Training in progress, step 2475

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilgpt2
+tags:
+- generated_from_trainer
+model-index:
+- name: distily_dummy
+  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. -->
+
+# distily_dummy
+
+This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6572
+
+## 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: 0.0002
+- 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: polynomial
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0     | 0    | 20.6500         |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.3.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilbert/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
+    }
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "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": "4.44.2"
+}

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=False, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725290500.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29025fd83e3f8bc2a5905c37c3cae8dc757f269064faed49233b2b358cc26e56
+size 46694

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=False, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725290822.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7237857399c721663bca2f18acc9aef76b23dae6fab2aa75a8e3828eaa1969ac
+size 5971

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=False, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725290981.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4eeb02084f4c86f214aaaf3edda386047207214f84af35f45c6578d0ab7023
+size 5518

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=True, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725290002.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8135887b078d6a913d4a605c63d2bbc87febb70438ccc675970b29ca88cd6e03
+size 98646

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=True, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725290452.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8632cb3335794cdcff2da516a92559fd1baa6aed1d7494deb441c61380cede9e
+size 520

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=True, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725290758.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0dce8f220367362343ab71f2fb8d55fee38c7665b87e0c37d482e6438048b09
+size 5969

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=True, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725290918.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe8f84d6572ab6641a44b7cb5d5df6e04a5414b652bcb3e91a0b64446fd7bf2
+size 5969

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=True, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725291053.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6188a98981f3e527d2eeba4b2cf6dd507e7a63d092cc88661b52f5c5c3d54d93
+size 49692

logs/attn_projector=orthogonal, attn_weight=5, extra_grad_stats=True, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725291337.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8b2bf09cd80b2e901425b026e212f73c7caae63936c529b75478c367769e88
+size 98666

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725284824.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4289bce3286b23794b522700c8a5900c0e129bc0dc1f98b5480ce9b7eb158a1
+size 5922

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725285131.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84f44a9d57957aa238f19a891ae90754cea49c31c7ecb28579d317ae7fd104d
+size 5922

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725286599.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1996c14401b93db15dc94fc5d1f5f8b87e5425da6925aa066c1c59d002c746
+size 5922

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725286753.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e80b9538c48078b87ef3fe5334b20e68e39422ad1200c7afe47f3d9efb7d0d7
+size 5922

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725288412.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9909db0d95081f9a5ee4274d5e552a7708314fc3ddfb6bc940cba2734dc03b12
+size 5922

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725288577.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566de0231b4048babcadc7ed3847708c0bbb123d18e229050535b59740f16ab0
+size 5922

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725288708.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bebf9fe4a6f9f22dcf7d658293058b7238a019706130a1a2884325881cd0371
+size 5922

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725288888.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d245f7ff6c1c656b99125c824427e8394495f7ba063419cc0befa55e4d41f8d4
+size 52398

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725289188.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4c8419a2d7cf231f3ac75d117b37c7878ab92c24653a2e417496d27c295ebe
+size 5923

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725289304.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ddd48f1bcdf8355912eed6fd1224c02a16365ce6972e339ca46c2993ee96996
+size 5923

logs/attn_projector=orthogonal, attn_weight=5, learning_rate=0.0002, per_device_train_batch_size=4, warmup_ratio=0/events.out.tfevents.1725289875.261a4d6fb516

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f31872a2cdbe975f8a9b525f8d07102ae51de876c5ac34d74b82de5581e490
+size 5923

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56dd2b32c86895edbe4cea2c79402f5377a83b774ffab9998370d291618d7bb9
+size 163832792

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1e09d16a48f446c465fdc06c6740b6d2c30025de598512ffb059d9f6320a9e
+size 5496