End of training

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilgpt2
+tags:
+- generated_from_trainer
+datasets:
+- eli5_category
+model-index:
+- name: my_awesome_eli5_clm-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. -->
+
+# my_awesome_eli5_clm-model
+
+This model is a fine-tuned version of [distilbert/distilgpt2](https://huggingface.co/distilbert/distilgpt2) on the eli5_category dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.8240
+
+## 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-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.9547        | 1.0   | 1315 | 3.8307          |
+| 3.8542        | 2.0   | 2630 | 3.8240          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.1

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": "float32",
+  "transformers_version": "4.46.1",
+  "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": "4.46.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711b146075314e574fbbcba06c4a5040c4be6db1bd05d1f8b022dace00b32337
+size 327657928

runs/Nov02_20-59-03_default/events.out.tfevents.1730581144.default.649.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c819ae3a7f5ef0a76579469ad4bd1f3a3257022a99b8835474029aa2a55396d7
+size 6276

runs/Nov02_21-17-50_default/events.out.tfevents.1730582271.default.931.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2de0fcf32198b86f68c6b07aeb82f31cad4e92e2a79d657e744a51bc4ec78d0
+size 5581

runs/Nov02_21-20-09_default/events.out.tfevents.1730582410.default.931.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2dfd49276ffd01c869b6046604930f198bb0748d15316644dac9dd7df84c26b
+size 8802

runs/Nov02_22-00-33_default/events.out.tfevents.1730584833.default.931.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd707178317144b612600d3b4ea136805826cc201298947b300c8d84cad52dd8
+size 5397

runs/Nov02_22-00-51_default/events.out.tfevents.1730584851.default.931.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01739839dd0174c45bbaa65a94675ed25c3bf7c050a6ef5401c269589e0b1d3
+size 6723

runs/Nov02_22-15-48_default/events.out.tfevents.1730585749.default.1665.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8192125433c090f0993d44dc4a81fc80bfa6f51ea5a4eec6ab9af05dec2afe3e
+size 7360

runs/Nov02_22-15-48_default/events.out.tfevents.1730588486.default.1665.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a743d1d02598826173ac1b8cfc993853f9f77335ad58c3af436e29f6035d2a8
+size 359

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": false,
+  "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 sha256:3f20bebf8cf81acb37ec2af83529c809d4a66b3ee3f318ce8e637d01b1da959d
+size 5304