lesso commited on
Commit
51f812e
·
verified ·
1 Parent(s): b6466ec

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 sha256:77e52893038481f4c395bc4766dc7267dd49ae9fd1d8760e1d0ef694c79e7060
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4a8466961cc058bc79be84783ad047f5f370bb064de830f03064a152526541b
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7111920ca12d19c8c60b0b989f7c68c23bb48f06ce33c6f8bd0ddfe18e281242
3
  size 23159290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819fa18ef87639bb4f5d18fc8930f46da087eb42f936aa5e80c217f241b8c303
3
  size 23159290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec01cee6b9922f10cdf184da58551aa02458d825a83b4df852d4f43f89b88f1a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f5adca46d5768b2528d11214bf50c169d41422785e8b729921c5399a7fed5df
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": 0.0011003790194400293,
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,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 5.681,
103
  "eval_steps_per_second": 2.841,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 1741900625215488.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.001222643354933366,
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,
 
102
  "eval_samples_per_second": 5.681,
103
  "eval_steps_per_second": 2.841,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.001222643354933366,
108
+ "grad_norm": 1.5255097150802612,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.6961,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1935445139128320.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null