantynk-out commited on
Commit
1802782
·
verified ·
1 Parent(s): 0516357

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 sha256:9a303ba42067fe34168824c821d1930586dcc4c80e913186e42e90945198e237
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b85b878bc56b1fa5a6bdde553b2744566b2bdc49761267ecd787ec4242b1294b
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:948777df18be8b3093a7e7e50de143e23b5b822398e7c635e7fd14a81389577e
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f92972e5d096388cb6ad69d0b8d1daa76588452cfd73cd02fe2146d483f8aea1
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d180772d69b89926e794aa30466cdd606442ea9d66f35dbb2913ac9b66eeae93
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1476bae18ff7688b46e86947a35a323e37e18b4672f99b284a48eb1d29baa70b
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": 0.002217862321931246,
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": 93.657,
61
  "eval_steps_per_second": 46.829,
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": 467154612781056.0,
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": 0.0028434132332451874,
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": 93.657,
61
  "eval_steps_per_second": 46.829,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.00227473058659615,
66
+ "grad_norm": 38.44550323486328,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 12.2806,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0028434132332451874,
73
+ "grad_norm": 57.16466522216797,
74
+ "learning_rate": 0.0,
75
+ "loss": 11.8007,
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": 589974604873728.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null