nathanialhunt commited on
Commit
9016efd
·
verified ·
1 Parent(s): 0b6f825

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 sha256:15a0bbfa5da5e81aa4f31244b5bb527bbdde75d8b21364286df793c5f8723042
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ddb7d5b141775866337286d7689a0089662e1f8555bf14c12f7333007eea66f
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57fd43981e21fc2385fa42e49745d98a61d9165283d59f5d2c3d0d0b5f61fa75
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71fd2f9b3767f7631e564123964e41ac0e6e5fc8ee1aad6c6acfa94500e6035d
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0004749277714014327,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 33.637,
45
  "eval_steps_per_second": 16.819,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 524868391010304.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009498555428028654,
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,
 
44
  "eval_samples_per_second": 33.637,
45
  "eval_steps_per_second": 16.819,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0006332370285352436,
50
+ "grad_norm": 1.4070159196853638,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.3978,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0007915462856690545,
57
+ "grad_norm": 1.4026979207992554,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.1565,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0009498555428028654,
64
+ "grad_norm": 1.2851192951202393,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.0725,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0009498555428028654,
71
+ "eval_loss": 0.9489461779594421,
72
+ "eval_runtime": 79.3249,
73
+ "eval_samples_per_second": 33.533,
74
+ "eval_steps_per_second": 16.766,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1049736782020608.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null