Hugging Face's logo

ChenWu98
/
proof.iter0_training_temp1.0.cluster_split.idx0.1

Transformers
Safetensors
Generated from Trainer
trl
sft
Model card Files
xet
Community
ChenWu98 commited on
Commit
b439947
·
verified ·
1 Parent(s): b73e857

Upload folder using huggingface_hub

Browse files
Files changed (31) hide show
  1. README.md +1 -1
  2. checkpoint-12/model-00001-of-00003.safetensors +1 -1
  3. checkpoint-12/model-00002-of-00003.safetensors +1 -1
  4. checkpoint-12/model-00003-of-00003.safetensors +1 -1
  5. checkpoint-12/trainer_state.json +4 -4
  6. checkpoint-12/training_args.bin +1 -1
  7. checkpoint-16/model-00001-of-00003.safetensors +1 -1
  8. checkpoint-16/model-00002-of-00003.safetensors +1 -1
  9. checkpoint-16/model-00003-of-00003.safetensors +1 -1
  10. checkpoint-16/trainer_state.json +4 -4
  11. checkpoint-16/training_args.bin +1 -1
  12. checkpoint-20/model-00001-of-00003.safetensors +1 -1
  13. checkpoint-20/model-00002-of-00003.safetensors +1 -1
  14. checkpoint-20/model-00003-of-00003.safetensors +1 -1
  15. checkpoint-20/trainer_state.json +7 -7
  16. checkpoint-20/training_args.bin +1 -1
  17. checkpoint-24/model-00001-of-00003.safetensors +1 -1
  18. checkpoint-24/model-00002-of-00003.safetensors +1 -1
  19. checkpoint-24/model-00003-of-00003.safetensors +1 -1
  20. checkpoint-24/trainer_state.json +7 -7
  21. checkpoint-24/training_args.bin +1 -1
  22. checkpoint-4/model-00001-of-00003.safetensors +1 -1
  23. checkpoint-4/model-00002-of-00003.safetensors +1 -1
  24. checkpoint-4/model-00003-of-00003.safetensors +1 -1
  25. checkpoint-4/trainer_state.json +1 -1
  26. checkpoint-4/training_args.bin +1 -1
  27. checkpoint-8/model-00001-of-00003.safetensors +1 -1
  28. checkpoint-8/model-00002-of-00003.safetensors +1 -1
  29. checkpoint-8/model-00003-of-00003.safetensors +1 -1
  30. checkpoint-8/trainer_state.json +1 -1
  31. checkpoint-8/training_args.bin +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ print(output["generated_text"])
27
 
28
  ## Training procedure
29
 
30
- [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chenwu/huggingface/runs/v5zsgh73)
31
 
32
 
33
  This model was trained with SFT.
 
27
 
28
  ## Training procedure
29
 
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chenwu/huggingface/runs/78qqbyni)
31
 
32
 
33
  This model was trained with SFT.
checkpoint-12/model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0946b09c998f13883b5a740c2f702228c3fd3041e8dc1d64a027ed205206079
3
  size 4987202208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e7e16e3f94be5c66c07c8d95bb2a328726b9e444939504687e430bdc26765f
3
  size 4987202208
checkpoint-12/model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f37049c6a6014ca3bac01d3ae87fea59cebec8f35dc7bead1638f618877c442a
3
  size 4980945440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e9b55f8602ff6780c1fe176f1bcb084a68b3af5bbdffbb75635fefdf131da7
3
  size 4980945440
checkpoint-12/model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b187aff046c2b2f5bfa1236f53f1e7f99a70aa5367986aad1b9d9240dc54fd6
3
  size 3852615520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d2ead9d2342e8d73051d16f455e149ea9f0e328cd56b73e55bffd38d85cfd5
3
  size 3852615520
checkpoint-12/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
- "grad_norm": 15.946384854163668,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
@@ -20,10 +20,10 @@
20
  },
21
  {
22
  "epoch": 2.6530612244897958,
23
- "grad_norm": 0.4320139298965557,
24
  "learning_rate": 0.0001,
25
- "loss": 0.3109,
26
- "mean_token_accuracy": 0.9018963078657786,
27
  "num_tokens": 2495915.0,
28
  "step": 10
29
  }
 
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
+ "grad_norm": 15.946330863810116,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
 
