Update MT Model

.gitattributes (1)

@@ -0,0 +1,16 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

.gitattributes (2)

@@ -0,0 +1,16 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

.gitattributes (3)

@@ -0,0 +1,16 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,36 @@
+---
+language: 
+- en
+- ar
+tags:
+- translation
+- Arabic Abjad Characters
+license: Apache 2.0
+datasets:
+- marefa-mt
+---
+
+# Marefa-Mt-En-Ar
+
+## Model description
+
+This is a model for translating English to Arabic. The special about this model that is take into considration the
+using of additional Arabic characters like `پ` or `گ`.
+
+## Intended uses & limitations
+
+#### How to use
+
+```python
+from transformers import MarianTokenizer, MarianMTModel
+mname = "marefa-nlp/marefa-mt-en-ar"
+tokenizer = MarianTokenizer.from_pretrained(mname)
+model = MarianMTModel.from_pretrained(mname)
+
+input = "Hello, I am here."
+
+translated_tokens = custom_model.generate(**tokenizer.prepare_seq2seq_batch([input], return_tensors="pt"))
+translated_text = [tokenizer.decode(t, skip_special_tokens=True) for t in translated_tokens]
+
+print(translated_text) # أهلا. أنا هنا
+```

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
+  "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": [
+    [
+      62801
+    ]
+  ],
+  "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": 62801,
+  "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,
+  "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": 62801,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.3.0.dev0",
+  "use_cache": true,
+  "vocab_size": 62802
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e9b93f2ada63a677b458931a2b3ac3fed100bbce10dc2cbbbf615aabe0d993d
+size 305511975

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "eng", "target_lang": "ara", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-mt-en-ar"}

train_results.txt

@@ -0,0 +1,3 @@
+epoch = 3.0
+train_runtime = 13647.3004
+train_samples_per_second = 9.068

