Add None checkpoint

README.md

@@ -0,0 +1,57 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: distilgpt2-ift
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# distilgpt2-ift
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 44.2744
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 12
+- eval_batch_size: 12
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- training_steps: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 41.4703       | 0.0   | 1    | 44.2744         |
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.12.0
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|assistant|>": 50259,
+  "<|end|>": 50260,
+  "<|system|>": 50257,
+  "<|user|>": 50258
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 0.0,
+    "eval_loss": 44.2744026184082,
+    "eval_runtime": 2.6297,
+    "eval_samples": 437,
+    "eval_samples_per_second": 166.177,
+    "eval_steps_per_second": 14.07,
+    "perplexity": 1.6909421376838556e+19,
+    "train_loss": 41.470333099365234,
+    "train_runtime": 8.8744,
+    "train_samples": 4005,
+    "train_samples_per_second": 1.352,
+    "train_steps_per_second": 0.113
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "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": "4.28.1",
+  "use_cache": false,
+  "vocab_size": 50261
+}

dialogue_template.json

@@ -0,0 +1,12 @@
+{
+  "system": "",
+  "messages": null,
+  "system_token": "<|system|>",
+  "system_format": "standard",
+  "user_token": "<|user|>",
+  "assistant_token": "<|assistant|>",
+  "end_token": "<|end|>",
+  "mid_str": "\n",
+  "end_str": "\n",
+  "extra_end_text": ""
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.0,
+    "eval_loss": 44.2744026184082,
+    "eval_runtime": 2.6297,
+    "eval_samples": 437,
+    "eval_samples_per_second": 166.177,
+    "eval_steps_per_second": 14.07,
+    "perplexity": 1.6909421376838556e+19
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.1"
+}

handler.py

@@ -0,0 +1,49 @@
+from typing import Any, Dict
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from peft import PeftConfig, PeftModel
+
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        # load model and processor from path
+        self.tokenizer = AutoTokenizer.from_pretrained(path)
+        try:
+            config = PeftConfig.from_pretrained(path)
+            model = AutoModelForCausalLM.from_pretrained(
+                config.base_model_name_or_path,
+                return_dict=True,
+                load_in_8bit=True,
+                device_map="auto",
+                torch_dtype=torch.float16,
+                trust_remote_code=True,
+            )
+            model.resize_token_embeddings(len(self.tokenizer))
+            model = PeftModel.from_pretrained(model, path)
+        except Exception:
+            model = AutoModelForCausalLM.from_pretrained(
+                path, device_map="auto", load_in_8bit=True, torch_dtype=torch.float16, trust_remote_code=True
+            )
+        self.model = model
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+
+    def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
+        # process input
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+
+        # preprocess
+        inputs = self.tokenizer(inputs, return_tensors="pt").to(self.device)
+
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            outputs = self.model.generate(**inputs, **parameters)
+        else:
+            outputs = self.model.generate(**inputs)
+
+        # postprocess the prediction
+        prediction = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+        return [{"generated_text": prediction}]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848535d0c25ef70e64ba3f99d2245d3c29a979f3bd1091dbfb4890d4f6833f67
+size 333982457

requirements.txt

@@ -0,0 +1,5 @@
+transformers==4.28.1
+accelerate>=0.16.0
+bitsandbytes
+sentencepiece
+git+https://github.com/huggingface/peft.git@632997d1fb776c3cf05d8c2537ac9a98a7ce9435

runs/May30_12-16-44_ip-26-0-150-12/1685449023.6511703/events.out.tfevents.1685449023.ip-26-0-150-12.3309750.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffdc263be7cc38468995e31f399977941fa03e60a96b930d462cf6934846ebe
+size 6282

runs/May30_12-16-44_ip-26-0-150-12/events.out.tfevents.1685449023.ip-26-0-150-12.3309750.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c39bc659b4bb330ed78df136c596d1152904b26f01bd51f17070a33aae8b47
+size 5391

runs/May30_12-16-44_ip-26-0-150-12/events.out.tfevents.1685449035.ip-26-0-150-12.3309750.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc8b768f35e3b2a5fe2663f574e03c376b1f6479850b118e17d5ff834052dfc1
+size 354

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|end|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "train_loss": 41.470333099365234,
+    "train_runtime": 8.8744,
+    "train_samples": 4005,
+    "train_samples_per_second": 1.352,
+    "train_steps_per_second": 0.113
+}

trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0029940119760479044,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 41.4703,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": 44.2744026184082,
+      "eval_runtime": 2.632,
+      "eval_samples_per_second": 166.03,
+      "eval_steps_per_second": 14.057,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "step": 1,
+      "total_flos": 3135561007104.0,
+      "train_loss": 41.470333099365234,
+      "train_runtime": 8.8744,
+      "train_samples_per_second": 1.352,
+      "train_steps_per_second": 0.113
+    }
+  ],
+  "max_steps": 1,
+  "num_train_epochs": 1,
+  "total_flos": 3135561007104.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f90f76c79c744e69aec7779d113507e23a9938df4c4b4680312f5ec4444f700
+size 3899