Hugging Face's logo

Weni
/
ZeroShot-3.3.18-Mistral-7b-runpod-test-Multilanguage-3.2.0

Safetensors
Portuguese
English
Spanish
trl
SFT
zeroshot
Model card Files Community
beamaia commited on
Commit
db6f799
·
verified ·
1 Parent(s): 9272e85

Upload folder using huggingface_hub

Browse files
Files changed (24) hide show
  1. checkpoint-10/adapter_config.json +2 -2
  2. checkpoint-10/adapter_model.safetensors +1 -1
  3. checkpoint-10/optimizer.pt +1 -1
  4. checkpoint-10/rng_state_0.pth +2 -2
  5. checkpoint-10/rng_state_1.pth +2 -2
  6. checkpoint-10/scheduler.pt +1 -1
  7. checkpoint-10/trainer_state.json +8 -8
  8. checkpoint-10/training_args.bin +1 -1
  9. checkpoint-20/adapter_config.json +2 -2
  10. checkpoint-20/adapter_model.safetensors +1 -1
  11. checkpoint-20/optimizer.pt +1 -1
  12. checkpoint-20/rng_state_0.pth +2 -2
  13. checkpoint-20/rng_state_1.pth +2 -2
  14. checkpoint-20/scheduler.pt +1 -1
  15. checkpoint-20/trainer_state.json +17 -17
  16. checkpoint-20/training_args.bin +1 -1
  17. checkpoint-30/adapter_config.json +2 -2
  18. checkpoint-30/adapter_model.safetensors +1 -1
  19. checkpoint-30/optimizer.pt +1 -1
  20. checkpoint-30/rng_state_0.pth +2 -2
  21. checkpoint-30/rng_state_1.pth +2 -2
  22. checkpoint-30/scheduler.pt +1 -1
  23. checkpoint-30/trainer_state.json +22 -22
  24. checkpoint-30/training_args.bin +1 -1
checkpoint-10/adapter_config.json CHANGED
@@ -20,9 +20,9 @@
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
 
23
  "v_proj",
24
- "o_proj",
25
- "k_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
23
+ "k_proj",
24
  "v_proj",
25
+ "o_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
checkpoint-10/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:295adcf7a85a06d5b387a0145156fbc30394cf527d4299df8679f99ee3f96b46
3
  size 436242776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a3e0cdae368d14a843151822c64d75b9e64eabba537d101b909316145d64f25
3
  size 436242776
checkpoint-10/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abda30c14b92d35ad5236abace4a51869a262c49d7133739bb24b1775d79cbe3
3
  size 872568314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fdb544e9a22a371a5d8df82da422560206b79b40d84a212a74ea56b50f59fa
3
  size 872568314
checkpoint-10/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af0af2da3cc3012ea4a8f9301b2a6e7e9d06001e0b5096195a77f505eac1c7e5
3
- size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5bc6d58edfb094654e0fd7d8830f6528f86d2a2c0b08173da1fe23f3fac2ef
3
+ size 14512
checkpoint-10/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9d899b59885b7ec3808e3a7026764ad10b2a497407c064388915efeeaaa6e5a
3
- size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1386ecdf853bc6f64d03fe0f70a1791d948a0933fed4c2a20ca0f9ecc9b5ac63
3
+ size 14512
checkpoint-10/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a07b84508289a8963f504037501519e5c3f9cd498e3e56b46c2f46cc319b62b
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:822c645454e57cd48b7e246c485396a32d986b666bc34f5e61eafab1e5f8c7e3
3
  size 1000
checkpoint-10/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.6981944441795349,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-10",
4
- "epoch": 0.09900990099009901,
5
  "eval_steps": 10,
6
  "global_step": 10,
7
  "is_hyper_param_search": false,
@@ -9,11 +9,11 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.1,
13
- "eval_loss": 0.6981944441795349,
14
- "eval_runtime": 94.6462,
15
- "eval_samples_per_second": 30.292,
16
- "eval_steps_per_second": 0.951,
17
  "step": 10
18
  }
19
  ],
@@ -22,7 +22,7 @@
22
  "num_input_tokens_seen": 0,
23
  "num_train_epochs": 1,
24
  "save_steps": 10,
25
- "total_flos": 8.94387167994839e+16,
26
  "train_batch_size": 16,
27
  "trial_name": null,
28
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6367942690849304,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-10",
4
+ "epoch": 0.04956629491945477,
5
  "eval_steps": 10,
6
  "global_step": 10,
7
  "is_hyper_param_search": false,
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.05,
13
+ "eval_loss": 0.6367942690849304,
14
+ "eval_runtime": 180.8957,
15
+ "eval_samples_per_second": 15.849,
16
+ "eval_steps_per_second": 0.995,
17
  "step": 10
18
  }
19
  ],
 
