End of training

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: ''
+license: apache-2.0
+base_model: distilgpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -12,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # EsperBERTo
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
 
 ## Model description
 
@@ -32,12 +33,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 32
+- train_batch_size: 8
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 5
 
 ### Training results
 

config.json

@@ -1,24 +1,46 @@
 {
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
   "architectures": [
-    "BertLMHeadModel"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 514,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "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": "4.32.0",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 52000
+  "vocab_size": 50257
 }

generation_config.json

@@ -1,5 +1,6 @@
 {
   "_from_model_config": true,
-  "pad_token_id": 0,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "transformers_version": "4.32.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e4f8b85e068d38652208b445837735bfbda1e6b7bd920051e80d7412200b77
-size 334056757
+oid sha256:0db9652ebcf7fdf6b01eb721b48b22de1e1618be1db5421c7a76914e47124b15
+size 327674773

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb480b2a72b8e22d82d2851f24930a6ad8dcd172123e97c9a3b79b9ce423802
+oid sha256:cb6b93a138516f924e451b7ff91d60c6a23e3d0b4b4c7fc27d0e46533ce46b59
 size 4091