End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: bert-base-uncased
+license: mit
+base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -14,14 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # checkpoints
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.0131
-- eval_runtime: 1367.6796
-- eval_samples_per_second: 139.329
-- eval_steps_per_second: 17.416
-- epoch: 0.0420
-- step: 1000
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 
 ## Model description
 
@@ -40,17 +33,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 8
+- learning_rate: 5e-05
+- 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: linear
-- num_epochs: 3
+- num_epochs: 1
+
+### Training results
+
+
 
 ### Framework versions
 
 - Transformers 4.44.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.1.0
 - Tokenizers 0.19.1

config.json

@@ -1,26 +1,39 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
   "architectures": [
-    "BertForQuestionAnswering"
+    "GPT2LMHeadModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "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,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "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": "4.44.2",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "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"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53e497fedb85fde671da7e5e599a0b293bacb64e4b3b51a5e0f42693be540985
-size 435596088
+oid sha256:c9a5fb8843c4d4099f380bba150fc50a8f756bdb391817a824f129eee95f5b24
+size 497774208

runs/Oct31_15-26-38_9c0dc4be863c/events.out.tfevents.1730388405.9c0dc4be863c.615.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498a85b3989e0745092be3d33f10fed92e92b19e7f75d2d67542569ffcf4fb8b
+size 7082

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b5222615ba48b12e344b3c124b0193b1fbb209275052e8d2cc228b9d83dd17a
+oid sha256:4ee3b672d2d73d5d9f2fda314763267750f8446945c7af90c13d1d5fe8d570b4
 size 5240