Model save

README.md

@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.0
+- PEFT 0.13.2
 - Transformers 4.45.2
-- Pytorch 2.4.0
-- Tokenizers 0.20.0
+- Pytorch 2.4.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "o_proj",
     "k_proj",
-    "q_proj",
-    "down_proj",
-    "v_proj",
     "up_proj",
-    "o_proj"
+    "down_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:c0608d2d5ada0132938ef49ee2ea5b795c004e70e8728f4f4d4541bb2bb63b07
+oid sha256:64ae2022f453d5bc64fcc557be09cba7e1a151bf480dcbe7e4ce44fbfb893bfa
 size 1103312056

trainer_state.json

@@ -10,68 +10,68 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 0.6597544550895691,
+      "grad_norm": 0.6159274578094482,
       "learning_rate": 8.786407766990292e-05,
-      "loss": 0.8187,
+      "loss": 0.7326,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 0.47376748919487,
+      "grad_norm": 0.45552706718444824,
       "learning_rate": 7.572815533980583e-05,
-      "loss": 0.4144,
+      "loss": 0.3702,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 0.4789002537727356,
+      "grad_norm": 0.440681517124176,
       "learning_rate": 6.359223300970875e-05,
-      "loss": 0.3726,
+      "loss": 0.3325,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 0.4547956883907318,
+      "grad_norm": 0.4214372932910919,
       "learning_rate": 5.145631067961165e-05,
-      "loss": 0.3592,
+      "loss": 0.3201,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 0.4283891022205353,
+      "grad_norm": 0.40064775943756104,
       "learning_rate": 3.9320388349514564e-05,
-      "loss": 0.3506,
+      "loss": 0.3109,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 0.45446979999542236,
+      "grad_norm": 0.4439554214477539,
       "learning_rate": 2.7184466019417475e-05,
-      "loss": 0.3453,
+      "loss": 0.3051,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 0.45201343297958374,
+      "grad_norm": 0.4426790773868561,
       "learning_rate": 1.5048543689320387e-05,
-      "loss": 0.337,
+      "loss": 0.2952,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 0.43229737877845764,
+      "grad_norm": 0.4219134747982025,
       "learning_rate": 2.912621359223301e-06,
-      "loss": 0.3328,
+      "loss": 0.2899,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
-      "total_flos": 5.02561395295531e+17,
-      "train_loss": 0.41385009358230146,
-      "train_runtime": 8590.7554,
-      "train_samples_per_second": 61.386,
-      "train_steps_per_second": 0.24
+      "total_flos": 4.867642930150072e+17,
+      "train_loss": 0.367200387565835,
+      "train_runtime": 8608.2467,
+      "train_samples_per_second": 61.261,
+      "train_steps_per_second": 0.239
     }
   ],
   "logging_steps": 250,
@@ -91,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.02561395295531e+17,
+  "total_flos": 4.867642930150072e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851af1312773776dcb2253f75cd2ee4b7ec12839684660397a6640baa82a6b18
+oid sha256:f6ad0b8eecbff5e8dbe3ece6c82b15da0f30681324000404361929c5959dac6a
 size 5240