Training in progress, epoch 3, checkpoint

checkpoint-11229/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-11229/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": 128,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 3,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.3"
+}

checkpoint-11229/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac769ff2ead4cda108e9786f02ee7e6130e76d5b988197dc47c7ff78153c7ee
+size 557116312

checkpoint-11229/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f23e16a15e25c22da8c5e31d18b2b92ac90e7b5f068bd70ac43b95bad5912a
+size 1113991930

checkpoint-11229/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f99022e181a77970e3a6857463977cab5e7d792fd32bde34ad676c18405ffe4
+size 14244

checkpoint-11229/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fdc546dcea799cc3279d2f78131a88fe48744c9f9399c924ab13bfb7606e90e
+size 1064

checkpoint-11229/sentencepiece.bpe.model

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

checkpoint-11229/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-11229/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-11229/trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_metric": 27.5466,
+  "best_model_checkpoint": "/content/drive/MyDrive/ArabartModel/checkpoint-7486",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 11229,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1335826876836762,
+      "grad_norm": 3.816420078277588,
+      "learning_rate": 4.7773621871938735e-05,
+      "loss": 2.0568,
+      "step": 500
+    },
+    {
+      "epoch": 0.2671653753673524,
+      "grad_norm": 4.217596054077148,
+      "learning_rate": 4.554724374387746e-05,
+      "loss": 1.949,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4007480630510286,
+      "grad_norm": 3.4469385147094727,
+      "learning_rate": 4.332086561581619e-05,
+      "loss": 1.9236,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5343307507347048,
+      "grad_norm": 3.3545796871185303,
+      "learning_rate": 4.1094487487754926e-05,
+      "loss": 1.9083,
+      "step": 2000
+    },
+    {
+      "epoch": 0.667913438418381,
+      "grad_norm": 3.905182361602783,
+      "learning_rate": 3.886810935969365e-05,
+      "loss": 1.8793,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8014961261020572,
+      "grad_norm": 3.746492862701416,
+      "learning_rate": 3.6641731231632384e-05,
+      "loss": 1.8767,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9350788137857333,
+      "grad_norm": 3.5829365253448486,
+      "learning_rate": 3.441535310357111e-05,
+      "loss": 1.8613,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4695754051208496,
+      "eval_rouge1": 27.3427,
+      "eval_rouge2": 11.5623,
+      "eval_rougeL": 23.8752,
+      "eval_runtime": 854.6158,
+      "eval_samples_per_second": 5.487,
+      "eval_steps_per_second": 0.549,
+      "step": 3743
+    },
+    {
+      "epoch": 1.0686615014694096,
+      "grad_norm": 3.6381685733795166,
+      "learning_rate": 3.218897497550984e-05,
+      "loss": 1.7299,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2022441891530857,
+      "grad_norm": 3.850755453109741,
+      "learning_rate": 2.9962596847448572e-05,
+      "loss": 1.6235,
+      "step": 4500
+    },
+    {
+      "epoch": 1.3358268768367618,
+      "grad_norm": 3.5649123191833496,
+      "learning_rate": 2.77362187193873e-05,
+      "loss": 1.6276,
+      "step": 5000
+    },
+    {
+      "epoch": 1.4694095645204381,
+      "grad_norm": 3.684051036834717,
+      "learning_rate": 2.5509840591326034e-05,
+      "loss": 1.635,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6029922522041145,
+      "grad_norm": 3.216923236846924,
+      "learning_rate": 2.3283462463264763e-05,
+      "loss": 1.6329,
+      "step": 6000
+    },
+    {
+      "epoch": 1.7365749398877905,
+      "grad_norm": 3.666384220123291,
+      "learning_rate": 2.1057084335203492e-05,
+      "loss": 1.628,
+      "step": 6500
+    },
+    {
+      "epoch": 1.8701576275714666,
+      "grad_norm": 3.5083119869232178,
+      "learning_rate": 1.883070620714222e-05,
+      "loss": 1.619,
+      "step": 7000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.552595376968384,
+      "eval_rouge1": 27.5466,
+      "eval_rouge2": 11.7619,
+      "eval_rougeL": 24.0393,
+      "eval_runtime": 855.3721,
+      "eval_samples_per_second": 5.482,
+      "eval_steps_per_second": 0.548,
+      "step": 7486
+    },
+    {
+      "epoch": 2.003740315255143,
+      "grad_norm": 3.350442409515381,
+      "learning_rate": 1.6604328079080954e-05,
+      "loss": 1.6169,
+      "step": 7500
+    },
+    {
+      "epoch": 2.1373230029388193,
+      "grad_norm": 3.3688511848449707,
+      "learning_rate": 1.4377949951019681e-05,
+      "loss": 1.463,
+      "step": 8000
+    },
+    {
+      "epoch": 2.270905690622495,
+      "grad_norm": 3.2857348918914795,
+      "learning_rate": 1.2151571822958412e-05,
+      "loss": 1.4713,
+      "step": 8500
+    },
+    {
+      "epoch": 2.4044883783061715,
+      "grad_norm": 3.8493173122406006,
+      "learning_rate": 9.925193694897141e-06,
+      "loss": 1.4733,
+      "step": 9000
+    },
+    {
+      "epoch": 2.5380710659898478,
+      "grad_norm": 3.59413480758667,
+      "learning_rate": 7.698815566835872e-06,
+      "loss": 1.4519,
+      "step": 9500
+    },
+    {
+      "epoch": 2.6716537536735236,
+      "grad_norm": 3.3809709548950195,
+      "learning_rate": 5.4724374387746014e-06,
+      "loss": 1.4904,
+      "step": 10000
+    },
+    {
+      "epoch": 2.8052364413572,
+      "grad_norm": 3.5270333290100098,
+      "learning_rate": 3.246059310713332e-06,
+      "loss": 1.4753,
+      "step": 10500
+    },
+    {
+      "epoch": 2.9388191290408763,
+      "grad_norm": 3.538780689239502,
+      "learning_rate": 1.0196811826520617e-06,
+      "loss": 1.4732,
+      "step": 11000
+    }
+  ],
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.587894865088512e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-11229/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90a40c8b4998ce26cba95f4373bae2ff702fd0914f61876da4a1d830482ceb1
+size 7032