adammandic87 commited on
Commit
9feb663
·
verified ·
1 Parent(s): 30eb84d

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:f48e75b610b6bff84b28ba08d838d1d9b87678b04740f9c0a83f948f5582abfd
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fca6962d38d8cd7568888653bcf54149a66bcc819a55babe72859702af3888ad
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ff2dca8aa649bf27d7ca3ef19751ccb6677d3e3d791a79ab2f4e8a48036e403
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ad0c44d1c3620b0bb55684310731bdb01c3062b983796922caece456ce6a2a
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:f5c3c915a3bb8b4192b1fe9ab2e40a6b8012bb6b2e4c94a894df47ee8a987a0e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e339279e44c5c15da33d41816eb20d1d43d6744958966d073b2d253a0420c7
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": 0.0005118689615458443,
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": 26.432,
74
  "eval_steps_per_second": 13.216,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1359453911777280.0,
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": 0.0007678034423187664,
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": 26.432,
74
  "eval_steps_per_second": 13.216,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0005971804551368183,
79
+ "grad_norm": 1.1074120998382568,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.7724,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0006824919487277923,
86
+ "grad_norm": 1.1702643632888794,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.5928,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0007678034423187664,
93
+ "grad_norm": 2.0787010192871094,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.2394,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0007678034423187664,
100
+ "eval_loss": 2.8718318939208984,
101
+ "eval_runtime": 186.8191,
102
+ "eval_samples_per_second": 26.421,
103
+ "eval_steps_per_second": 13.211,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1894996361871360.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null