upload 11 files

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "riotu-lab/ArabianGPT-08B-V2",
+  "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": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1280,
+  "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": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 64002
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 64000,
+  "transformers_version": "4.40.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd0dea1b21b5323ac0e90d62a6c9741f0587284727531cfe3fc4848fdfc2508
+size 3167851048

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a7ed32b0cddbb11196891ddbc1c779548c7ef53dff27ef0eef3fd60f0b8e29
+size 6335983849

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca249c1df8d53ec61d6cccea95e8fcc9661000285942a47bb090e73e6d10da70
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b465cfcf298c7fe2e3c05f34cea308cc6305acad8a9561ce9f002e5a0969fa
+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 +1,210 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9582557247726524,
+  "eval_steps": 500,
+  "global_step": 27000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10956502684343157,
+      "grad_norm": 236960.390625,
+      "learning_rate": 1e-05,
+      "loss": 3.4547,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21913005368686314,
+      "grad_norm": 229318.0,
+      "learning_rate": 9.964588530796566e-06,
+      "loss": 3.3466,
+      "step": 2000
+    },
+    {
+      "epoch": 0.3286950805302947,
+      "grad_norm": 262596.53125,
+      "learning_rate": 9.858855712046716e-06,
+      "loss": 3.296,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4382601073737263,
+      "grad_norm": 236514.921875,
+      "learning_rate": 9.684299205532435e-06,
+      "loss": 3.2622,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5478251342171578,
+      "grad_norm": 218812.8125,
+      "learning_rate": 9.443391532195597e-06,
+      "loss": 3.2396,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6573901610605895,
+      "grad_norm": 215752.28125,
+      "learning_rate": 9.1395450498983e-06,
+      "loss": 3.2215,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7669551879040211,
+      "grad_norm": 226011.546875,
+      "learning_rate": 8.777063618780717e-06,
+      "loss": 3.2002,
+      "step": 7000
+    },
+    {
+      "epoch": 0.8765202147474526,
+      "grad_norm": 231935.09375,
+      "learning_rate": 8.361081638856787e-06,
+      "loss": 3.1887,
+      "step": 8000
+    },
+    {
+      "epoch": 0.9860852415908842,
+      "grad_norm": 234562.9375,
+      "learning_rate": 7.897491323355013e-06,
+      "loss": 3.1683,
+      "step": 9000
+    },
+    {
+      "epoch": 1.0956502684343157,
+      "grad_norm": 250418.53125,
+      "learning_rate": 7.392859237947555e-06,
+      "loss": 3.0454,
+      "step": 10000
+    },
+    {
+      "epoch": 1.2052152952777473,
+      "grad_norm": 235960.84375,
+      "learning_rate": 6.8543332880550015e-06,
+      "loss": 3.0308,
+      "step": 11000
+    },
+    {
+      "epoch": 1.314780322121179,
+      "grad_norm": 226152.703125,
+      "learning_rate": 6.289541471713303e-06,
+      "loss": 3.0182,
+      "step": 12000
+    },
+    {
+      "epoch": 1.4243453489646105,
+      "grad_norm": 241202.96875,
+      "learning_rate": 5.706483832126753e-06,
+      "loss": 3.0191,
+      "step": 13000
+    },
+    {
+      "epoch": 1.5339103758080421,
+      "grad_norm": 258991.890625,
+      "learning_rate": 5.113419140354569e-06,
+      "loss": 3.014,
+      "step": 14000
+    },
+    {
+      "epoch": 1.6434754026514735,
+      "grad_norm": 226265.984375,
+      "learning_rate": 4.518747913224088e-06,
+      "loss": 3.0095,
+      "step": 15000
+    },
+    {
+      "epoch": 1.7530404294949054,
+      "grad_norm": 217093.515625,
+      "learning_rate": 3.930893423473588e-06,
+      "loss": 3.0173,
+      "step": 16000
+    },
+    {
+      "epoch": 1.8626054563383367,
+      "grad_norm": 240746.34375,
+      "learning_rate": 3.3581823875670306e-06,
+      "loss": 3.0111,
+      "step": 17000
+    },
+    {
+      "epoch": 1.9721704831817684,
+      "grad_norm": 248730.8125,
+      "learning_rate": 2.808727021188604e-06,
+      "loss": 3.0062,
+      "step": 18000
+    },
+    {
+      "epoch": 2.0817355100252,
+      "grad_norm": 236184.765625,
+      "learning_rate": 2.29031013305238e-06,
+      "loss": 2.9252,
+      "step": 19000
+    },
+    {
+      "epoch": 2.1913005368686314,
+      "grad_norm": 229251.96875,
+      "learning_rate": 1.8102748846258644e-06,
+      "loss": 2.9005,
+      "step": 20000
+    },
+    {
+      "epoch": 2.300865563712063,
+      "grad_norm": 237543.8125,
+      "learning_rate": 1.375420777275549e-06,
+      "loss": 2.9009,
+      "step": 21000
+    },
+    {
+      "epoch": 2.4104305905554946,
+      "grad_norm": 218966.203125,
+      "learning_rate": 9.91907340133601e-07,
+      "loss": 2.8984,
+      "step": 22000
+    },
+    {
+      "epoch": 2.5199956173989264,
+      "grad_norm": 241322.34375,
+      "learning_rate": 6.651668829074043e-07,
+      "loss": 2.9062,
+      "step": 23000
+    },
+    {
+      "epoch": 2.629560644242358,
+      "grad_norm": 225327.21875,
+      "learning_rate": 3.9982754945239067e-07,
+      "loss": 2.9034,
+      "step": 24000
+    },
+    {
+      "epoch": 2.739125671085789,
+      "grad_norm": 235030.6875,
+      "learning_rate": 1.996477620226006e-07,
+      "loss": 2.9027,
+      "step": 25000
+    },
+    {
+      "epoch": 2.848690697929221,
+      "grad_norm": 220099.25,
+      "learning_rate": 6.746298476912328e-08,
+      "loss": 2.9065,
+      "step": 26000
+    },
+    {
+      "epoch": 2.9582557247726524,
+      "grad_norm": 241653.828125,
+      "learning_rate": 5.1455605595079894e-09,
+      "loss": 2.9021,
+      "step": 27000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 27381,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 1.0153803112261632e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b27f7a2c745bf748c91ba24a49eba1d9638f6856acdd3868d5c70a82641eea
+size 4539