Hugging Face's logo

jasmeeetsingh
/
TQL_2

TensorBoard
Safetensors
Model card Files Metrics Community
jasmeeetsingh commited on
Commit
e1e9a9f
·
1 Parent(s): 174f267

Training in progress, step 3000, checkpoint

Browse files
Files changed (15) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/global_step3000/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  3. last-checkpoint/global_step3000/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  4. last-checkpoint/global_step3000/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  5. last-checkpoint/global_step3000/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  6. last-checkpoint/global_step3000/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  7. last-checkpoint/global_step3000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  8. last-checkpoint/global_step3000/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  9. last-checkpoint/global_step3000/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:fed3d0a014b7ac5bbf1f83a3a549bc3b56211d657c975c53a4f07f6dde47d01b
3
  size 2384440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988222c18e3f64048638d3c02bc08fd31d975a6406a8caceb210af1620d62743
3
  size 2384440
last-checkpoint/global_step3000/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 sha256:8aee52a41a94ce0ebfcae51ccde81684d12e6847d2b2cc8052119eee2e6d7b40
3
+ size 3621285613
last-checkpoint/global_step3000/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:d3a50df0f62784d2f40d94b8429ded2394dfd89383c5c5aeb26b343eea510f26
3
+ size 3542398
last-checkpoint/global_step3000/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:fbbe8d9858de362e3bb6b0938d8e8ee2dd7eac9e81ec99beeff9c300b6b321d2
3
+ size 3621285613
last-checkpoint/global_step3000/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 sha256:74fa3ff81ff4880564efa57ea1b09145ec778780dbd4153e8fd68708c7b85621
3
+ size 3542398
last-checkpoint/global_step3000/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 sha256:2667df30bb5b7d01d4566c8871049ab5b65eee4328c20deae1ff4ce4a6c2b75a
3
+ size 3621285613
last-checkpoint/global_step3000/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:a83ddeb1d865f61f3b81fe3e38ea1923f06c1bb0b952eb8bed52506903d5afad
3
+ size 3542398
last-checkpoint/global_step3000/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 sha256:56d79512a5304b9a076c850afe983b8b89566ec56236cf0384f17f0e2ce3dae4
3
+ size 3621285613
last-checkpoint/global_step3000/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 sha256:922283194bfa79a6e6430be2d0ceb10dafbfe438a547b9f946dab8eb9e8f3d04
3
+ size 3542398
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step2000
 
1
+ global_step3000
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6978e908c92772fe19c7d622c0523251d41ab05aaef529e7acd2caf4d0eafcb5
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1393a1bd6340e761de7801e9c6f7e59e9706236926efa740dd59227d925a310
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 sha256:1e3cd3cde36f4529c33ca348673132abd387870ddc25d7664ce7bed468955d89
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16bc554ee121374c951d62b0801c1c0d7d1548c19e234b64560be1bb9eb187e9
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:f1d69d053ab98fad68ae2c8253970f3b7496f23830112d8923e49b3ccba17590
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288fca69a948dbe63f462f084f6093a2adcb386d14c1cdd31b5223788308e476
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:ec44e66877bdf688eefe2444b516fec47140ba260f54ef402b4b8193b6a7f35b
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85ce05b205ee73adeedec373f739143d8e0b9c49a5a9a8053966c410d6e493a
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": 1.5637216575449568,
5
  "eval_steps": 500,
6
- "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -19,13 +19,19 @@
19
  "learning_rate": 0.0001,
20
  "loss": 0.5373,
21
  "step": 2000
 
 
 
 
 
 
22
  }
23
  ],
24
  "logging_steps": 1000,
25
  "max_steps": 12790,
26
  "num_train_epochs": 10,
27
  "save_steps": 1000,
28
- "total_flos": 14607257174016.0,
29
  "trial_name": null,
30
  "trial_params": null
31
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.3455824863174355,
5
  "eval_steps": 500,
6
+ "global_step": 3000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
19
  "learning_rate": 0.0001,
20
  "loss": 0.5373,
21
  "step": 2000
22
+ },
23
+ {
24
+ "epoch": 2.35,
25
+ "learning_rate": 0.0001,
26
+ "loss": 0.4889,
27
+ "step": 3000
28
  }
29
  ],
30
  "logging_steps": 1000,
31
  "max_steps": 12790,
32
  "num_train_epochs": 10,
33
  "save_steps": 1000,
34
+ "total_flos": 21870936064000.0,
35
  "trial_name": null,
36
  "trial_params": null
37
  }