Training in progress, epoch 1

adapter_config.json

@@ -14,14 +14,14 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
     "classifier"
   ],
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888b7a246087863947dece026546b16c5b9874999347eae36c3a549fefac1b99
-size 2372592
+oid sha256:14ac509eaf5eacf8c37f09b45fb8556c83de0808c2fd9221ac37913a45e2ef87
+size 4731912

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3.405838778276659e+17,
+    "train_loss": 0.6811685698372977,
+    "train_runtime": 162.9509,
+    "train_samples_per_second": 26.787,
+    "train_steps_per_second": 0.215
+}

runs/Aug15_13-57-16_c03d0dbfda2e/events.out.tfevents.1723730439.c03d0dbfda2e.1885.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e482f34e703102e60b97dbb9bb277609325bfe8c34633f35b8843dfbc51a766
+size 405

runs/Aug15_14-03-02_c03d0dbfda2e/events.out.tfevents.1723730583.c03d0dbfda2e.1885.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563b06d2895a4058a43bcaa21b13664e9aa225f6015de0687fc169a331d0e9a5
+size 5879

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3.405838778276659e+17,
+    "train_loss": 0.6811685698372977,
+    "train_runtime": 162.9509,
+    "train_samples_per_second": 26.787,
+    "train_steps_per_second": 0.215
+}

trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": 0.5714285714285714,
+  "best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-qlora-houseplant/checkpoint-35",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 35,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5204081632653061,
+      "eval_loss": 0.6893933415412903,
+      "eval_runtime": 2.0373,
+      "eval_samples_per_second": 48.103,
+      "eval_steps_per_second": 1.963,
+      "step": 7
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.5420740246772766,
+      "learning_rate": 4.032258064516129e-05,
+      "loss": 0.6869,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5306122448979592,
+      "eval_loss": 0.6856390237808228,
+      "eval_runtime": 2.0142,
+      "eval_samples_per_second": 48.654,
+      "eval_steps_per_second": 1.986,
+      "step": 14
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.44206592440605164,
+      "learning_rate": 2.4193548387096777e-05,
+      "loss": 0.6797,
+      "step": 20
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5612244897959183,
+      "eval_loss": 0.6827691793441772,
+      "eval_runtime": 2.3921,
+      "eval_samples_per_second": 40.969,
+      "eval_steps_per_second": 1.672,
+      "step": 21
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5612244897959183,
+      "eval_loss": 0.6809878945350647,
+      "eval_runtime": 2.0128,
+      "eval_samples_per_second": 48.688,
+      "eval_steps_per_second": 1.987,
+      "step": 28
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.47674253582954407,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 0.6808,
+      "step": 30
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5714285714285714,
+      "eval_loss": 0.6803476810455322,
+      "eval_runtime": 1.9919,
+      "eval_samples_per_second": 49.198,
+      "eval_steps_per_second": 2.008,
+      "step": 35
+    },
+    {
+      "epoch": 5.0,
+      "step": 35,
+      "total_flos": 3.405838778276659e+17,
+      "train_loss": 0.6811685698372977,
+      "train_runtime": 162.9509,
+      "train_samples_per_second": 26.787,
+      "train_steps_per_second": 0.215
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 35,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.405838778276659e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7f8a025fdf080b905c81a3c18cb532bb04175d55bf1dfe38dd734373dcb71e
+oid sha256:7a2816daebe68496c7c177291686be8bff9b425ea88a7c6c51e2422304bdb6f5
 size 5304