adammandic87 commited on
Commit
c3173d4
·
verified ·
1 Parent(s): b906790

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 sha256:86f109732b92fb386bb9b8f1fafa4c06892bc1e39f696cac48e5d95af9266fe1
3
  size 327040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87bdace5dedcacc381a1c7bbf9744f0fd5671f72a3662532184e2987d07f8fa5
3
  size 327040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f36625464e7d75986526cb0acd985210b5fe94b1b8eda87561aa62fcaf28549
3
  size 739258
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a73bb27857b9ed1dc49a6f98016795bfdd2791b4aeabbb6c51c136621fc54d
3
  size 739258
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fb5f1f2063cc0fc9d69930536ad8305cd213d31011d601a76e1f19f1f368b7a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce48dec86ac6000671bbcda61602ac669c6643b660b3c79e45fe5bfda138dc71
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": 0.006012024048096192,
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": 21.261,
74
  "eval_steps_per_second": 10.656,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1501871210496.0,
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": 0.009018036072144289,
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": 21.261,
74
  "eval_steps_per_second": 10.656,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0070140280561122245,
79
+ "grad_norm": 0.17056019604206085,
80
+ "learning_rate": 0.00014,
81
+ "loss": 11.9374,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.008016032064128256,
86
+ "grad_norm": 0.1461707204580307,
87
+ "learning_rate": 0.00016,
88
+ "loss": 11.9358,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.009018036072144289,
93
+ "grad_norm": 0.1584092676639557,
94
+ "learning_rate": 0.00018,
95
+ "loss": 11.9383,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.009018036072144289,
100
+ "eval_loss": 11.93490219116211,
101
+ "eval_runtime": 19.8691,
102
+ "eval_samples_per_second": 21.189,
103
+ "eval_steps_per_second": 10.619,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2252806815744.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null