Training in progress, epoch 1

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "aubmindlab/aragpt2-large",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "AraGPT2LMHeadModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attn_pdrop": 0.1,
+  "auto_map": {
+    "AutoConfig": "aubmindlab/aragpt2-large--configuration_aragpt2.AraGPT2Config",
+    "AutoModel": "aubmindlab/aragpt2-large--modeling_aragpt2.AraGPT2Model",
+    "AutoModelForCausalLM": "aubmindlab/aragpt2-large--modeling_aragpt2.AraGPT2LMHeadModel"
+  },
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "initializer_range": 0.014142135623731,
+  "intermediate_size": 5120,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "aragpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 5,
+      "repetition_penalty": 3.0,
+      "top_p": 0.95
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 64000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370388e15cea77a093c5f12f91d39cdb6cdf64bdbfa33ced0a41638a1f17f452
+size 3166530072

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 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "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:e95dc191bcbd4c8e4ddc8bf159d73dec68af766d97a1276935a60707a3359609
+size 5368