Training in progress, epoch 2, checkpoint

checkpoint-3056/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-3056/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-3056/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad463059a49b613eb03df4c048d797ae396203ad55df2966259cf6d0832bf908
+size 557116312

checkpoint-3056/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c5b5a9472f5b369c41cc0223a54d821c73eef9313bfc84104b0a8c08145c9f
+size 1113991930

checkpoint-3056/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2b170a520baa1ce18377bdacbbdccab7978596a4a772af3bdbdf4cfda617a7
+size 14244

checkpoint-3056/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a10d959c75e03b0f3e40ddccae75cc1c3bb4a7dda726c8500cf7cde82fc0151
+size 1064

checkpoint-3056/sentencepiece.bpe.model

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

checkpoint-3056/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-3056/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-3056/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_metric": 25.2705,
+  "best_model_checkpoint": "./ArabartModel-1/checkpoint-1528",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3056,
+  "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": 3.447214365005493,
+      "learning_rate": 3.691099476439791e-05,
+      "loss": 0.0416,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6361256544502618,
+      "grad_norm": 1.726170301437378,
+      "learning_rate": 3.3638743455497386e-05,
+      "loss": 0.0536,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9633507853403143,
+      "grad_norm": 5.475728511810303,
+      "learning_rate": 3.036649214659686e-05,
+      "loss": 0.0841,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 5.553058624267578,
+      "eval_rouge1": 25.1196,
+      "eval_rouge2": 9.8402,
+      "eval_rougeL": 21.832,
+      "eval_runtime": 384.1983,
+      "eval_samples_per_second": 5.713,
+      "eval_steps_per_second": 0.573,
+      "step": 3056
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7640,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.4662889498529792e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3056/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db0c5c28c9a1e67e13675dc0782cb65baca4516e1c39cf487f5c45dc85be680
+size 6904