trenden commited on
Commit
efb3662
·
verified ·
1 Parent(s): e042854

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:d881d9d3deb48b6d059ab42b29a452e2aa3abf34f0b08f65457b2a80467d0ca3
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e893e1eb229b5d8bfdc440b8003b12d0dae5396c16e22b31c76cb22951170a8
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a3a1a630cb056559d21c90652d21623cfafd66daba138a2a675c36ef094f916
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e0f7b13c23ee94f1981489a9bc60395a11173f035ec681a8dc9b2f59e241f69
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3483100185f9bb64a1baea7d0678dd8819a763e19d4dc3947a4c495c2a757eec
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b20db3596a2edec9e10a5bcdb00be79cffac991bb5d006b2a6127e36af7471
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": 0.003947368421052632,
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": 20.717,
74
  "eval_steps_per_second": 10.358,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1689018496450560.0,
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": 0.0059210526315789476,
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": 20.717,
74
  "eval_steps_per_second": 10.358,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.004605263157894736,
79
+ "grad_norm": 0.3247911334037781,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.9942,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.005263157894736842,
86
+ "grad_norm": 0.4075062572956085,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.4667,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0059210526315789476,
93
+ "grad_norm": 0.507950484752655,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.1074,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0059210526315789476,
100
+ "eval_loss": 2.1078224182128906,
101
+ "eval_runtime": 30.8858,
102
+ "eval_samples_per_second": 20.721,
103
+ "eval_steps_per_second": 10.361,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2512929958133760.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null