Hugging Face's logo

naman1011
/
TQL

Text2Text Generation
Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
1
naman1011 commited on
Commit
8e6ae5c
•
1 Parent(s): f9c5220

Training in progress, step 6000, checkpoint

Browse files
Files changed (15) hide show
  1. last-checkpoint/adapter_model.bin +1 -1
  2. last-checkpoint/global_step6000/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  3. last-checkpoint/global_step6000/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  4. last-checkpoint/global_step6000/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  5. last-checkpoint/global_step6000/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  6. last-checkpoint/global_step6000/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  7. last-checkpoint/global_step6000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  8. last-checkpoint/global_step6000/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  9. last-checkpoint/global_step6000/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.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9046729082553bffbbf8d0e0cac1eada34c1cab928ee43f8c80538e282701a48
3
  size 2141578
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:781f8255312ac29d7b0905b671970c5c88bc0aad0ea8171c39b62c80d027727d
3
  size 2141578
last-checkpoint/global_step6000/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 sha256:53bdd486222170242f9d05d5c6e4d3aa94c55b795341d31616b654f03f52eb19
3
+ size 3369573916
last-checkpoint/global_step6000/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:d3831fad40f9a1d513dbe5d20c3fd22e01a73b0b69170f466201f98673263677
3
+ size 3149677
last-checkpoint/global_step6000/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:df4b2f26f5e78bfa7b4c3f33812f692b08dce62e5efab9f657163ce9aafcfe4f
3
+ size 3369573916
last-checkpoint/global_step6000/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 sha256:09312966db5306bc614c068d9a5afe783ec346773674ba78d2d32508ac3726cf
3
+ size 3149677
last-checkpoint/global_step6000/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:a78a68c1711c627fd920e0c1239fe1eedc354e4ff4499212656ee3114a3869ce
3
+ size 3369573916
last-checkpoint/global_step6000/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 sha256:0f6489bb9c5fe91a1c1bfd8f050f6e7ad6e7f3162a7593faa0c2d664436a3901
3
+ size 3149677
last-checkpoint/global_step6000/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 sha256:1e71784570cd64378f7a4d13e28f0209428b2317f1005648e2bd11254cb9582d
3
+ size 3369573916
last-checkpoint/global_step6000/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:f8a1a3c694fe6f818c3b7564f277424eb827af78879517304fc7d80ac3d7ba73
3
+ size 3149677
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step3000
 
1
+ global_step6000
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:075d19a98a161dd41b22953b88968106e072f65a707d53d0eba42094eb565ca0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9780f1ee023de7b650b7965f645488af756c7115f4c6d44e4833faa258c0384f
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08196a2ce29aaa623a1d33352a238026f278deee20c1aeafc729e6950f4d6f34
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8131458e77032327880766ba705798810b9272c6f2274b019acd8f10c0041a11
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:864a0722927155f4e5989416d78f8a8d144c5a196f6850f853c9c218e30d7178
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49089b274cf8dbc45224e6ec7d4c1c9a872fb5bd0150a4be015bf1420744494a
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d5921de3329d7f101252046b392f3f099daa7f4bbee0195234f7c5c1f2469a2
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5cfbb4b45fc94fcc45a8405667aee425b617b66b35ec5a353811e960e3b6c2d
3
  size 15024
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.1727912431587177,
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,
@@ -13,13 +13,19 @@
13
  "learning_rate": 0.0001,
14
  "loss": 0.204,
15
  "step": 3000
 
 
 
 
 
 
16
  }
17
  ],
18
  "logging_steps": 3000,
19
  "max_steps": 12790,
20
  "num_train_epochs": 5,
21
  "save_steps": 3000,
22
- "total_flos": 39574520725504.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.3455824863174355,
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,
 
13
  "learning_rate": 0.0001,
14
  "loss": 0.204,
15
  "step": 3000
16
+ },
17
+ {
18
+ "epoch": 2.35,
19
+ "learning_rate": 0.0001,
20
+ "loss": 0.1084,
21
+ "step": 6000
22
  }
23
  ],
24
  "logging_steps": 3000,
25
  "max_steps": 12790,
26
  "num_train_epochs": 5,
27
  "save_steps": 3000,
28
+ "total_flos": 78856039956480.0,
29
  "trial_name": null,
30
  "trial_params": null
31
  }