Training in progress, epoch 5, checkpoint

checkpoint-515/config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "moussaKam/AraBART",
+  "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": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 50002
+}

checkpoint-515/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": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.4"
+}

checkpoint-515/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05677fd1087cabfd521291a19ba2d2616660d24ae178b05e5593eea69719846c
+size 557116312

checkpoint-515/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fdab9eb69068366a0c20ad0d38bc2ddfaeab89a1aa1dd079f89b428999ac308
+size 1113991930

checkpoint-515/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b2b26857510bd77127d4bbf7a801a59008e84d5c67f4c3258cfa323290a5903
+size 14244

checkpoint-515/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de1f98585d9d449844da3a93ea21e05d7a52ec14347e32aa8c2fc1c0b2228592
+size 1064

checkpoint-515/sentencepiece.bpe.model

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

checkpoint-515/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-515/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-515/trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": 12.2639,
+  "best_model_checkpoint": "/content/drive/MyDrive/checkpoint-515",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 515,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.960695505142212,
+      "eval_rouge1": 10.9978,
+      "eval_rouge2": 1.8139,
+      "eval_rougeL": 9.3092,
+      "eval_runtime": 37.5249,
+      "eval_samples_per_second": 3.598,
+      "eval_steps_per_second": 0.373,
+      "step": 103
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.9071261882781982,
+      "eval_rouge1": 11.2604,
+      "eval_rouge2": 1.5524,
+      "eval_rougeL": 9.4921,
+      "eval_runtime": 37.0173,
+      "eval_samples_per_second": 3.647,
+      "eval_steps_per_second": 0.378,
+      "step": 206
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.897859811782837,
+      "eval_rouge1": 11.5027,
+      "eval_rouge2": 1.6912,
+      "eval_rougeL": 9.7326,
+      "eval_runtime": 38.5637,
+      "eval_samples_per_second": 3.501,
+      "eval_steps_per_second": 0.363,
+      "step": 309
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.913738965988159,
+      "eval_rouge1": 11.5951,
+      "eval_rouge2": 1.6186,
+      "eval_rougeL": 9.7334,
+      "eval_runtime": 37.7045,
+      "eval_samples_per_second": 3.58,
+      "eval_steps_per_second": 0.371,
+      "step": 412
+    },
+    {
+      "epoch": 4.854368932038835,
+      "grad_norm": 3.041771411895752,
+      "learning_rate": 2.9773462783171523e-05,
+      "loss": 4.1656,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.9279515743255615,
+      "eval_rouge1": 12.2639,
+      "eval_rouge2": 1.9291,
+      "eval_rougeL": 10.3429,
+      "eval_runtime": 43.0225,
+      "eval_samples_per_second": 3.138,
+      "eval_steps_per_second": 0.325,
+      "step": 515
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1236,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "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": 2465114571325440.0,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-515/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba72222d592aca9157df4394002b8d87e7ceb8b983ac1cc1d936d11e3cf9270
+size 7032