Hugging Face's logo

Logic12
/
DeepSeek-R1-Distill-Llama-8B-RedMind

Text Generation
PEFT
Safetensors
Transformers
lora
conversational
Model card Files
xet
 Community
Logic12 commited on
Commit
dfb9578
·
verified ·
1 Parent(s): 9fdfd47

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. all_results.json +3 -3
  4. checkpoint-12/adapter_config.json +2 -2
  5. checkpoint-12/adapter_model.safetensors +1 -1
  6. checkpoint-12/optimizer.pt +1 -1
  7. checkpoint-12/tokenizer.json +2 -2
  8. checkpoint-12/trainer_state.json +3 -3
  9. checkpoint-12/training_args.bin +1 -1
  10. checkpoint-15/adapter_config.json +2 -2
  11. checkpoint-15/adapter_model.safetensors +1 -1
  12. checkpoint-15/optimizer.pt +1 -1
  13. checkpoint-15/tokenizer.json +2 -2
  14. checkpoint-15/trainer_state.json +3 -3
  15. checkpoint-15/training_args.bin +1 -1
  16. checkpoint-3/adapter_config.json +2 -2
  17. checkpoint-3/adapter_model.safetensors +1 -1
  18. checkpoint-3/optimizer.pt +1 -1
  19. checkpoint-3/tokenizer.json +2 -2
  20. checkpoint-3/trainer_state.json +1 -1
  21. checkpoint-3/training_args.bin +1 -1
  22. checkpoint-6/adapter_config.json +2 -2
  23. checkpoint-6/adapter_model.safetensors +1 -1
  24. checkpoint-6/optimizer.pt +1 -1
  25. checkpoint-6/tokenizer.json +2 -2
  26. checkpoint-6/trainer_state.json +1 -1
  27. checkpoint-6/training_args.bin +1 -1
  28. checkpoint-9/adapter_config.json +2 -2
  29. checkpoint-9/adapter_model.safetensors +1 -1
  30. checkpoint-9/optimizer.pt +1 -1
  31. checkpoint-9/tokenizer.json +2 -2
  32. checkpoint-9/trainer_state.json +1 -1
  33. checkpoint-9/training_args.bin +1 -1
  34. tokenizer.json +2 -2
  35. train_results.json +3 -3
  36. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -25,8 +25,8 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "q_proj",
29
+ "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:133e4bb0a915a887187fb6ede6068b37d193b9f0993e49f702172ffbf5f4095e
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13572b11fe9a4a36204b8371056d3e9b0c94bec3a94d8be2cda525dd5ea925f3
3
  size 27280152
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.661476792172544e+16,
4
- "train_loss": 2.636483589808146,
5
- "train_runtime": 62.1929,
6
- "train_samples_per_second": 2.894,
7
  "train_steps_per_second": 0.241
8
  }
 
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.661476792172544e+16,
4
+ "train_loss": 2.6358705043792723,
5
+ "train_runtime": 62.1406,
6
+ "train_samples_per_second": 2.897,
7
  "train_steps_per_second": 0.241
8
  }
checkpoint-12/adapter_config.json CHANGED
@@ -25,8 +25,8 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "q_proj",
29
+ "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
checkpoint-12/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7039f6db1c37e56b143c3a68a735ff9d674299969216f94f1045a16cedec3be5
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57c1bdbca5d30a1155a9b627540da7ae4988351f9e15304bf06ab689c9b1009
3
  size 27280152
checkpoint-12/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5803637869d68814f0a07627c78e9c515fbbcaf1f578984aee695dfcaac2d9b7
3
  size 13996875
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:539aed3b3a30e126a096ce0e7ce46f3ec82f74a35ef583d4ee6c38ece9ee89df
3
  size 13996875
checkpoint-12/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1e3f1928b50bea1b1ee1ed82ccbbc735df6bd3d8af2ade5c3bbca3130ae8977
3
- size 17209629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
3
+ size 17209530
checkpoint-12/trainer_state.json CHANGED
@@ -11,16 +11,16 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
- "grad_norm": 0.6128925681114197,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 3.4444444444444446,
21
- "grad_norm": 0.6554281115531921,
22
  "learning_rate": 9.230769230769232e-06,
23
- "loss": 2.6182,
24
  "step": 10
25
  }
26
  ],
 
