chauhoang commited on
Commit
7f47b84
·
verified ·
1 Parent(s): 2563deb

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 sha256:826e3216d0b889f30cd6541bcb3ec7137fd3c9876f2e874e3fdf56707b500ad8
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56fd86b8cfb9320d9f65f51f5dbdebb4fe26cc8823eddc4db670b3957a439248
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b857f93b09c96138646b5e849071772b090b5cf28fd843ec26ad51bd11081e9
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b735b021b416f4a405994dc29943b47aa65804d9f7ad8f98e5dc2be6df3c31fa
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:a66ada259260869481e778bff01664524ba6c2c0487bad481b74d64a06cf7bc3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff6ab78eb6b684556bd3fc94acbb1f0761d97a15280b8729d3bb78e27e36717
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": 0.0007281587386050159,
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": 0.2826,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 831323929313280.0,
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": 0.0010922381079075238,
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": 0.2826,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0008401831599288645,
72
+ "grad_norm": 1.3753119707107544,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.2473,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0008401831599288645,
79
+ "eval_loss": 0.2126530557870865,
80
+ "eval_runtime": 483.8367,
81
+ "eval_samples_per_second": 31.075,
82
+ "eval_steps_per_second": 15.538,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0009802136865836753,
87
+ "grad_norm": 1.5297538042068481,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.1736,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1259775492882432.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null