nat-hunt commited on
Commit
569a86d
·
verified ·
1 Parent(s): ecf312a

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 sha256:67a6bdfe33c00b70ba11a6ee7feed2390b4ba5c9725a44f7bcb5692827dc0cfe
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c745863dcd39a9aa81f81aefc60866a6d4133814f177fd247666c50e42c1f32
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:446e36431a4c0e96a1b320dad7959705c99aeb4deeaa01873885833426e25629
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e663cf026a0efead3eaa78b8c39c7405404ad24767b450f58f8faed47c6c604
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07d77b60a4a6ac9b1290011cfbb000725f2f3c555f2baada62884afb493a185f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d05d926a13e2b0db86e596e2ee777dcc8276585d379e27b6ca55897b2ce7fe
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.022966507177033493,
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": 10.666,
74
  "eval_steps_per_second": 5.333,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3799446517186560.0,
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": 0.03444976076555024,
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": 10.666,
74
  "eval_steps_per_second": 5.333,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.026794258373205742,
79
+ "grad_norm": 0.510155439376831,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.7204,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.03062200956937799,
86
+ "grad_norm": 0.47774097323417664,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.6391,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.03444976076555024,
93
+ "grad_norm": 0.5274300575256348,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.5699,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.03444976076555024,
100
+ "eval_loss": 1.6443548202514648,
101
+ "eval_runtime": 10.2944,
102
+ "eval_samples_per_second": 10.685,
103
+ "eval_steps_per_second": 5.343,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 5699169775779840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null