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
+ "grad_norm": 0.6222278475761414,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 3.4444444444444446,
21
+ "grad_norm": 0.6586010456085205,
22
  "learning_rate": 9.230769230769232e-06,
23
+ "loss": 2.6178,
24
  "step": 10
25
  }
26
  ],
checkpoint-12/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d919ca4e468a9675f9f2e970150a2f202cb064d641275ebf5c372e713f00c2b
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4d40e18a0bc3b2120432cb3b199fbdc2a0f36717715f5ab4e485faee11a5ba
3
  size 5777
checkpoint-15/adapter_config.json CHANGED
@@ -25,8 +25,8 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "q_proj",
29
+ "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
checkpoint-15/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:133e4bb0a915a887187fb6ede6068b37d193b9f0993e49f702172ffbf5f4095e
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13572b11fe9a4a36204b8371056d3e9b0c94bec3a94d8be2cda525dd5ea925f3
3
  size 27280152
checkpoint-15/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:278a5ec4122271c3dc5c6f44e683ce3b9c29a4d9dcf243f02bbdff3ee703dc8d
3
  size 13996875
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31380a95229da7fd08e7646fafec31e8415699e7df3f84cd0bcacabd58e3ab9c
3
  size 13996875
checkpoint-15/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1e3f1928b50bea1b1ee1ed82ccbbc735df6bd3d8af2ade5c3bbca3130ae8977
3
- size 17209629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
3
+ size 17209530
checkpoint-15/trainer_state.json CHANGED
@@ -11,16 +11,16 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
- "grad_norm": 0.6128925681114197,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 3.4444444444444446,
21
- "grad_norm": 0.6554281115531921,
22
  "learning_rate": 9.230769230769232e-06,
23
- "loss": 2.6182,
24
  "step": 10
25
  }
26
  ],
 
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
+ "grad_norm": 0.6222278475761414,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 3.4444444444444446,
21
+ "grad_norm": 0.6586010456085205,
22
  "learning_rate": 9.230769230769232e-06,
23
+ "loss": 2.6178,
24
  "step": 10
25
  }
26
  ],
checkpoint-15/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d919ca4e468a9675f9f2e970150a2f202cb064d641275ebf5c372e713f00c2b
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4d40e18a0bc3b2120432cb3b199fbdc2a0f36717715f5ab4e485faee11a5ba
3
  size 5777
checkpoint-3/adapter_config.json CHANGED
@@ -25,8 +25,8 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "q_proj",
29
+ "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
checkpoint-3/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d89ec6f0c555454bca3fc39939594105026d269fb29f825ac1b396edc0690780
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841779679d788866b1133493a14c3a3f46d60ca1657c3ec2168bf99175257a99
3
  size 27280152
checkpoint-3/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26de127b07e18be34799ee1a2ece850659d62b7945ecdf3c95c525236562ac5d
3
  size 13996875
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b04ddcc10bd7a1a62c5a2843fb947c5273beee8dbc67627b4724830352677d
3
  size 13996875
checkpoint-3/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1e3f1928b50bea1b1ee1ed82ccbbc735df6bd3d8af2ade5c3bbca3130ae8977
3
- size 17209629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
3
+ size 17209530
checkpoint-3/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
- "grad_norm": 0.6128925681114197,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
 