22
  "num_input_tokens_seen": 0,
23
  "num_train_epochs": 1,
24
  "save_steps": 10,
25
+ "total_flos": 4.493525352080998e+16,
26
  "train_batch_size": 16,
27
  "trial_name": null,
28
  "trial_params": null
checkpoint-10/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
3
  size 5176
checkpoint-20/adapter_config.json CHANGED
@@ -20,9 +20,9 @@
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
 
23
  "v_proj",
24
- "o_proj",
25
- "k_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
23
+ "k_proj",
24
  "v_proj",
25
+ "o_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
checkpoint-20/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d92ebaca9f39e58260e5fd0986ae831944b38b613bc026beed264733021292c
3
  size 436242776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f93cdadbe7004e290ff17d7efaf31b1ad0c58e951c63623a7ec2db46baa3a0
3
  size 436242776
checkpoint-20/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:218a54094316a9e52229eccf60346ea4f16ea75c546bb58ae1812eac0b1878c7
3
  size 872568314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1f3350cd435ac056c183cc29db9441a9f89e9e4bcdebaa06bdd15e0287bb1f1
3
  size 872568314
checkpoint-20/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22d602c1deb78b9595b2b25e679aeb5e9164c6fee9da5d72443b40b85c613bd7
3
- size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08c0c3fb3de62a4c39c2dd09221b2c5eb71b33e9ddfa0dcea7e1d8b3175714f
3
+ size 14512
checkpoint-20/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:353c60d4bfc98b97ccf640512c4e8cbc1e4fed0b400b0194b18399d7475f986c
3
- size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3436f6b74a42fc7a55137f98c160bcde850031a076725f6cd3792a86a06ebdbc
3
+ size 14512
checkpoint-20/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69ef5eee58b82f54616c0e2c590d3e3b3237d203b45aac85ddccbd8b2b34fb5c
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c60be257347464a2f4f18286e268e0f4810c0e6453e5c9541c35f430dab6c52
3
  size 1000
checkpoint-20/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.467332661151886,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-20",
4
- "epoch": 0.19801980198019803,
5
  "eval_steps": 10,
6
  "global_step": 20,
7
  "is_hyper_param_search": false,
@@ -9,26 +9,26 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.1,
13
- "eval_loss": 0.6981944441795349,
14
- "eval_runtime": 94.6462,
15
- "eval_samples_per_second": 30.292,
16
- "eval_steps_per_second": 0.951,
17
  "step": 10
18
  },
19
  {
20
- "epoch": 0.2,
21
- "grad_norm": 0.2654201090335846,
22
- "learning_rate": 0.0001961261695938319,
23
- "loss": 1.0016,
24
  "step": 20
25
  },
26
  {
27
- "epoch": 0.2,
28
- "eval_loss": 0.467332661151886,
29
- "eval_runtime": 94.5373,
30
- "eval_samples_per_second": 30.327,
31
- "eval_steps_per_second": 0.952,
32
  "step": 20
33
  }
34
  ],
@@ -37,7 +37,7 @@
37
  "num_input_tokens_seen": 0,
38
  "num_train_epochs": 1,
39
  "save_steps": 10,
40
- "total_flos": 1.7984776120041472e+17,
41
  "train_batch_size": 16,
42
  "trial_name": null,
43
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.48089343309402466,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-20",
4
+ "epoch": 0.09913258983890955,
5
  "eval_steps": 10,
6
  "global_step": 20,
7
  "is_hyper_param_search": false,
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.05,
13
+ "eval_loss": 0.6367942690849304,
14
+ "eval_runtime": 180.8957,
15
+ "eval_samples_per_second": 15.849,
16
+ "eval_steps_per_second": 0.995,
17
  "step": 10
18
  },
19
  {
20
+ "epoch": 0.1,
21
+ "grad_norm": 0.34346863627433777,
22
+ "learning_rate": 0.00019510565162951537,
23
+ "loss": 0.9774,
24
  "step": 20
25
  },
26
  {
27
+ "epoch": 0.1,
28
+ "eval_loss": 0.48089343309402466,
29
+ "eval_runtime": 180.8882,
30
+ "eval_samples_per_second": 15.85,
31
+ "eval_steps_per_second": 0.995,
32
  "step": 20
33
  }
34
  ],
 
37
  "num_input_tokens_seen": 0,
38
  "num_train_epochs": 1,
39
  "save_steps": 10,
40
+ "total_flos": 9.010061420947046e+16,
41
  "train_batch_size": 16,
42
  "trial_name": null,
43
  "trial_params": null
checkpoint-20/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
3
  size 5176
checkpoint-30/adapter_config.json CHANGED
@@ -20,9 +20,9 @@
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
 
