Upload 11 files

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "riotu-lab/ArabianGPT-03B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": null,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 64000,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "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": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 64002
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 64000,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31225c59d89cd340eef9cf7047074e2a8cb3dbbeb0662e1da4418b71b0ac2ca4
+size 1475622400

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f4288eadb9d3f91da8ec325037b8b81a7134d40bcdf17721953c74189a0d6a
+size 2951355589

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b369becd2c870a929b5405d3012ecc433fff37815691cfbf40b24e2353863e90
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e3de12ab10485e3fdade09dbab9f4ceb36de09837ddef27a0872e8c88e7c56
+size 627

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<EOS>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<EOS>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64000": {
+      "content": "<EOS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64001": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<EOS>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<EOS>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 2120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.72,
+      "learning_rate": 5.4439794766146746e-05,
+      "loss": 0.8136,
+      "step": 1000
+    },
+    {
+      "epoch": 9.43,
+      "learning_rate": 7.884711026201585e-07,
+      "loss": 0.2175,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 2120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 10000,
+  "total_flos": 7918421362409472.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c758af5c4c27048587d3aa1c4870d8ac6e99c1843bc3e78562480819ef0ad069
+size 4283