End of training

README.md

@@ -1,10 +1,10 @@
 ---
 library_name: transformers
-base_model: danasone/bart-small-ru-en
+language:
+- hi
+base_model: ar5entum/bart_eng_hin_mt
 tags:
 - generated_from_trainer
-metrics:
-- bleu
 model-index:
 - name: bart_eng_hin_mt
   results: []
@@ -15,11 +15,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bart_eng_hin_mt
 
-This model is a fine-tuned version of [danasone/bart-small-ru-en](https://huggingface.co/danasone/bart-small-ru-en) on an unknown dataset.
+This model is a fine-tuned version of [ar5entum/bart_eng_hin_mt](https://huggingface.co/ar5entum/bart_eng_hin_mt) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3398
-- Bleu: 10.015
-- Gen Len: 123.5141
+- eval_loss: 0.5147
+- eval_model_preparation_time: 0.0051
+- eval_bleu: 11.8141
+- eval_gen_len: 122.6932
+- eval_runtime: 3.6543
+- eval_samples_per_second: 142.3
+- eval_steps_per_second: 1.642
+- step: 0
 
 ## Model description
 
@@ -38,28 +43,17 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0008
-- train_batch_size: 300
-- eval_batch_size: 20
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 22
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 8
-- total_train_batch_size: 2400
-- total_eval_batch_size: 160
+- num_devices: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 88
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 1000
-- num_epochs: 15.0
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len  |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
-| 0.5522        | 1.0   | 689  | 0.5343          | 3.4797 | 123.3969 |
-| 0.3988        | 2.0   | 1378 | 0.4020          | 7.5644 | 123.3578 |
-| 0.3496        | 3.0   | 2067 | 0.3601          | 9.3506 | 123.4641 |
-| 0.3191        | 4.0   | 2756 | 0.3398          | 10.015 | 123.5141 |
-
+- num_epochs: 3.0
 
 ### Framework versions
 

all_results.json

@@ -0,0 +1,18 @@
+{
+    "eval_bleu": 11.8141,
+    "eval_gen_len": 122.6932,
+    "eval_loss": 0.5147402286529541,
+    "eval_model_preparation_time": 0.0051,
+    "eval_runtime": 3.6543,
+    "eval_samples": 520,
+    "eval_samples_per_second": 142.3,
+    "eval_steps_per_second": 1.642,
+    "predict_bleu": 10.684,
+    "predict_gen_len": 125.2625,
+    "predict_loss": 0.5075575113296509,
+    "predict_model_preparation_time": 0.0051,
+    "predict_runtime": 13.2991,
+    "predict_samples": 2507,
+    "predict_samples_per_second": 188.508,
+    "predict_steps_per_second": 2.181
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "eval_bleu": 11.8141,
+    "eval_gen_len": 122.6932,
+    "eval_loss": 0.5147402286529541,
+    "eval_model_preparation_time": 0.0051,
+    "eval_runtime": 3.6543,
+    "eval_samples": 520,
+    "eval_samples_per_second": 142.3,
+    "eval_steps_per_second": 1.642
+}

predict_results.json

@@ -0,0 +1,10 @@
+{
+    "predict_bleu": 10.684,
+    "predict_gen_len": 125.2625,
+    "predict_loss": 0.5075575113296509,
+    "predict_model_preparation_time": 0.0051,
+    "predict_runtime": 13.2991,
+    "predict_samples": 2507,
+    "predict_samples_per_second": 188.508,
+    "predict_steps_per_second": 2.181
+}

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -298,7 +303,7 @@
       },
       {
         "SpecialToken": {
-          "id": "hi_IN",
+          "id": "hi",
           "type_id": 0
         }
       }
@@ -324,7 +329,7 @@
       },
       {
         "SpecialToken": {
-          "id": "hi_IN",
+          "id": "hi",
           "type_id": 0
         }
       }
@@ -339,13 +344,13 @@
           "</s>"
         ]
       },
-      "hi_IN": {
-        "id": "hi_IN",
+      "hi": {
+        "id": "hi",
         "ids": [
-          65545
+          16960
         ],
         "tokens": [
-          "hi_IN"
+          "hi"
         ]
       }
     }

tokenizer_config.json

@@ -276,12 +276,16 @@
   "errors": "replace",
   "mask_token": "<mask>",
   "max_len": 512,
+  "max_length": 128,
   "model_max_length": 1024,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "src_lang": "hi_IN",
-  "tgt_lang": "hi_IN",
+  "src_lang": "hi",
+  "stride": 0,
+  "tgt_lang": "hi",
   "tokenizer_class": "MBartTokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9ab7eba83a79e87db243724a12249417762143b24d1e6428dc9f11c29fa98ab
+oid sha256:9978ca1266b644df458f44c58f94cb2fa8701d0adf54a28412b474f8abf5599e
 size 5368