20
  },
21
  {
22
  "epoch": 2.6530612244897958,
23
+ "grad_norm": 0.42994698419563937,
24
  "learning_rate": 0.0001,
25
+ "loss": 0.3108,
26
+ "mean_token_accuracy": 0.9019484138279631,
27
  "num_tokens": 2495915.0,
28
  "step": 10
29
  }
checkpoint-12/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8de56a258be58da5bdd98ce16f113ce488d852bbc7c3afb550ae64ccc77945
3
  size 8017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f41cb084a1787473827f98e9a8a3c9e4bcc235e71ad54358c0b732c2faa36f
3
  size 8017
checkpoint-16/model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4eb607b09520f2ef7f86948d6bce118f8e6da3b28c3eef576386d1639958e65
3
  size 4987202208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425dd39d8a4fe9a73322873d6115a4c4698241c83d7e09bc7a5cc607c3047251
3
  size 4987202208
checkpoint-16/model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbd3415969c4e6888f2deb3038c5f3b809a8042d6d85e453799ffeb288852808
3
  size 4980945440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b7641ed96e94ed22def923ab3a3aafcd70009051d029bf5f5aba4e1cbac5f4
3
  size 4980945440
checkpoint-16/model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcc75f7059bc3e6b91955aea496cd10ed11b7c5a5fd523be23ee3ee95446b2c1
3
  size 3852615520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:922807eae22661146a4b62d38e61b405875f5f796a76ef92b0bcd27fdd0f8a68
3
  size 3852615520
checkpoint-16/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
- "grad_norm": 15.946384854163668,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
@@ -20,10 +20,10 @@
20
  },
21
  {
22
  "epoch": 2.6530612244897958,
23
- "grad_norm": 0.4320139298965557,
24
  "learning_rate": 0.0001,
25
- "loss": 0.3109,
26
- "mean_token_accuracy": 0.9018963078657786,
27
  "num_tokens": 2495915.0,
28
  "step": 10
29
  }
 
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
+ "grad_norm": 15.946330863810116,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
 
20
  },
21
  {
22
  "epoch": 2.6530612244897958,
23
+ "grad_norm": 0.42994698419563937,
24
  "learning_rate": 0.0001,
25
+ "loss": 0.3108,
26
+ "mean_token_accuracy": 0.9019484138279631,
27
  "num_tokens": 2495915.0,
28
  "step": 10
29
  }
checkpoint-16/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8de56a258be58da5bdd98ce16f113ce488d852bbc7c3afb550ae64ccc77945
3
  size 8017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f41cb084a1787473827f98e9a8a3c9e4bcc235e71ad54358c0b732c2faa36f
3
  size 8017
checkpoint-20/model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f29e9031f1bf5de7bb08ecfc1e875af62379aef7a046ad6764f22d293c72e07
3
  size 4987202208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e87647c139332a98369a7e5e2c0ad3377d5c8d965321a79b175d68a311e38d6
3
  size 4987202208
checkpoint-20/model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c0ebe9b2a0517429ae3f427fbd07bf387d29cc9ade839ffe7222a44d59cb0d99
3
  size 4980945440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0f7b510e683b5d3bfcf78e1ac8750e1102fb57a3f246729d8e664042ea667d
3
  size 4980945440
checkpoint-20/model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b61dc8e4e57f87d2c1cf7966a47119f0f87212f5467b67d373d375af298d4e6
3
  size 3852615520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb25114b529a557aaf9f1348f3d70065a2de39f4803a4e5ed7a757674d7e3cf
3
  size 3852615520
checkpoint-20/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
- "grad_norm": 15.946384854163668,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
@@ -20,19 +20,19 @@
20
  },
21
  {
22
  "epoch": 2.6530612244897958,
23
- "grad_norm": 0.4320139298965557,
24
  "learning_rate": 0.0001,
25
- "loss": 0.3109,
26
- "mean_token_accuracy": 0.9018963078657786,
27
  "num_tokens": 2495915.0,
28
  "step": 10
29
  },
30
  {
31
  "epoch": 5.0,
32
- "grad_norm": 0.7963301174196257,
33
  "learning_rate": 0.0001,
34
- "loss": 0.1421,
35
- "mean_token_accuracy": 0.9460180824217589,
36
  "num_tokens": 4708046.0,
37
  "step": 20
38
  }
 
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
+ "grad_norm": 15.946330863810116,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
 
20
  },
21
  {
22
  "epoch": 2.6530612244897958,
23
+ "grad_norm": 0.42994698419563937,
24
  "learning_rate": 0.0001,
25
+ "loss": 0.3108,
26
+ "mean_token_accuracy": 0.9019484138279631,
27
  "num_tokens": 2495915.0,
28
  "step": 10
29
  },
30
  {
31
  "epoch": 5.0,
32
+ "grad_norm": 0.7870531010460464,
33
  "learning_rate": 0.0001,
34
+ "loss": 0.142,
35
+ "mean_token_accuracy": 0.9460842391718989,
36
  "num_tokens": 4708046.0,
37
  "step": 20
38
  }
checkpoint-20/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8de56a258be58da5bdd98ce16f113ce488d852bbc7c3afb550ae64ccc77945
3
  size 8017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f41cb084a1787473827f98e9a8a3c9e4bcc235e71ad54358c0b732c2faa36f
3
  size 8017
checkpoint-24/model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b0780f4cfd44bbb1a09a44102da53a11f5743383cb0b0d5e58ed930bc80ce74
3
  size 4987202208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9832ee851609fec9a7137c1b6ac00bed0a1467c0e422e1cb72598e96c7245b72
3
  size 4987202208
checkpoint-24/model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a513f97a2cd099a717975c29fb713808bd5806512c0f5ce2ff59c6b8b11dce45
3
  size 4980945440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7abba12b333f3bd44f43890c9f2474af8f55e913b21e914929d77937cd513b30
3
  size 4980945440
checkpoint-24/model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f499993b97bdff3861b8d6227c42a220b153b3b71bd85bb91b07b7771617bb58
3
  size 3852615520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:712c7e50e7f615c0127f911103b424860642e47232ae3df392153b04ec73e100
3
  size 3852615520
checkpoint-24/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
- "grad_norm": 15.946384854163668,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
@@ -20,19 +20,19 @@
20
  },
21
  {
22
  "epoch": 2.6530612244897958,
23
- "grad_norm": 0.4320139298965557,
24
  "learning_rate": 0.0001,
25
- "loss": 0.3109,
26
- "mean_token_accuracy": 0.9018963078657786,
27
  "num_tokens": 2495915.0,
28
  "step": 10
29
  },
30
  {
31
  "epoch": 5.0,
32
- "grad_norm": 0.7963301174196257,
33
  "learning_rate": 0.0001,
34
- "loss": 0.1421,
35
- "mean_token_accuracy": 0.9460180824217589,
36
  "num_tokens": 4708046.0,
37
  "step": 20
38
  }
 
