Training in progress, step 400

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-hi
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: Transformer_MT
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Transformer_MT
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-hi](https://huggingface.co/Helsinki-NLP/opus-mt-en-hi) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2471
+- Bleu: 0.4736
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2
+- training_steps: 2000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu   |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log        | 2.53  | 200  | 2.4508          | 0.1996 |
+| No log        | 5.06  | 400  | 2.3803          | 0.3002 |
+| 2.49          | 7.59  | 600  | 2.3398          | 0.4351 |
+| 2.49          | 10.13 | 800  | 2.3148          | 0.3753 |
+| 2.3247        | 12.66 | 1000 | 2.2919          | 0.4252 |
+| 2.3247        | 15.19 | 1200 | 2.2747          | 0.4268 |
+| 2.3247        | 17.72 | 1400 | 2.2633          | 0.4506 |
+| 2.2349        | 20.25 | 1600 | 2.2563          | 0.4861 |
+| 2.2349        | 22.78 | 1800 | 2.2486          | 0.4783 |
+| 2.1924        | 25.32 | 2000 | 2.2471          | 0.4736 |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-hi",
+  "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": [
+    [
+      61949
+    ]
+  ],
+  "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": 61949,
+  "decoder_vocab_size": 61950,
+  "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": 61950,
+  "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": 61949,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "use_cache": true,
+  "vocab_size": 61950
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      61949
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 61949,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 61949,
+  "renormalize_logits": true,
+  "transformers_version": "4.39.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50556203b32e7af164b79bd2520fd614d6c5941f23b6f5342afb534de84b3ba2
+size 303704440

runs/Jun06_13-17-16_kudsit-dgxserver/events.out.tfevents.1717660047.kudsit-dgxserver.1125867.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a2c4beebdadbbecbdba03b418405c1be8e81d0047f096c9aada1dcd8aea354
+size 5833

runs/Jun06_14-42-09_kudsit-dgxserver/events.out.tfevents.1717665137.kudsit-dgxserver.1125867.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ccf411618c87cb0f4846df4bb49d2ffef6c37556d9b8b8262d5fc21792d5b23
+size 5833

runs/Jun06_16-39-55_kudsit-dgxserver/events.out.tfevents.1717672213.kudsit-dgxserver.1125867.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a5352821985e836a452507ab1353fea1d9e40d9c6b34aa48d3f2672e022239e
+size 9902

runs/Jun07_10-19-42_kudsit-dgxserver/events.out.tfevents.1717735820.kudsit-dgxserver.1125867.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec671671010626cc6006edce93143c979d1ccfb3cb3f3bc6614695f4e7a3bf7
+size 6152

special_tokens_map.json

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

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5529d3a72f8c1d5f7e357f1b6fd30e3cf58f6e1ba0401db135a118ac92f4a76
+size 1067935

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61949": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "hin",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e54a6eb1aa70d6b0800fa8c7535ac20a66ffb5854fac1175fff597a302da5d0
+size 5048