fats-fme commited on
Commit
dbd9b9b
·
verified ·
1 Parent(s): f8f3661

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 sha256:835a05bea8b920044351cf9bbf13ed89428fc60ac0fb1f3c54bcbc15f0ca35aa
3
  size 45118424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75911dd042b0427dee24dcb9321c7b50b5ce9356cf31fb08e109efa4101a1f2f
3
  size 45118424
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81f62f08123e1d4cdd74bc9822cf423608015326db7ddec1e5cf7668dd5f5804
3
  size 23159290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f809699b39576aa332a27d83711ee2d4ed777683b4f521f19df7137dd6d3dce
3
  size 23159290
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da6d51f12e3f9c5a361768047223feb6775db64aa121716b67d57cbb0fda80a5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d46b6ef7ca2c27dbd6779326446a3edbfe63f588b2738801236c0928f47f3c1
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": 0.009832036050798854,
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": 3.241,
74
  "eval_steps_per_second": 1.627,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1161267083476992.0,
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": 0.014748054076198279,
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": 3.241,
74
  "eval_steps_per_second": 1.627,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.011470708725931995,
79
+ "grad_norm": 1.779176950454712,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.1033,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.013109381401065138,
86
+ "grad_norm": 1.6860111951828003,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7718,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.014748054076198279,
93
+ "grad_norm": 1.8793421983718872,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.7841,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.014748054076198279,
100
+ "eval_loss": 1.7667855024337769,
101
+ "eval_runtime": 78.8217,
102
+ "eval_samples_per_second": 3.261,
103
+ "eval_steps_per_second": 1.637,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1741900625215488.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null