adammandic87 commited on
Commit
61d411c
·
verified ·
1 Parent(s): 3c6ae2c

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 sha256:222e64246cfa50cde7627147ee784ea9de96a7c54a9a184cfb3eaf85a5512b55
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5daa46155fb7b0cc263ef1799291136a05796a67b8b1434be1d8bfbd73a1d0b9
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:251ef88ee39d1863e7f74f7dd92ff2576c88474615e5ea67dcd5a196e3b247cc
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89cc0e06f1e3c8ec34237abddcdadcb5dd413df45bc76eb9e1b8ef2caf4402c5
3
  size 33424212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fced2d2adf59e7d8d0452116b0ba560f1e6f57a22ac2d89903844fdaf93c8bfa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f303dbdb6e91e8d3f652bf7aa35cf837fd0e49b11625945338e0249a07acebc
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": 0.0006536659766859135,
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": 21.901,
74
  "eval_steps_per_second": 10.953,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1958973636870144.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009804989650288702,
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": 21.901,
74
  "eval_steps_per_second": 10.953,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0007626103061335657,
79
+ "grad_norm": 3.4829514026641846,
80
+ "learning_rate": 0.00014,
81
+ "loss": 9.251,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.000871554635581218,
86
+ "grad_norm": 5.667882442474365,
87
+ "learning_rate": 0.00016,
88
+ "loss": 9.0865,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0009804989650288702,
93
+ "grad_norm": 4.481005668640137,
94
+ "learning_rate": 0.00018,
95
+ "loss": 7.4192,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0009804989650288702,
100
+ "eval_loss": 1.9611176252365112,
101
+ "eval_runtime": 176.2277,
102
+ "eval_samples_per_second": 21.932,
103
+ "eval_steps_per_second": 10.969,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2897648504537088.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null