Upload folder using huggingface_hub

checkpoint-30/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "k_proj",
     "v_proj",
-    "o_proj",
-    "k_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

checkpoint-30/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ab022ca343660d1f280ec34a80faffada6b025a2a7879119d1810181a75394
+oid sha256:24867322dfb4671521880b7952dfecf869c9ddf50ba8c8d0ab60442d46c3b6e7
 size 436242776

checkpoint-30/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19650f1cc2280227bbfe7e965edd69b2ee9cacbd13b3e7bb3742aba3a3e324d5
+oid sha256:6a095acb983c64222b3980c352b38e58ba4bd6e2f0b8e559eddea78a65277790
 size 872568314

checkpoint-30/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dadf22c8d1bce4ad601a4f73bbe39dc8987d3b42389b4025267f79988efccce
-size 15024
+oid sha256:2c2a616f0c7a81cc42f0138e0036f3bc925663524713430ec02128feb7cc22f7
+size 14512

checkpoint-30/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:528debf43ac8e68f3972cc6eedc188d70690e0a9bfc2feeeff97e757be99c6b8
-size 15024
+oid sha256:3547aee58cf2280e2d966f891fba83ef181a792754cf251e62b59ae644dd2253
+size 14512

checkpoint-30/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8783ce7e95711682ad7c1657af7a6be242f3bc4b6aac1f9aa4521dd59b1618c4
+oid sha256:35079c4c5c54e3e2a4600c729d1fa32b43362d22b0baf443894af8a786492df1
 size 1000

checkpoint-30/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.434685617685318,
+  "best_metric": 0.44581571221351624,
   "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",
-  "epoch": 0.297029702970297,
+  "epoch": 0.14869888475836432,
   "eval_steps": 10,
   "global_step": 30,
   "is_hyper_param_search": false,
@@ -9,34 +9,34 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.1,
-      "eval_loss": 0.6981944441795349,
-      "eval_runtime": 94.6462,
-      "eval_samples_per_second": 30.292,
-      "eval_steps_per_second": 0.951,
+      "epoch": 0.05,
+      "eval_loss": 0.6367942690849304,
+      "eval_runtime": 180.8957,
+      "eval_samples_per_second": 15.849,
+      "eval_steps_per_second": 0.995,
       "step": 10
     },
     {
-      "epoch": 0.2,
-      "grad_norm": 0.2654201090335846,
-      "learning_rate": 0.0001961261695938319,
-      "loss": 1.0016,
+      "epoch": 0.1,
+      "grad_norm": 0.34346863627433777,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.9774,
       "step": 20
     },
     {
-      "epoch": 0.2,
-      "eval_loss": 0.467332661151886,
-      "eval_runtime": 94.5373,
-      "eval_samples_per_second": 30.327,
-      "eval_steps_per_second": 0.952,
+      "epoch": 0.1,
+      "eval_loss": 0.48089343309402466,
+      "eval_runtime": 180.8882,
+      "eval_samples_per_second": 15.85,
+      "eval_steps_per_second": 0.995,
       "step": 20
     },
     {
-      "epoch": 0.3,
-      "eval_loss": 0.434685617685318,
-      "eval_runtime": 94.5899,
-      "eval_samples_per_second": 30.31,
-      "eval_steps_per_second": 0.951,
+      "epoch": 0.15,
+      "eval_loss": 0.44581571221351624,
+      "eval_runtime": 180.8305,
+      "eval_samples_per_second": 15.855,
+      "eval_steps_per_second": 0.995,
       "step": 30
     }
   ],
@@ -45,7 +45,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 2.6847278785573683e+17,
+  "total_flos": 1.3497349192024064e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-30/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
+oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
 size 5176

checkpoint-40/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "k_proj",
     "v_proj",
-    "o_proj",
-    "k_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

checkpoint-40/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f4591fb4db57788c1d5980e4f03bad1b5d20469e935858f70b9470b0272c71
+oid sha256:7b041c9a2283489464450c8f036707f48c1437ef863952d49130a0f6ffff827a
 size 436242776

checkpoint-40/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a08fe71eb4b0f6212455ce0cb2b747581415bf7441f0367bc16d14b31234dea6
+oid sha256:bbf571fc43c326ce5b7f8ab1133043927c1104c6b8d07f4365744906cc3954f2
 size 872568314

