Aivesa commited on
Commit
ceb68d6
·
verified ·
1 Parent(s): 30ba0dc

Training in progress, step 9, 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:aaf8f68e016622e20b5b8884b7668caf68393715a0269977949f3fa87661703f
3
  size 7586384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03991258c12f067eb8f6740c658c5d4a9ec018d59b089be0af48b0e7d92cbd8e
3
  size 7586384
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e80006fb87770d7fcee254a5c9bb082fbadd9bdccbbeec1c87cf0883718eebd4
3
  size 4027642
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa9dc8ade88be6ada5888525aed5c6287020dc5d8f90fa89dc1db77673849bde
3
  size 4027642
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2afd8b059029a840fb85e4e259b50a09ed671e60a6916ddb1666b41fa532c772
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252ee14cb440203dbc9a036ce807d18ac00757efdc7beb446e076604019f4754
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.012048192771084338,
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,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 21.41,
66
  "eval_steps_per_second": 10.705,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 33190753075200.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.018072289156626505,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
65
  "eval_samples_per_second": 21.41,
66
  "eval_steps_per_second": 10.705,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.014056224899598393,
71
+ "grad_norm": 0.667701005935669,
72
+ "learning_rate": 0.00014,
73
+ "loss": 10.6087,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.01606425702811245,
78
+ "grad_norm": 0.8505023121833801,
79
+ "learning_rate": 0.00016,
80
+ "loss": 10.5687,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.018072289156626505,
85
+ "grad_norm": 0.8433892130851746,
86
+ "learning_rate": 0.00018,
87
+ "loss": 10.5445,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.018072289156626505,
92
+ "eval_loss": 10.517779350280762,
93
+ "eval_runtime": 5.8197,
94
+ "eval_samples_per_second": 36.084,
95
+ "eval_steps_per_second": 18.042,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 49122314551296.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null