Hugging Face's logo

jasmeeetsingh
/
TQL_2

TensorBoard
Safetensors
Model card Files Metrics Community
jasmeeetsingh commited on
Commit
c0602c0
•
1 Parent(s): 7a9a3f3

Training in progress, step 10000, checkpoint

Browse files
Files changed (15) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/global_step10000/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  3. last-checkpoint/global_step10000/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  4. last-checkpoint/global_step10000/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  5. last-checkpoint/global_step10000/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  6. last-checkpoint/global_step10000/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  7. last-checkpoint/global_step10000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  8. last-checkpoint/global_step10000/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  9. last-checkpoint/global_step10000/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 sha256:5d4b8a611c78492ec65d6d7a2da55329935a39e9b8a3cd0c5bf99798d09299a0
3
  size 2384440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1369b02d89701e28f033efb1fdfba6cd30f8ada70562c93809d9883be5b9de7
3
  size 2384440
last-checkpoint/global_step10000/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 sha256:96799b57b801d9d0fc6048fb0a2d546098a04632db4bdbd2c8b24f5836bf8473
3
+ size 3621285613
last-checkpoint/global_step10000/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:ddc24b739f9a82f8fe36ad9470f7580dd00d856be26299ab8fb0461b795fb797
3
+ size 3542398
last-checkpoint/global_step10000/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 sha256:17e8c598b180f0b6819f408896d3eb1cecf7fdd521e87891a849d4529fc43bcc
3
+ size 3621285613
last-checkpoint/global_step10000/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:b290f64f5a5de4dc41d1f365cedb083e9d3a04895fc0e6bde3baa7c178d6b0fa
3
+ size 3542398
last-checkpoint/global_step10000/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:d807bcc0bd8f55188ba72ebd0592f034172f8dd7e1b4f1cd80fbbb2c202968aa
3
+ size 3621285613
last-checkpoint/global_step10000/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 sha256:9ad36af3560502b3e6af742e96681d0f14b40bec0f873f94464593c19665bc5a
3
+ size 3542398
last-checkpoint/global_step10000/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:e73f1bdea34f7eaa89912600aff0ede5e5f4b6462a0f753b5fc58e0445ad47f8
3
+ size 3621285613
last-checkpoint/global_step10000/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:ac003671c4f72968f2bbc985d1f92d07aada12b2149357ffeff295fc603da697
3
+ size 3542398
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step9000
 
1
+ global_step10000
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a805bd616ccdac6dba6f69a3058ed1f5c140f4b21a6bc8c5505bf332612aea4
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfa02571e999b30d0d68db203d90860835ed576add579d94609958c91e7b09a3
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 sha256:08649115a0a04e160f11a3d25af112e6a4600731e5279f6f1b0bc8a6298808e7
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c248e07247a95e6c83e8ae323322b82a1e853159d5005510e323c697c46c54
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 sha256:154fd6ff64461873de0cafd2ae78c7095b55185a2077adf01302d525ea956546
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84dc7dd2db4843621003e2ea8697005b3f04a7bc93e21bbb989f813c9486dc7c
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 sha256:27452b3662516d6f81953eff38599ed706cdf82c4e49aaf4a2c161cbfbf13bf0
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:585e72b3001d4cb10eaaa2d832401b7dac69a6f6d999ec8b6d8ef0d97db02ad4
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": 7.0367474589523065,
5
  "eval_steps": 500,
6
- "global_step": 9000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -61,13 +61,19 @@
61
  "learning_rate": 0.0001,
62
  "loss": 0.3891,
63
  "step": 9000
 
 
 
 
 
 
64
  }
65
  ],
66
  "logging_steps": 1000,
67
  "max_steps": 12790,
68
  "num_train_epochs": 10,
69
  "save_steps": 1000,
70
- "total_flos": 65748888190976.0,
71
  "trial_name": null,
72
  "trial_params": null
73
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 7.818608287724785,
5
  "eval_steps": 500,
6
+ "global_step": 10000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
61
  "learning_rate": 0.0001,
62
  "loss": 0.3891,
63
  "step": 9000
64
+ },
65
+ {
66
+ "epoch": 7.82,
67
+ "learning_rate": 0.0001,
68
+ "loss": 0.3771,
69
+ "step": 10000
70
  }
71
  ],
72
  "logging_steps": 1000,
73
  "max_steps": 12790,
74
  "num_train_epochs": 10,
75
  "save_steps": 1000,
76
+ "total_flos": 73042358173696.0,
77
  "trial_name": null,
78
  "trial_params": null
79
  }