nathanialhunt commited on
Commit
1bad21c
·
verified ·
1 Parent(s): 6d30571

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:df60136d03e23f4d49bf6eba23440ffaa370b225ab93d45cc24036370a3a5715
3
  size 15182728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aee93598f700b4285cd4b3ccb8b92bb23848b7e93737a33f9038f02155adc42
3
  size 15182728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9e2c6bed21db4281a194ccffd66c4b93d0039bfacc5b0d33dc37e017ca37f85
3
  size 8075796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb4b58f1c94e75686ffdbc0acd0e0c1c29e29c7bc47aa4ff0859a4551397458
3
  size 8075796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75edea52d41d208ca719ebf2156cdc8388477750345a58b2d3c205bcb4108543
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3609422b48ac694e14d0016dc68a3103e611f8728ccdca3de9f7f68d54673223
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": 0.04913385826771653,
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": 55.241,
61
  "eval_steps_per_second": 27.703,
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": 299222830153728.0,
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": 0.06299212598425197,
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": 55.241,
61
  "eval_steps_per_second": 27.703,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.050393700787401574,
66
+ "grad_norm": 0.7553784847259521,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 3.0366,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.06299212598425197,
73
+ "grad_norm": 0.8436616659164429,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.932,
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": 383619013017600.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null