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:b09ed42f9fc722e8de303bf10d9c647e331cf482c4da74d6e9f2740bc692bd6e
-size 4528664
+oid sha256:b269938c34c9dfa5c26ad08ae1b594ec40dd7d488514d7b3c4f7a328b8343792
+size 9034480

trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 29.62962962962963,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 0.0909423828125,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.6288,
+      "step": 10
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.10809326171875,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.6116,
+      "step": 20
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.11297607421875,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.5986,
+      "step": 30
+    },
+    {
+      "epoch": 5.925925925925926,
+      "grad_norm": 0.128173828125,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.5896,
+      "step": 40
+    },
+    {
+      "epoch": 7.407407407407407,
+      "grad_norm": 0.158447265625,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.5726,
+      "step": 50
+    },
+    {
+      "epoch": 8.88888888888889,
+      "grad_norm": 0.1737060546875,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.568,
+      "step": 60
+    },
+    {
+      "epoch": 10.37037037037037,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.5506,
+      "step": 70
+    },
+    {
+      "epoch": 11.851851851851851,
+      "grad_norm": 0.2071533203125,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5438,
+      "step": 80
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.5304,
+      "step": 90
+    },
+    {
+      "epoch": 14.814814814814815,
+      "grad_norm": 0.2379150390625,
+      "learning_rate": 0.0001,
+      "loss": 0.5216,
+      "step": 100
+    },
+    {
+      "epoch": 16.296296296296298,
+      "grad_norm": 0.23876953125,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.5081,
+      "step": 110
+    },
+    {
+      "epoch": 17.77777777777778,
+      "grad_norm": 0.271484375,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5036,
+      "step": 120
+    },
+    {
+      "epoch": 19.25925925925926,
+      "grad_norm": 0.26171875,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.4958,
+      "step": 130
+    },
+    {
+      "epoch": 20.74074074074074,
+      "grad_norm": 0.326904296875,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.4899,
+      "step": 140
+    },
+    {
+      "epoch": 22.22222222222222,
+      "grad_norm": 0.302978515625,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.4826,
+      "step": 150
+    },
+    {
+      "epoch": 23.703703703703702,
+      "grad_norm": 0.28662109375,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.482,
+      "step": 160
+    },
+    {
+      "epoch": 25.185185185185187,
+      "grad_norm": 0.27880859375,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.4789,
+      "step": 170
+    },
+    {
+      "epoch": 26.666666666666668,
+      "grad_norm": 0.284912109375,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.4792,
+      "step": 180
+    },
+    {
+      "epoch": 28.14814814814815,
+      "grad_norm": 0.293212890625,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.4757,
+      "step": 190
+    },
+    {
+      "epoch": 29.62962962962963,
+      "grad_norm": 0.273193359375,
+      "learning_rate": 0.0,
+      "loss": 0.478,
+      "step": 200
+    },
+    {
+      "epoch": 29.62962962962963,
+      "step": 200,
+      "total_flos": 4.058253918575002e+16,
+      "train_loss": 0.5294780325889588,
+      "train_runtime": 572.2712,
+      "train_samples_per_second": 11.184,
+      "train_steps_per_second": 0.349
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 34,
+  "save_steps": 500,
+  "total_flos": 4.058253918575002e+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 sha256:8fa2ad5f85763d481382be06d193af0f8535eb0208c12e3419204fa1bbb8a0c2
+oid sha256:ec8ed8ce547379d8cb02292b1e83868013b93db96aa1311f55c4cd6b4a853f60
 size 4984