Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: TheBloke/Llama-2-7B-fp16
+library_name: peft
 ---
 
 # Model Card for Model ID

adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a8f71955b57e8e1082d6f6f180646592764af968e225bda2b732733e64a34c
+oid sha256:6bdfd134cf3b5e167c3aa127bf57024a3e8ff71b6b0ea16d5493a51a01d7e317
 size 67143296

checkpoint-10/README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: TheBloke/Llama-2-7B-fp16
+library_name: peft
 ---
 
 # Model Card for Model ID

checkpoint-10/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-10/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232e478a97bd908880b31806be86d4debfd0492ee0eb83ba509e3293c6c3565a
+oid sha256:2e16adf919d93d6441c2583be16d89fc2157635291e0c18a1835380e4dd25668
 size 67143296

checkpoint-10/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40afa20170f291b125eb81d0ffabecaf09477598d9e256ea01ff0b97e18e70a9
+oid sha256:90d3b34bfbd9c3f0886fa09e483a0a1fa8853028f68e4ce50843d14911e15412
 size 134433530

checkpoint-10/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a35af14c8f81087292db706fc180cce03fb0f692ed151b0664293b217dd11fa5
+oid sha256:04d2341737bca7648a4cdb3a55768450f9758f2298ef492fe1db7f093eaa1902
 size 1064

checkpoint-10/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.733155369758606,
+  "best_metric": 1.737181544303894,
   "best_model_checkpoint": "/kaggle/working/checkpoint-10",
   "epoch": 1.1111111111111112,
   "eval_steps": 10,
@@ -10,24 +10,24 @@
   "log_history": [
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 0.022282764315605164,
-      "learning_rate": 0.0001851851851851852,
-      "loss": 2.0424,
+      "grad_norm": 0.02217627689242363,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 2.0442,
       "step": 10
     },
     {
       "epoch": 1.1111111111111112,
-      "eval_loss": 1.733155369758606,
-      "eval_runtime": 34.5543,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.737181544303894,
+      "eval_runtime": 35.1318,
+      "eval_samples_per_second": 1.025,
+      "eval_steps_per_second": 0.142,
       "step": 10
     }
   ],
   "logging_steps": 10,
-  "max_steps": 135,
+  "max_steps": 90,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 10,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {

checkpoint-10/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+oid sha256:2f0053334cab1bfd2838c507b240d05093bc205b1d5fbe6dc54a022fef5dcaa7
 size 5112

checkpoint-20/README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: TheBloke/Llama-2-7B-fp16
+library_name: peft
 ---
 
 # Model Card for Model ID

checkpoint-20/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-20/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b330fca16a5ab17049bdd4e6e42df52bd8bd0ac1fbeb1577f683e7b1212f0d83
+oid sha256:a5ab93af4ed23c52b82729ff3b3f871c19b732c90f1094f90d5a9f4ade1ccfac
 size 67143296

checkpoint-20/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e5faf17f41fc7dcd6907ecd97bc5e5b82bfa377a6683ddd9d25e9c5a4f3efd
+oid sha256:a07f3020a10b2a9d3e215c9651b159e8c3b297ab1db69b013b8c7817d5f52a7c
 size 134433530

checkpoint-20/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18bf434d2955f164730aed9c7994cdd6c773ed80052fc3ef975fae4adef61283
+oid sha256:f9e7e75183c7081ca7f8f52ddfd0d5f4b8e8dbcf7f7bcd495fc6e0cfff80e3a2
 size 1064

checkpoint-20/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.5428930521011353,
+  "best_metric": 1.5489343404769897,
   "best_model_checkpoint": "/kaggle/working/checkpoint-20",
   "epoch": 2.2222222222222223,
   "eval_steps": 10,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 0.022282764315605164,
-      "learning_rate": 0.0001851851851851852,
-      "loss": 2.0424,
+      "grad_norm": 0.02217627689242363,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 2.0442,
       "step": 10
     },
     {
       "epoch": 1.1111111111111112,
-      "eval_loss": 1.733155369758606,
-      "eval_runtime": 34.5543,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.737181544303894,
+      "eval_runtime": 35.1318,
+      "eval_samples_per_second": 1.025,
+      "eval_steps_per_second": 0.142,
       "step": 10
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 0.018981408327817917,
-      "learning_rate": 0.00017037037037037037,
-      "loss": 1.6072,
+      "grad_norm": 0.0346713550388813,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.6131,
       "step": 20
     },
     {
       "epoch": 2.2222222222222223,
-      "eval_loss": 1.5428930521011353,
-      "eval_runtime": 34.6485,
-      "eval_samples_per_second": 1.039,
+      "eval_loss": 1.5489343404769897,
+      "eval_runtime": 34.8402,
+      "eval_samples_per_second": 1.033,
       "eval_steps_per_second": 0.144,
       "step": 20
     }
   ],
   "logging_steps": 10,
-  "max_steps": 135,
+  "max_steps": 90,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 10,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {

checkpoint-20/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+oid sha256:2f0053334cab1bfd2838c507b240d05093bc205b1d5fbe6dc54a022fef5dcaa7
 size 5112

checkpoint-30/README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: TheBloke/Llama-2-7B-fp16
+library_name: peft
 ---
 