trainer_state.json

@@ -0,0 +1,1505 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 123750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.97979797979798e-05,
+      "loss": 1.9971,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9595959595959594e-05,
+      "loss": 1.9127,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.93939393939394e-05,
+      "loss": 1.822,
+      "step": 1500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.919191919191919e-05,
+      "loss": 1.799,
+      "step": 2000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.898989898989899e-05,
+      "loss": 1.7302,
+      "step": 2500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.878787878787879e-05,
+      "loss": 1.7547,
+      "step": 3000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.858585858585859e-05,
+      "loss": 1.7697,
+      "step": 3500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.838383838383839e-05,
+      "loss": 1.729,
+      "step": 4000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8181818181818186e-05,
+      "loss": 1.7333,
+      "step": 4500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.797979797979798e-05,
+      "loss": 1.7238,
+      "step": 5000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.7777777777777784e-05,
+      "loss": 1.678,
+      "step": 5500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.7575757575757576e-05,
+      "loss": 1.6989,
+      "step": 6000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7373737373737375e-05,
+      "loss": 1.7389,
+      "step": 6500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.7171717171717174e-05,
+      "loss": 1.6863,
+      "step": 7000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.696969696969697e-05,
+      "loss": 1.6846,
+      "step": 7500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.676767676767677e-05,
+      "loss": 1.6653,
+      "step": 8000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.656565656565657e-05,
+      "loss": 1.6418,
+      "step": 8500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.636363636363636e-05,
+      "loss": 1.6847,
+      "step": 9000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.616161616161616e-05,
+      "loss": 1.6139,
+      "step": 9500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.595959595959596e-05,
+      "loss": 1.632,
+      "step": 10000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.575757575757576e-05,
+      "loss": 1.6174,
+      "step": 10500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.555555555555556e-05,
+      "loss": 1.6112,
+      "step": 11000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.535353535353535e-05,
+      "loss": 1.621,
+      "step": 11500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.515151515151516e-05,
+      "loss": 1.635,
+      "step": 12000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.494949494949495e-05,
+      "loss": 1.6097,
+      "step": 12500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.474747474747475e-05,
+      "loss": 1.6452,
+      "step": 13000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.454545454545455e-05,
+      "loss": 1.6256,
+      "step": 13500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.4343434343434346e-05,
+      "loss": 1.5971,
+      "step": 14000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.4141414141414145e-05,
+      "loss": 1.6227,
+      "step": 14500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.3939393939393944e-05,
+      "loss": 1.5739,
+      "step": 15000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.3737373737373736e-05,
+      "loss": 1.5691,
+      "step": 15500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.3535353535353535e-05,
+      "loss": 1.5546,
+      "step": 16000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 1.5823,
+      "step": 16500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.313131313131313e-05,
+      "loss": 1.5551,
+      "step": 17000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.292929292929293e-05,
+      "loss": 1.5894,
+      "step": 17500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.2727272727272724e-05,
+      "loss": 1.5619,
+      "step": 18000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.252525252525253e-05,
+      "loss": 1.5391,
+      "step": 18500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.232323232323233e-05,
+      "loss": 1.5915,
+      "step": 19000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.212121212121212e-05,
+      "loss": 1.5544,
+      "step": 19500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.191919191919192e-05,
+      "loss": 1.5526,
+      "step": 20000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.171717171717172e-05,
+      "loss": 1.6034,
+      "step": 20500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.151515151515152e-05,
+      "loss": 1.5726,
+      "step": 21000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.131313131313132e-05,
+      "loss": 1.5359,
+      "step": 21500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 1.5478,
+      "step": 22000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.0909090909090915e-05,
+      "loss": 1.5536,
+      "step": 22500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.070707070707071e-05,
+      "loss": 1.5392,
+      "step": 23000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.0505050505050506e-05,
+      "loss": 1.5625,
+      "step": 23500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.0303030303030305e-05,
+      "loss": 1.5591,
+      "step": 24000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.01010101010101e-05,
+      "loss": 1.5213,
+      "step": 24500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.98989898989899e-05,
+      "loss": 1.5745,
+      "step": 25000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.96969696969697e-05,
+      "loss": 1.5482,
+      "step": 25500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.9494949494949494e-05,
+      "loss": 1.5316,
+      "step": 26000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.929292929292929e-05,
+      "loss": 1.5337,
+      "step": 26500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.909090909090909e-05,
+      "loss": 1.4942,
+      "step": 27000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 1.5151,
+      "step": 27500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.868686868686869e-05,
+      "loss": 1.5496,
+      "step": 28000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.848484848484848e-05,
+      "loss": 1.5163,
+      "step": 28500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.828282828282829e-05,
+      "loss": 1.5256,
+      "step": 29000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8080808080808087e-05,
+      "loss": 1.4599,
+      "step": 29500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.787878787878788e-05,
+      "loss": 1.4989,
+      "step": 30000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.767676767676768e-05,
+      "loss": 1.5055,
+      "step": 30500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.747474747474748e-05,
+      "loss": 1.5022,
+      "step": 31000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.7272727272727276e-05,
