Training in progress, epoch 2, checkpoint

checkpoint-7486/config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "nour4286/ArabartModel",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "tokenizer_class": "BarthezTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 50002
+}

checkpoint-7486/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_new_tokens": 100,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.3"
+}

checkpoint-7486/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff36ceec5644fd3f33c54f7df20745f002afee034d3ad1cb03834e760fe8b833
+size 557116312

checkpoint-7486/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88965dd84507e4c94a284e42b27c516cc5781816e8dfb6d51a9c2bc9841081b8
+size 1113991930

checkpoint-7486/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfd2e272a31850aa6ba9f85fce31b68682b5b792f76342d9305bf77e9f3add5
+size 14244

checkpoint-7486/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2530cb9367e9a97e253d716557508627759abd16d160e2830b09e33266b8f7c
+size 1064

checkpoint-7486/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb59d772bc9bb2da5dc4a73a00c61c0912c6d2596aad970fa2cd3d69898b245
+size 1315170

checkpoint-7486/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>"
+}

checkpoint-7486/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BarthezTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-7486/trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_metric": 27.0396,
+  "best_model_checkpoint": "/content/drive/MyDrive/Arabart/checkpoint-7486",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 7486,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1335826876836762,
+      "grad_norm": 3.386234998703003,
+      "learning_rate": 3.7102997922232118e-06,
+      "loss": 1.0678,
+      "step": 500
+    },
+    {
+      "epoch": 0.2671653753673524,
+      "grad_norm": 3.5773236751556396,
+      "learning_rate": 7.4205995844464235e-06,
+      "loss": 1.0284,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4007480630510286,
+      "grad_norm": 3.3108386993408203,
+      "learning_rate": 1.1130899376669635e-05,
+      "loss": 1.0298,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5343307507347048,
+      "grad_norm": 3.4388937950134277,
+      "learning_rate": 1.4841199168892847e-05,
+      "loss": 1.0412,
+      "step": 2000
+    },
+    {
+      "epoch": 0.667913438418381,
+      "grad_norm": 3.6874964237213135,
+      "learning_rate": 1.855149896111606e-05,
+      "loss": 1.0445,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8014961261020572,
+      "grad_norm": 3.868025541305542,
+      "learning_rate": 2.226179875333927e-05,
+      "loss": 1.0759,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9350788137857333,
+      "grad_norm": 3.5139052867889404,
+      "learning_rate": 2.5972098545562486e-05,
+      "loss": 1.0966,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.939680814743042,
+      "eval_rouge1": 26.8205,
+      "eval_rouge2": 11.1497,
+      "eval_rougeL": 23.3343,
+      "eval_runtime": 806.3685,
+      "eval_samples_per_second": 5.815,
+      "eval_steps_per_second": 0.582,
+      "step": 3743
+    },
+    {
+      "epoch": 1.0686615014694096,
+      "grad_norm": 3.590301036834717,
+      "learning_rate": 2.9682398337785694e-05,
+      "loss": 1.0519,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2022441891530857,
+      "grad_norm": 4.0262770652771,
+      "learning_rate": 3.33926981300089e-05,
+      "loss": 1.0335,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3358268768367618,
+      "grad_norm": 3.4733996391296387,
+      "learning_rate": 3.710299792223212e-05,
+      "loss": 1.0759,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4694095645204381,
+      "grad_norm": 4.025749206542969,
+      "learning_rate": 4.0813297714455326e-05,
+      "loss": 1.1336,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6029922522041145,
+      "grad_norm": 3.807826280593872,
+      "learning_rate": 4.452359750667854e-05,
+      "loss": 1.1922,
+      "step": 6000
+    },
+    {
+      "epoch": 1.7365749398877905,
+      "grad_norm": 4.066860198974609,
+      "learning_rate": 4.8233897298901756e-05,
+      "loss": 1.2401,
+      "step": 6500
+    },
+    {
+      "epoch": 1.8701576275714666,
+      "grad_norm": 4.048403739929199,
+      "learning_rate": 4.708305499888667e-05,
+      "loss": 1.2936,
+      "step": 7000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.8382859230041504,
+      "eval_rouge1": 27.0396,
+      "eval_rouge2": 11.288,
+      "eval_rougeL": 23.5434,
+      "eval_runtime": 802.1911,
+      "eval_samples_per_second": 5.845,
+      "eval_steps_per_second": 0.585,
+      "step": 7486
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11229,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 4.390892214460416e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-7486/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76331aef1246e3dac8c5b8a8b0b0d4c08a9426a6e56fde87f4dc39d35372157
+size 7032