gpt2_imdb_1000

README.md

@@ -0,0 +1,76 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: model
+  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. -->
+
+# model
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.5952
+
+## 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: 2e-06
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 10000
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 3.8102        | 0.14  | 500   | 3.6588          |
+| 3.7552        | 0.27  | 1000  | 3.6436          |
+| 3.7437        | 0.41  | 1500  | 3.6327          |
+| 3.7243        | 0.55  | 2000  | 3.6255          |
+| 3.7095        | 0.68  | 2500  | 3.6187          |
+| 3.6972        | 0.82  | 3000  | 3.6148          |
+| 3.6993        | 0.96  | 3500  | 3.6104          |
+| 3.6896        | 1.09  | 4000  | 3.6069          |
+| 3.6824        | 1.23  | 4500  | 3.6051          |
+| 3.674         | 1.37  | 5000  | 3.6024          |
+| 3.6823        | 1.5   | 5500  | 3.6015          |
+| 3.6823        | 1.64  | 6000  | 3.6002          |
+| 3.6687        | 1.78  | 6500  | 3.5988          |
+| 3.6759        | 1.92  | 7000  | 3.5974          |
+| 3.6735        | 2.05  | 7500  | 3.5968          |
+| 3.6571        | 2.19  | 8000  | 3.5961          |
+| 3.6575        | 2.33  | 8500  | 3.5959          |
+| 3.6757        | 2.46  | 9000  | 3.5955          |
+| 3.6749        | 2.6   | 9500  | 3.5952          |
+| 3.6662        | 2.74  | 10000 | 3.5952          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "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": "4.35.2",
+  "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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618aed5e22af937ea2f546931cc4b0c072fac4f7948b0c0ed6b89302b1ff6eab
+size 497774208

runs/Dec09_04-34-16_a514acb7aae8/events.out.tfevents.1702096463.a514acb7aae8.638.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03db3536dda256918acc66eefa0d38b5d05508e04fcf306682a5e7edba4c7b3a
+size 13357

runs/Dec09_04-34-16_a514acb7aae8/events.out.tfevents.1702105881.a514acb7aae8.638.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd02762be1ddb11213e22fef3cc00030abf00cbb3f5d8fb86264aeadb431c35d
+size 359

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e61872004f12a6dc7fca46e7668ecff8b67e4adda104edac4e6d0ddf4da6a0
+size 4536