Paladiso commited on
Commit
40bfd20
·
verified ·
1 Parent(s): c276ab1

Training in progress, step 10, 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:f2878fee165aa6b9d2507f7fe45fb55aee5e09761d3e2150ba3c8314065fedf2
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7abd8f036109074c6a36c6254e075cf7bcbe9fb296be7a2a8a8893c3851720f
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38d798d606b3792266e60f50fe385645297ac266fe6683f2ef2a691384ea8778
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a61bfd5232162feb21f9c0aaef5e68c3dc7384d35f2b70106b713b58caa9c9a9
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7488249a173aa3a68e75b7fc67895bff57ea66b904aac2ae135d49c25f884c96
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77861f6e653a60cb0c2a7b2944b0344b4ac0b7da358980a3ce592ccea3d3c929
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.001115690953605851,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -94,6 +94,13 @@
94
  "eval_samples_per_second": 14.306,
95
  "eval_steps_per_second": 7.155,
96
  "step": 9
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 1,
@@ -108,12 +115,12 @@
108
  "should_evaluate": false,
109
  "should_log": false,
110
  "should_save": true,
111
- "should_training_stop": false
112
  },
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 364835540828160.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0012396566151176124,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
94
  "eval_samples_per_second": 14.306,
95
  "eval_steps_per_second": 7.155,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0012396566151176124,
100
+ "grad_norm": 1.475090503692627,
101
+ "learning_rate": 0.0002,
102
+ "loss": 2.0393,
103
+ "step": 10
104
  }
105
  ],
106
  "logging_steps": 1,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 397265366679552.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null