Mithul27/GPT2-medium-fine-tuned

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: gpt2-medium
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

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": "4.41.2",
+  "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": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae31103acbf5c328fe56e8a0ae2e5ef0bd1f02f5db63e67c76e2e549c7b08a1
+size 1419322880

runs/Jun28_09-13-02_20bf414aaf2a/events.out.tfevents.1719565982.20bf414aaf2a.16191.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f19638c00711dc500c00aadf83f1ed0d4ef70acef601961a56788ce4d34217e
+size 5362

runs/Jun28_10-08-38_20bf414aaf2a/events.out.tfevents.1719569319.20bf414aaf2a.16191.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd1464ca9ecd7eb28149ce71751be160715e6dd2c384f53c75d4cf4f2a79c7a
+size 5362

runs/Jun28_12-34-40_20bf414aaf2a/events.out.tfevents.1719578081.20bf414aaf2a.16191.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11690c89e32bedeb09112f3881c117878b8e590b4337105f91bc2be26a98db7b
+size 5368

runs/Jun28_13-18-18_20bf414aaf2a/events.out.tfevents.1719580698.20bf414aaf2a.16191.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:272044c41519559ce9cb4e8ccb88fd0424e259587d9b7b8ef7e81a268ff7a587
+size 4184

runs/Jun28_13-21-33_20bf414aaf2a/events.out.tfevents.1719580894.20bf414aaf2a.84782.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d0a406916c530705ea908e0cdbb95c20ac95f67603b0e0c1237efe1b20c708
+size 5428

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ec3fb53b5583bfb949cbe203a0e4ae37d0ba5047061dee4395b08cd5ffc9e66
+size 5048