tuanna08go commited on
Commit
a6cfafc
·
verified ·
1 Parent(s): 506f145

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:b762063a0a9b6608b0d8641af49144086ae1fd65c181aa9a0a43e0578a5402f1
3
  size 25192496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7d7a7a8daf6554e34ef9b66bb466fe187bdc0169a30786636e380f8feeb49a
3
  size 25192496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d1c4fefa78e23324a45960e7950003dc9f282d9b8738d87934157b573f05a6d
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82db042a0b3b1dd429fe946ac01b740594b666e41698f2283bef51f6370f4c2a
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fddb71a9a3d250332f98e562706fe25ec1ff4e66f7c9c4eb0af41236fd2dde1a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75caa14d0693086c5957e78bfabc5e03e26e0a02e3ebab6e9c7167f2b79dbe10
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": 0.0014210173937994452,
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": 8.8218,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1552576319324160.0,
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": 0.0021315260906991677,
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": 8.8218,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0016396354543839753,
72
+ "grad_norm": 7.44797945022583,
73
+ "learning_rate": 5e-05,
74
+ "loss": 8.5272,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0016396354543839753,
79
+ "eval_loss": 2.082500696182251,
80
+ "eval_runtime": 695.0217,
81
+ "eval_samples_per_second": 11.085,
82
+ "eval_steps_per_second": 5.542,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0019129080301146378,
87
+ "grad_norm": 9.079113960266113,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 8.1588,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2328864478986240.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null