Upload 11 files

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 4.0,
+    "eval_bleu": 59.7829,
+    "eval_gen_len": 29.475,
+    "eval_loss": 0.7762163877487183,
+    "eval_runtime": 3.4667,
+    "eval_samples": 80,
+    "eval_samples_per_second": 23.077,
+    "eval_steps_per_second": 2.019,
+    "train_loss": 0.678381743254485,
+    "train_runtime": 23.2951,
+    "train_samples": 319,
+    "train_samples_per_second": 54.776,
+    "train_steps_per_second": 4.636
+}

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-fr-en",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 59513,
+  "decoder_vocab_size": 59514,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "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_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 59513,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "vocab_size": 59514
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 4.0,
+    "eval_bleu": 59.7829,
+    "eval_gen_len": 29.475,
+    "eval_loss": 0.7762163877487183,
+    "eval_runtime": 3.4667,
+    "eval_samples": 80,
+    "eval_samples_per_second": 23.077,
+    "eval_steps_per_second": 2.019
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59513,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59513,
+  "transformers_version": "4.31.0.dev0"
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "fr",
+  "sp_model_kwargs": {},
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.678381743254485,
+    "train_runtime": 23.2951,
+    "train_samples": 319,
+    "train_samples_per_second": 54.776,
+    "train_steps_per_second": 4.636
+}

trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_bleu": 57.2256,
+      "eval_gen_len": 29.225,
+      "eval_loss": 0.8249181509017944,
+      "eval_runtime": 3.4566,
+      "eval_samples_per_second": 23.144,
+      "eval_steps_per_second": 2.025,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 58.125,
+      "eval_gen_len": 28.95,
+      "eval_loss": 0.7963635325431824,
+      "eval_runtime": 3.3627,
+      "eval_samples_per_second": 23.79,
+      "eval_steps_per_second": 2.082,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 59.3353,
+      "eval_gen_len": 29.35,
+      "eval_loss": 0.778590977191925,
+      "eval_runtime": 3.3696,
+      "eval_samples_per_second": 23.742,
+      "eval_steps_per_second": 2.077,
+      "step": 81
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 59.7829,
+      "eval_gen_len": 29.475,
+      "eval_loss": 0.7762163877487183,
+      "eval_runtime": 3.3687,
+      "eval_samples_per_second": 23.748,
+      "eval_steps_per_second": 2.078,
+      "step": 108
+    },
+    {
+      "epoch": 4.0,
+      "step": 108,
+      "total_flos": 26710057746432.0,
+      "train_loss": 0.678381743254485,
+      "train_runtime": 23.2951,
+      "train_samples_per_second": 54.776,
+      "train_steps_per_second": 4.636
+    }
+  ],
+  "max_steps": 108,
+  "num_train_epochs": 4,
+  "total_flos": 26710057746432.0,
+  "trial_name": null,
+  "trial_params": null
+}