Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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
+checkpoint-150/model.SRC filter=lfs diff=lfs merge=lfs -text
+checkpoint-150/model.TGT filter=lfs diff=lfs merge=lfs -text
+model.SRC filter=lfs diff=lfs merge=lfs -text
+model.TGT filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,35 @@
+
+---
+library_name: transformers
+tags:
+- autotrain
+- text2text-generation
+base_model: ai4bharat/indictrans2-indic-en-dist-200M
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Seq2Seq
+
+## Validation Metrics
+loss: 4.0998663902282715
+
+rouge1: 17.7166
+
+rouge2: 12.3004
+
+rougeL: 17.617
+
+rougeLsum: 17.7018
+
+gen_len: 17.55
+
+runtime: 32.9351
+
+samples_per_second: 3.036
+
+steps_per_second: 1.518
+
+: 3.0

checkpoint-150/config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "ai4bharat/indictrans2-indic-en-dist-200M",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "IndicTransForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attn_implementation": null,
+  "auto_map": {
+    "AutoConfig": "ai4bharat/indictrans2-indic-en-dist-200M--configuration_indictrans.IndicTransConfig",
+    "AutoModelForSeq2SeqLM": "ai4bharat/indictrans2-indic-en-dist-200M--modeling_indictrans.IndicTransForConditionalGeneration"
+  },
+  "bos_token_id": 0,
+  "decoder_attention_heads": 8,
+  "decoder_embed_dim": 512,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 18,
+  "decoder_normalize_before": true,
+  "decoder_start_token_id": 2,
+  "decoder_vocab_size": 32296,
+  "dropout": 0.2,
+  "encoder_attention_heads": 8,
+  "encoder_embed_dim": 512,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 18,
+  "encoder_normalize_before": true,
+  "encoder_vocab_size": 122706,
+  "eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "layernorm_embedding": true,
+  "max_source_positions": 256,
+  "max_target_positions": 256,
+  "model_type": "IndicTrans",
+  "num_hidden_layers": 18,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "share_decoder_input_output_embed": true,
+  "tokenizer_class": "IndicTransTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_cache": false,
+  "vocab_size": 32296
+}

checkpoint-150/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.48.0"
+}

checkpoint-150/model.SRC

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9257c8e76b8b607705b959cc3d075656ea33032f7a974e467b8941df6e98d4
+size 3256903

checkpoint-150/model.TGT

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cedc5cbcc740369b76201942a0f096fec7287fee039b55bdb956f301235b914
+size 759425

checkpoint-150/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f46186b661b9c4894a7240df315b02232c3a7e81de9f2c4d01a3f5143a1b97
+size 847211256

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43f9c0c78e7a651e03dd797169da635c4f58a5d928b297aac837e6fb6f63a573
+size 1694887884

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e55b6a10cfc36cc275f509c2dba8c4447653d5b657c2294a068d965ebce25a2
+size 14244

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19e92325f0c6d72344bbada6185b144f4397af0a0f2e4e91f7b4bca18fbdc61
+size 1064

checkpoint-150/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-150/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "ai4bharat/indictrans2-indic-en-dist-200M--tokenization_indictrans.IndicTransTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "src_vocab_file": "/root/.cache/huggingface/hub/models--ai4bharat--indictrans2-indic-en-dist-200M/snapshots/44e264ffa07dc1cae043e0fd864cab035068bf78/dict.SRC.json",
+  "tgt_vocab_file": "/root/.cache/huggingface/hub/models--ai4bharat--indictrans2-indic-en-dist-200M/snapshots/44e264ffa07dc1cae043e0fd864cab035068bf78/dict.SRC.json",
+  "tokenizer_class": "IndicTransTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-150/trainer_state.json

@@ -0,0 +1,130 @@
+{
+  "best_metric": 4.0998663902282715,
+  "best_model_checkpoint": "kn-en-legal-translation-update/checkpoint-150",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 14.293238639831543,
+      "learning_rate": 1.9703703703703704e-05,
+      "loss": 5.9193,
+      "step": 20
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 13.594751358032227,
+      "learning_rate": 1.674074074074074e-05,
+      "loss": 4.5628,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 16.68,
+      "eval_loss": 4.330910682678223,
+      "eval_rouge1": 13.5399,
+      "eval_rouge2": 8.5306,
+      "eval_rougeL": 13.1416,
+      "eval_rougeLsum": 13.1714,
+      "eval_runtime": 30.4105,
+      "eval_samples_per_second": 3.288,
+      "eval_steps_per_second": 1.644,
+      "step": 50
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 11.074690818786621,
+      "learning_rate": 1.377777777777778e-05,
+      "loss": 4.1048,
+      "step": 60
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 9.352710723876953,
+      "learning_rate": 1.0814814814814816e-05,
+      "loss": 3.9522,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 18.36586570739746,
+      "learning_rate": 7.851851851851853e-06,
+      "loss": 3.8364,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 18.11,
+      "eval_loss": 4.152203559875488,
+      "eval_rouge1": 16.4573,
+      "eval_rouge2": 10.4035,
+      "eval_rougeL": 16.2952,
+      "eval_rougeLsum": 16.3805,
+      "eval_runtime": 32.813,
+      "eval_samples_per_second": 3.048,
+      "eval_steps_per_second": 1.524,
+      "step": 100
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 11.676989555358887,
+      "learning_rate": 4.888888888888889e-06,
+      "loss": 3.546,
+      "step": 120
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 12.43088150024414,
+      "learning_rate": 1.925925925925926e-06,
+      "loss": 3.7224,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 17.55,
+      "eval_loss": 4.0998663902282715,
+      "eval_rouge1": 17.7166,
+      "eval_rouge2": 12.3004,
+      "eval_rougeL": 17.617,
+      "eval_rougeLsum": 17.7018,
+      "eval_runtime": 32.1665,
+      "eval_samples_per_second": 3.109,
+      "eval_steps_per_second": 1.554,
+      "step": 150
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 76471515242496.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213d8dbb5afa16fb3b7bfa77de55ea16a5330936898fdb0bb4cf446879c097fe
+size 5496

