Upload folder using huggingface_hub

config.json

@@ -1,5 +1,6 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
+  "_name_or_path": "Helsinki-NLP/opus-mt-ar-en",
+  "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "swish",
   "add_bias_logits": false,
@@ -10,7 +11,7 @@
   "attention_dropout": 0.0,
   "bad_words_ids": [
     [
-      62801
+      62833
     ]
   ],
   "bos_token_id": 0,
@@ -21,15 +22,14 @@
   "decoder_ffn_dim": 2048,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 6,
-  "decoder_start_token_id": 62801,
-  "decoder_vocab_size": 62802,
+  "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,
-  "extra_pos_embeddings": 62802,
   "forced_eos_token_id": 0,
   "id2label": {
     "0": "LABEL_0",
@@ -50,12 +50,12 @@
   "normalize_embedding": false,
   "num_beams": 4,
   "num_hidden_layers": 6,
-  "pad_token_id": 62801,
+  "pad_token_id": 62833,
   "scale_embedding": true,
   "share_encoder_decoder_embeddings": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.0.dev0",
+  "transformers_version": "4.40.0.dev0",
   "use_cache": true,
-  "vocab_size": 62802
+  "vocab_size": 62834
 }

generation_config.json

@@ -1,16 +1,16 @@
 {
   "bad_words_ids": [
     [
-      62801
+      62833
     ]
   ],
   "bos_token_id": 0,
-  "decoder_start_token_id": 62801,
+  "decoder_start_token_id": 62833,
   "eos_token_id": 0,
   "forced_eos_token_id": 0,
   "max_length": 512,
   "num_beams": 4,
-  "pad_token_id": 62801,
+  "pad_token_id": 62833,
   "renormalize_logits": true,
-  "transformers_version": "4.39.0.dev0"
+  "transformers_version": "4.40.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:876fdabd8de9b8a1552a39a5ab70a384fb6299b3fb723e27aae9d8bf5f5aaecc
-size 305452744
+oid sha256:841061ba1ca3134e21bfcc1c1c1895510fa2bd0a169a26c331af414c02f2097e
+size 305518408

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00695810b63e4d0d0bc59d08b245bb4cf962172f04a4261c6f5bff21d68be4d
-size 610556538
+oid sha256:c5045d77adc6f5d5e5358a28f934868700fcd9ebb529ddb2dfcff446fa3f07b7
+size 610687610

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b544591965cfbdb044fe4698d517bdab9ae3a234ad953cbe6f274cdccacaff5
+oid sha256:28958b8a49074d60dae4c819a3294a6ed04762bd423b4401526de28ec6641877
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81c27dd7e7913173594e575e6690cdc3d1efab5f3f899a296c53fb607c1cf521
+oid sha256:f0c19b22a8c3caaf5a630137d937fd728638cfd0893ce6477cf5def613cd1cae
 size 1064

tokenizer_config.json

@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "62801": {
+    "62833": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": false,
@@ -30,9 +30,9 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "separate_vocabs": false,
-  "source_lang": "eng",
+  "source_lang": "ar",
   "sp_model_kwargs": {},
-  "target_lang": "ara",
+  "target_lang": "en",
   "tokenizer_class": "MarianTokenizer",
   "unk_token": "<unk>"
 }

trainer_state.json

@@ -1,27 +1,146 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.824858757062147,
+  "epoch": 2.860775588048315,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 2.82,
-      "grad_norm": 3.9365735054016113,
-      "learning_rate": 2.919020715630885e-06,
-      "loss": 0.1939,
+      "epoch": 0.16,
+      "grad_norm": 18.022613525390625,
+      "learning_rate": 4.735113371477008e-05,
+      "loss": 2.3719,
       "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 21.23277473449707,
+      "learning_rate": 4.4702267429540156e-05,
+      "loss": 2.0069,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 16.839088439941406,
+      "learning_rate": 4.205340114431024e-05,
+      "loss": 1.8155,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 15.446898460388184,
+      "learning_rate": 3.9404534859080315e-05,
+      "loss": 1.7476,
+      "step": 2000
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 24.382474899291992,
+      "learning_rate": 3.675566857385039e-05,
+      "loss": 1.6636,
+      "step": 2500
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 21.278900146484375,
+      "learning_rate": 3.410680228862047e-05,
+      "loss": 1.624,
+      "step": 3000
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 14.305024147033691,
+      "learning_rate": 3.1457936003390545e-05,
+      "loss": 1.2214,
+      "step": 3500
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 13.627291679382324,
+      "learning_rate": 2.8809069718160632e-05,
+      "loss": 1.0202,
+      "step": 4000
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 11.309160232543945,
+      "learning_rate": 2.616020343293071e-05,
+      "loss": 1.0545,
+      "step": 4500
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 12.876075744628906,
+      "learning_rate": 2.3511337147700785e-05,
+      "loss": 1.0358,
+      "step": 5000
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 11.487010955810547,
+      "learning_rate": 2.0862470862470865e-05,
+      "loss": 1.0278,
+      "step": 5500
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 12.434341430664062,
+      "learning_rate": 1.821360457724094e-05,
+      "loss": 1.0069,
+      "step": 6000
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 11.067166328430176,
+      "learning_rate": 1.5564738292011018e-05,
+      "loss": 0.8587,
+      "step": 6500
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 9.134782791137695,
+      "learning_rate": 1.29158720067811e-05,
+      "loss": 0.6709,
+      "step": 7000
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 12.168549537658691,
+      "learning_rate": 1.0267005721551176e-05,
+      "loss": 0.6534,
+      "step": 7500
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 8.282147407531738,
+      "learning_rate": 7.6181394363212545e-06,
+      "loss": 0.6821,
+      "step": 8000
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 22.135112762451172,
+      "learning_rate": 4.9692731510913336e-06,
+      "loss": 0.671,
+      "step": 8500
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 7.933387756347656,
+      "learning_rate": 2.3204068658614114e-06,
+      "loss": 0.669,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 531,
+  "max_steps": 9438,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 6335551438848.0,
+  "total_flos": 184716162957312.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2d8a8c3cce0b00111924516d0009d42009475d9cc4facd034884be6d737922
+oid sha256:ec3d61400a7fee3acf0865b303ca025c1aa50ee1eb181cdf52416963ef7e88a0
 size 5048