jssky commited on
Commit
0bb2030
1 Parent(s): 34a5652

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 sha256:646b91df502035f771c32f79628a5d33f562a0a80d72bdd1ad506d11e9831c21
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1db89bdbbee60613b2809b8557eab743b76363e5ac2dbf52830a3bc2fdd2a5f
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c797d444df6d175c431d7c6439766226ced8a1d607cd53d64c1e297f7408bfaa
3
  size 42608388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38a2e19b72b9c96cfd8b569d757267eb0eeae1f399bd088a5ba6ecc985dc3842
3
  size 42608388
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:975e2fef0ce023c45a0d7bbabf76a79358b37a1de8f82a4354020f8b97bfa2fa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8fb5c2de708c8564f6e7216f5673a79fe25a9c85499b64b7385f5503a9d7208
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
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": 0.004109119963474489,
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": 7.713,
103
  "eval_steps_per_second": 7.713,
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": 1809536922943488.0,
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": 0.004565688848304988,
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": 7.713,
103
  "eval_steps_per_second": 7.713,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.004565688848304988,
108
+ "grad_norm": 68.01629638671875,
109
+ "learning_rate": 4e-05,
110
+ "loss": 7.7139,
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": 2010596581048320.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null