nathanialhunt commited on
Commit
e69d0cc
·
verified ·
1 Parent(s): 3ce18ce

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 sha256:0d57b45737f1ad7f28b1e074270298a7463b0b02c74fc9835d85c8d795768a2e
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e870a9323359775baafa92b567fe10385e5f5302a30ef2eac6fd333705c14ce1
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b334044cf3c342986be6fe1ec1eedb0a3a59079793c52e0d1ac951909711736c
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b140d4679e0ea0372e6e5bdb72f8a777715b33658185e2699682b8b31aa73e05
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c972796619e858bb767b916dc5bb8f6ea7a4b1f4ef85a988373da5f475a4e0ca
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66734fcb570e483a3b6f6260a87666c97cf11e29764d9942fbe0a9d194db7eb0
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": 0.0019286403085824494,
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": 21.927,
74
  "eval_steps_per_second": 10.964,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2424884554629120.0,
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": 0.0028929604628736743,
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": 21.927,
74
  "eval_steps_per_second": 10.964,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0022500803600128574,
79
+ "grad_norm": 1.947957158088684,
80
+ "learning_rate": 0.00014,
81
+ "loss": 7.3814,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0025715204114432656,
86
+ "grad_norm": 3.4860267639160156,
87
+ "learning_rate": 0.00016,
88
+ "loss": 8.7578,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0028929604628736743,
93
+ "grad_norm": 2.8685097694396973,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.9682,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0028929604628736743,
100
+ "eval_loss": 1.8758397102355957,
101
+ "eval_runtime": 59.7212,
102
+ "eval_samples_per_second": 21.935,
103
+ "eval_steps_per_second": 10.968,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3637326831943680.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null