lesso commited on
Commit
d81a8a5
1 Parent(s): ff0d471

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 sha256:24616924943a6f3ccbeedb41c498b680225ea3f4456b6939e2435c501d186344
3
  size 101752088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15679099041d5f8646276ecc7fba9d01064afa2817e6353b8fd74e7209405be7
3
  size 101752088
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84524474f3e23eb217898e6a07bfcffd330ba7927d061a39e9a098234b3924cf
3
  size 52046596
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67bab7ea9dbeaa8a5a94aff58d475e4a1c3c4c05133b74de6ababd248f6b9c93
3
  size 52046596
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bc758cdf54cfc640ea7dfa079c4a2d02488281639614f10e41e866a95706831
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d1f11de18d4e9ef6bdeb7258af0375124a7854512f87a9816217c5f29857ce
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": 0.0006896155393368198,
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": 3.657,
103
  "eval_steps_per_second": 1.829,
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": 5926845614653440.0,
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": 0.0007662394881520219,
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": 3.657,
103
  "eval_steps_per_second": 1.829,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0007662394881520219,
108
+ "grad_norm": 0.6040265560150146,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.083,
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": 6585384016281600.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null