trenden commited on
Commit
4f9145f
·
verified ·
1 Parent(s): dd22b99

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:ad2966bf4012d6d773783bdc5a54690f30ecf910f9cb666bdff84c63ceedcd60
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e870406301de248966ff822cece364b08d52fe619ac7140448c6b5fbb814753
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:501546aff4abbb8e5ed0d55f657ce42c26b8bf5f0e0260069b9a19802f21aef1
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c2b86dff0314b91385966ec7b0f01f1b8d6137c798396cd4a69bc5456f7e0c
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9b931b5fc0c1bd85ac8b5cf7dfdfe32425d1d78ecf18cf7fdcddc467f06765e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
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": 6.319398182646406e-05,
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": 322.225,
74
  "eval_steps_per_second": 161.112,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 109912719360.0,
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": 9.479097273969609e-05,
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": 322.225,
74
  "eval_steps_per_second": 161.112,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 7.372631213087474e-05,
79
+ "grad_norm": 0.0235343836247921,
80
+ "learning_rate": 0.00014,
81
+ "loss": 10.3782,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 8.425864243528541e-05,
86
+ "grad_norm": 0.02634567767381668,
87
+ "learning_rate": 0.00016,
88
+ "loss": 10.3819,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 9.479097273969609e-05,
93
+ "grad_norm": 0.021794479340314865,
94
+ "learning_rate": 0.00018,
95
+ "loss": 10.379,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 9.479097273969609e-05,
100
+ "eval_loss": 10.377360343933105,
101
+ "eval_runtime": 124.0443,
102
+ "eval_samples_per_second": 322.288,
103
+ "eval_steps_per_second": 161.144,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 148705443840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null