tuanna08go commited on
Commit
a745585
·
verified ·
1 Parent(s): dddbcb6

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 sha256:2e394a046cee7ed331342927da84217c15ec393b0856ea7874da286101ed937d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:189466a215f15d663b8d82d72c933eb9f21c8f09d909193fabc1e53f0cc07ac6
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:171a8f3032784f1965d01c46c25ba9bbd35a4525643787bc38f3e61af993208d
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91dc90f3251d1b3ddbbd52a76c9cedb1cb37b9ed070785c0e5561178a4396a9
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c4d27121fab067bc2de3268a7564a068ae9e664d1d190e48cc49eafb04fd334
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48387a63bde87dc1fe3c98a1e6ea341819380eedccc04e7d52e113dc6afcad0
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": 0.0107095046854083,
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": 0.2166,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8241181536288768.0,
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": 0.01606425702811245,
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": 0.2166,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.01235712079085573,
72
+ "grad_norm": 1.1249637603759766,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.2605,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.01235712079085573,
79
+ "eval_loss": 0.0556037500500679,
80
+ "eval_runtime": 164.1499,
81
+ "eval_samples_per_second": 6.232,
82
+ "eval_steps_per_second": 3.119,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.014416640922665019,
87
+ "grad_norm": 1.0365431308746338,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.182,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.2186428016427008e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null