chauhoang commited on
Commit
b6c5def
·
verified ·
1 Parent(s): 3a7701b

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:ae9fd9eaa506b4feb8a9ecf63ed9ca310a83ff042b407b56d8871d6b230e1397
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b002dca4a99d77985055026a30fbe3dd493ef525e449d627fcdbddd8a53df9f1
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3f7ff1e38ab4819b6d47ea512fce4892f6e38383c42accf7faba37d3a7123c4
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88607babbfb5b750543771bcef37834276881dfe07f5850935510a77bdecb547
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e09cb2b8a3dc2a098c18d23fdb5888e53f1ad9362c554ce30e6ccb721f5f16d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd19e18c4ac18e3c1719cc1acfa191482fdb0394cd8eba0fe84d1e0799ffc4cb
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": 0.057617728531855955,
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": 1.634,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2386678782099456.0,
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": 0.08642659279778393,
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": 1.634,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0664819944598338,
72
+ "grad_norm": 2.851886034011841,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.6273,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0664819944598338,
79
+ "eval_loss": 0.2936846613883972,
80
+ "eval_runtime": 9.2486,
81
+ "eval_samples_per_second": 20.544,
82
+ "eval_steps_per_second": 10.272,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.07756232686980609,
87
+ "grad_norm": 2.2271878719329834,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.1119,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3580018173149184.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null