phungkhaccuong commited on
Commit
49f337c
·
verified ·
1 Parent(s): 395f32d

Training in progress, step 39, 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:ed61c7936dae97aae0a24e777a79eca28bd0187c88504007bc473ee488ab3cc3
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79392552a34cf7abb8be5a94069449dc771d418b2bf6a1d03621592d43d3b5b7
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0831fd660070800fc9b6a70f708ed6573b14ce2b7e6a6cb478eb4ba6fc8da8f5
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ecaa99ab53b6bbb2351d0fd49836c7aa22cc9ce538b9506c0a1916533f1d2b1
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b847a8cd1b26df3203e5f791e819fcb6639128a42bf45c31f188ba28eed52b45
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cefa6a2299162804c371eb63bafa7bf7943efdc7f99741c213760a8ea7e6c23e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.006405518600640552,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.7381,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8276800010452992.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009608277900960829,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.7381,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.007390983000739098,
72
+ "grad_norm": 0.4189673662185669,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.5604,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.007390983000739098,
79
+ "eval_loss": 0.6136700510978699,
80
+ "eval_runtime": 186.5457,
81
+ "eval_samples_per_second": 9.161,
82
+ "eval_steps_per_second": 4.583,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.008622813500862282,
87
+ "grad_norm": 0.31886205077171326,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.7209,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.2438319568781312e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null