Initial commit of fine-tuned model

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "abdullahsn/AraT5-ImprovedTranslatedWikiSQL",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 110080
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae6f1bafbfb6a95b400f7598d5ec1531a758d9226aee1834dbdb0d5896239bd
+size 1131116304

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c97702e86c60d0e4e505a48783d49c50456f5a9f0bd8b941856a3868c8a04d3
+size 2262402234

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49ae831510bdaac020f2c0159ecfdc7b115a2bd6d506fa32c614b0dfc88bc43
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd1d926228d99bbb80fac68aaf8a85b3fc4cba141fa8929fac85cbdce527141
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7ae4407451bf02b459edec774d0539a06615005dd34d5c85c5c06765ff1606
+size 2435308

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "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": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": 8.105906632790287,
+  "best_model_checkpoint": "/opt/dlami/nvme/AAA/checkpoint-1986",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1986,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.04436992481350899,
+      "learning_rate": 0.0006666666666666668,
+      "loss": 0.6502,
+      "step": 331
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 4.361617844387214,
+      "eval_loss": 0.007830865681171417,
+      "eval_runtime": 121.9513,
+      "eval_samples_per_second": 10.849,
+      "eval_steps_per_second": 0.681,
+      "step": 331
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.038081083446741104,
+      "learning_rate": 0.0005333333333333334,
+      "loss": 0.0071,
+      "step": 662
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 7.843100767141589,
+      "eval_loss": 0.0018343101255595684,
+      "eval_runtime": 122.0918,
+      "eval_samples_per_second": 10.836,
+      "eval_steps_per_second": 0.68,
+      "step": 662
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.019110124558210373,
+      "learning_rate": 0.00045714285714285713,
+      "loss": 0.0027,
+      "step": 993
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 8.040733224615437,
+      "eval_loss": 0.0016475560842081904,
+      "eval_runtime": 122.063,
+      "eval_samples_per_second": 10.839,
+      "eval_steps_per_second": 0.68,
+      "step": 993
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.006580352783203125,
+      "learning_rate": 0.00034285714285714285,
+      "loss": 0.0016,
+      "step": 1324
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 8.046469246678804,
+      "eval_loss": 0.0006783127901144326,
+      "eval_runtime": 122.0945,
+      "eval_samples_per_second": 10.836,
+      "eval_steps_per_second": 0.68,
+      "step": 1324
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.0007480424828827381,
+      "learning_rate": 0.00022857142857142857,
+      "loss": 0.001,
+      "step": 1655
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 8.065670810538343,
+      "eval_loss": 0.0004619210085365921,
+      "eval_runtime": 122.0219,
+      "eval_samples_per_second": 10.842,
+      "eval_steps_per_second": 0.68,
+      "step": 1655
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.00835416093468666,
+      "learning_rate": 0.00011428571428571428,
+      "loss": 0.0007,
+      "step": 1986
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 8.105906632790287,
+      "eval_loss": 0.00035273091634735465,
+      "eval_runtime": 121.9325,
+      "eval_samples_per_second": 10.85,
+      "eval_steps_per_second": 0.681,
+      "step": 1986
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2317,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.933197719371776e+16,
+  "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 sha256:3cb05baa837520c882fa6b8297455b743019db6da1f36036b9c8a2649087e12c
+size 5240