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
+ "grad_norm": 15.946330863810116,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
 
20
  },
21
  {
22
  "epoch": 2.6530612244897958,
23
+ "grad_norm": 0.42994698419563937,
24
  "learning_rate": 0.0001,
25
+ "loss": 0.3108,
26
+ "mean_token_accuracy": 0.9019484138279631,
27
  "num_tokens": 2495915.0,
28
  "step": 10
29
  },
30
  {
31
  "epoch": 5.0,
32
+ "grad_norm": 0.7870531010460464,
33
  "learning_rate": 0.0001,
34
+ "loss": 0.142,
35
+ "mean_token_accuracy": 0.9460842391718989,
36
  "num_tokens": 4708046.0,
37
  "step": 20
38
  }
checkpoint-24/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8de56a258be58da5bdd98ce16f113ce488d852bbc7c3afb550ae64ccc77945
3
  size 8017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f41cb084a1787473827f98e9a8a3c9e4bcc235e71ad54358c0b732c2faa36f
3
  size 8017
checkpoint-4/model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c50c7221bfc1831aa055eff546b17153e02e332eef2f97835f3435b0483cc31
3
  size 4987202208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33419a5df28c03757db3956e079ca93868945c856ac822f9d9f9dd993895f7f5
3
  size 4987202208
checkpoint-4/model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e61e61fb64e3792ee16ca4ad637dfa2c959eaee3125f5587de53e7a50c6f696
3
  size 4980945440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed8f9c46df31522f2c14f49f5cfaf34a089e3997b2e32be1c2aa99b406e2ef3
3
  size 4980945440
checkpoint-4/model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f340a2b07938f68c83327883cc79e46e4ebb9a432d60de8958a8f7af9d643cd7
3
  size 3852615520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948530506d504d6426f308efca66fbff78ba94eb9d3c5bb90057e8c99dbf1353
3
  size 3852615520
checkpoint-4/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
- "grad_norm": 15.946384854163668,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
 
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
+ "grad_norm": 15.946330863810116,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
checkpoint-4/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8de56a258be58da5bdd98ce16f113ce488d852bbc7c3afb550ae64ccc77945
3
  size 8017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f41cb084a1787473827f98e9a8a3c9e4bcc235e71ad54358c0b732c2faa36f
3
  size 8017
checkpoint-8/model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:acf495cba3d918171b8f0ce1e5e26fb523127a7f5fa4fa5aa783d13441dfa826
3
  size 4987202208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bec2c7c9ef3eb3e3054bc55a856dff7b1f903640679847a0fced5e717b1c080
3
  size 4987202208
checkpoint-8/model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ff9148035d37720f0da88ac3e3efc2991426b92786814759c0e2dda7129464e
3
  size 4980945440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b230c3e61eb30f85cc9ccdb527bdf73f40b7f96203f27cb1abc8a67b43dcec56
3
  size 4980945440
checkpoint-8/model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58b785f5b20ffee34e5276f3865e454c7e9d1ec4a345ac7a95d0e6664281a198
3
  size 3852615520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9a88f8c37cdb0b970a82fa82ca17919c72c004b6ab3f4287a81ef1b962bf55
3
  size 3852615520
checkpoint-8/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
- "grad_norm": 15.946384854163668,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
 
11
  "log_history": [
12
  {
13
  "epoch": 0.32653061224489793,
14
+ "grad_norm": 15.946330863810116,
15
  "learning_rate": 0.0001,
16
  "loss": 0.4052,
17
  "mean_token_accuracy": 0.9151133690029383,
checkpoint-8/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8de56a258be58da5bdd98ce16f113ce488d852bbc7c3afb550ae64ccc77945
3
  size 8017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f41cb084a1787473827f98e9a8a3c9e4bcc235e71ad54358c0b732c2faa36f
3
  size 8017