Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: mak109/distilgpt2-finetuned-lyrics
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# mak109/distilgpt2-finetuned-lyrics
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 3.2803
+- Validation Loss: 3.1504
+- Epoch: 0
+
+## 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 3.2803     | 3.1504          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.18.0
+- TensorFlow 2.6.3
+- Datasets 2.1.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,45 @@
+{
+  "_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
+    }
+  },
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

logs/train/events.out.tfevents.1651592905.93dc2b7f2684.33.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a2b694fec37aede6593ae9776cc93e3451e977085fb48e76817138dab0913f
+size 1220610

logs/train/events.out.tfevents.1651592907.93dc2b7f2684.profile-empty

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7203146736e38b676157a285e9d8b3baa933f516b2053da4781c6a7e212052e5
+size 40

logs/train/plugins/profile/2022_05_03_15_48_27/93dc2b7f2684.input_pipeline.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067ca11f5801195df8515fb6709489d9e398fe2bea9efe521eda7676473b9518
+size 3051

logs/train/plugins/profile/2022_05_03_15_48_27/93dc2b7f2684.kernel_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa87cefd08d334688f01c146449dee1ad7c2c8cb747117b24037a7fd4acd84c
+size 293679

logs/train/plugins/profile/2022_05_03_15_48_27/93dc2b7f2684.memory_profile.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f87d9debc614d4e0fff69cefda97df29be953a22791238446b9c83ec17f8f67
+size 34281

logs/train/plugins/profile/2022_05_03_15_48_27/93dc2b7f2684.overview_page.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668d9d6f60cec12b5193d667260bb7cb009caa93ff23bcec8044da9ed8133db4
+size 5754

logs/train/plugins/profile/2022_05_03_15_48_27/93dc2b7f2684.tensorflow_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6995016cb9ce592ad26f1825dcf3de738db31372da82876c25992b28ea885b2f
+size 157281

logs/train/plugins/profile/2022_05_03_15_48_27/93dc2b7f2684.trace.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb8ef9d2171011fdbf6aa4311de42fe086770b0a0801dccc72aaea51e4a88222
+size 146974

logs/train/plugins/profile/2022_05_03_15_48_27/93dc2b7f2684.xplane.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d85a47bd36d8ccdc946da33eb431bfebcc04ee03d381090d356f113b001ead
+size 1010756

logs/validation/events.out.tfevents.1651594582.93dc2b7f2684.33.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ff39a9b2653e135598ca2d5723d122c4cd077f571202bc5e28f2016c5bc2514
+size 194

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1687bc55ab31891c6862db4c87b24c55e8efa5092d7e8ef78b0c3428b93256
+size 327744824

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}