ClarenceDan commited on
Commit
7d75991
·
verified ·
1 Parent(s): 3591032

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:d84d04512c0da1ebca248ab8e17978b6c7333a0acd8b4d1fc63a6cb0a780eb88
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b6adf66f4a57586b5b0116eee048802a396283d4662e5bc407bafc4bb4eed5
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45292e773b689a2e7361f51e274c06b805c5fb568aaadef12c613596aa600903
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed39396bcea5ae4335cd531c79736ed021e5992c047d03ba30faf9e7daa44340
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d3253e1657e0e5e1dce4606e0080d6574b33a3e708581e44bc5526ab5260da9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a26cffb30d94dfb85a910a3e3a744db87392e329b9566998aa7724bb44f185
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": 0.002639876805749065,
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": 19.973,
103
  "eval_steps_per_second": 9.987,
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": 1847154255593472.0,
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": 0.0029331964508322946,
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": 19.973,
103
  "eval_steps_per_second": 9.987,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0029331964508322946,
108
+ "grad_norm": 0.7887467741966248,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.2929,
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": 2052393617326080.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null