JacksonBrune commited on
Commit
2b88b86
·
verified ·
1 Parent(s): 0401cd7

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c4afbd478445e3d8004653a0876cf7e938550db7ec6a132e85aea4efd78c3cb
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec946e8a228de7972f42da92a32e823227dba16fe49149bd3ef84c717f169371
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2da34a9cfcb8138d80c45cc9d89f4430f00b82a9e6930667f29617850004aaec
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f08a217b81ef050d112a349afd5ac7206baa0ba1d4cfab28c2e3f3d86b481b1
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69acfd531402f1d52576291f438970a989d185d78c1d891577d2b37a00ff3918
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec39f0c2cbcafeaa336e1b2da556e5fb3b8e22e8092d418b202df0681b6f6ba7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.1440443213296399,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 34.06,
61
  "eval_steps_per_second": 17.03,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 3580018173149184.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.18467220683287167,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 34.06,
61
  "eval_steps_per_second": 17.03,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.14773776546629733,
66
+ "grad_norm": 8.130218505859375,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 5.1934,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.18467220683287167,
73
+ "grad_norm": 6.545614719390869,
74
+ "learning_rate": 0.0,
75
+ "loss": 4.7704,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 4589766888652800.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null