 # Model Card for Model ID

checkpoint-30/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-30/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473c4bd6da7c40c632f6b8a627a42ab5e26f5bc3b977b422287013a48424e372
+oid sha256:d8576250f42c32085cdb174e306461292b115ea33d910d0a59d062fcad935bf0
 size 67143296

checkpoint-30/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a69f8968f0b0dc5be6245d8969030cda587b4b349b62c8e5c647bd89875fa2
+oid sha256:16613c572dcb0ccca606ca4a382a4476b3f69ed3cf64a7095e7f852e897c8426
 size 134433530

checkpoint-30/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8a3ad18d2d099317927f68afa34f1d799ef6644ec4025b52033947a650a29e2
+oid sha256:14d970dabadfb95eaf7812b80cb7816a58d7911bb09df450b100b1c052b74a02
 size 1064

checkpoint-30/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.4176721572875977,
+  "best_metric": 1.4295110702514648,
   "best_model_checkpoint": "/kaggle/working/checkpoint-30",
   "epoch": 3.3333333333333335,
   "eval_steps": 10,
@@ -10,54 +10,54 @@
   "log_history": [
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 0.022282764315605164,
-      "learning_rate": 0.0001851851851851852,
-      "loss": 2.0424,
+      "grad_norm": 0.02217627689242363,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 2.0442,
       "step": 10
     },
     {
       "epoch": 1.1111111111111112,
-      "eval_loss": 1.733155369758606,
-      "eval_runtime": 34.5543,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.737181544303894,
+      "eval_runtime": 35.1318,
+      "eval_samples_per_second": 1.025,
+      "eval_steps_per_second": 0.142,
       "step": 10
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 0.018981408327817917,
-      "learning_rate": 0.00017037037037037037,
-      "loss": 1.6072,
+      "grad_norm": 0.0346713550388813,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.6131,
       "step": 20
     },
     {
       "epoch": 2.2222222222222223,
-      "eval_loss": 1.5428930521011353,
-      "eval_runtime": 34.6485,
-      "eval_samples_per_second": 1.039,
+      "eval_loss": 1.5489343404769897,
+      "eval_runtime": 34.8402,
+      "eval_samples_per_second": 1.033,
       "eval_steps_per_second": 0.144,
       "step": 20
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.023157037794589996,
-      "learning_rate": 0.00015555555555555556,
-      "loss": 1.4025,
+      "grad_norm": 0.02501535415649414,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.4152,
       "step": 30
     },
     {
       "epoch": 3.3333333333333335,
-      "eval_loss": 1.4176721572875977,
-      "eval_runtime": 34.5433,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.4295110702514648,
+      "eval_runtime": 34.8537,
+      "eval_samples_per_second": 1.033,
+      "eval_steps_per_second": 0.143,
       "step": 30
     }
   ],
   "logging_steps": 10,
-  "max_steps": 135,
+  "max_steps": 90,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 10,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {

checkpoint-30/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+oid sha256:2f0053334cab1bfd2838c507b240d05093bc205b1d5fbe6dc54a022fef5dcaa7
 size 5112

checkpoint-40/README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: TheBloke/Llama-2-7B-fp16
+library_name: peft
 ---
 
 # Model Card for Model ID

checkpoint-40/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-40/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801d3ce570c9b9ff575f960af3a00ccd6ba6d98cf418a3b2d0dc14a716f5dc87
+oid sha256:ab38361a67b61947cafd5230ca79626082a1d26b72f5440faf199b3216bc6704
 size 67143296

checkpoint-40/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c5b4e8da000e9b0681d015858d5f844f66483488fdbbc351086278b492e7ad
+oid sha256:2a38dd3cb56490e5a9b4d6a05ea97f3a761cd71841c3d9f7f129c1e4c0b4730f
 size 134433530

checkpoint-40/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb020d6653a8f320452374f8532b2d5f261a1314bca08cdf554ed4cd89610334
+oid sha256:dc5423f1af1182c2163f569e8f44b9ee18e1849c11acaaa76a185745ad274c02
 size 1064

