jssky commited on
Commit
c1e03cc
·
verified ·
1 Parent(s): 9e49900

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:af51ed12a53da64ecc8e9c87e5e8063013f2f35b5af6afb74b3e0a1c6940012a
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27e3c4159e312ecbcba94a7663c8df2fa2de873ec718836afe1bb533bf26700
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83a75932b16c482ad3a118057f92f3963b920b95e1de6a0fbb7d78b183cf7633
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5543b44e891d6374daa37ae9240a32b6fe7915c4a82e6b21df88ef39c7dddc28
3
  size 335922386
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e42948693d0243175ec25af5f43dccfdb2fdeaacca5b7172fb3d8248f75d7deb
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a7deec1670363e76317c4e10028713db4bd5ae35567259a6715e71930c147e
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d00cce3b8e1acf72f4996dc389b00ca3276bd487604e83d236e50d6a8022097c
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:935f725697082add340a8de1b0f91a164fcaccab8b0aacb7a561fac711f78a30
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0004570848146267141,
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": 9.539,
103
  "eval_steps_per_second": 4.77,
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": 1.3354203032322048e+16,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0005078720162519045,
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": 9.539,
103
  "eval_steps_per_second": 4.77,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0005078720162519045,
108
+ "grad_norm": 16.735069274902344,
109
+ "learning_rate": 0.00012,
110
+ "loss": 8.5394,
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": 1.483800336924672e+16,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null