Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "ccore/opt-350-smart-test",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

README.md

@@ -1,3 +1,58 @@
 ---
-license: mit
+base_model: ./core-350
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: core-350
+  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. -->
+
+# core-350
+
+This model is a fine-tuned version of [./core-350](https://huggingface.co/./core-350) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8128
+- Accuracy: 0.8237
+
+## 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- num_epochs: 10.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 9.96,
+    "eval_accuracy": 0.8237438771090703,
+    "eval_loss": 0.8127619624137878,
+    "eval_runtime": 26.2028,
+    "eval_samples": 729,
+    "eval_samples_per_second": 27.821,
+    "eval_steps_per_second": 3.511,
+    "perplexity": 2.254125205956005,
+    "train_loss": 0.46730201305062685,
+    "train_runtime": 11414.299,
+    "train_samples": 13879,
+    "train_samples_per_second": 12.159,
+    "train_steps_per_second": 0.189
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "./core-350",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 9.96,
+    "eval_accuracy": 0.8237438771090703,
+    "eval_loss": 0.8127619624137878,
+    "eval_runtime": 26.2028,
+    "eval_samples": 729,
+    "eval_samples_per_second": 27.821,
+    "eval_steps_per_second": 3.511,
+    "perplexity": 2.254125205956005
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.35.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d54edfc342cc4eeb8a79794dfee69e6bce3ad1ed5c2bd465d45dc2d3fd3edc3
+size 1324917722

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.96,
+    "train_loss": 0.46730201305062685,
+    "train_runtime": 11414.299,
+    "train_samples": 13879,
+    "train_samples_per_second": 12.159,
+    "train_steps_per_second": 0.189
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4ad8dd01643d9e5baa36c717e2ce73bd1754504e576e5b4b4ac76fcd1d2000
+size 4472