Upload 10 files

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f69b09542a6672e7d1b466def7ade25f5be3d619c0d9119b4b0c89ccf707e35
-size 3558888
+oid sha256:73c83fcec63a448c775bfe15252caa4c8c93ce997ee107bb3897e9bdd650fec3
+size 1389456

app.py

@@ -0,0 +1,21 @@
+import torch
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+from peft import PeftModel, LoraConfig
+import gradio as gr
+
+# Load base model
+base_model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")
+tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")
+
+# Load LoRA adapter (from local folder containing safetensor + json)
+adapter_path = "/content/" 
+model = PeftModel.from_pretrained(base_model, adapter_path)
+model.eval()
+
+# Gradio interface
+def generate(prompt): 
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=100)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+gr.Interface(fn=generate, inputs="text", outputs="text", title="FLAN-T5 StackOverflow Assistant").launch()

events.out.tfevents.1754682715.d9342d05aac2.3374.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1b9c94ee60d588e2b489d1ebc65fc4d0a4903961cd7d6887fe02195047af21
+size 7646

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81cc25b94b55bf811c5e168856e878f3844e598bc82e92e14e0e200212e0010
+size 2833402

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f3d877395a79fb2e76ddf3aed2267c58e0143309e34b21fdad618a8448934b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4120a9b57085876b0b849321be75f59a03135f5c9b6c7705fc3459e2b52cf36
+size 1064

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_global_step": 500,
+  "best_metric": 2.775390625,
+  "best_model_checkpoint": "./stackoverflow_flan_finetune/checkpoint-500",
+  "epoch": 0.14819205690574985,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02963841138114997,
+      "grad_norm": 0.5776488780975342,
+      "learning_rate": 0.0004853289863663308,
+      "loss": 9.4912,
+      "step": 100
+    },
+    {
+      "epoch": 0.02963841138114997,
+      "eval_loss": 3.810546875,
+      "eval_runtime": 26.2211,
+      "eval_samples_per_second": 57.168,
+      "eval_steps_per_second": 7.17,
+      "step": 100
+    },
+    {
+      "epoch": 0.05927682276229994,
+      "grad_norm": 0.5113403797149658,
+      "learning_rate": 0.0004705097806757558,
+      "loss": 3.9372,
+      "step": 200
+    },
+    {
+      "epoch": 0.05927682276229994,
+      "eval_loss": 3.38671875,
+      "eval_runtime": 26.0016,
+      "eval_samples_per_second": 57.65,
+      "eval_steps_per_second": 7.23,
+      "step": 200
+    },
+    {
+      "epoch": 0.08891523414344991,
+      "grad_norm": 1.3626296520233154,
+      "learning_rate": 0.0004556905749851808,
+      "loss": 3.5486,
+      "step": 300
+    },
+    {
+      "epoch": 0.08891523414344991,
+      "eval_loss": 3.048828125,
+      "eval_runtime": 27.2076,
+      "eval_samples_per_second": 55.095,
+      "eval_steps_per_second": 6.91,
+      "step": 300
+    },
+    {
+      "epoch": 0.11855364552459988,
+      "grad_norm": 0.4870101511478424,
+      "learning_rate": 0.0004408713692946058,
+      "loss": 3.2785,
+      "step": 400
+    },
+    {
+      "epoch": 0.11855364552459988,
+      "eval_loss": 2.828125,
+      "eval_runtime": 26.0791,
+      "eval_samples_per_second": 57.479,
+      "eval_steps_per_second": 7.209,
+      "step": 400
+    },
+    {
+      "epoch": 0.14819205690574985,
+      "grad_norm": 1.628702163696289,
+      "learning_rate": 0.00042605216360403083,
+      "loss": 3.1755,
+      "step": 500
+    },
+    {
+      "epoch": 0.14819205690574985,
+      "eval_loss": 2.775390625,
+      "eval_runtime": 26.1328,
+      "eval_samples_per_second": 57.361,
+      "eval_steps_per_second": 7.194,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3374,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 1,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 373894938624000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}