duyphu commited on
Commit
1f9cedc
·
verified ·
1 Parent(s): 5c99b62

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:bd4fe95a33e8eb6b26398664868d21139eb0dd3c1d6c364ba8aabf7f4e64bcd3
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:190c7a6593fd8455b16867a1f19329a4f665b21d39aada11e8d6a487328ebf58
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01ccc8b629e4aa1786f7f2a282a8ee56612a6356d10ffc3b8899b5aa9da54086
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6724ef3d3855b0f55c4a0611e70d0d35cd23663c3a3848cb295522ba31cf0f6b
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b03e90faa1967f18f72061550dc7b793bd6230a686d92c6466c314f9d209bd4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b626c13d49d84d2de1b88ddb2d6b4b95b03930a7805888e3dde5b34dc87399a
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": 0.014027515511195037,
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": 8.3489,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4600758188113920.0,
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": 0.021041273266792556,
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": 8.3489,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.016185594820609658,
72
+ "grad_norm": 7.083747863769531,
73
+ "learning_rate": 5e-05,
74
+ "loss": 8.2269,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.016185594820609658,
79
+ "eval_loss": 2.0463201999664307,
80
+ "eval_runtime": 48.4484,
81
+ "eval_samples_per_second": 16.12,
82
+ "eval_steps_per_second": 8.07,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.018883193957377933,
87
+ "grad_norm": 8.091001510620117,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 7.7337,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6879228909846528.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null