End of training

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+base_model: openai-community/gpt2-medium
+tags:
+- generated_from_trainer
+model-index:
+- name: redsolarsky
+  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. -->
+
+# redsolarsky
+
+This model is a fine-tuned version of [openai-community/gpt2-medium](https://huggingface.co/openai-community/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: 0.0001372
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 651907945
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.14.5
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "openai-community/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": 200,
+      "min_length": 100,
+      "temperature": 1.0,
+      "top_p": 0.95
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "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": "4.37.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9786cbce6f78b883f7c7f11daf02169e80d7f0a9192a22b97c2af6d1940d7d64
+size 1419322880

runs/Feb29_23-34-18_c97925fb259b/events.out.tfevents.1709249665.c97925fb259b.85.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65129b829047c5462d6fd9ac03af042d88025891f72a3312ce7c02020efbbcf5
+size 4681

runs/Feb29_23-48-37_c97925fb259b/events.out.tfevents.1709250526.c97925fb259b.213.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57699ab0264dc7499e6ff3afdd244d182ada65f3ade744585eb7bcc4f9f78d44
+size 5697

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9656c38895f21bbd46016d6c68ca940ee34e53daeb0c7fd24fbfd6c43a0809
+size 4728