add model files

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-ar-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": [
+    [
+      62833
+    ]
+  ],
+  "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": 62833,
+  "decoder_vocab_size": 62834,
+  "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,
+  "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": 62833,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 62834
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a83b7701a1b58df5cab82f9c7af326c02debf5427abb158ea79472871e661c88
+size 610624517

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cad576ee017d39807c31b547cb3046116fe386f601db72f525c5c11c7daf859
+size 305575877

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b265a7b340cd17f16ab3488b8c8b7f9ba0a60f2cdf7143558a3c3761756b1c64
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d810deb6dff718ecfd7e25148d29ab8f7e0c54d612042e9544105023f96f534b
+size 627

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "Helsinki-NLP/opus-mt-ar-en",
+  "pad_token": "<pad>",
+  "return_tensors": "pt",
+  "separate_vocabs": false,
+  "source_lang": "ar",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,260 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.999339933993399,
+  "global_step": 9841,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.779832672831352e-05,
+      "loss": 1.7977,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 3.9153311559768165,
+      "eval_cer": 0.20409235310303425,
+      "eval_loss": 0.6436189413070679,
+      "eval_runtime": 882.9917,
+      "eval_samples_per_second": 5.717,
+      "eval_steps_per_second": 0.287,
+      "step": 757
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 4.5596653456627034e-05,
+      "loss": 0.768,
+      "step": 1000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.3394980184940556e-05,
+      "loss": 0.5495,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 14.177638708391077,
+      "eval_cer": 0.14333241613928008,
+      "eval_loss": 0.4357180893421173,
+      "eval_runtime": 876.0468,
+      "eval_samples_per_second": 5.762,
+      "eval_steps_per_second": 0.289,
+      "step": 1514
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 4.119330691325408e-05,
+      "loss": 0.4073,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 18.97804010069212,
+      "eval_cer": 0.12509693073517272,
+      "eval_loss": 0.36574670672416687,
+      "eval_runtime": 906.2682,
+      "eval_samples_per_second": 5.57,
+      "eval_steps_per_second": 0.279,
+      "step": 2271
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 3.8991633641567594e-05,
+      "loss": 0.3404,
+      "step": 2500
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 3.678996036988111e-05,
+      "loss": 0.3022,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 21.33582813630578,
+      "eval_cer": 0.11919353628336293,
+      "eval_loss": 0.3364902138710022,
+      "eval_runtime": 749.8243,
+      "eval_samples_per_second": 6.732,
+      "eval_steps_per_second": 0.337,
+      "step": 3028
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 3.4588287098194625e-05,
+      "loss": 0.2458,
+      "step": 3500
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 21.899151496248283,
+      "eval_cer": 0.11376541511369037,
+      "eval_loss": 0.31889599561691284,
+      "eval_runtime": 778.901,
+      "eval_samples_per_second": 6.481,
+      "eval_steps_per_second": 0.325,
+      "step": 3785
+    },
+    {
+      "epoch": 5.28,
+      "learning_rate": 3.238661382650815e-05,
+      "loss": 0.2265,
+      "step": 4000
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 3.0184940554821667e-05,
+      "loss": 0.2088,
+      "step": 4500
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 23.47915169940915,
+      "eval_cer": 0.11028841583910749,
+      "eval_loss": 0.3102637529373169,
+      "eval_runtime": 958.4916,
+      "eval_samples_per_second": 5.267,
+      "eval_steps_per_second": 0.264,
+      "step": 4542
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 2.7983267283135182e-05,
+      "loss": 0.1791,
+      "step": 5000
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 24.623759800702004,
+      "eval_cer": 0.11083873227105585,
+      "eval_loss": 0.3097042739391327,
+      "eval_runtime": 840.3831,
+      "eval_samples_per_second": 6.007,
+      "eval_steps_per_second": 0.301,
+      "step": 5299
+    },
+    {
+      "epoch": 7.27,
+      "learning_rate": 2.57815940114487e-05,
+      "loss": 0.1675,
+      "step": 5500
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 2.357992073976222e-05,
+      "loss": 0.1571,
+      "step": 6000
+    },
+    {
+      "epoch": 8.0,
+      "eval_bleu": 25.52886648930721,
+      "eval_cer": 0.10933786927483304,
+      "eval_loss": 0.3041631877422333,
+      "eval_runtime": 953.6191,
+      "eval_samples_per_second": 5.294,
+      "eval_steps_per_second": 0.265,
+      "step": 6056
+    },
+    {
+      "epoch": 8.59,
+      "learning_rate": 2.1378247468075736e-05,
+      "loss": 0.1412,
+      "step": 6500
+    },
+    {
+      "epoch": 9.0,
+      "eval_bleu": 25.84181280580903,
+      "eval_cer": 0.11188933636841183,
+      "eval_loss": 0.2990793287754059,
+      "eval_runtime": 911.9381,
+      "eval_samples_per_second": 5.535,
+      "eval_steps_per_second": 0.277,
+      "step": 6813
+    },
+    {
+      "epoch": 9.25,
+      "learning_rate": 1.917657419638926e-05,
+      "loss": 0.1334,
+      "step": 7000
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 1.6974900924702774e-05,
+      "loss": 0.1261,
+      "step": 7500
+    },
+    {
+      "epoch": 10.0,
+      "eval_bleu": 26.361598197934196,
+      "eval_cer": 0.11131400555319308,
+      "eval_loss": 0.29519614577293396,
+      "eval_runtime": 800.3687,
+      "eval_samples_per_second": 6.307,
+      "eval_steps_per_second": 0.316,
+      "step": 7570
+    },
+    {
+      "epoch": 10.57,
+      "learning_rate": 1.4773227653016295e-05,
+      "loss": 0.1172,
+      "step": 8000
+    },
+    {
+      "epoch": 11.0,
+      "eval_bleu": 26.89660242215556,
+      "eval_cer": 0.10981314255697026,
+      "eval_loss": 0.3019121289253235,
+      "eval_runtime": 782.4891,
+      "eval_samples_per_second": 6.451,
+      "eval_steps_per_second": 0.323,
+      "step": 8327
+    },
+    {
+      "epoch": 11.23,
+      "learning_rate": 1.2571554381329812e-05,
+      "loss": 0.114,
+      "step": 8500
+    },
+    {
+      "epoch": 11.89,
+      "learning_rate": 1.036988110964333e-05,
+      "loss": 0.1079,
+      "step": 9000
+    },
+    {
+      "epoch": 12.0,
+      "eval_bleu": 27.22667561487407,
+      "eval_cer": 0.110913775420867,
+      "eval_loss": 0.2969663143157959,
+      "eval_runtime": 847.1515,
+      "eval_samples_per_second": 5.959,
+      "eval_steps_per_second": 0.299,
+      "step": 9084
+    },
+    {
+      "epoch": 12.55,
+      "learning_rate": 8.168207837956847e-06,
+      "loss": 0.101,
+      "step": 9500
+    },
+    {
+      "epoch": 13.0,
+      "eval_bleu": 27.621253608478224,
+      "eval_cer": 0.11243965280036021,
+      "eval_loss": 0.29766184091567993,
+      "eval_runtime": 818.4316,
+      "eval_samples_per_second": 6.168,
+      "eval_steps_per_second": 0.309,
+      "step": 9841
+    }
+  ],
+  "max_steps": 11355,
+  "num_train_epochs": 15,
+  "total_flos": 1473244126248960.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1a90a340bb3d171379543a4b07cc5446e686570e103ffe1d82e5d7d81db40c
+size 3579