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 sha256:5c3d3394c48429b6998dba34fa6d8e46a510f3e87807348469f9404de8d2ceb3
-size 4528664
+oid sha256:bed78482c2845205ffadb4413876c60dd1d85352891754691696da8d38247934
+size 9034480

trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 27.586206896551722,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.3793103448275863,
+      "grad_norm": 0.12481689453125,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.6433,
+      "step": 10
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.11810302734375,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.6101,
+      "step": 20
+    },
+    {
+      "epoch": 4.137931034482759,
+      "grad_norm": 0.1224365234375,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.5938,
+      "step": 30
+    },
+    {
+      "epoch": 5.517241379310345,
+      "grad_norm": 0.12646484375,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.58,
+      "step": 40
+    },
+    {
+      "epoch": 6.896551724137931,
+      "grad_norm": 0.1378173828125,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.564,
+      "step": 50
+    },
+    {
+      "epoch": 8.275862068965518,
+      "grad_norm": 0.150634765625,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.5522,
+      "step": 60
+    },
+    {
+      "epoch": 9.655172413793103,
+      "grad_norm": 0.189453125,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.5496,
+      "step": 70
+    },
+    {
+      "epoch": 11.03448275862069,
+      "grad_norm": 0.208984375,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5279,
+      "step": 80
+    },
+    {
+      "epoch": 12.413793103448276,
+      "grad_norm": 0.2149658203125,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.5211,
+      "step": 90
+    },
+    {
+      "epoch": 13.793103448275861,
+      "grad_norm": 0.256103515625,
+      "learning_rate": 0.0001,
+      "loss": 0.5138,
+      "step": 100
+    },
+    {
+      "epoch": 15.172413793103448,
+      "grad_norm": 0.2479248046875,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.5024,
+      "step": 110
+    },
+    {
+      "epoch": 16.551724137931036,
+      "grad_norm": 0.276123046875,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.4982,
+      "step": 120
+    },
+    {
+      "epoch": 17.93103448275862,
+      "grad_norm": 0.26318359375,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.4884,
+      "step": 130
+    },
+    {
+      "epoch": 19.310344827586206,
+      "grad_norm": 0.276123046875,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.482,
+      "step": 140
+    },
+    {
+      "epoch": 20.689655172413794,
+      "grad_norm": 0.271240234375,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.4791,
+      "step": 150
+    },
+    {
+      "epoch": 22.06896551724138,
+      "grad_norm": 0.33056640625,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.4761,
+      "step": 160
+    },
+    {
+      "epoch": 23.448275862068964,
+      "grad_norm": 0.27001953125,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.4733,
+      "step": 170
+    },
+    {
+      "epoch": 24.82758620689655,
+      "grad_norm": 0.289794921875,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.4728,
+      "step": 180
+    },
+    {
+      "epoch": 26.20689655172414,
+      "grad_norm": 0.273681640625,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.4683,
+      "step": 190
+    },
+    {
+      "epoch": 27.586206896551722,
+      "grad_norm": 0.2841796875,
+      "learning_rate": 0.0,
+      "loss": 0.4744,
+      "step": 200
+    },
+    {
+      "epoch": 27.586206896551722,
+      "step": 200,
+      "total_flos": 4.059527895633101e+16,
+      "train_loss": 0.5235269355773926,
+      "train_runtime": 570.5675,
+      "train_samples_per_second": 11.217,
+      "train_steps_per_second": 0.351
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 29,
+  "save_steps": 500,
+  "total_flos": 4.059527895633101e+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:e6dd96b52e3390028a6847b62d73589fef80f948b4bd743f27eee2956407b3bb
+oid sha256:2a1f80e6a7eb35f96d72ed01de3541c768b1cadec81ee6a99a3232cc79484015
 size 4984