jssky commited on
Commit
d3318ad
·
verified ·
1 Parent(s): e199615

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 sha256:04b255e069ef4d9ccded50912ffd77df9f511daa2cf4657e22c8603a32d21b2d
3
  size 119801528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3d32fa34fe6346f9149b2934817f1eab4284ccacd652bedb9715658068476dc
3
  size 119801528
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cc09797f98870c04f80f51cf10b74e7b4da248ea3e048ad808aacaf09d2f449
3
  size 61392180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0901cb66d2a412e63dac5040f14bc1256c18261e646273b42177e849b2ab708
3
  size 61392180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7a828c2e59b5f6f81648438992697915c97f8cbac9e986c22bf9f071d0a4b91
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ca4e52a8ff86f0f650364416f5046b64a5370f50691b48fcfcc3c4dc51ebc4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.0007670999360750053,
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": 6.91,
103
  "eval_steps_per_second": 6.91,
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": 2481425542545408.0,
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": 0.0008523332623055614,
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": 6.91,
103
  "eval_steps_per_second": 6.91,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0008523332623055614,
108
+ "grad_norm": 5.738803863525391,
109
+ "learning_rate": 0.00016,
110
+ "loss": 5.8223,
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": 2757139491717120.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null