checkpoint-40/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa79b6205f47f6bc3f42fc7af51c14822e2a566a3aaf2dc09246fbe343751e3
-size 15024
+oid sha256:562c6644f18ed45bd23812c0c9184280a67775561c0f90429c64bbb0b4cfdd52
+size 14512

checkpoint-40/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34467bd4ec00665d227cf44d137c4ef3d307f23ed69db18dbcedb53da88a6bb8
-size 15024
+oid sha256:6e449608c637ff3eb44facd6dbe70487e4bba04dec462d49ef0b0b376478b590
+size 14512

checkpoint-40/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5849ed9499535f9ffc23dafcb42ec8d336c161ca18201ff7d098f2b17aac424f
+oid sha256:9f3f71a5b5e00e23a44af22895931ea5920a9f7ce8cbf52213ba10a1597ee79b
 size 1000

checkpoint-40/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.4082697033882141,
+  "best_metric": 0.4221758544445038,
   "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-40",
-  "epoch": 0.39603960396039606,
+  "epoch": 0.1982651796778191,
   "eval_steps": 10,
   "global_step": 40,
   "is_hyper_param_search": false,
@@ -9,49 +9,49 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.1,
-      "eval_loss": 0.6981944441795349,
-      "eval_runtime": 94.6462,
-      "eval_samples_per_second": 30.292,
-      "eval_steps_per_second": 0.951,
+      "epoch": 0.05,
+      "eval_loss": 0.6367942690849304,
+      "eval_runtime": 180.8957,
+      "eval_samples_per_second": 15.849,
+      "eval_steps_per_second": 0.995,
       "step": 10
     },
     {
-      "epoch": 0.2,
-      "grad_norm": 0.2654201090335846,
-      "learning_rate": 0.0001961261695938319,
-      "loss": 1.0016,
+      "epoch": 0.1,
+      "grad_norm": 0.34346863627433777,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.9774,
       "step": 20
     },
     {
-      "epoch": 0.2,
-      "eval_loss": 0.467332661151886,
-      "eval_runtime": 94.5373,
-      "eval_samples_per_second": 30.327,
-      "eval_steps_per_second": 0.952,
+      "epoch": 0.1,
+      "eval_loss": 0.48089343309402466,
+      "eval_runtime": 180.8882,
+      "eval_samples_per_second": 15.85,
+      "eval_steps_per_second": 0.995,
       "step": 20
     },
     {
-      "epoch": 0.3,
-      "eval_loss": 0.434685617685318,
-      "eval_runtime": 94.5899,
-      "eval_samples_per_second": 30.31,
-      "eval_steps_per_second": 0.951,
+      "epoch": 0.15,
+      "eval_loss": 0.44581571221351624,
+      "eval_runtime": 180.8305,
+      "eval_samples_per_second": 15.855,
+      "eval_steps_per_second": 0.995,
       "step": 30
     },
     {
-      "epoch": 0.4,
-      "grad_norm": 1.3763986825942993,
-      "learning_rate": 0.0001559192903470747,
-      "loss": 0.4357,
+      "epoch": 0.2,
+      "grad_norm": 0.22729116678237915,
+      "learning_rate": 0.0001529919264233205,
+      "loss": 0.4459,
       "step": 40
     },
     {
-      "epoch": 0.4,
-      "eval_loss": 0.4082697033882141,
-      "eval_runtime": 94.551,
-      "eval_samples_per_second": 30.322,
-      "eval_steps_per_second": 0.952,
+      "epoch": 0.2,
+      "eval_loss": 0.4221758544445038,
+      "eval_runtime": 180.8406,
+      "eval_samples_per_second": 15.854,
+      "eval_steps_per_second": 0.995,
       "step": 40
     }
   ],
@@ -60,7 +60,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 3.5844587589625446e+17,
+  "total_flos": 1.8087006649607782e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-40/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
+oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
 size 5176

checkpoint-50/adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "k_proj",
     "v_proj",
-    "o_proj",
-    "k_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

checkpoint-50/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e638a9f9216b03397158412851fd7d42949246bfa2ad7c3058437c76160f7d09
+oid sha256:792bf8f744bca5db30a5b2fe80e0610d871d2e0e9c0a4f386c15921efdc2cada
 size 436242776

checkpoint-50/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66dd45f2150a0a6d4c60db415e39f4e3b5a2c0f9141ca87580540f33e9090d61
+oid sha256:4bfe60b7f0163e31d4d317b854f7aa8b441fdda4591c40ed389e383d3a3f89cf
 size 872568314

