chauhoang commited on
Commit
e5f349e
·
verified ·
1 Parent(s): 7b244cb

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:a632de4053e874329e7ea18858af6fea49f2e6f4190b5378c9c1447529ceaaf6
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34087bd882cf8b5632e0c826eab8bb617648eaa98773b6589b6a703514bd3180
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5ac9f8d961777f43a1b2f579cf71d530a466c6e13e891de9bcdf782b04042ad
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e81c20a2abc9a07c1f30c9eaf898f32d154bd008018dc1040dd3594073a3f7
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73f33e6b80d342e2ea8d5543c9a256e63e8dbc96b02b4a8b5cc6ff467fc2c384
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79145c5ad830b757213674108b84f21e354aa0a205c7b5da804f4b64fcb082d
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": 0.07957153787299158,
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": 0.9044,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 991193915719680.0,
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": 0.11935730680948738,
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": 0.9044,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.09181331293037491,
72
+ "grad_norm": 0.5938111543655396,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.7093,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.09181331293037491,
79
+ "eval_loss": 0.7915513515472412,
80
+ "eval_runtime": 4.6291,
81
+ "eval_samples_per_second": 29.811,
82
+ "eval_steps_per_second": 14.906,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.10711553175210406,
87
+ "grad_norm": 0.7431860566139221,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.807,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1464409075482624.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null