duyphu commited on
Commit
e616131
·
verified ·
1 Parent(s): fc98625

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 sha256:0af78d25c48ca110b354ccc57e202307a03174c9f181973414fbdbb378ac4fab
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fad9c0d6b8b826c612ce6aef3d1d6aa41d76e1ca4c7c04ef9815f98d998090d
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6554c0639b80b1dd91f1e0981450090fdc2227d8a1bcd7400c632cdbc1cc15a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ac3cbe059dd8bf4d1745ddc04c51027d7b7886f2eff6707a218fae4bff75b5
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
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": 0.012109920819748486,
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": 2.9618,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4808867045179392.0,
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": 0.018164881229622728,
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": 2.9618,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.013972985561248253,
72
+ "grad_norm": 4.308791637420654,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.9387,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.013972985561248253,
79
+ "eval_loss": 2.854153871536255,
80
+ "eval_runtime": 61.2445,
81
+ "eval_samples_per_second": 14.777,
82
+ "eval_steps_per_second": 7.397,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.016301816488122962,
87
+ "grad_norm": 4.229650020599365,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.5853,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7213300567769088.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null