dzanbek commited on
Commit
1cc9bd8
·
verified ·
1 Parent(s): ebdf01b

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4be2626d3b87d9dbd789da90488adc34acc26530f34be6279b08c5cdd50310cc
3
  size 63592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17131e2dcf0e09a0777cef5e5be461c26e2e79db8a7830f7c681821ceba2d1d
3
  size 63592
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:985c1381512b3380f5f38cfff918a152258ae3bb132b9e3d40910503fd9c7f83
3
  size 132798
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75256d7e13cbb0818e99cef5a26ba483a115571e64ef664512babf1fff9d146c
3
  size 132798
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f365462a622095c1188d25620d5e08eaced77b1a289f50e3e26cffab7c3f7d8b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d00dfae48b2782ecf08c0272c6aeaedad798ddbb45fa725272d2fe913436954
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
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": 0.00013630245514797336,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,28 @@
59
  "eval_samples_per_second": 108.242,
60
  "eval_steps_per_second": 54.125,
61
  "step": 4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -78,7 +100,7 @@
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 12166103040.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00020445368272196002,
5
  "eval_steps": 2,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 108.242,
60
  "eval_steps_per_second": 54.125,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.0001703780689349667,
65
+ "grad_norm": 2.7002158164978027,
66
+ "learning_rate": 5e-05,
67
+ "loss": 44.4089,
68
+ "step": 5
69
+ },
70
+ {
71
+ "epoch": 0.00020445368272196002,
72
+ "grad_norm": 2.5694777965545654,
73
+ "learning_rate": 6e-05,
74
+ "loss": 44.3066,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00020445368272196002,
79
+ "eval_loss": 11.091360092163086,
80
+ "eval_runtime": 114.2137,
81
+ "eval_samples_per_second": 108.192,
82
+ "eval_steps_per_second": 54.1,
83
+ "step": 6
84
  }
85
  ],
86
  "logging_steps": 1,
 
100
  "attributes": {}
101
  }
102
  },
103
+ "total_flos": 17781227520.0,
104
  "train_batch_size": 2,
105
  "trial_name": null,
106
  "trial_params": null