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 sha256:0ef8bbe84d3302568518e1b356cc7a8a2696d1dd3cbfff7a50bd4075c4ce84d3
-size 4528664
+oid sha256:f1d00b9cbf7615069fd8a4c16953e8dadc1bc120f41de6ee5a8792d47b22db9c
+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": 0.11053466796875,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.6601,
+      "step": 10
+    },
+    {
+      "epoch": 2.7586206896551726,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.6308,
+      "step": 20
+    },
+    {
+      "epoch": 4.137931034482759,
+      "grad_norm": 0.10504150390625,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.6239,
+      "step": 30
+    },
+    {
+      "epoch": 5.517241379310345,
+      "grad_norm": 0.129150390625,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.6176,
+      "step": 40
+    },
+    {
+      "epoch": 6.896551724137931,
+      "grad_norm": 0.1370849609375,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.5979,
+      "step": 50
+    },
+    {
+      "epoch": 8.275862068965518,
+      "grad_norm": 0.1435546875,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.5908,
+      "step": 60
+    },
+    {
+      "epoch": 9.655172413793103,
+      "grad_norm": 0.1844482421875,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.5818,
+      "step": 70
+    },
+    {
+      "epoch": 11.03448275862069,
+      "grad_norm": 0.1978759765625,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5691,
+      "step": 80
+    },
+    {
+      "epoch": 12.413793103448276,
+      "grad_norm": 0.192138671875,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.5608,
+      "step": 90
+    },
+    {
+      "epoch": 13.793103448275861,
+      "grad_norm": 0.2030029296875,
+      "learning_rate": 0.0001,
+      "loss": 0.5493,
+      "step": 100
+    },
+    {
+      "epoch": 15.172413793103448,
+      "grad_norm": 0.2073974609375,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.5386,
+      "step": 110
+    },
+    {
+      "epoch": 16.551724137931036,
+      "grad_norm": 0.2435302734375,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5347,
+      "step": 120
+    },
+    {
+      "epoch": 17.93103448275862,
+      "grad_norm": 0.25048828125,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.5289,
+      "step": 130
+    },
+    {
+      "epoch": 19.310344827586206,
+      "grad_norm": 0.250244140625,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.5228,
+      "step": 140
+    },
+    {
+      "epoch": 20.689655172413794,
+      "grad_norm": 0.2484130859375,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.5149,
+      "step": 150
+    },
+    {
+      "epoch": 22.06896551724138,
+      "grad_norm": 0.255615234375,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.513,
+      "step": 160
+    },
+    {
+      "epoch": 23.448275862068964,
+      "grad_norm": 0.244140625,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.5145,
+      "step": 170
+    },
+    {
+      "epoch": 24.82758620689655,
+      "grad_norm": 0.251953125,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.5053,
+      "step": 180
+    },
+    {
+      "epoch": 26.20689655172414,
+      "grad_norm": 0.253173828125,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.5119,
+      "step": 190
+    },
+    {
+      "epoch": 27.586206896551722,
+      "grad_norm": 0.259033203125,
+      "learning_rate": 0.0,
+      "loss": 0.5105,
+      "step": 200
+    },
+    {
+      "epoch": 27.586206896551722,
+      "step": 200,
+      "total_flos": 4.059527895633101e+16,
+      "train_loss": 0.558857798576355,
+      "train_runtime": 573.5027,
+      "train_samples_per_second": 11.159,
+      "train_steps_per_second": 0.349
+    }
+  ],
+  "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 sha256:139d48d9a175651aa8ededd79a211c139b36b8fd31ce08ff5bff6a9d0b486b34
+oid sha256:2ee7e31757159709fecfc49de11ffd0cd0afb5a13cd269bc0a4fc6db73247b44
 size 4984