chauhoang commited on
Commit
6f7a9b0
·
verified ·
1 Parent(s): 6890cc4

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 sha256:2f0e1f3958db37933089f994826bc701c9a74bd6075f6af8944725c5956514e3
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07796f324678c9383b29f9aada70bcf5ea48d4651c0dbb71f2d2a0327196b37
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abe9f0fd7aedba5364a97ca0fc7ff23b691a4bc1b21b5caf1478ad37e1deb75a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a28a7ebcb31d5a2c7eb50797fac5e0dde98ccf5a4c690cd2a5f43d97cea6ba17
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72d2123828a202521fed49695ce20694823d9999d33262dd05d88a1ab8cbe183
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
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": 0.007347227128223242,
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": 1.3488,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9113893355913216.0,
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": 0.011020840692334864,
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": 1.3488,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.008477569763334511,
72
+ "grad_norm": 2.1892991065979004,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.2326,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.008477569763334511,
79
+ "eval_loss": 0.31931397318840027,
80
+ "eval_runtime": 178.5123,
81
+ "eval_samples_per_second": 8.347,
82
+ "eval_steps_per_second": 4.173,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.009890498057223597,
87
+ "grad_norm": 3.244086742401123,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.2139,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3670840033869824e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null