Model save

README.md

@@ -41,7 +41,6 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2
 - num_epochs: 4
 
 ### Training results

adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "o_proj",
     "down_proj",
+    "v_proj",
     "up_proj",
     "k_proj",
-    "o_proj",
-    "v_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d209c54a5d95be6e1246f9254828bb85ebf2c9da9c8a5016d8aa65f0d84eb0ca
+oid sha256:6367bd7f0fb3ab036311a0aab0599e1ed32039ee2f89d86153d7b2b9be39edba
 size 1635969696

trainer_state.json

@@ -10,67 +10,67 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 0.5123344659805298,
-      "learning_rate": 8.794946550048592e-05,
-      "loss": 0.9496,
+      "grad_norm": 0.9188441634178162,
+      "learning_rate": 8.786407766990292e-05,
+      "loss": 0.8368,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 0.8029014468193054,
-      "learning_rate": 7.580174927113704e-05,
-      "loss": 0.6426,
+      "grad_norm": 0.6881112456321716,
+      "learning_rate": 7.572815533980583e-05,
+      "loss": 0.4246,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 0.9907676577568054,
-      "learning_rate": 6.365403304178815e-05,
-      "loss": 0.5632,
+      "grad_norm": 0.6344935297966003,
+      "learning_rate": 6.359223300970875e-05,
+      "loss": 0.3804,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 0.9990822672843933,
-      "learning_rate": 5.150631681243926e-05,
-      "loss": 0.5117,
+      "grad_norm": 0.6141209006309509,
+      "learning_rate": 5.145631067961165e-05,
+      "loss": 0.3646,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 0.7601630687713623,
-      "learning_rate": 3.9358600583090386e-05,
-      "loss": 0.4772,
+      "grad_norm": 0.5896692276000977,
+      "learning_rate": 3.9320388349514564e-05,
+      "loss": 0.3538,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 0.7860077023506165,
-      "learning_rate": 2.72108843537415e-05,
-      "loss": 0.4564,
+      "grad_norm": 0.6480565667152405,
+      "learning_rate": 2.7184466019417475e-05,
+      "loss": 0.3462,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 0.5943681597709656,
-      "learning_rate": 1.5063168124392615e-05,
-      "loss": 0.4392,
+      "grad_norm": 0.6381719708442688,
+      "learning_rate": 1.5048543689320387e-05,
+      "loss": 0.3338,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 0.5319840908050537,
-      "learning_rate": 2.915451895043732e-06,
-      "loss": 0.4318,
+      "grad_norm": 0.610920250415802,
+      "learning_rate": 2.912621359223301e-06,
+      "loss": 0.3259,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
       "total_flos": 1.4445804612483994e+18,
-      "train_loss": 0.5552371376926459,
-      "train_runtime": 17453.3458,
-      "train_samples_per_second": 30.215,
+      "train_loss": 0.4179296539825143,
+      "train_runtime": 17434.171,
+      "train_samples_per_second": 30.248,
       "train_steps_per_second": 0.118
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:617a99532cd91765e0705e15346b67e9640bce2631da172c620125a4f5bbf68b
+oid sha256:7484e26a2443ab001dada28afc5e4336045ee6f01f36bb190af4ea081f0e6eb8
 size 5240