checkpoint-40/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.3449772596359253,
+  "best_metric": 1.3598744869232178,
   "best_model_checkpoint": "/kaggle/working/checkpoint-40",
   "epoch": 4.444444444444445,
   "eval_steps": 10,
@@ -10,69 +10,69 @@
   "log_history": [
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 0.022282764315605164,
-      "learning_rate": 0.0001851851851851852,
-      "loss": 2.0424,
+      "grad_norm": 0.02217627689242363,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 2.0442,
       "step": 10
     },
     {
       "epoch": 1.1111111111111112,
-      "eval_loss": 1.733155369758606,
-      "eval_runtime": 34.5543,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.737181544303894,
+      "eval_runtime": 35.1318,
+      "eval_samples_per_second": 1.025,
+      "eval_steps_per_second": 0.142,
       "step": 10
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 0.018981408327817917,
-      "learning_rate": 0.00017037037037037037,
-      "loss": 1.6072,
+      "grad_norm": 0.0346713550388813,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.6131,
       "step": 20
     },
     {
       "epoch": 2.2222222222222223,
-      "eval_loss": 1.5428930521011353,
-      "eval_runtime": 34.6485,
-      "eval_samples_per_second": 1.039,
+      "eval_loss": 1.5489343404769897,
+      "eval_runtime": 34.8402,
+      "eval_samples_per_second": 1.033,
       "eval_steps_per_second": 0.144,
       "step": 20
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.023157037794589996,
-      "learning_rate": 0.00015555555555555556,
-      "loss": 1.4025,
+      "grad_norm": 0.02501535415649414,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.4152,
       "step": 30
     },
     {
       "epoch": 3.3333333333333335,
-      "eval_loss": 1.4176721572875977,
-      "eval_runtime": 34.5433,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.4295110702514648,
+      "eval_runtime": 34.8537,
+      "eval_samples_per_second": 1.033,
+      "eval_steps_per_second": 0.143,
       "step": 30
     },
     {
       "epoch": 4.444444444444445,
-      "grad_norm": 0.021338749676942825,
-      "learning_rate": 0.00014074074074074076,
-      "loss": 1.285,
+      "grad_norm": 0.02104916237294674,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 1.3068,
       "step": 40
     },
     {
       "epoch": 4.444444444444445,
-      "eval_loss": 1.3449772596359253,
-      "eval_runtime": 34.5594,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.3598744869232178,
+      "eval_runtime": 35.0281,
+      "eval_samples_per_second": 1.028,
+      "eval_steps_per_second": 0.143,
       "step": 40
     }
   ],
   "logging_steps": 10,
-  "max_steps": 135,
+  "max_steps": 90,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 10,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {

checkpoint-40/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+oid sha256:2f0053334cab1bfd2838c507b240d05093bc205b1d5fbe6dc54a022fef5dcaa7
 size 5112

checkpoint-50/README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: TheBloke/Llama-2-7B-fp16
+library_name: peft
 ---
 
 # Model Card for Model ID

checkpoint-50/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-50/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:462ccb4de1a6868b9c314278aa410416a2271f7f6242771f282ecb17db91aa9a
+oid sha256:b692c5f45a06d84947aef0a222d424aecd480e40aabcd9ca87aa5d3007aa46e8
 size 67143296

checkpoint-50/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc1bc1ee11e2e518af04ea6813d8a018c28d601435ab40fb94b4429e7463a6f
+oid sha256:44ab022dad22b0f149a3b1fb04e9cd79842aad48780ac055c542631a6fc57822
 size 134433530

checkpoint-50/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:965332493d5d51377ce3dafe8e14c60e285cd11a8955550ce87e8ef7114ed890
+oid sha256:a9425a09cb4fd41e0b7c88529bcda485c5bb777b677ec7982ea20ad9edbd69fc
 size 1064