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "ai4bharat/indictrans2-indic-en-dist-200M",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "IndicTransForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attn_implementation": null,
+  "auto_map": {
+    "AutoConfig": "ai4bharat/indictrans2-indic-en-dist-200M--configuration_indictrans.IndicTransConfig",
+    "AutoModelForSeq2SeqLM": "ai4bharat/indictrans2-indic-en-dist-200M--modeling_indictrans.IndicTransForConditionalGeneration"
+  },
+  "bos_token_id": 0,
+  "decoder_attention_heads": 8,
+  "decoder_embed_dim": 512,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 18,
+  "decoder_normalize_before": true,
+  "decoder_start_token_id": 2,
+  "decoder_vocab_size": 32296,
+  "dropout": 0.2,
+  "encoder_attention_heads": 8,
+  "encoder_embed_dim": 512,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 18,
+  "encoder_normalize_before": true,
+  "encoder_vocab_size": 122706,
+  "eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "layernorm_embedding": true,
+  "max_source_positions": 256,
+  "max_target_positions": 256,
+  "model_type": "IndicTrans",
+  "num_hidden_layers": 18,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "share_decoder_input_output_embed": true,
+  "tokenizer_class": "IndicTransTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_cache": true,
+  "vocab_size": 32296
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.48.0"
+}

model.SRC

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9257c8e76b8b607705b959cc3d075656ea33032f7a974e467b8941df6e98d4
+size 3256903

model.TGT

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cedc5cbcc740369b76201942a0f096fec7287fee039b55bdb956f301235b914
+size 759425

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f46186b661b9c4894a7240df315b02232c3a7e81de9f2c4d01a3f5143a1b97
+size 847211256

runs/Apr20_17-52-24_c76ce57be9eb/events.out.tfevents.1745171551.c76ce57be9eb.3288.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aeef7fb2fa645e2fa2171dade6675da2ff8e3bc0da62c599c0eec5e79956e40
-size 4184
+oid sha256:8b5e9ce67481cf119d421c7b96b044e78b0de91cd2c1bfe3fe1c467da677f268
+size 9405

runs/Apr20_17-52-24_c76ce57be9eb/events.out.tfevents.1745171992.c76ce57be9eb.3288.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cd9d73a9a08c7eee001f84232851d1f202a6daee5d9cdc4f2b1f11aaf5626ba
+size 613

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "ai4bharat/indictrans2-indic-en-dist-200M--tokenization_indictrans.IndicTransTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 256,
+  "pad_token": "<pad>",
+  "src_vocab_file": "/root/.cache/huggingface/hub/models--ai4bharat--indictrans2-indic-en-dist-200M/snapshots/44e264ffa07dc1cae043e0fd864cab035068bf78/dict.SRC.json",
+  "tgt_vocab_file": "/root/.cache/huggingface/hub/models--ai4bharat--indictrans2-indic-en-dist-200M/snapshots/44e264ffa07dc1cae043e0fd864cab035068bf78/dict.SRC.json",
+  "tokenizer_class": "IndicTransTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213d8dbb5afa16fb3b7bfa77de55ea16a5330936898fdb0bb4cf446879c097fe
+size 5496

training_params.json

@@ -0,0 +1,37 @@
+{
+    "data_path": "kn-en-legal-translation-update/autotrain-data",
+    "model": "ai4bharat/indictrans2-indic-en-dist-200M",
+    "username": "pv1031",
+    "seed": 42,
+    "train_split": "train",
+    "valid_split": "validation",
+    "project_name": "kn-en-legal-translation-update",
+    "push_to_hub": true,
+    "text_column": "autotrain_text",
+    "target_column": "autotrain_label",
+    "lr": 2e-05,
+    "epochs": 3,
+    "max_seq_length": 256,
+    "max_target_length": 128,
+    "batch_size": 1,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 8,
+    "optimizer": "adamw_torch",
+    "scheduler": "linear",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "logging_steps": -1,
+    "eval_strategy": "epoch",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "peft": false,
+    "quantization": "int8",
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "target_modules": "all-linear",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}