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
+ "grad_norm": 0.6222278475761414,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
checkpoint-3/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d919ca4e468a9675f9f2e970150a2f202cb064d641275ebf5c372e713f00c2b
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4d40e18a0bc3b2120432cb3b199fbdc2a0f36717715f5ab4e485faee11a5ba
3
  size 5777
checkpoint-6/adapter_config.json CHANGED
@@ -25,8 +25,8 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "q_proj",
29
+ "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
checkpoint-6/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c9258e385f36f160c918bd3a3bfdd9db44df1436490880855722a2e26dcbab6
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0778cf2ac8525610c154883e87f6f12f4435db9c9a00974ee8f303e233af452
3
  size 27280152
checkpoint-6/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f04a89996f547ecde46d7ff27460ad3c16711cca6c5fdba656757b68debbdb42
3
  size 13996875
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a20de1f5fd30b22dc42ed27c76c3ca159ad5031fc073a44c39121aa45d9c6ad
3
  size 13996875
checkpoint-6/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1e3f1928b50bea1b1ee1ed82ccbbc735df6bd3d8af2ade5c3bbca3130ae8977
3
- size 17209629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
3
+ size 17209530
checkpoint-6/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
- "grad_norm": 0.6128925681114197,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
 
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
+ "grad_norm": 0.6222278475761414,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
checkpoint-6/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d919ca4e468a9675f9f2e970150a2f202cb064d641275ebf5c372e713f00c2b
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4d40e18a0bc3b2120432cb3b199fbdc2a0f36717715f5ab4e485faee11a5ba
3
  size 5777
checkpoint-9/adapter_config.json CHANGED
@@ -25,8 +25,8 @@
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
- "v_proj",
29
- "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
 
25
  "rank_pattern": {},
26
  "revision": null,
27
  "target_modules": [
28
+ "q_proj",
29
+ "v_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "trainable_token_indices": null,
checkpoint-9/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9eaf8ba829a33ca90f32b45774fd117c338493471830dfc995cae277e1575d79
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3b4b0dcd18471efb1518e25f2ef2c5af98c140f817ec3e8a1250f91420ff15
3
  size 27280152
checkpoint-9/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e83639e4412e6f573022a57ddd4c93f69d55b067ce43026903bc68a6ce56ee7b
3
  size 13996875
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e39fcf32d16ef408956aca4d8951df7fd6d84f09ed36fbc2b55151ac5aae37
3
  size 13996875
checkpoint-9/tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1e3f1928b50bea1b1ee1ed82ccbbc735df6bd3d8af2ade5c3bbca3130ae8977
3
- size 17209629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
3
+ size 17209530
checkpoint-9/trainer_state.json CHANGED
@@ -11,7 +11,7 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
- "grad_norm": 0.6128925681114197,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
 
11
  "log_history": [
12
  {
13
  "epoch": 0.4444444444444444,
14
+ "grad_norm": 0.6222278475761414,
15
  "learning_rate": 0.0,
16
  "loss": 2.6858,
17
  "step": 1
checkpoint-9/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d919ca4e468a9675f9f2e970150a2f202cb064d641275ebf5c372e713f00c2b
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4d40e18a0bc3b2120432cb3b199fbdc2a0f36717715f5ab4e485faee11a5ba
3
  size 5777
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1e3f1928b50bea1b1ee1ed82ccbbc735df6bd3d8af2ade5c3bbca3130ae8977
3
- size 17209629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
3
+ size 17209530
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.661476792172544e+16,
4
- "train_loss": 2.636483589808146,
5
- "train_runtime": 62.1929,
6
- "train_samples_per_second": 2.894,
7
  "train_steps_per_second": 0.241
8
  }
 
1
  {
2
  "epoch": 5.0,
3
  "total_flos": 1.661476792172544e+16,
4
+ "train_loss": 2.6358705043792723,
5
+ "train_runtime": 62.1406,
6
+ "train_samples_per_second": 2.897,
7
  "train_steps_per_second": 0.241
8
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d919ca4e468a9675f9f2e970150a2f202cb064d641275ebf5c372e713f00c2b
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a4d40e18a0bc3b2120432cb3b199fbdc2a0f36717715f5ab4e485faee11a5ba
3
  size 5777