checkpoint-50/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.2951068878173828,
+  "best_metric": 1.3168741464614868,
   "best_model_checkpoint": "/kaggle/working/checkpoint-50",
   "epoch": 5.555555555555555,
   "eval_steps": 10,
@@ -10,84 +10,84 @@
   "log_history": [
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 0.022282764315605164,
-      "learning_rate": 0.0001851851851851852,
-      "loss": 2.0424,
+      "grad_norm": 0.02217627689242363,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 2.0442,
       "step": 10
     },
     {
       "epoch": 1.1111111111111112,
-      "eval_loss": 1.733155369758606,
-      "eval_runtime": 34.5543,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.737181544303894,
+      "eval_runtime": 35.1318,
+      "eval_samples_per_second": 1.025,
+      "eval_steps_per_second": 0.142,
       "step": 10
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 0.018981408327817917,
-      "learning_rate": 0.00017037037037037037,
-      "loss": 1.6072,
+      "grad_norm": 0.0346713550388813,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.6131,
       "step": 20
     },
     {
       "epoch": 2.2222222222222223,
-      "eval_loss": 1.5428930521011353,
-      "eval_runtime": 34.6485,
-      "eval_samples_per_second": 1.039,
+      "eval_loss": 1.5489343404769897,
+      "eval_runtime": 34.8402,
+      "eval_samples_per_second": 1.033,
       "eval_steps_per_second": 0.144,
       "step": 20
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.023157037794589996,
-      "learning_rate": 0.00015555555555555556,
-      "loss": 1.4025,
+      "grad_norm": 0.02501535415649414,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.4152,
       "step": 30
     },
     {
       "epoch": 3.3333333333333335,
-      "eval_loss": 1.4176721572875977,
-      "eval_runtime": 34.5433,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.4295110702514648,
+      "eval_runtime": 34.8537,
+      "eval_samples_per_second": 1.033,
+      "eval_steps_per_second": 0.143,
       "step": 30
     },
     {
       "epoch": 4.444444444444445,
-      "grad_norm": 0.021338749676942825,
-      "learning_rate": 0.00014074074074074076,
-      "loss": 1.285,
+      "grad_norm": 0.02104916237294674,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 1.3068,
       "step": 40
     },
     {
       "epoch": 4.444444444444445,
-      "eval_loss": 1.3449772596359253,
-      "eval_runtime": 34.5594,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.3598744869232178,
+      "eval_runtime": 35.0281,
+      "eval_samples_per_second": 1.028,
+      "eval_steps_per_second": 0.143,
       "step": 40
     },
     {
       "epoch": 5.555555555555555,
-      "grad_norm": 0.02489505708217621,
-      "learning_rate": 0.00012592592592592592,
-      "loss": 1.1687,
+      "grad_norm": 0.022395364940166473,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 1.2049,
       "step": 50
     },
     {
       "epoch": 5.555555555555555,
-      "eval_loss": 1.2951068878173828,
-      "eval_runtime": 34.5896,
-      "eval_samples_per_second": 1.041,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.3168741464614868,
+      "eval_runtime": 34.692,
+      "eval_samples_per_second": 1.038,
+      "eval_steps_per_second": 0.144,
       "step": 50
     }
   ],
   "logging_steps": 10,
-  "max_steps": 135,
+  "max_steps": 90,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 10,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {

checkpoint-50/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+oid sha256:2f0053334cab1bfd2838c507b240d05093bc205b1d5fbe6dc54a022fef5dcaa7
 size 5112

checkpoint-60/README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: TheBloke/Llama-2-7B-fp16
+library_name: peft
 ---
 
 # Model Card for Model ID

checkpoint-60/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-60/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db2917762f8b15e3bf37ffb24d36fadc8281664684350c104e7663e270ea20dc
+oid sha256:14ebbefdf71daa025996a412ce6c4f2fd2d5bbf084a4ee0f0ca1dc123cbb85e5
 size 67143296

checkpoint-60/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ee00713e8f75fec9ac92a487fe43f23b824b8125bd0f0413507f283ce38111
+oid sha256:5863ac3d6f865bddc72753e9a6db83e90985a3348345c91097785f539b2d743e
 size 134433530

checkpoint-60/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2dae0587e75ddf657c6d2f1bfc77ac82e3e62449951f53cbb9a382f8e039b79
+oid sha256:a6dfdd6ca5178c66b713159a2bfe5731fea568ef91adf9d3f8039a74c6ff0f6b
 size 1064