+      "loss": 1.4822,
+      "step": 31500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.7070707070707075e-05,
+      "loss": 1.5122,
+      "step": 32000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.686868686868687e-05,
+      "loss": 1.4803,
+      "step": 32500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 1.4926,
+      "step": 33000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.6464646464646465e-05,
+      "loss": 1.4901,
+      "step": 33500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.6262626262626264e-05,
+      "loss": 1.4719,
+      "step": 34000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.606060606060606e-05,
+      "loss": 1.4807,
+      "step": 34500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.5858585858585855e-05,
+      "loss": 1.5062,
+      "step": 35000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.565656565656566e-05,
+      "loss": 1.5005,
+      "step": 35500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.545454545454546e-05,
+      "loss": 1.4907,
+      "step": 36000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.525252525252525e-05,
+      "loss": 1.4665,
+      "step": 36500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.505050505050505e-05,
+      "loss": 1.4935,
+      "step": 37000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.484848484848485e-05,
+      "loss": 1.4598,
+      "step": 37500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.464646464646465e-05,
+      "loss": 1.4724,
+      "step": 38000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.444444444444445e-05,
+      "loss": 1.4927,
+      "step": 38500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.424242424242424e-05,
+      "loss": 1.4694,
+      "step": 39000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.4040404040404045e-05,
+      "loss": 1.479,
+      "step": 39500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.3838383838383844e-05,
+      "loss": 1.5048,
+      "step": 40000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.3636363636363636e-05,
+      "loss": 1.4738,
+      "step": 40500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.3434343434343435e-05,
+      "loss": 1.4608,
+      "step": 41000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.3232323232323234e-05,
+      "loss": 1.3329,
+      "step": 41500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.303030303030303e-05,
+      "loss": 1.3101,
+      "step": 42000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.282828282828283e-05,
+      "loss": 1.2492,
+      "step": 42500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.2626262626262624e-05,
+      "loss": 1.2951,
+      "step": 43000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.2424242424242423e-05,
+      "loss": 1.2733,
+      "step": 43500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.222222222222223e-05,
+      "loss": 1.2937,
+      "step": 44000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.202020202020202e-05,
+      "loss": 1.2735,
+      "step": 44500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.181818181818182e-05,
+      "loss": 1.2602,
+      "step": 45000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.161616161616161e-05,
+      "loss": 1.2623,
+      "step": 45500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.141414141414142e-05,
+      "loss": 1.2759,
+      "step": 46000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.121212121212122e-05,
+      "loss": 1.2684,
+      "step": 46500
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.101010101010101e-05,
+      "loss": 1.2501,
+      "step": 47000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.080808080808081e-05,
+      "loss": 1.3255,
+      "step": 47500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.060606060606061e-05,
+      "loss": 1.2538,
+      "step": 48000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.0404040404040406e-05,
+      "loss": 1.2527,
+      "step": 48500
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 3.0202020202020205e-05,
+      "loss": 1.2417,
+      "step": 49000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3e-05,
+      "loss": 1.2679,
+      "step": 49500
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.9797979797979796e-05,
+      "loss": 1.2634,
+      "step": 50000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.95959595959596e-05,
+      "loss": 1.2838,
+      "step": 50500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 2.9393939393939394e-05,
+      "loss": 1.2911,
+      "step": 51000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.9191919191919193e-05,
+      "loss": 1.2957,
+      "step": 51500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.898989898989899e-05,
+      "loss": 1.2989,
+      "step": 52000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.878787878787879e-05,
+      "loss": 1.2837,
+      "step": 52500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8585858585858587e-05,
+      "loss": 1.2799,
+      "step": 53000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.8383838383838386e-05,
+      "loss": 1.3081,
+      "step": 53500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.818181818181818e-05,
+      "loss": 1.2611,
+      "step": 54000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.7979797979797984e-05,
+      "loss": 1.2629,
+      "step": 54500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.2824,
+      "step": 55000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.7575757575757578e-05,
+      "loss": 1.2779,
+      "step": 55500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.7373737373737374e-05,
+      "loss": 1.2509,
+      "step": 56000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.717171717171717e-05,
+      "loss": 1.2767,
+      "step": 56500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.696969696969697e-05,
+      "loss": 1.2694,
+      "step": 57000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.676767676767677e-05,
+      "loss": 1.2863,
+      "step": 57500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.6565656565656566e-05,
+      "loss": 1.2726,
+      "step": 58000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.636363636363636e-05,
+      "loss": 1.2869,
+      "step": 58500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6161616161616164e-05,
+      "loss": 1.2701,
+      "step": 59000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.5959595959595963e-05,
+      "loss": 1.2943,
+      "step": 59500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.575757575757576e-05,
+      "loss": 1.2579,
+      "step": 60000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5555555555555554e-05,
+      "loss": 1.2592,
+      "step": 60500
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5353535353535356e-05,
+      "loss": 1.2633,
+      "step": 61000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5151515151515155e-05,
+      "loss": 1.2764,
+      "step": 61500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.494949494949495e-05,
+      "loss": 1.2795,
+      "step": 62000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.474747474747475e-05,
+      "loss": 1.2626,
