duyphu commited on
Commit
29b0876
·
verified ·
1 Parent(s): e1e24b9

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 sha256:24f5230dc978f7baed0362876dc9ae3a54f6878765684f8b68277b41fa9a7457
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c817a4be4a708541c2761946db1bc48b1e027449939c221c809ea8e4871ac0e9
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2955cbe5c615737ae080563595ea65a272de78c6e923876b6f5c3c07a81c99c2
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8467d55e6afc3e03a46cf93d82be4a4a3ee6501b5ca7027f092bdd89c61e7910
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:ff7e137117c7946038800b1a4022151a2c285ccd73758892158218b4c83c4671
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f9b9752f49f9f52e6605be303590b8adaa339e8456ccb350b68c2878cbc286
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": 0.011057947900053162,
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": 1.8541,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1304539089076224.0,
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": 0.016586921850079744,
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": 1.8541,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.012759170653907496,
72
+ "grad_norm": 0.767362117767334,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.6768,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.012759170653907496,
79
+ "eval_loss": 1.74953293800354,
80
+ "eval_runtime": 33.6627,
81
+ "eval_samples_per_second": 29.409,
82
+ "eval_steps_per_second": 14.705,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.014885699096225412,
87
+ "grad_norm": 0.9434619545936584,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.6874,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1931229435789312.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null