adammandic87 commited on
Commit
0fc0728
·
verified ·
1 Parent(s): 8d05a74

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 sha256:17cfacbfc6e46c65880281935a82e25cefe2d655996b96898cfb63891ca440dd
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1358b8b190919bd5d80075c9be42192588b66519259848c7e276d0d9c80c6577
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6a5338f3aacc6c53f012eb6f05af4d20b496cfa287c99710ff66915048711dc
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba2be0e3db54ef3f67117a9883069d13b43d7eb1fa3d8d6401f6c0368c89f4f3
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200897803867d9476163ce84baa477ea4bfc2d20fbca1d606afa2d969206fa8c
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": 0.000427807486631016,
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": 16.821,
74
  "eval_steps_per_second": 8.41,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 977239881547776.0,
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": 0.0006417112299465241,
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": 16.821,
74
  "eval_steps_per_second": 8.41,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0004991087344028521,
79
+ "grad_norm": 1.320258378982544,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.5131,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0005704099821746881,
86
+ "grad_norm": 1.641695499420166,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.702,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0006417112299465241,
93
+ "grad_norm": 1.4608796834945679,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.3921,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0006417112299465241,
100
+ "eval_loss": 3.664571762084961,
101
+ "eval_runtime": 349.8869,
102
+ "eval_samples_per_second": 16.88,
103
+ "eval_steps_per_second": 8.44,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1465859822321664.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null