+      "step": 62500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.4545454545454545e-05,
+      "loss": 1.2653,
+      "step": 63000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.4343434343434344e-05,
+      "loss": 1.277,
+      "step": 63500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.4141414141414143e-05,
+      "loss": 1.271,
+      "step": 64000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.393939393939394e-05,
+      "loss": 1.3027,
+      "step": 64500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.3737373737373738e-05,
+      "loss": 1.2827,
+      "step": 65000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.3535353535353537e-05,
+      "loss": 1.2849,
+      "step": 65500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 1.244,
+      "step": 66000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.313131313131313e-05,
+      "loss": 1.2626,
+      "step": 66500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.292929292929293e-05,
+      "loss": 1.224,
+      "step": 67000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.272727272727273e-05,
+      "loss": 1.2652,
+      "step": 67500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.2525252525252528e-05,
+      "loss": 1.2503,
+      "step": 68000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 2.2323232323232324e-05,
+      "loss": 1.2417,
+      "step": 68500
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.2121212121212123e-05,
+      "loss": 1.285,
+      "step": 69000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.191919191919192e-05,
+      "loss": 1.2628,
+      "step": 69500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.171717171717172e-05,
+      "loss": 1.2363,
+      "step": 70000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.1515151515151516e-05,
+      "loss": 1.2178,
+      "step": 70500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.1313131313131315e-05,
+      "loss": 1.2634,
+      "step": 71000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.111111111111111e-05,
+      "loss": 1.2865,
+      "step": 71500
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.090909090909091e-05,
+      "loss": 1.263,
+      "step": 72000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.070707070707071e-05,
+      "loss": 1.2734,
+      "step": 72500
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 2.0505050505050504e-05,
+      "loss": 1.2881,
+      "step": 73000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.0303030303030303e-05,
+      "loss": 1.2164,
+      "step": 73500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.0101010101010102e-05,
+      "loss": 1.2381,
+      "step": 74000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.98989898989899e-05,
+      "loss": 1.2552,
+      "step": 74500
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.9696969696969697e-05,
+      "loss": 1.2883,
+      "step": 75000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.9494949494949496e-05,
+      "loss": 1.238,
+      "step": 75500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.9292929292929295e-05,
+      "loss": 1.2566,
+      "step": 76000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.9090909090909094e-05,
+      "loss": 1.2648,
+      "step": 76500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.2749,
+      "step": 77000
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8686868686868688e-05,
+      "loss": 1.2534,
+      "step": 77500
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.8484848484848487e-05,
+      "loss": 1.2511,
+      "step": 78000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.8282828282828286e-05,
+      "loss": 1.2808,
+      "step": 78500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.808080808080808e-05,
+      "loss": 1.2687,
+      "step": 79000
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.787878787878788e-05,
+      "loss": 1.2495,
+      "step": 79500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.7676767676767676e-05,
+      "loss": 1.2671,
+      "step": 80000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.7474747474747475e-05,
+      "loss": 1.2517,
+      "step": 80500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.7272727272727274e-05,
+      "loss": 1.2058,
+      "step": 81000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.707070707070707e-05,
+      "loss": 1.2215,
+      "step": 81500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.686868686868687e-05,
+      "loss": 1.2407,
+      "step": 82000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.2347,
+      "step": 82500
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.6464646464646466e-05,
+      "loss": 1.0606,
+      "step": 83000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.6262626262626262e-05,
+      "loss": 1.0993,
+      "step": 83500
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.606060606060606e-05,
+      "loss": 1.0871,
+      "step": 84000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.585858585858586e-05,
+      "loss": 1.0975,
+      "step": 84500
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.565656565656566e-05,
+      "loss": 1.098,
+      "step": 85000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.5454545454545454e-05,
+      "loss": 1.105,
+      "step": 85500
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.5252525252525255e-05,
+      "loss": 1.1159,
+      "step": 86000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.505050505050505e-05,
+      "loss": 1.1012,
+      "step": 86500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.484848484848485e-05,
+      "loss": 1.0811,
+      "step": 87000
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.4646464646464647e-05,
+      "loss": 1.0882,
+      "step": 87500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.4444444444444444e-05,
+      "loss": 1.0659,
+      "step": 88000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.4242424242424243e-05,
+      "loss": 1.0932,
+      "step": 88500
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.404040404040404e-05,
+      "loss": 1.0818,
+      "step": 89000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.383838383838384e-05,
+      "loss": 1.096,
+      "step": 89500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.3636363636363637e-05,
+      "loss": 1.0844,
+      "step": 90000
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 1.3434343434343436e-05,
+      "loss": 1.0893,
+      "step": 90500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.3232323232323233e-05,
+      "loss": 1.1083,
+      "step": 91000
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.3030303030303032e-05,
+      "loss": 1.0416,
+      "step": 91500
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.2828282828282829e-05,
+      "loss": 1.1267,
+      "step": 92000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2626262626262628e-05,
+      "loss": 1.0787,
+      "step": 92500
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.2424242424242424e-05,
+      "loss": 1.0863,
+      "step": 93000
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.2222222222222222e-05,
+      "loss": 1.0955,
+      "step": 93500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 1.202020202020202e-05,
