daniel40 commited on
Commit
18f3c17
·
verified ·
1 Parent(s): 543c262

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52fc5db9d91acbb1c0c1fd9e7139ea0f58857286f6675ffc38b1bb5fa3eb19c4
3
  size 161714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4192f826e5e7cac3519e5161a809b62bdd9518d24fa60d149630c1c14bef664f
3
  size 161714
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aae876b24b6f65654eddab2033e80ca04f4ca8b33340ea4c9dbc174b79aef27
3
  size 64750
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd8a06a5f01d3d29c3dc2bd594e96f602e0245dbf4ca1415347886bb2aba0e3
3
  size 64750
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6427ffbd65b4be1b2f3fbb643f167933e7260181d95492a2b6d8cd2d25b75737
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c72530c1181e385391bf43f1fdf08c8275fccd52a2134362ec0beb66af41fd8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.0027813931927184554,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 461.065,
61
  "eval_steps_per_second": 230.533,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 59324866560.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.003565888708613404,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 461.065,
61
  "eval_steps_per_second": 230.533,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0028527109668907234,
66
+ "grad_norm": 0.442854642868042,
67
+ "learning_rate": 2.9289321881345254e-05,
68
+ "loss": 6.8022,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.003565888708613404,
73
+ "grad_norm": 0.344386488199234,
74
+ "learning_rate": 0.0,
75
+ "loss": 6.7959,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 76463161344.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null