robiual-awal commited on
Commit
c8c5068
·
verified ·
1 Parent(s): 5d2f36c

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 sha256:49c7b6ebcf9ea68ee53d12e5f0089ae2f338b9b6035a539ad083020b0409cd34
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587e8f1a94583d26e4281826c2547e2e18958a087d1955d6a3414189c0e96c99
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e51b74a2a86b71cfbf45a2441f3a677398812d1f554c37684bddde33e3c9add2
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8bd24511b40d54cd3bf9e3f4f48c64c4fb2c7745bb7d373c55506b0c626e65e
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d747a1d95bfbc9502602b6045cb8e76f44203a0cef8ff04142bfaa84e03a92e8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc86ff2ff5cb9db0e45c1755eb6f915f0352cbcbea59a4e33eb6c782e36ae2c
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": 0.0029047574713713807,
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": 34.744,
61
  "eval_steps_per_second": 17.372,
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": 6796280579751936.0,
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": 0.003724048040219719,
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": 34.744,
61
  "eval_steps_per_second": 17.372,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.002979238432175775,
66
+ "grad_norm": 1.1550804376602173,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.5223,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.003724048040219719,
73
+ "grad_norm": 1.402665615081787,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.4384,
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": 8756746131603456.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null