dimasik87 commited on
Commit
14bcda4
·
verified ·
1 Parent(s): 4ebfe63

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 sha256:34ffebc8520cfd036116ae46f6b2835a8e50eaa1d1c8088c4612a581676ee410
3
  size 97307544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ab6fd653601bf5e219b20bb50339e3bbec145ceaf911210053576021e2e924b
3
  size 97307544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cadcbd061e25e907e905d60404aa395a8802ca73261374aed9b94401f9381a1f
3
  size 194742714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e5bd4cb06d32d6358e5c59fa2201aa11d30388cbcf52ed25d3719a0281c6620
3
  size 194742714
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59ee2cd8c5c5beec086c14fd6869707b8b3d6d60db535cc5e7213498a9856b51
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74f46576d78c309688c1ae33ea2463cd8aa66d2038ce7dfe1ae107ed841cdc74
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.0016178775468931696,
5
  "eval_steps": 2,
6
- "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -103,6 +103,28 @@
103
  "eval_samples_per_second": 7.895,
104
  "eval_steps_per_second": 7.895,
105
  "step": 8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
106
  }
107
  ],
108
  "logging_steps": 1,
@@ -117,12 +139,12 @@
117
  "should_evaluate": false,
118
  "should_log": false,
119
  "should_save": true,
120
- "should_training_stop": false
121
  },
122
  "attributes": {}
123
  }
124
  },
125
- "total_flos": 2235874343387136.0,
126
  "train_batch_size": 1,
127
  "trial_name": null,
128
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.002022346933616462,
5
  "eval_steps": 2,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
103
  "eval_samples_per_second": 7.895,
104
  "eval_steps_per_second": 7.895,
105
  "step": 8
106
+ },
107
+ {
108
+ "epoch": 0.0018201122402548156,
109
+ "grad_norm": 1.2191482782363892,
110
+ "learning_rate": 0.00018,
111
+ "loss": 1.9804,
112
+ "step": 9
113
+ },
114
+ {
115
+ "epoch": 0.002022346933616462,
116
+ "grad_norm": 0.34325483441352844,
117
+ "learning_rate": 0.0002,
118
+ "loss": 2.0201,
119
+ "step": 10
120
+ },
121
+ {
122
+ "epoch": 0.002022346933616462,
123
+ "eval_loss": 2.0338456630706787,
124
+ "eval_runtime": 131.8006,
125
+ "eval_samples_per_second": 7.898,
126
+ "eval_steps_per_second": 7.898,
127
+ "step": 10
128
  }
129
  ],
130
  "logging_steps": 1,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 2794842929233920.0,
148
  "train_batch_size": 1,
149
  "trial_name": null,
150
  "trial_params": null