shibajustfor commited on
Commit
3b6b5d4
·
verified ·
1 Parent(s): 660ea19

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 sha256:97b1974bf1fb51c6888cd70a54e013e6a649a0d4d324f7c89f061434abe90176
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e92859c223cde3ffa37e0f9d0a62993af4d11ef15a00c9570c4b9b62ddf088d
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c3954adf779a7399652613ebc8f9f6926c8a5109787f86e7aa8bb42f7bedf1a
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288fbd024e8ef7eb2073f6e029b5dabf9e684d86706ad7018d8e444af6ff90c5
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e35b5bb0d616f96cf22cde6c0b105020dcc8ca9dd7be611f2c9cd9b2b20f6404
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d07170801f17a1f2fecb925d53c82a6f7835a1be2b0a6b7f399eb2988390489c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.009805770318687535,
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": 25.569,
61
  "eval_steps_per_second": 12.792,
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": 3900759179526144.0,
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": 0.012571500408573763,
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": 25.569,
61
  "eval_steps_per_second": 12.792,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.01005720032685901,
66
+ "grad_norm": 0.23028379678726196,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 0.6795,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.012571500408573763,
73
+ "grad_norm": 0.25149258971214294,
74
+ "learning_rate": 0.0,
75
+ "loss": 0.6983,
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": 5000973307084800.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null