Hugging Face's logo

jasmeeetsingh
/
TQL_2

TensorBoard
Safetensors
Model card Files Metrics Community
jasmeeetsingh commited on
Commit
379a506
•
1 Parent(s): a1eaddb

Training in progress, step 8000, checkpoint

Browse files
Files changed (15) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/global_step8000/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  3. last-checkpoint/global_step8000/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  4. last-checkpoint/global_step8000/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  5. last-checkpoint/global_step8000/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  6. last-checkpoint/global_step8000/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  7. last-checkpoint/global_step8000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  8. last-checkpoint/global_step8000/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  9. last-checkpoint/global_step8000/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 sha256:89fb5da75453d2f404dc97aa0a52474356d152c41188fdc1aedeaead3dd31f61
3
  size 2384440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:127c29daa652d15a402772fab46fa36865792858c972c85b48cd04788a60ae24
3
  size 2384440
last-checkpoint/global_step8000/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 sha256:5aca3f2fadc6c72ea246476fe3322e3b69a060f6d1d0d40b3cc8cab5877fbeab
3
+ size 3621285613
last-checkpoint/global_step8000/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 sha256:1fcb20e26c7d3d7d55b71044bd7de54008982424ec61d81dcd3e6d114373a3d2
3
+ size 3542398
last-checkpoint/global_step8000/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:cc2a03cfa81aa402a4e011a5c6004e9b26a5706caf58077cd2b91ad93d42300d
3
+ size 3621285613
last-checkpoint/global_step8000/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:ae5e09c7ed2ef8882d1e0d1a76b0d48e1c0f8745e663f10ab6dbc6e12f764e4c
3
+ size 3542398
last-checkpoint/global_step8000/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:f55ce807c44b38f423e19decd36868eb415535c4a34d793aa048a44581e4892f
3
+ size 3621285613
last-checkpoint/global_step8000/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 sha256:44a511849dcd67bf0eb25acedf7587a63a0f9a1169966df4376729523f7c4603
3
+ size 3542398
last-checkpoint/global_step8000/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 sha256:03cc8c8f1273fe5aff676bc21eac9946f6babd6b4ba9ac19d886305f04976347
3
+ size 3621285613
last-checkpoint/global_step8000/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:c02ac5f1c2b564cb70640aad78ca53d1675bd91946f13258cb1c0cd9ae5c3c54
3
+ size 3542398
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step7000
 
1
+ global_step8000
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3eb6c6b4eec6662e216ddc2552fee417eee52f74b4e58d01306d5995fb0c4e7
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aab78d5911bfedfff252a9bc0a535b5255c416ae24fe8b79f967d5a4c394275
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 sha256:2e526ad7890c854a0d63ee624e21da32e269b651078cc13122a414cca2509be0
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c290bcbdcc2a3985b993c0b83951f457314268d568f6c4e660e38a438cf0ea3b
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 sha256:6dc332c17e0ce22934471a79280a2e4ae0caaeee3d2756e7cb2a3aa3c68ba85f
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642f17ea3b6349a4328b55dca99ae6dee30ed10f1fe383fd83ae10f08bb86aaf
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 sha256:55d1734a89ba6f5837beca9d0e771c8a8293f6f31be93d6499cb1a979bbbdc64
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:794d2f4f89806b21ae90fa0cfe26ad283012964c79982afaba1ae7d6bb047792
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": 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,
@@ -49,13 +49,19 @@
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
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 6.254886630179828,
5
  "eval_steps": 500,
6
+ "global_step": 8000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
49
  "learning_rate": 0.0001,
50
  "loss": 0.407,
51
  "step": 7000
52
+ },
53
+ {
54
+ "epoch": 6.25,
55
+ "learning_rate": 0.0001,
56
+ "loss": 0.3962,
57
+ "step": 8000
58
  }
59
  ],
60
  "logging_steps": 1000,
61
  "max_steps": 12790,
62
  "num_train_epochs": 10,
63
  "save_steps": 1000,
64
+ "total_flos": 58460658466816.0,
65
  "trial_name": null,
66
  "trial_params": null
67
  }