adammandic87 commited on
Commit
60cebd0
·
verified ·
1 Parent(s): 06291e5

Training in progress, step 9, 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:f0e1668d042e4b91a8f74e8a0e088ecb9f27a48518b6b84386bdeeadedfc98a9
3
  size 81576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4569e3cac81108943796d359ff444e0b23a6a8f13623fe90cfffa02c6c7f9733
3
  size 81576
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a3ade91cf2913a5db09840e715a6867e232b6bc8339f8deae976693f715f7e3
3
  size 173094
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf5c86d0ce7df8ef22f5077c968adf202ead315512db43a8e6dca9cff7734af7
3
  size 173094
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8f9bfbb25b5742af971410f7969204872224492d0748212c97b7e3aec33a144
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6a6a011f28f85007de1213aaf2d9d99df9d84c0278f3612751bd8de1562285
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.015873015873015872,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 321.683,
74
  "eval_steps_per_second": 160.841,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 820295761920.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.023809523809523808,
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,
 
73
  "eval_samples_per_second": 321.683,
74
  "eval_steps_per_second": 160.841,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.018518518518518517,
79
+ "grad_norm": 0.30775487422943115,
80
+ "learning_rate": 0.00014,
81
+ "loss": 10.8418,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.021164021164021163,
86
+ "grad_norm": 0.3520079255104065,
87
+ "learning_rate": 0.00016,
88
+ "loss": 10.843,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.023809523809523808,
93
+ "grad_norm": 0.31247809529304504,
94
+ "learning_rate": 0.00018,
95
+ "loss": 10.8267,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.023809523809523808,
100
+ "eval_loss": 10.838133811950684,
101
+ "eval_runtime": 0.4872,
102
+ "eval_samples_per_second": 328.439,
103
+ "eval_steps_per_second": 164.219,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1168921460736.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null