trenden commited on
Commit
32dce98
·
verified ·
1 Parent(s): b362cb8

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:d0f326578a09ef507591c503b094980600aca849174f6dff98f05b21ce532e7b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0afcbb45190929647e30a0679643ba239b6b9d4010e0c171135f1651be6ce2f
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:330894170178c23ae4a97146bcd4e82271a247d476e735e8ca49045512152317
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f86b8ffbf9707e0928db1c75e6a92d457d049e54e0ce7a6494e231f73bf52ea0
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83e1d42fa3a43f0b49fecc1fb9869481eef60e0607192a6ff7e39173952f7302
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b706875855f2be5f34e8de6609fc6e1b16fd875f08c9910f48619db8c936bf46
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": 0.00012546526703191,
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": 30.242,
74
  "eval_steps_per_second": 15.121,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1095418616217600.0,
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": 0.000188197900547865,
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": 30.242,
74
  "eval_steps_per_second": 15.121,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00014637614487056166,
79
+ "grad_norm": 18.32404899597168,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.3212,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00016728702270921332,
86
+ "grad_norm": 13.443620681762695,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.9222,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.000188197900547865,
93
+ "grad_norm": 7.744986534118652,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.2771,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.000188197900547865,
100
+ "eval_loss": 0.8026406764984131,
101
+ "eval_runtime": 666.0511,
102
+ "eval_samples_per_second": 30.232,
103
+ "eval_steps_per_second": 15.116,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1708853041299456.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null