Hugging Face's logo

thinhlpg
/
bigscience_mt0-small_LORA_SEQ_2_SEQ_LM

PyTorch
TensorBoard
Model card Files Metrics Community
thinhlpg commited on
Commit
1686ef7
•
1 Parent(s): 27a854b

Training in progress, step 16

Browse files
Files changed (13) hide show
  1. .gitignore +1 -0
  2. last-checkpoint/global_step16/mp_rank_00_model_states.pt +3 -0
  3. last-checkpoint/latest +1 -0
  4. last-checkpoint/pytorch_model.bin +3 -0
  5. last-checkpoint/rng_state.pth +3 -0
  6. last-checkpoint/trainer_state.json +72 -0
  7. last-checkpoint/training_args.bin +3 -0
  8. pytorch_model.bin +3 -0
  9. runs/May07_10-21-27_4b70004df776/1683455005.2091758/events.out.tfevents.1683455005.4b70004df776.3696.1 +3 -0
  10. runs/May07_10-21-27_4b70004df776/events.out.tfevents.1683455005.4b70004df776.3696.0 +3 -0
  11. runs/May07_10-28-14_4b70004df776/1683455317.7778356/events.out.tfevents.1683455317.4b70004df776.5727.1 +3 -0
  12. runs/May07_10-28-14_4b70004df776/events.out.tfevents.1683455317.4b70004df776.5727.0 +3 -0
  13. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
last-checkpoint/global_step16/mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8248d55428725c8bb343f19acd50595a7f3f12861f568fb6e6817bedd8c43e1
3
+ size 610143229
last-checkpoint/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step16
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f5c5d9336a98e819ce08f74b1e04456d99a025bc8fa11cb7c891364f03c2f3
3
+ size 601880905
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6bb867ea9a5e3cb0801d1f1f898b34196647e594bdb5c684789cca6b3f060e
3
+ size 14575
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 10.5859375,
3
+ "best_model_checkpoint": "./output/checkpoint-8",
4
+ "epoch": 0.3395225464190981,
5
+ "global_step": 16,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 0,
13
+ "loss": 0.0,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 0,
19
+ "loss": 0.0,
20
+ "step": 4
21
+ },
22
+ {
23
+ "epoch": 0.17,
24
+ "learning_rate": 0,
25
+ "loss": 0.0,
26
+ "step": 8
27
+ },
28
+ {
29
+ "epoch": 0.17,
30
+ "eval_gen_len": 164.125,
31
+ "eval_loss": 10.5859375,
32
+ "eval_rouge1": 24.167,
33
+ "eval_rouge2": 7.6936,
34
+ "eval_rougeL": 17.9025,
35
+ "eval_rougeLsum": 18.0915,
36
+ "eval_runtime": 67.149,
37
+ "eval_samples_per_second": 0.119,
38
+ "eval_steps_per_second": 0.03,
39
+ "step": 8
40
+ },
41
+ {
42
+ "epoch": 0.25,
43
+ "learning_rate": 0,
44
+ "loss": 0.0,
45
+ "step": 12
46
+ },
47
+ {
48
+ "epoch": 0.34,
49
+ "learning_rate": 0,
50
+ "loss": 0.0,
51
+ "step": 16
52
+ },
53
+ {
54
+ "epoch": 0.34,
55
+ "eval_gen_len": 164.125,
56
+ "eval_loss": 10.5859375,
57
+ "eval_rouge1": 24.5587,
58
+ "eval_rouge2": 7.7531,
59
+ "eval_rougeL": 18.153,
60
+ "eval_rougeLsum": 18.3692,
61
+ "eval_runtime": 67.4414,
62
+ "eval_samples_per_second": 0.119,
63
+ "eval_steps_per_second": 0.03,
64
+ "step": 16
65
+ }
66
+ ],
67
+ "max_steps": 188,
68
+ "num_train_epochs": 4,
69
+ "total_flos": 203851630116864.0,
70
+ "trial_name": null,
71
+ "trial_params": null
72
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273daabbee6a1697c84fbe312719df2d9bd01849397a7cb95859c3baac61b930
3
+ size 4731
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f5c5d9336a98e819ce08f74b1e04456d99a025bc8fa11cb7c891364f03c2f3
3
+ size 601880905
runs/May07_10-21-27_4b70004df776/1683455005.2091758/events.out.tfevents.1683455005.4b70004df776.3696.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466447c323c5730719b1d83fbda6e22058f184e5b1ee48b71cd29b1bebb0bf19
3
+ size 6163
runs/May07_10-21-27_4b70004df776/events.out.tfevents.1683455005.4b70004df776.3696.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88e14f3241a91d05f4528347cfa96f5e0506d47ded689ba8996513c0e810b1f6
3
+ size 5292
runs/May07_10-28-14_4b70004df776/1683455317.7778356/events.out.tfevents.1683455317.4b70004df776.5727.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232f773ea29bde9ce7b2bb8432f911d1a3cdb2ac362c54f421018e95e240ed1c
3
+ size 6163
runs/May07_10-28-14_4b70004df776/events.out.tfevents.1683455317.4b70004df776.5727.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb3690c4a47304851554a641e97b1815c900665d8c301431e6b2bf44d4b7efb
3
+ size 5140
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273daabbee6a1697c84fbe312719df2d9bd01849397a7cb95859c3baac61b930
3
+ size 4731