Aivesa commited on
Commit
2f1cfe7
·
verified ·
1 Parent(s): 97700aa

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 sha256:070e9047813199e58d5bbac097593f9d1efbc798c1aaf02fd3ec644574ffdc06
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d652bab68d7eb4e8c2671a941ca16c0b2f13b9f8d375c3bfb99015ef50971550
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb0fdd2af9056795ae9699aeaa9a03650af351bd5fa9fa101d1978f44db5902
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e1b3521bbe7e20a37adf5c3b9f8b41af9f66dbeedf5097a18c6ff0c2065de3
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b453903d08153f576c10e1892a0535fb09ece105a29e0721c2e414bf14170ba
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d6f87dc95ff15819fcba74baaa39847b99daff8487bf382d9e736bcf11711d
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": 0.0009473434909607642,
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": 26.864,
66
  "eval_steps_per_second": 13.437,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 230212780425216.0,
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": 0.0014210152364411463,
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": 26.864,
66
  "eval_steps_per_second": 13.437,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0011052340727875582,
71
+ "grad_norm": 0.26632893085479736,
72
+ "learning_rate": 0.00014,
73
+ "loss": 0.9681,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.0012631246546143523,
78
+ "grad_norm": 0.28235024213790894,
79
+ "learning_rate": 0.00016,
80
+ "loss": 1.0387,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.0014210152364411463,
85
+ "grad_norm": 0.45062515139579773,
86
+ "learning_rate": 0.00018,
87
+ "loss": 1.215,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.0014210152364411463,
92
+ "eval_loss": 1.0538045167922974,
93
+ "eval_runtime": 92.7417,
94
+ "eval_samples_per_second": 28.757,
95
+ "eval_steps_per_second": 14.384,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 345319170637824.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null