Training in progress, epoch 0

adapter_config.json

@@ -10,20 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "q_proj",
     "o_proj",
     "v_proj",
-    "q_proj"
+    "k_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:ccbe48dd562349af62529b27dcdde492737ca802b5e3d3972ca96da2156e101e
-size 4528664
+oid sha256:bf0ce3efe48eb420b8d7939f246235b0544acb9da14b571c26b823609f68865e
+size 9034480

trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 40.0,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.354248046875,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.9502,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.322021484375,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.74,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.179931640625,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.6284,
+      "step": 30
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.132080078125,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.5907,
+      "step": 40
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.12481689453125,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.5757,
+      "step": 50
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.130859375,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.5632,
+      "step": 60
+    },
+    {
+      "epoch": 14.0,
+      "grad_norm": 0.143310546875,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.5519,
+      "step": 70
+    },
+    {
+      "epoch": 16.0,
+      "grad_norm": 0.1419677734375,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5405,
+      "step": 80
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.1556396484375,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.5309,
+      "step": 90
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.16796875,
+      "learning_rate": 0.0001,
+      "loss": 0.5212,
+      "step": 100
+    },
+    {
+      "epoch": 22.0,
+      "grad_norm": 0.179443359375,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.513,
+      "step": 110
+    },
+    {
+      "epoch": 24.0,
+      "grad_norm": 0.19970703125,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5052,
+      "step": 120
+    },
+    {
+      "epoch": 26.0,
+      "grad_norm": 0.1968994140625,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.4986,
+      "step": 130
+    },
+    {
+      "epoch": 28.0,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.4939,
+      "step": 140
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.2227783203125,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.49,
+      "step": 150
+    },
+    {
+      "epoch": 32.0,
+      "grad_norm": 0.200439453125,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4867,
+      "step": 160
+    },
+    {
+      "epoch": 34.0,
+      "grad_norm": 0.2117919921875,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.4846,
+      "step": 170
+    },
+    {
+      "epoch": 36.0,
+      "grad_norm": 0.2088623046875,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.4832,
+      "step": 180
+    },
+    {
+      "epoch": 38.0,
+      "grad_norm": 0.2152099609375,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.4829,
+      "step": 190
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 0.211181640625,
+      "learning_rate": 0.0,
+      "loss": 0.4828,
+      "step": 200
+    },
+    {
+      "epoch": 40.0,
+      "step": 200,
+      "total_flos": 4.000287962431488e+16,
+      "train_loss": 0.5556855773925782,
+      "train_runtime": 573.2976,
+      "train_samples_per_second": 11.163,
+      "train_steps_per_second": 0.349
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 40,
+  "save_steps": 500,
+  "total_flos": 4.000287962431488e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c439d50d5663a612456ce5c9cca4cb0d6691bcd7b9ee8544536e03d9ab2cd5
+oid sha256:3a9df969320ba1045d43ad75a9eaab4b85bb1f498fcd8c28a0cfaf5493c2c96e
 size 4984