Hugging Face's logo

subset-data
/
falcon-7b-bt

Text Generation
Transformers
RefinedWeb
custom_code
4-bit precision
Model card Files
xet
Community
brian-todd commited on
Commit
d577c26
·
1 Parent(s): ffa3a23

Training in progress, step 160

Browse files
Files changed (6) hide show
  1. adapter_model.bin +1 -1
  2. last-checkpoint/adapter_model.bin +1 -1
  3. last-checkpoint/optimizer.pt +1 -1
  4. last-checkpoint/rng_state.pth +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +9 -3
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af04f516604e06958c79ad27fb8aaf8e7a3262ffc8299a5c6416a831f6a24eb1
3
  size 522284877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17325da574bc4de45d40e009daa3f7adc44be55823cfbef4b8be9afdcd36663
3
  size 522284877
last-checkpoint/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af04f516604e06958c79ad27fb8aaf8e7a3262ffc8299a5c6416a831f6a24eb1
3
  size 522284877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f17325da574bc4de45d40e009daa3f7adc44be55823cfbef4b8be9afdcd36663
3
  size 522284877
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6148b1958e4a69a8b85a107e365104027fc249c7a22091cf38a9b292e19bb2c5
3
  size 1044539653
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46a23fcd6874a1853674994bee58a2a786096d6a41cbad082a14e2a21191dc30
3
  size 1044539653
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe692295c91e854e9bdd4bad4f298114db98992d153f864e93bbb4a53a049eab
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c787baf8f99d6b2efc301f4aff54d4957ec120513fe6d10f749a942c07bf7140
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01422943191c18f4ce94fe70c7ffd85d7e6e08513a418ac2779ae0b3b3ba38a4
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e87ab8212c9c1b5c9ac2af513be72fc40777cbdb25e7df360e56de5cd75aab0
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 37.5,
5
- "global_step": 150,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -96,11 +96,17 @@
96
  "learning_rate": 0.0002,
97
  "loss": 0.0091,
98
  "step": 150
 
 
 
 
 
 
99
  }
100
  ],
101
  "max_steps": 200,
102
  "num_train_epochs": 50,
103
- "total_flos": 4.904852547895296e+16,
104
  "trial_name": null,
105
  "trial_params": null
106
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 40.0,
5
+ "global_step": 160,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
96
  "learning_rate": 0.0002,
97
  "loss": 0.0091,
98
  "step": 150
99
+ },
100
+ {
101
+ "epoch": 40.0,
102
+ "learning_rate": 0.0002,
103
+ "loss": 0.009,
104
+ "step": 160
105
  }
106
  ],
107
  "max_steps": 200,
108
  "num_train_epochs": 50,
109
+ "total_flos": 5.23073568374784e+16,
110
  "trial_name": null,
111
  "trial_params": null
112
  }