+      "loss": 1.0723,
+      "step": 94000
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.1818181818181819e-05,
+      "loss": 1.107,
+      "step": 94500
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.1616161616161616e-05,
+      "loss": 1.0941,
+      "step": 95000
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 1.1414141414141415e-05,
+      "loss": 1.0638,
+      "step": 95500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.1212121212121212e-05,
+      "loss": 1.0862,
+      "step": 96000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.1010101010101011e-05,
+      "loss": 1.0879,
+      "step": 96500
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 1.0808080808080808e-05,
+      "loss": 1.1124,
+      "step": 97000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.0606060606060607e-05,
+      "loss": 1.0761,
+      "step": 97500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.0404040404040405e-05,
+      "loss": 1.0931,
+      "step": 98000
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.0202020202020204e-05,
+      "loss": 1.0835,
+      "step": 98500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1e-05,
+      "loss": 1.0746,
+      "step": 99000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 9.7979797979798e-06,
+      "loss": 1.099,
+      "step": 99500
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 9.595959595959595e-06,
+      "loss": 1.1072,
+      "step": 100000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 9.393939393939394e-06,
+      "loss": 1.0603,
+      "step": 100500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 9.191919191919192e-06,
+      "loss": 1.0652,
+      "step": 101000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 8.98989898989899e-06,
+      "loss": 1.0734,
+      "step": 101500
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 8.787878787878788e-06,
+      "loss": 1.0666,
+      "step": 102000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.585858585858587e-06,
+      "loss": 1.0672,
+      "step": 102500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.383838383838384e-06,
+      "loss": 1.0576,
+      "step": 103000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 1.0902,
+      "step": 103500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.97979797979798e-06,
+      "loss": 1.0693,
+      "step": 104000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 1.0336,
+      "step": 104500
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.5757575757575764e-06,
+      "loss": 1.0752,
+      "step": 105000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.3737373737373745e-06,
+      "loss": 1.0896,
+      "step": 105500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.171717171717173e-06,
+      "loss": 1.0674,
+      "step": 106000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 6.969696969696971e-06,
+      "loss": 1.0682,
+      "step": 106500
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 6.767676767676769e-06,
+      "loss": 1.0851,
+      "step": 107000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 6.565656565656567e-06,
+      "loss": 1.0671,
+      "step": 107500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.363636363636363e-06,
+      "loss": 1.1211,
+      "step": 108000
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.161616161616162e-06,
+      "loss": 1.0873,
+      "step": 108500
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 5.9595959595959605e-06,
+      "loss": 1.0913,
+      "step": 109000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 5.7575757575757586e-06,
+      "loss": 1.113,
+      "step": 109500
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 1.0346,
+      "step": 110000
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.353535353535354e-06,
+      "loss": 1.1079,
+      "step": 110500
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.151515151515152e-06,
+      "loss": 1.0749,
+      "step": 111000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.949494949494949e-06,
+      "loss": 1.0824,
+      "step": 111500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.747474747474747e-06,
+      "loss": 1.0841,
+      "step": 112000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.0914,
+      "step": 112500
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.343434343434344e-06,
+      "loss": 1.0605,
+      "step": 113000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.141414141414142e-06,
+      "loss": 1.0965,
+      "step": 113500
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.939393939393939e-06,
+      "loss": 1.0902,
+      "step": 114000
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 3.7373737373737375e-06,
+      "loss": 1.0711,
+      "step": 114500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.5353535353535352e-06,
+      "loss": 1.1054,
+      "step": 115000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.0563,
+      "step": 115500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 3.1313131313131314e-06,
+      "loss": 1.0524,
+      "step": 116000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.9292929292929295e-06,
+      "loss": 1.0564,
+      "step": 116500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 1.0935,
+      "step": 117000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.5252525252525253e-06,
+      "loss": 1.0868,
+      "step": 117500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.3232323232323234e-06,
+      "loss": 1.0526,
+      "step": 118000
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.1212121212121216e-06,
+      "loss": 1.0539,
+      "step": 118500
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 1.9191919191919192e-06,
+      "loss": 1.0605,
+      "step": 119000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.7171717171717171e-06,
+      "loss": 1.0406,
+      "step": 119500
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.5151515151515152e-06,
+      "loss": 1.0582,
+      "step": 120000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.3131313131313131e-06,
+      "loss": 1.0763,
+      "step": 120500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.1111111111111112e-06,
+      "loss": 1.0838,
+      "step": 121000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 9.09090909090909e-07,
+      "loss": 1.0547,
+      "step": 121500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 7.070707070707071e-07,
+      "loss": 1.07,
+      "step": 122000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.050505050505052e-07,
+      "loss": 1.0643,
+      "step": 122500
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 3.0303030303030305e-07,
+      "loss": 1.0826,
+      "step": 123000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.0101010101010101e-07,
+      "loss": 1.0529,
+      "step": 123500
+    },
+    {
+      "epoch": 3.0,
+      "step": 123750,
+      "total_flos": 14680805909643264,
+      "train_runtime": 13647.3004,
+      "train_samples_per_second": 9.068
+    }
+  ],
+  "max_steps": 123750,
+  "num_train_epochs": 3,
+  "total_flos": 14680805909643264,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1e27171ecc64c359faf78cdec31874ba555c298b4f87f37c5de5ce219e8965
+size 2223