Training in progress, epoch 9, checkpoint

checkpoint-927/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-927/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-927/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dcd962899239357542176c10036644175385ac32d3a2cadcb65f939d86de348
+size 557116312

checkpoint-927/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ddb23e9f410e70b90ddc30f4fdeffa9b70ec329f7599e68d60740073dd7e9a
+size 1113991930

checkpoint-927/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93c3415d125965bacb610f3417f523323dc7096d7f1a6e543477c2ad018df65
+size 14244

checkpoint-927/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d815c723cf9db746730f0a6ad4882969dd7258200a35483a659701a5672b3017
+size 1064

checkpoint-927/sentencepiece.bpe.model

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

checkpoint-927/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-927/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-927/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": 11.8502,
+  "best_model_checkpoint": "/content/drive/MyDrive/checkpoint-103",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 927,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.9408411979675293,
+      "eval_rouge1": 11.8502,
+      "eval_rouge2": 1.8646,
+      "eval_rougeL": 10.0537,
+      "eval_runtime": 32.4385,
+      "eval_samples_per_second": 4.162,
+      "eval_steps_per_second": 0.432,
+      "step": 103
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.919276714324951,
+      "eval_rouge1": 11.4557,
+      "eval_rouge2": 1.6263,
+      "eval_rougeL": 9.5566,
+      "eval_runtime": 35.158,
+      "eval_samples_per_second": 3.84,
+      "eval_steps_per_second": 0.398,
+      "step": 206
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.93249773979187,
+      "eval_rouge1": 11.3452,
+      "eval_rouge2": 1.6252,
+      "eval_rougeL": 9.4233,
+      "eval_runtime": 35.6445,
+      "eval_samples_per_second": 3.787,
+      "eval_steps_per_second": 0.393,
+      "step": 309
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.9606802463531494,
+      "eval_rouge1": 11.1245,
+      "eval_rouge2": 1.4369,
+      "eval_rougeL": 9.1208,
+      "eval_runtime": 35.6479,
+      "eval_samples_per_second": 3.787,
+      "eval_steps_per_second": 0.393,
+      "step": 412
+    },
+    {
+      "epoch": 4.854368932038835,
+      "grad_norm": 2.7092502117156982,
+      "learning_rate": 4.029126213592233e-05,
+      "loss": 3.9031,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.997608184814453,
+      "eval_rouge1": 11.2245,
+      "eval_rouge2": 1.6971,
+      "eval_rougeL": 9.5112,
+      "eval_runtime": 40.7258,
+      "eval_samples_per_second": 3.315,
+      "eval_steps_per_second": 0.344,
+      "step": 515
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 4.051816940307617,
+      "eval_rouge1": 10.9712,
+      "eval_rouge2": 1.5798,
+      "eval_rougeL": 9.2054,
+      "eval_runtime": 33.8454,
+      "eval_samples_per_second": 3.989,
+      "eval_steps_per_second": 0.414,
+      "step": 618
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.091370105743408,
+      "eval_rouge1": 10.943,
+      "eval_rouge2": 1.8423,
+      "eval_rougeL": 9.5291,
+      "eval_runtime": 40.1147,
+      "eval_samples_per_second": 3.365,
+      "eval_steps_per_second": 0.349,
+      "step": 721
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 4.1535868644714355,
+      "eval_rouge1": 11.2298,
+      "eval_rouge2": 1.8217,
+      "eval_rougeL": 9.5514,
+      "eval_runtime": 40.0201,
+      "eval_samples_per_second": 3.373,
+      "eval_steps_per_second": 0.35,
+      "step": 824
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 4.204010963439941,
+      "eval_rouge1": 11.0982,
+      "eval_rouge2": 1.6705,
+      "eval_rougeL": 9.5211,
+      "eval_runtime": 45.7788,
+      "eval_samples_per_second": 2.949,
+      "eval_steps_per_second": 0.306,
+      "step": 927
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2575,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "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": 4458755482030080.0,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-927/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0629f5bf929772a13484bf905e938f15627b80ea05d0ec84bccf7329330835f9
+size 7032