Upload folder using huggingface_hub

checkpoint-14000/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "aubmindlab/bert-large-arabertv2",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

checkpoint-14000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2b9a7dab83312f9426b1455202bbe29d96e42b92369ed5dee2389d0aa684fc8
+size 2956144601

checkpoint-14000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d48e871d9a1c8e88df51e48b56d93647b24ad0bb638b41a720b69d3c92ae869
+size 1478119979

checkpoint-14000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08cfd414868bb8a88d943b7e1e4e857282b0705c2ee31624be08fd4bf356a631
+size 15523

checkpoint-14000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ac4a7c35b52110e48733d9f73de54ee6cae62641bd0e3f45234b49faa59de1
+size 623

checkpoint-14000/trainer_state.json

@@ -0,0 +1,212 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9215358931552586,
+  "global_step": 14000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.652198107957708e-05,
+      "loss": 3.4104,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 2.8557941913604736,
+      "eval_runtime": 912.4041,
+      "eval_samples_per_second": 168.064,
+      "eval_steps_per_second": 10.504,
+      "step": 1000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.304396215915415e-05,
+      "loss": 2.8175,
+      "step": 2000
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 2.6051383018493652,
+      "eval_runtime": 902.9796,
+      "eval_samples_per_second": 169.818,
+      "eval_steps_per_second": 10.614,
+      "step": 2000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.956594323873122e-05,
+      "loss": 2.6285,
+      "step": 3000
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 2.4875028133392334,
+      "eval_runtime": 904.858,
+      "eval_samples_per_second": 169.465,
+      "eval_steps_per_second": 10.592,
+      "step": 3000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.608792431830829e-05,
+      "loss": 2.5091,
+      "step": 4000
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 2.428805351257324,
+      "eval_runtime": 903.5608,
+      "eval_samples_per_second": 169.709,
+      "eval_steps_per_second": 10.607,
+      "step": 4000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.2609905397885366e-05,
+      "loss": 3.4219,
+      "step": 5000
+    },
+    {
+      "epoch": 1.04,
+      "eval_loss": 5.509440898895264,
+      "eval_runtime": 902.6374,
+      "eval_samples_per_second": 169.882,
+      "eval_steps_per_second": 10.618,
+      "step": 5000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.913188647746244e-05,
+      "loss": 3.0413,
+      "step": 6000
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 2.3123719692230225,
+      "eval_runtime": 903.1677,
+      "eval_samples_per_second": 169.782,
+      "eval_steps_per_second": 10.612,
+      "step": 6000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2.5653867557039513e-05,
+      "loss": 2.3193,
+      "step": 7000
+    },
+    {
+      "epoch": 1.46,
+      "eval_loss": 2.2579617500305176,
+      "eval_runtime": 903.9178,
+      "eval_samples_per_second": 169.642,
+      "eval_steps_per_second": 10.603,
+      "step": 7000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.2175848636616583e-05,
+      "loss": 2.2688,
+      "step": 8000
+    },
+    {
+      "epoch": 1.67,
+      "eval_loss": 2.231369972229004,
+      "eval_runtime": 903.0629,
+      "eval_samples_per_second": 169.802,
+      "eval_steps_per_second": 10.613,
+      "step": 8000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8697829716193657e-05,
+      "loss": 2.2357,
+      "step": 9000
+    },
+    {
+      "epoch": 1.88,
+      "eval_loss": 2.1945502758026123,
+      "eval_runtime": 903.9088,
+      "eval_samples_per_second": 169.643,
+      "eval_steps_per_second": 10.603,
+      "step": 9000
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.521981079577073e-05,
+      "loss": 2.2002,
+      "step": 10000
+    },
+    {
+      "epoch": 2.09,
+      "eval_loss": 2.1717965602874756,
+      "eval_runtime": 903.6883,
+      "eval_samples_per_second": 169.685,
+      "eval_steps_per_second": 10.605,
+      "step": 10000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.1741791875347802e-05,
+      "loss": 2.1509,
+      "step": 11000
+    },
+    {
+      "epoch": 2.3,
+      "eval_loss": 2.1417629718780518,
+      "eval_runtime": 903.5674,
+      "eval_samples_per_second": 169.707,
+      "eval_steps_per_second": 10.607,
+      "step": 11000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.263772954924876e-06,
+      "loss": 2.1288,
+      "step": 12000
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 2.1314194202423096,
+      "eval_runtime": 902.6397,
+      "eval_samples_per_second": 169.882,
+      "eval_steps_per_second": 10.618,
+      "step": 12000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.785754034501947e-06,
+      "loss": 2.1154,
+      "step": 13000
+    },
+    {
+      "epoch": 2.71,
+      "eval_loss": 2.120832920074463,
+      "eval_runtime": 902.7038,
+      "eval_samples_per_second": 169.87,
+      "eval_steps_per_second": 10.617,
+      "step": 13000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.3077351140790207e-06,
+      "loss": 2.1057,
+      "step": 14000
+    },
+    {
+      "epoch": 2.92,
+      "eval_loss": 2.1087450981140137,
+      "eval_runtime": 902.6299,
+      "eval_samples_per_second": 169.884,
+      "eval_steps_per_second": 10.618,
+      "step": 14000
+    }
+  ],
+  "max_steps": 14376,
+  "num_train_epochs": 3,
+  "total_flos": 2.7036839150594458e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-14000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c46c0a49ca6f1f112e8d16e32b8f311fb7d4219e83f9a55609f157c26aebfe7
+size 2927

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "aubmindlab/bert-large-arabertv2",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:748157c33544829d631e64286f1514e7120d464e08d83cd3c9cfd711ccb9613c
+size 1478119979

runs/Oct22_14-11-22_41acf1b089de/1697983885.8937836/events.out.tfevents.1697983885.41acf1b089de.124913.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84744179aa05fe45539fe21db18b07a13a1ef395a046c4302536a15d95d71751
+size 4639

runs/Oct22_14-11-22_41acf1b089de/events.out.tfevents.1697983885.41acf1b089de.124913.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c86ed0f40f406f441b057d02dcf1e662efde1dbc4432a64bcae3f1b1768181c
+size 9591

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "do_basic_tokenize": true, "never_split": ["+ك", "+كما", "ك+", "+وا", "+ين", "و+", "+كن", "+ان", "+هم", "+ة", "[بريد]", "لل+", "+ي", "+ت", "+ن", "س+", "ل+", "[مستخدم]", "+كم", "+ا", "ب+", "ف+", "+نا", "+ها", "+ون", "+هما", "ال+", "+ه", "+هن", "+ات", "[رابط]"], "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-large-arabertv2", "tokenizer_class": "BertTokenizer"}