checkpoint-50/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1acbc70db12510c2b2cee4658b6acfca9e76743915e6d5251c5387fc60850037
-size 15024
+oid sha256:155af0328dced3a7822123bfbbfc0a98082468058997d134358c43dd61128a48
+size 14512

checkpoint-50/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29aac9ff927aa57aaa01a137c1fa61f3cbd6758e0fdcb77bcf8f5a4ddaebeb8f
-size 15024
+oid sha256:a4b7ab3a551c96c4ceca4cd3993bf33763b09c0ba81bc2a77fec0f7faa8f7890
+size 14512

checkpoint-50/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a711e3dc499e314bc1a87cadf8f61ca720790ae9992957172045f5ab8655fd0
+oid sha256:17f23ea92413fa32eaeae1119269ac938b5f442880c1543708aed43058dfbadd
 size 1000

checkpoint-50/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.40642818808555603,
+  "best_metric": 0.40922558307647705,
   "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-50",
-  "epoch": 0.49504950495049505,
+  "epoch": 0.24783147459727387,
   "eval_steps": 10,
   "global_step": 50,
   "is_hyper_param_search": false,
@@ -9,57 +9,57 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.1,
-      "eval_loss": 0.6981944441795349,
-      "eval_runtime": 94.6462,
-      "eval_samples_per_second": 30.292,
-      "eval_steps_per_second": 0.951,
+      "epoch": 0.05,
+      "eval_loss": 0.6367942690849304,
+      "eval_runtime": 180.8957,
+      "eval_samples_per_second": 15.849,
+      "eval_steps_per_second": 0.995,
       "step": 10
     },
     {
-      "epoch": 0.2,
-      "grad_norm": 0.2654201090335846,
-      "learning_rate": 0.0001961261695938319,
-      "loss": 1.0016,
+      "epoch": 0.1,
+      "grad_norm": 0.34346863627433777,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.9774,
       "step": 20
     },
     {
-      "epoch": 0.2,
-      "eval_loss": 0.467332661151886,
-      "eval_runtime": 94.5373,
-      "eval_samples_per_second": 30.327,
-      "eval_steps_per_second": 0.952,
+      "epoch": 0.1,
+      "eval_loss": 0.48089343309402466,
+      "eval_runtime": 180.8882,
+      "eval_samples_per_second": 15.85,
+      "eval_steps_per_second": 0.995,
       "step": 20
     },
     {
-      "epoch": 0.3,
-      "eval_loss": 0.434685617685318,
-      "eval_runtime": 94.5899,
-      "eval_samples_per_second": 30.31,
-      "eval_steps_per_second": 0.951,
+      "epoch": 0.15,
+      "eval_loss": 0.44581571221351624,
+      "eval_runtime": 180.8305,
+      "eval_samples_per_second": 15.855,
+      "eval_steps_per_second": 0.995,
       "step": 30
     },
     {
-      "epoch": 0.4,
-      "grad_norm": 1.3763986825942993,
-      "learning_rate": 0.0001559192903470747,
-      "loss": 0.4357,
+      "epoch": 0.2,
+      "grad_norm": 0.22729116678237915,
+      "learning_rate": 0.0001529919264233205,
+      "loss": 0.4459,
       "step": 40
     },
     {
-      "epoch": 0.4,
-      "eval_loss": 0.4082697033882141,
-      "eval_runtime": 94.551,
-      "eval_samples_per_second": 30.322,
-      "eval_steps_per_second": 0.952,
+      "epoch": 0.2,
+      "eval_loss": 0.4221758544445038,
+      "eval_runtime": 180.8406,
+      "eval_samples_per_second": 15.854,
+      "eval_steps_per_second": 0.995,
       "step": 40
     },
     {
-      "epoch": 0.5,
-      "eval_loss": 0.40642818808555603,
-      "eval_runtime": 94.5831,
-      "eval_samples_per_second": 30.312,
-      "eval_steps_per_second": 0.952,
+      "epoch": 0.25,
+      "eval_loss": 0.40922558307647705,
+      "eval_runtime": 181.1791,
+      "eval_samples_per_second": 15.824,
+      "eval_steps_per_second": 0.993,
       "step": 50
     }
   ],
@@ -68,7 +68,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 10,
-  "total_flos": 4.502771471776481e+17,
+  "total_flos": 2.2680060137832448e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-50/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
+oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
 size 5176