tuanna08go commited on
Commit
2389829
·
verified ·
1 Parent(s): 16b0893

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:ea2329ad0dc56bc5e72c11194832cf97ba56fca047704fc09e966e9eecf4f655
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641355f7dc6e45a7f9e8908a0c1e8f9078df88aa22b23c592f35baf3b4f22a88
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec9a7ffa722c03ee24ab5abaf8a08c2888030dc78796d9eb4195ba864c68b690
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65c47a8319e1d02d97629723abf29eccb33ba0f86a1349588fb6614b9dd184d4
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4da9e326c98fd1fa44c4b4094cfd55b913b813091d6f24dc3017dbeb3731795d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b88f1cc52e016d0f487edd487fed23adecfbbe085084d34ab449df1f1583b7b9
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": 0.020011545122185878,
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": 0.8793,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4530853719834624.0,
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": 0.030017317683278814,
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": 0.8793,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.023090244371752933,
72
+ "grad_norm": 2.402998924255371,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.7494,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.023090244371752933,
79
+ "eval_loss": 0.7266308665275574,
80
+ "eval_runtime": 93.1145,
81
+ "eval_samples_per_second": 5.885,
82
+ "eval_steps_per_second": 2.943,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.02693861843371176,
87
+ "grad_norm": 4.128040790557861,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.7426,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6796280579751936.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null