Best model

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/marwan/roberta/mr.marwan1/checkpoint-1969",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "language": "english",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "name": "Roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca382ce5b3e7a57007cc8a547454703826f58f4c33f4f165819b9679103227e5
+size 2834824306

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:736997cb54de26b774be0d2abcd948b7756fe60d51f318eed8027a943c7f4085
+size 1417383721

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e737184ee0f4a65911856bd37e230b5191a4090509e6a3688ca840f5b6dc89c9
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa799afc23e2e5fc3bba3460bb7d573bb882122292e4b5d1b2cc617d0f7548e
+size 627

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,72 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_length": 384,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "stride": 128,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5907,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.6920473773265652e-05,
+      "loss": 0.1219,
+      "step": 500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8461249059443193e-05,
+      "loss": 0.1518,
+      "step": 1000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.658013544018059e-05,
+      "loss": 0.2016,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5147968530654907,
+      "eval_runtime": 257.5566,
+      "eval_samples_per_second": 14.754,
+      "eval_steps_per_second": 3.689,
+      "step": 1969
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.4699021820917985e-05,
+      "loss": 0.2186,
+      "step": 2000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.281790820165538e-05,
+      "loss": 0.1625,
+      "step": 2500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.0936794582392779e-05,
+      "loss": 0.1441,
+      "step": 3000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 9.055680963130174e-06,
+      "loss": 0.1338,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.28966760635375977,
+      "eval_runtime": 257.227,
+      "eval_samples_per_second": 14.773,
+      "eval_steps_per_second": 3.693,
+      "step": 3938
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 7.17456734386757e-06,
+      "loss": 0.1363,
+      "step": 4000
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 5.293453724604967e-06,
+      "loss": 0.0811,
+      "step": 4500
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 3.4123401053423627e-06,
+      "loss": 0.0905,
+      "step": 5000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 1.5312264860797594e-06,
+      "loss": 0.0738,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.33886802196502686,
+      "eval_runtime": 257.6049,
+      "eval_samples_per_second": 14.751,
+      "eval_steps_per_second": 3.688,
+      "step": 5907
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5907,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3.290896444280371e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc094e595e903f84a2107498620efd36c84da71092041c3c626f601506af27e
+size 4027