23
  "v_proj",
24
- "o_proj",
25
- "k_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
23
+ "k_proj",
24
  "v_proj",
25
+ "o_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
checkpoint-30/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78ab022ca343660d1f280ec34a80faffada6b025a2a7879119d1810181a75394
3
  size 436242776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24867322dfb4671521880b7952dfecf869c9ddf50ba8c8d0ab60442d46c3b6e7
3
  size 436242776
checkpoint-30/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19650f1cc2280227bbfe7e965edd69b2ee9cacbd13b3e7bb3742aba3a3e324d5
3
  size 872568314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a095acb983c64222b3980c352b38e58ba4bd6e2f0b8e559eddea78a65277790
3
  size 872568314
checkpoint-30/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dadf22c8d1bce4ad601a4f73bbe39dc8987d3b42389b4025267f79988efccce
3
- size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2a616f0c7a81cc42f0138e0036f3bc925663524713430ec02128feb7cc22f7
3
+ size 14512
checkpoint-30/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:528debf43ac8e68f3972cc6eedc188d70690e0a9bfc2feeeff97e757be99c6b8
3
- size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3547aee58cf2280e2d966f891fba83ef181a792754cf251e62b59ae644dd2253
3
+ size 14512
checkpoint-30/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8783ce7e95711682ad7c1657af7a6be242f3bc4b6aac1f9aa4521dd59b1618c4
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35079c4c5c54e3e2a4600c729d1fa32b43362d22b0baf443894af8a786492df1
3
  size 1000
checkpoint-30/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.434685617685318,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-30",
4
- "epoch": 0.297029702970297,
5
  "eval_steps": 10,
6
  "global_step": 30,
7
  "is_hyper_param_search": false,
@@ -9,34 +9,34 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.1,
13
- "eval_loss": 0.6981944441795349,
14
- "eval_runtime": 94.6462,
15
- "eval_samples_per_second": 30.292,
16
- "eval_steps_per_second": 0.951,
17
  "step": 10
18
  },
19
  {
20
- "epoch": 0.2,
21
- "grad_norm": 0.2654201090335846,
22
- "learning_rate": 0.0001961261695938319,
23
- "loss": 1.0016,
24
  "step": 20
25
  },
26
  {
27
- "epoch": 0.2,
28
- "eval_loss": 0.467332661151886,
29
- "eval_runtime": 94.5373,
30
- "eval_samples_per_second": 30.327,
31
- "eval_steps_per_second": 0.952,
32
  "step": 20
33
  },
34
  {
35
- "epoch": 0.3,
36
- "eval_loss": 0.434685617685318,
37
- "eval_runtime": 94.5899,
38
- "eval_samples_per_second": 30.31,
39
- "eval_steps_per_second": 0.951,
40
  "step": 30
41
  }
42
  ],
@@ -45,7 +45,7 @@
45
  "num_input_tokens_seen": 0,
46
  "num_train_epochs": 1,
47
  "save_steps": 10,
48
- "total_flos": 2.6847278785573683e+17,
49
  "train_batch_size": 16,
50
  "trial_name": null,
51
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.44581571221351624,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-30",
4
+ "epoch": 0.14869888475836432,
5
  "eval_steps": 10,
6
  "global_step": 30,
7
  "is_hyper_param_search": false,
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.05,
13
+ "eval_loss": 0.6367942690849304,
14
+ "eval_runtime": 180.8957,
15
+ "eval_samples_per_second": 15.849,
16
+ "eval_steps_per_second": 0.995,
17
  "step": 10
18
  },
19
  {
20
+ "epoch": 0.1,
21
+ "grad_norm": 0.34346863627433777,
22
+ "learning_rate": 0.00019510565162951537,
23
+ "loss": 0.9774,
24
  "step": 20
25
  },
26
  {
27
+ "epoch": 0.1,
28
+ "eval_loss": 0.48089343309402466,
29
+ "eval_runtime": 180.8882,
30
+ "eval_samples_per_second": 15.85,
31
+ "eval_steps_per_second": 0.995,
32
  "step": 20
33
  },
34
  {
35
+ "epoch": 0.15,
36
+ "eval_loss": 0.44581571221351624,
37
+ "eval_runtime": 180.8305,
38
+ "eval_samples_per_second": 15.855,
39
+ "eval_steps_per_second": 0.995,
40
  "step": 30
41
  }
42
  ],
 
45
  "num_input_tokens_seen": 0,
46
  "num_train_epochs": 1,
47
  "save_steps": 10,
48
+ "total_flos": 1.3497349192024064e+17,
49
  "train_batch_size": 16,
50
  "trial_name": null,
51
  "trial_params": null
checkpoint-30/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
3
  size 5176