tuanna08go commited on
Commit
390f501
·
verified ·
1 Parent(s): 24f6969

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 sha256:3093ef7158b1bad6f89b97833dce5215132082e48c6f46f7a9faa4ed62df4180
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662d9d92d0a90b200d41e4f2d685bd1433fdbb720d20581e4507fc21df423084
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ec6f52b77d972b31db4926239c97abf4b9f2e4a8622c4af27e54f8032f3b5ae
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a2a31feb770a316761014c3e502f0c0e2893aa78e4886c444f048279a37fd7
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52355d530a9ba3c18873a09f4ff948fbf5a3c45f4e36f78fd66ecd368202fbdf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae934d65190093320064112674f419dd4d38402a2a91c463be02542785440cec
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": 0.0032710574322199156,
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": 0.8343,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 7352017886380032.0,
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": 0.004906586148329874,
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": 0.8343,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0037742970371768257,
72
+ "grad_norm": 0.7812676429748535,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.7194,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0037742970371768257,
79
+ "eval_loss": 0.8442201018333435,
80
+ "eval_runtime": 472.7127,
81
+ "eval_samples_per_second": 7.08,
82
+ "eval_steps_per_second": 3.541,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.004403346543372964,
87
+ "grad_norm": 0.5659365653991699,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.6455,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.1051146382671872e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null