checkpoint-60/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.2674343585968018,
+  "best_metric": 1.2939578294754028,
   "best_model_checkpoint": "/kaggle/working/checkpoint-60",
   "epoch": 6.666666666666667,
   "eval_steps": 10,
@@ -10,99 +10,99 @@
   "log_history": [
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 0.022282764315605164,
-      "learning_rate": 0.0001851851851851852,
-      "loss": 2.0424,
+      "grad_norm": 0.02217627689242363,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 2.0442,
       "step": 10
     },
     {
       "epoch": 1.1111111111111112,
-      "eval_loss": 1.733155369758606,
-      "eval_runtime": 34.5543,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.737181544303894,
+      "eval_runtime": 35.1318,
+      "eval_samples_per_second": 1.025,
+      "eval_steps_per_second": 0.142,
       "step": 10
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 0.018981408327817917,
-      "learning_rate": 0.00017037037037037037,
-      "loss": 1.6072,
+      "grad_norm": 0.0346713550388813,
+      "learning_rate": 0.00015555555555555556,
+      "loss": 1.6131,
       "step": 20
     },
     {
       "epoch": 2.2222222222222223,
-      "eval_loss": 1.5428930521011353,
-      "eval_runtime": 34.6485,
-      "eval_samples_per_second": 1.039,
+      "eval_loss": 1.5489343404769897,
+      "eval_runtime": 34.8402,
+      "eval_samples_per_second": 1.033,
       "eval_steps_per_second": 0.144,
       "step": 20
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 0.023157037794589996,
-      "learning_rate": 0.00015555555555555556,
-      "loss": 1.4025,
+      "grad_norm": 0.02501535415649414,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.4152,
       "step": 30
     },
     {
       "epoch": 3.3333333333333335,
-      "eval_loss": 1.4176721572875977,
-      "eval_runtime": 34.5433,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.4295110702514648,
+      "eval_runtime": 34.8537,
+      "eval_samples_per_second": 1.033,
+      "eval_steps_per_second": 0.143,
       "step": 30
     },
     {
       "epoch": 4.444444444444445,
-      "grad_norm": 0.021338749676942825,
-      "learning_rate": 0.00014074074074074076,
-      "loss": 1.285,
+      "grad_norm": 0.02104916237294674,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 1.3068,
       "step": 40
     },
     {
       "epoch": 4.444444444444445,
-      "eval_loss": 1.3449772596359253,
-      "eval_runtime": 34.5594,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.3598744869232178,
+      "eval_runtime": 35.0281,
+      "eval_samples_per_second": 1.028,
+      "eval_steps_per_second": 0.143,
       "step": 40
     },
     {
       "epoch": 5.555555555555555,
-      "grad_norm": 0.02489505708217621,
-      "learning_rate": 0.00012592592592592592,
-      "loss": 1.1687,
+      "grad_norm": 0.022395364940166473,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 1.2049,
       "step": 50
     },
     {
       "epoch": 5.555555555555555,
-      "eval_loss": 1.2951068878173828,
-      "eval_runtime": 34.5896,
-      "eval_samples_per_second": 1.041,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.3168741464614868,
+      "eval_runtime": 34.692,
+      "eval_samples_per_second": 1.038,
+      "eval_steps_per_second": 0.144,
       "step": 50
     },
     {
       "epoch": 6.666666666666667,
-      "grad_norm": 0.028962766751646996,
-      "learning_rate": 0.00011111111111111112,
-      "loss": 1.0521,
+      "grad_norm": 0.02603345364332199,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.1086,
       "step": 60
     },
     {
       "epoch": 6.666666666666667,
-      "eval_loss": 1.2674343585968018,
-      "eval_runtime": 34.5586,
-      "eval_samples_per_second": 1.042,
-      "eval_steps_per_second": 0.145,
+      "eval_loss": 1.2939578294754028,
+      "eval_runtime": 34.6444,
+      "eval_samples_per_second": 1.039,
+      "eval_steps_per_second": 0.144,
       "step": 60
     }
   ],
   "logging_steps": 10,
-  "max_steps": 135,
+  "max_steps": 90,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 10,
   "save_steps": 10,
   "stateful_callbacks": {
     "EarlyStoppingCallback": {

checkpoint-60/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c753ff1ba946038f620bad3e42a35ce583c9e8ed52b49fd22fb6614fea0f43
+oid sha256:2f0053334cab1bfd2838c507b240d05093bc205b1d5fbe6dc54a022fef5dcaa7
 size 5112

checkpoint-70/README.md

@@ -1,6 +1,6 @@
 ---
-library_name: peft
 base_model: TheBloke/Llama-2-7B-fp16
+library_name: peft
 ---
 
 # Model Card for Model ID

checkpoint-70/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
+    "q_proj",
     "o_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

checkpoint-70/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf3c37297ed626b47ab9c41ebb2a26326a24e606918ef7c7fd629793854a6799
+oid sha256:0c44abb9173442b0bc413ba469da95e7be794812df0c2a2c16e54fc301511e3e
 size 67143296

checkpoint-70/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4df5d5144e456b9ea6bf7bd481d07a757eea5bf300085855555e34b8b031648
+oid sha256:2df92dd99064eb6aa6542b203055cf8cc892cff2f30a210807b7667c96cedc3a
 size 134433530

checkpoint-70/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b4acdcca4bce1d839ad3b2f3830a589ce711414ff4548cbd4704149e66a014f
+oid sha256:2b55d3cbe104822729f4f45e02a6c248fb8a4cb356c229f5c93e65066ff6a397
 size 1064