Upload 10 files

app.py

@@ -0,0 +1,48 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import streamlit as st
+import streamlit_antd_components as sac
+
+st.set_page_config(layout="wide")
+
+
+@st.cache_resource
+class AppModel: 
+    def __init__(self):
+        self.tokenizer = AutoTokenizer.from_pretrained("gpt2-medium")
+        self.tokenizer.pad_token = self.tokenizer.eos_token
+        self.model = AutoModelForCausalLM.from_pretrained("./output/model/checkpoint-1000/")
+
+    def generate_plot(self, prompt: str):
+        inputs = self.tokenizer(prompt, return_tensors="pt").to("cpu")
+        outputs = self.model.generate(
+            inputs.input_ids,
+            max_new_tokens=100,
+            do_sample=True,
+            top_k=5,
+            top_p=0.35,
+            temperature= 0.2,
+            num_return_sequences= 1,
+        )
+        output_string = self.tokenizer.batch_decode(outputs)
+        return output_string
+
+model = AppModel()
+
+st.title("Welcome to the GPT Olympics generator")
+prompt = st.text_area("Enter the beginning of your plot...")
+clicked = st.button("Generate my movie")
+
+sac.divider(label='label', icon='house', align='center', size='md', color='yellow')
+
+if clicked:
+    generated_plot = model.generate_plot(prompt)[0]
+    chat_message = st.chat_message("assistant")
+    chat_message.markdown(generated_plot)
+
+with open('./style.css') as f:
+    css = f.read()
+    st.markdown(f'<style>{css}</style>', unsafe_allow_html=True)
+
+
+
+

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.39.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d407ab13e27f9da55942399863fc413394ba277e2b1bf30326463059b88335fd
+size 1419322880

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e3881f2ece43162ab2569dc81775a14350c423cc46233e67bfa0fd6a094914
+size 2838821114

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da1db5c227c2000e391e1d225e13a38eda71746be2164bab198c44af9ae0882b
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74b67834aacf6f555d713cdb4b053a4620bd2b12a56cc8d1be6b42a81da28112
+size 1064

style.css

@@ -0,0 +1,75 @@
+section[data-testid='stSidebar'] {
+    background-color: #d81e1e;
+    flex-shrink: unset !important;
+}
+
+@media(hover:hover) and (min-width: 600px) and (max-width: 769px){
+
+    header[data-testid="stHeader"] {
+        display:none;
+    }
+
+    section[data-testid='stSidebar'] {
+        height: 100%;
+        min-width:95px !important;
+        width: 95px !important;
+        margin-left: 305px;
+        position: relative;
+        z-index: 1;
+        top: 0;
+        left: 0;
+        background-color: #111;
+        overflow-x: hidden;
+        transition: 0.5s ease;
+        padding-top: 60px;
+        white-space: nowrap;
+    }
+
+    section[data-testid='stSidebar']:hover{
+        min-width: 330px !important;
+        }
+
+    button[kind="header"] {
+        display: none;
+    }
+
+    div[data-testid="collapsedControl"]{
+        display: none;
+    }
+
+}
+
+@media(hover: hover) and (min-width: 769px){
+
+    header[data-testid="stHeader"] {
+        display:none;
+    }
+
+    section[data-testid='stSidebar'] {
+        height: 100%;
+        min-width:95px !important;
+        width: 95px !important;
+        transform:translateX(0px);
+        position: relative;
+        z-index: 1;
+        top: 0;
+        left: 0;
+        background-color: #111;
+        overflow-x: hidden;
+        transition: 0.5s ease;
+        padding-top: 60px;
+        white-space: nowrap;
+    }
+
+    section[data-testid='stSidebar']:hover{
+        min-width: 330px !important;
+        }
+
+    button[kind="header"] {
+        display: none;
+    }
+
+    div[data-testid="collapsedControl"]{
+        display: none;
+    }
+}

trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4529900550842285,
+      "eval_runtime": 3.9942,
+      "eval_samples_per_second": 50.073,
+      "eval_steps_per_second": 6.259,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.183900833129883,
+      "eval_runtime": 4.5703,
+      "eval_samples_per_second": 43.761,
+      "eval_steps_per_second": 5.47,
+      "step": 200
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.071335554122925,
+      "eval_runtime": 3.8996,
+      "eval_samples_per_second": 51.287,
+      "eval_steps_per_second": 6.411,
+      "step": 300
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.011983871459961,
+      "eval_runtime": 6.9041,
+      "eval_samples_per_second": 28.968,
+      "eval_steps_per_second": 3.621,
+      "step": 400
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 28.10818099975586,
+      "learning_rate": 1e-05,
+      "loss": 2.123,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.9926012754440308,
+      "eval_runtime": 10.0553,
+      "eval_samples_per_second": 19.89,
+      "eval_steps_per_second": 2.486,
+      "step": 500
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.9686007499694824,
+      "eval_runtime": 4.4521,
+      "eval_samples_per_second": 44.922,
+      "eval_steps_per_second": 5.615,
+      "step": 600
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.9791488647460938,
+      "eval_runtime": 2.9406,
+      "eval_samples_per_second": 68.014,
+      "eval_steps_per_second": 8.502,
+      "step": 700
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.9794409275054932,
+      "eval_runtime": 2.4017,
+      "eval_samples_per_second": 83.276,
+      "eval_steps_per_second": 10.409,
+      "step": 800
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.0054731369018555,
+      "eval_runtime": 9.7036,
+      "eval_samples_per_second": 20.611,
+      "eval_steps_per_second": 2.576,
+      "step": 900
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 27.559810638427734,
+      "learning_rate": 0.0,
+      "loss": 1.2718,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 248093683974144.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}