Hugging Face's logo

jasmeeetsingh
/
TQL_2

TensorBoard
Safetensors
Model card Files Metrics Community
jasmeeetsingh commited on
Commit
7f1ea6a
•
1 Parent(s): 830272d

Training in progress, step 12000, checkpoint

Browse files
Files changed (15) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/global_step12000/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  3. last-checkpoint/global_step12000/zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  4. last-checkpoint/global_step12000/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  5. last-checkpoint/global_step12000/zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  6. last-checkpoint/global_step12000/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  7. last-checkpoint/global_step12000/zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  8. last-checkpoint/global_step12000/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  9. last-checkpoint/global_step12000/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:c759ebf82040d6924a05c3ef4316882f71fdfc5e1b34d803d1cf5e7f577947dc
3
  size 2384440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6641859b13008d844e76683c1912b461b43885ce0adae7efeeaaa1f1a173d0
3
  size 2384440
last-checkpoint/global_step12000/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 sha256:3ad69ba88c0c69c3d5b6419d99f0b0197c6e53f2ff32fad6d07fcade1b0a09e9
3
+ size 3621285613
last-checkpoint/global_step12000/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 sha256:26f49044cd7c467c5fb5f20199e4507e9d4505cae890038eaab47d9964e15cb1
3
+ size 3542398
last-checkpoint/global_step12000/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 sha256:8431f44294a6d0142412ad274e93cd996bcab1bdfa770fc63978ab44a34f8616
3
+ size 3621285613
last-checkpoint/global_step12000/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 sha256:371b4ae4cce9f080e1aee386b6e14d324785c0a196e84a0c58fcbbf11a38a2de
3
+ size 3542398
last-checkpoint/global_step12000/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 sha256:5ad3f605a11dc5fed67afd2e076163327c616e4cd96f4a868a0cb331187cf204
3
+ size 3621285613
last-checkpoint/global_step12000/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:ad941d8f3991a518c11b47cc4ed24ffb0269697f5834b75ec4f5a0087f300c7f
3
+ size 3542398
last-checkpoint/global_step12000/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:b4fb259325d85845d6d53c2345eafd9a1b4392f9b82ec04482daadd31fafdef3
3
+ size 3621285613
last-checkpoint/global_step12000/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:b7b565c17fa0d62eec56bb075488498b7b4af141a9eee05c8b0093bf1806714e
3
+ size 3542398
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step11000
 
1
+ global_step12000
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52a13920852463d3760190660bdbe29994e27158b7378d417b535b5ef21324ea
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f977c31b0804eb9bc61b27092a3201269d7d9b7e42e032b5dc1aa9c83ca5f1c6
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 sha256:78d89e2d388155ee26c42c6125f61bfc2ba203bd49f50c360d30f1c842192bf7
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72f7314dad22f20dcc104c74fd3c5cf13016da87201625e50bf7540ebebfedd6
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:d1165af8401156c8f098205da71e41b90fedaad3a533634c223b68d0f661152b
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b319525de0d97be1f7cdf6f350bc54592e402c94e8d2b122c1154cf4f275cc91
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 sha256:4cd048a9881e1fce04ccdea656f2f647f3f1bba4b88a2f3ad6be8c37959e86e6
3
  size 17655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a8c9d92e38ebcb4333e50c426edf44936bbebd6810c37c3c5aa20a77b10bba8
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": 8.600469116497264,
5
  "eval_steps": 500,
6
- "global_step": 11000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,13 +73,19 @@
73
  "learning_rate": 0.0001,
74
  "loss": 0.371,
75
  "step": 11000
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1000,
79
  "max_steps": 12790,
80
  "num_train_epochs": 10,
81
  "save_steps": 1000,
82
- "total_flos": 80322346614784.0,
83
  "trial_name": null,
84
  "trial_params": null
85
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 9.382329945269742,
5
  "eval_steps": 500,
6
+ "global_step": 12000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "learning_rate": 0.0001,
74
  "loss": 0.371,
75
  "step": 11000
76
+ },
77
+ {
78
+ "epoch": 9.38,
79
+ "learning_rate": 0.0001,
80
+ "loss": 0.3644,
81
+ "step": 12000
82
  }
83
  ],
84
  "logging_steps": 1000,
85
  "max_steps": 12790,
86
  "num_train_epochs": 10,
87
  "save_steps": 1000,
88
+ "total_flos": 87654664241152.0,
89
  "trial_name": null,
90
  "trial_params": null
91
  }