Upload folder using huggingface_hub

adapter_config.json

@@ -25,10 +25,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
-    "k_proj",
-    "o_proj"
+    "o_proj",
+    "v_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ba49c8c8687d106786e91b8c0258edff6596f2dd11380fe35f520091103336
+oid sha256:e468e2d77297d7ad91d2aa50ebdc3d4dcefb69defd07547654dbdaa3484a17f1
 size 33588528

checkpoint-50/adapter_config.json

@@ -25,9 +25,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
     "q_proj",
+    "o_proj",
+    "v_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

checkpoint-50/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13be47a2dabeff36de460c674873690540819ce5dc76774e918e6c6350816d01
+oid sha256:e468e2d77297d7ad91d2aa50ebdc3d4dcefb69defd07547654dbdaa3484a17f1
 size 33588528

checkpoint-50/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b131699f30ee0b6f7adbe1e51d969e0f294bff32e6a3e5b10457540c26eeea
+oid sha256:a8fba518fb2ff6da256d9f7c587bf8689c7ee4025b42948ae0259e31306c7d11
 size 17338708

checkpoint-50/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a206d9f667d8ea3ff758745bc598392dfea22625e5fa47093cb96bf116f36e32
+oid sha256:3cf89169291703cf6b96550e33edc2c6a95bc870029fa76b33d1b7b4507afeb6
 size 14244

checkpoint-50/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:679891a6f5a888edbeebb4d778cff89972ef778c4087bae746c97dfe9244f249
+oid sha256:9d4e40b4ba2b33c214f8a0e942f429620d2826c1735b2b9fa48265d44caa87cb
 size 988

checkpoint-50/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e417c65f270cd74e6f1d7db3f4d911a6218769029f43db0bb8de7fec70c27119
+oid sha256:281827ead75066f664b29f5c22ee974cb25ad2d35f99b381f96c3f43fe213728
 size 1064

checkpoint-50/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.88888888888889,
+  "epoch": 25.0,
   "eval_steps": 500,
   "global_step": 50,
   "is_hyper_param_search": false,
@@ -10,45 +10,45 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.4444444444444446,
-      "grad_norm": 0.23509381711483002,
-      "learning_rate": 0.00018,
-      "loss": 1.8657,
+      "epoch": 5.0,
+      "grad_norm": 1.823412537574768,
+      "learning_rate": 0.00014,
+      "loss": 2.6875,
       "step": 10
     },
     {
-      "epoch": 6.888888888888889,
-      "grad_norm": 0.4787384867668152,
-      "learning_rate": 0.000155,
-      "loss": 1.6866,
+      "epoch": 10.0,
+      "grad_norm": 0.30645912885665894,
+      "learning_rate": 0.000165,
+      "loss": 1.9697,
       "step": 20
     },
     {
-      "epoch": 10.0,
-      "grad_norm": 0.880219042301178,
-      "learning_rate": 0.000105,
-      "loss": 1.3819,
+      "epoch": 15.0,
+      "grad_norm": 0.487067312002182,
+      "learning_rate": 0.00011499999999999999,
+      "loss": 1.5021,
       "step": 30
     },
     {
-      "epoch": 13.444444444444445,
-      "grad_norm": 0.641683042049408,
-      "learning_rate": 5.500000000000001e-05,
-      "loss": 1.1817,
+      "epoch": 20.0,
+      "grad_norm": 0.8200891613960266,
+      "learning_rate": 6.500000000000001e-05,
+      "loss": 1.234,
       "step": 40
     },
     {
-      "epoch": 16.88888888888889,
-      "grad_norm": 0.681348979473114,
-      "learning_rate": 5e-06,
-      "loss": 1.022,
+      "epoch": 25.0,
+      "grad_norm": 0.9909401535987854,
+      "learning_rate": 1.5e-05,
+      "loss": 0.9953,
       "step": 50
     }
   ],
   "logging_steps": 10,
   "max_steps": 50,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 17,
+  "num_train_epochs": 25,
   "save_steps": 50,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -62,7 +62,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3089176467603456.0,
+  "total_flos": 4064705878425600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

checkpoint-50/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd48ad7e7c5bcb67d8f7bec6dd926a2d8d3ad361b44ce136d6d2d7c994e8199
+oid sha256:3e806016397e36524f90ee92db251177b3f47cb2b360e8ff461ef1d934439559
 size 5304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4e8f1dd9a9d5ca2ecbbfcb36f632a8f15434d2f5f952ac45738d3abf965e26a
+oid sha256:3e806016397e36524f90ee92db251177b3f47cb2b360e8ff461ef1d934439559
 size 5304