kooff11 commited on
Commit
c16a68f
·
verified ·
1 Parent(s): 7f4961a

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 sha256:5f6cefef2854151810b9c13a0cb0bf5a7c35afd5832abec0244aa468d9fecdf9
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f317f6a0c511a7f23df9645b98197df98f14034ccf063b9d4a1032532a6bce7
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b06aa655fc8b7ba16903685b5832a5f9180dc01eeb97927dd5b064e23a1408cb
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3381d8f64e9fac412596e1a44b625ae5d48fddb41456467fe2b4583224ee9e2
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75b7fe1ed9d1a988cf26f4ac07eea6ab570c3b37f92d1c4968cd69d6c61bd803
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:891155de6377a4508f22e954f15f57ef4af67ae2e130e02796b781a8ce5af0a1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b68eadda5190f74fabbe61c66b0c0f1ecff37d5b9533c9627db38134274ac084
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e3b504f4b478d50a181eaa2ef317405b60ed8d97be9beec3f1a5226df2330f
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": 0.002325806764221339,
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": 5.963,
74
  "eval_steps_per_second": 2.984,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 8902647402725376.0,
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": 0.003488710146332009,
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": 5.963,
74
  "eval_steps_per_second": 2.984,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002713441224924896,
79
+ "grad_norm": 25.194347381591797,
80
+ "learning_rate": 0.00020999999999999998,
81
+ "loss": 4.5397,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0031010756856284525,
86
+ "grad_norm": 20.890501022338867,
87
+ "learning_rate": 0.00023999999999999998,
88
+ "loss": 2.785,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.003488710146332009,
93
+ "grad_norm": 17.46876335144043,
94
+ "learning_rate": 0.00027,
95
+ "loss": 1.6347,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.003488710146332009,
100
+ "eval_loss": 1.2919782400131226,
101
+ "eval_runtime": 182.2823,
102
+ "eval_samples_per_second": 5.963,
103
+ "eval_steps_per_second": 2.984,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1.3353971104088064e+16,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null