Training in progress, epoch 4, checkpoint

checkpoint-6112/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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50002
+}

checkpoint-6112/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": "4.41.2"
+}

checkpoint-6112/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a5dc405d7315e6272a085e7477d2ba66206cbbe3f792460254d05fc389d2f1
+size 557116312

checkpoint-6112/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2541443fa9d9c056c4cce6899915cf5162a14a1bb2f939bd08e4cda11f3b346d
+size 1113991930

checkpoint-6112/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61452000e70e2b50dbac9e487e1828eeb816725960673eeb14278e12e0cf6cb5
+size 14244

checkpoint-6112/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0feffa048a9742ed26c2f8f981f090e38acfd0d9565f157d22262d12ebfba3f9
+size 1064

checkpoint-6112/sentencepiece.bpe.model

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

checkpoint-6112/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-6112/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-6112/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_metric": 26.5258,
+  "best_model_checkpoint": "/content/drive/My Drive/ArabartModel/checkpoint-6112",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 6112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.32722513089005234,
+      "grad_norm": 1.563672423362732,
+      "learning_rate": 4.6727748691099475e-05,
+      "loss": 0.0195,
+      "step": 500
+    },
+    {
+      "epoch": 0.6544502617801047,
+      "grad_norm": 1.7397737503051758,
+      "learning_rate": 4.3455497382198955e-05,
+      "loss": 0.0244,
+      "step": 1000
+    },
+    {
+      "epoch": 0.981675392670157,
+      "grad_norm": 3.006633758544922,
+      "learning_rate": 4.018324607329843e-05,
+      "loss": 0.0293,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.626201629638672,
+      "eval_rouge1": 25.2705,
+      "eval_rouge2": 9.9865,
+      "eval_rougeL": 21.8678,
+      "eval_runtime": 372.5145,
+      "eval_samples_per_second": 5.892,
+      "eval_steps_per_second": 0.591,
+      "step": 1528
+    },
+    {
+      "epoch": 1.3089005235602094,
+      "grad_norm": 3.4732136726379395,
+      "learning_rate": 4.3455497382198955e-05,
+      "loss": 0.0456,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6361256544502618,
+      "grad_norm": 2.2575156688690186,
+      "learning_rate": 4.181937172774869e-05,
+      "loss": 0.0619,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9633507853403143,
+      "grad_norm": 6.030032157897949,
+      "learning_rate": 4.018324607329843e-05,
+      "loss": 0.0993,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.542174339294434,
+      "eval_rouge1": 25.0744,
+      "eval_rouge2": 9.8534,
+      "eval_rougeL": 21.6992,
+      "eval_runtime": 411.9676,
+      "eval_samples_per_second": 5.328,
+      "eval_steps_per_second": 0.534,
+      "step": 3056
+    },
+    {
+      "epoch": 2.2905759162303667,
+      "grad_norm": 6.401626110076904,
+      "learning_rate": 3.8547120418848174e-05,
+      "loss": 0.21,
+      "step": 3500
+    },
+    {
+      "epoch": 2.6178010471204187,
+      "grad_norm": 5.806931495666504,
+      "learning_rate": 3.691099476439791e-05,
+      "loss": 0.3595,
+      "step": 4000
+    },
+    {
+      "epoch": 2.945026178010471,
+      "grad_norm": 5.840355396270752,
+      "learning_rate": 3.5274869109947647e-05,
+      "loss": 0.6436,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.927168369293213,
+      "eval_rouge1": 25.5914,
+      "eval_rouge2": 10.2904,
+      "eval_rougeL": 22.3089,
+      "eval_runtime": 412.3529,
+      "eval_samples_per_second": 5.323,
+      "eval_steps_per_second": 0.534,
+      "step": 4584
+    },
+    {
+      "epoch": 3.2722513089005236,
+      "grad_norm": 5.320337772369385,
+      "learning_rate": 3.3638743455497386e-05,
+      "loss": 0.7617,
+      "step": 5000
+    },
+    {
+      "epoch": 3.599476439790576,
+      "grad_norm": 5.708410739898682,
+      "learning_rate": 3.2002617801047126e-05,
+      "loss": 0.9186,
+      "step": 5500
+    },
+    {
+      "epoch": 3.9267015706806285,
+      "grad_norm": 6.043923377990723,
+      "learning_rate": 3.036649214659686e-05,
+      "loss": 1.112,
+      "step": 6000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.2077620029449463,
+      "eval_rouge1": 26.5258,
+      "eval_rouge2": 11.116,
+      "eval_rougeL": 23.3381,
+      "eval_runtime": 397.8337,
+      "eval_samples_per_second": 5.517,
+      "eval_steps_per_second": 0.553,
+      "step": 6112
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15280,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 2.930549272296653e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6112/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35dd57590090f24ebba9a087e2c3d94297cd357e1c5960144536e9514488b6a
+size 6904