Hugging Face's logo

jasmeeetsingh
/
TQL_2

TensorBoard
Safetensors
Model card Files Metrics Community
jasmeeetsingh commited on
Commit
b4ad992
·
1 Parent(s): a89c867

Training in progress, step 7000, checkpoint

Browse files
Files changed (15) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/global_step7000/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  3. last-checkpoint/global_step7000/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  4. last-checkpoint/global_step7000/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  5. last-checkpoint/global_step7000/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  6. last-checkpoint/global_step7000/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  7. last-checkpoint/global_step7000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  8. last-checkpoint/global_step7000/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  9. last-checkpoint/global_step7000/zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  10. last-checkpoint/latest +1 -1
  11. last-checkpoint/rng_state_0.pth +1 -1
  12. last-checkpoint/rng_state_1.pth +1 -1
  13. last-checkpoint/rng_state_2.pth +1 -1
  14. last-checkpoint/rng_state_3.pth +1 -1
  15. last-checkpoint/trainer_state.json +9 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85b422ee3958e189a80805f9f965a72c206d8049b9f09de490eb890e2ce1a613
3
  size 2384440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89fb5da75453d2f404dc97aa0a52474356d152c41188fdc1aedeaead3dd31f61
3
  size 2384440
last-checkpoint/global_step7000/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca045544799cf4d8e7b7494554eb06c189b3be278a4299a7c9c8e5273272863b
3
+ size 3621285613
last-checkpoint/global_step7000/zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3983142cbc1d29fb32c103443c360924ee7fdcb86a6b9676fdf6ecace3ff7dec
3
+ size 3542398
last-checkpoint/global_step7000/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4161680910ea6000ad80872d8c1c29c2c893e12813d8d28f8df1315e7317ecc2
3
+ size 3621285613
last-checkpoint/global_step7000/zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f160eb66058b0d905bb294930530fec42a1011bd4efce2ec422f8ff36ae2c26d
3
+ size 3542398
last-checkpoint/global_step7000/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c0b26f55a2f563711846213c7ccb5c364b58326aa5242c1f1aa111322b850b
3
+ size 3621285613
last-checkpoint/global_step7000/zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69b65fce7e82e45be605fbb7d1eeb0fc42b7884e8e08e2650ecfd73336d1c8f7
3
+ size 3542398
last-checkpoint/global_step7000/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72eebcd0b610b7d656f2762cc26445d85f06e44ec48cc04f6719d63dec45b07
3
+ size 3621285613
last-checkpoint/global_step7000/zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71bdd3e7efba3d0495461db3f2a740b6f5336cfc8bb1ad1904e48104f115d8f5
3
+ size 3542398
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step6000
 
1
+ global_step7000
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d32349f4b48b9fb4729a79147fd7b83d66f0d4c2474b9f1e25ff4d1f056ed81b
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3eb6c6b4eec6662e216ddc2552fee417eee52f74b4e58d01306d5995fb0c4e7
3
  size 17655
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3b1142fca547114f3d0a445f9800567d556596ee89ff6a986d92b5245f0dd93
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e526ad7890c854a0d63ee624e21da32e269b651078cc13122a414cca2509be0
3
  size 17655
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93cde37cb441ecff6612fae913672d7d9b71d9755e386684e5be26f202a20f4d
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dc332c17e0ce22934471a79280a2e4ae0caaeee3d2756e7cb2a3aa3c68ba85f
3
  size 17655
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5a1d857da05e0f9f6ddfb61aacc0dff2f758b31c8fb47768b2dafe568cfc92d
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55d1734a89ba6f5837beca9d0e771c8a8293f6f31be93d6499cb1a979bbbdc64
3
  size 17655
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 4.691164972634871,
5
  "eval_steps": 500,
6
- "global_step": 6000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -43,13 +43,19 @@
43
  "learning_rate": 0.0001,
44
  "loss": 0.4208,
45
  "step": 6000
 
 
 
 
 
 
46
  }
47
  ],
48
  "logging_steps": 1000,
49
  "max_steps": 12790,
50
  "num_train_epochs": 10,
51
  "save_steps": 1000,
52
- "total_flos": 43787607343104.0,
53
  "trial_name": null,
54
  "trial_params": null
55
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 5.473025801407349,
5
  "eval_steps": 500,
6
+ "global_step": 7000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
43
  "learning_rate": 0.0001,
44
  "loss": 0.4208,
45
  "step": 6000
46
+ },
47
+ {
48
+ "epoch": 5.47,
49
+ "learning_rate": 0.0001,
50
+ "loss": 0.407,
51
+ "step": 7000
52
  }
53
  ],
54
  "logging_steps": 1000,
55
  "max_steps": 12790,
56
  "num_train_epochs": 10,
57
  "save_steps": 1000,
58
+ "total_flos": 51101412360192.0,
59
  "trial_name": null,
60
  "trial_params": null
61
  }