Upload folder using huggingface_hub

adapter_config.json

@@ -25,10 +25,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "v_proj",
+    "o_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 sha256:7527027d86c2f99fb4a21349c730585d104c214f60e49f314d66f5a733bc9a50
+oid sha256:9ac099278fb9edf2d9edd340cd938ebc99ed9467c2547d549454c07c111b2001
 size 33588528

checkpoint-50/adapter_config.json

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

checkpoint-50/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7527027d86c2f99fb4a21349c730585d104c214f60e49f314d66f5a733bc9a50
+oid sha256:9ac099278fb9edf2d9edd340cd938ebc99ed9467c2547d549454c07c111b2001
 size 33588528

checkpoint-50/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c074625f59c355cb1db0e83337b49e4b45d7202294c8e85514c2b801bff024e7
+oid sha256:2c537e0c84aa504189db3fddf5fb061cd10f26d31badc473a95d8113bde31a81
 size 17338708

checkpoint-50/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354615fc8387693f24d82e680c5229ada92ecc73c65770aa0d2ec2f22d519ce2
+oid sha256:11a24299ffe9e5c367ac48641a0b20a024a9ffa4dadd88ff0de1d80366031fc1
 size 14244

checkpoint-50/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae5b6e1493c7b53e741deaed6ac33c1459c9d8e052b89f8241e547b1872d8a8
+oid sha256:9d4e40b4ba2b33c214f8a0e942f429620d2826c1735b2b9fa48265d44caa87cb
 size 988

checkpoint-50/trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.533333333333333,
+  "epoch": 10.0,
   "eval_steps": 500,
   "global_step": 50,
   "is_hyper_param_search": false,
@@ -10,45 +10,45 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 2.533333333333333,
-      "grad_norm": 5.1353068351745605,
+      "epoch": 2.0,
+      "grad_norm": 3.0599591732025146,
       "learning_rate": 0.00014,
-      "loss": 7.9209,
+      "loss": 7.1516,
       "step": 10
     },
     {
-      "epoch": 5.0,
-      "grad_norm": 1.2159311771392822,
+      "epoch": 4.0,
+      "grad_norm": 4.054620265960693,
       "learning_rate": 0.000165,
-      "loss": 3.5184,
+      "loss": 3.4319,
       "step": 20
     },
     {
-      "epoch": 7.533333333333333,
-      "grad_norm": 0.17727278172969818,
+      "epoch": 6.0,
+      "grad_norm": 0.3359832763671875,
       "learning_rate": 0.00011499999999999999,
-      "loss": 1.3178,
+      "loss": 1.5166,
       "step": 30
     },
     {
-      "epoch": 10.0,
-      "grad_norm": 0.20721666514873505,
+      "epoch": 8.0,
+      "grad_norm": 0.26995959877967834,
       "learning_rate": 6.500000000000001e-05,
-      "loss": 1.3595,
+      "loss": 1.452,
       "step": 40
     },
     {
-      "epoch": 12.533333333333333,
-      "grad_norm": 0.1987001746892929,
+      "epoch": 10.0,
+      "grad_norm": 0.3264690935611725,
       "learning_rate": 1.5e-05,
-      "loss": 1.2959,
+      "loss": 1.4391,
       "step": 50
     }
   ],
   "logging_steps": 10,
   "max_steps": 50,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 13,
+  "num_train_epochs": 10,
   "save_steps": 50,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -62,7 +62,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7641647051440128.0,
+  "total_flos": 7113235287244800.0,
   "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:d803a248f86aede78be3460d30806bdea503d572393c5e5c9706e3cd81f51c6e
+oid sha256:04edd0948095c87ea1433f93e6ceefa73471f05f49a9b2091578fb002ea5db87
 size 5304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d803a248f86aede78be3460d30806bdea503d572393c5e5c9706e3cd81f51c6e
+oid sha256:04edd0948095c87ea1433f93e6ceefa73471f05f49a9b2091578fb002ea5db87
 size 5304