trenden commited on
Commit
02e36c4
·
verified ·
1 Parent(s): 7a6d008

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 sha256:9df52e2dca4152b8adbad0882d91c5c3c0f2a369264d1d3f9461c1319c554a22
3
  size 12609416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776a3f20a5743b32e0ac16c047d8dd784d8dadcafe37631d786ca49f03bced28
3
  size 12609416
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af2ada5606eb0f92a75468757cd3e2ab8e1df3bf6612b62e6e1c7efea2af2d7a
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46abfe435502802945ba596c47b15b16651f5c173c861c4a35cc79359f9aa14e
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a05e8c8d4f4ea5c6947dad0aa69b6f43b41a930416dd2c1ca05214316cbbf69
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6279e2d6d30b2ce7f2189e648e383ab146d51fb0fecf44d1e16d05504562e6f8
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": 0.003410544266022453,
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": 65.482,
74
  "eval_steps_per_second": 32.785,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 50672015769600.0,
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": 0.005115816399033679,
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": 65.482,
74
  "eval_steps_per_second": 32.785,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.003978968310359528,
79
+ "grad_norm": 4.464724540710449,
80
+ "learning_rate": 0.00014,
81
+ "loss": 8.9876,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004547392354696604,
86
+ "grad_norm": 4.148013591766357,
87
+ "learning_rate": 0.00016,
88
+ "loss": 7.7473,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.005115816399033679,
93
+ "grad_norm": 3.7501184940338135,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.5865,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.005115816399033679,
100
+ "eval_loss": 1.9691568613052368,
101
+ "eval_runtime": 11.2667,
102
+ "eval_samples_per_second": 65.769,
103
+ "eval_steps_per_second": 32.929,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 75069652992000.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null