chauhoang commited on
Commit
879236f
·
verified ·
1 Parent(s): 07a18ac

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 sha256:2c50a9c9cb2d3814e1a4922382b697da87aa6f724992a9eafd91689e486e929b
3
  size 1579352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:366cece83fccaaba8bd4b42ae5cb145f96e5d5e0297d5d03f307c33eb5ba2423
3
  size 1579352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c9410a1a246561cf2525845a93fa23ac985652324eecab9cb51825078006e1d
3
  size 857338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5af05afff2a0c9ab40826a04bb1288a181f810968f0a243f01319912c074109
3
  size 857338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bcca48a778be86146efdd9c58ed4aeb246a0ede27cd32337d0c999e879389d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ef582aee20a74150e9453503b6181f999d478c653e0f80448b88e81817295d
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": 0.0066462167689161555,
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": 77.0789,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 28794937147392.0,
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": 0.009969325153374233,
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": 77.0789,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.007668711656441718,
72
+ "grad_norm": 654.0535888671875,
73
+ "learning_rate": 5e-05,
74
+ "loss": 79.6657,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.007668711656441718,
79
+ "eval_loss": 20.094011306762695,
80
+ "eval_runtime": 11.6588,
81
+ "eval_samples_per_second": 141.352,
82
+ "eval_steps_per_second": 70.676,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.00894683026584867,
87
+ "grad_norm": 1161.23974609375,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 89.0292,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 43192405721088.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null