kk-aivio commited on
Commit
e2e8f20
·
verified ·
1 Parent(s): 871d3c0

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fd5d50085745a666d2ecea036d9b3fcaeb6ac13d6574d9cf6fa1dde5e7ff0ef
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d03aa7e33f46459ad8720c7eae0022caa17b0c099a5591e39b2e175b4e8a58
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ffca6aafeda17b19877b639d4b044f801458aaf6f06a37eae2a8d5a582adca9
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b0364f2d5d6c24ab0f435ad23e715a8be206f07bf0912ceb4b8e45cf6267098
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0140f92d9a33adb908ea3be0b8c364b4a22dd5603c63bb74b7c160c14426f840
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df84a2b73072e596576ed6a8ed3d1cfbd3c26c96d47bd7bdb99c207da369cac
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0025194205332773464,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 15.949,
45
  "eval_steps_per_second": 7.974,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1146654849761280.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005038841066554693,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 15.949,
45
  "eval_steps_per_second": 7.974,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.003359227377703128,
50
+ "grad_norm": 0.6957189440727234,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.9805,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.004199034222128911,
57
+ "grad_norm": 0.7422357797622681,
58
+ "learning_rate": 0.0001,
59
+ "loss": 0.8764,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.005038841066554693,
64
+ "grad_norm": 0.6519572138786316,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.8963,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.005038841066554693,
71
+ "eval_loss": 0.7828396558761597,
72
+ "eval_runtime": 31.5287,
73
+ "eval_samples_per_second": 15.922,
74
+ "eval_steps_per_second": 7.961,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 2293309699522560.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null