DesDea1 commited on
Commit
0677de3
·
verified ·
1 Parent(s): c3d7e6f

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 sha256:6ede2c8630156f4d30493e5f75fca203cde379edb2f9d20ff1d68af351efc3d9
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9caa8aad73a9fab00ceef17acba24aad73730ff8f050123448b4176c1829802
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecd73ed0b22797ad7080565bc487ff05b4271d36414f8cacb84d9d5e4f569b54
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6c833d7c4fbccce451889d5c92a79582558810d40aad84c8eeb0d0ca7681ba
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b77ec1d9059fbf29655439de7be3898314e6d6e711dfa2949a49c214c62651ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d43ab25a0e82acb814d1ea8e6e3081e15589e0ffbcf9e9292c2a91fda2e5dfa4
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": 0.0074188562596599695,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 2.318,
74
  "eval_steps_per_second": 2.318,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4451323701362688.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.011128284389489953,
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,
 
73
  "eval_samples_per_second": 2.318,
74
  "eval_steps_per_second": 2.318,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00865533230293663,
79
+ "grad_norm": 12.877334594726562,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.5622,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.009891808346213293,
86
+ "grad_norm": 24.434354782104492,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.8512,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.011128284389489953,
93
+ "grad_norm": 16.24271583557129,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.0013,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.011128284389489953,
100
+ "eval_loss": 2.780280113220215,
101
+ "eval_runtime": 73.7018,
102
+ "eval_samples_per_second": 2.32,
103
+ "eval_steps_per_second": 2.32,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6676985552044032.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null