Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-mul",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 64109,
+  "decoder_vocab_size": 64110,
+  "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": 64110,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 64109,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 64110
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      64109
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 64109,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 64109,
+  "renormalize_logits": true,
+  "transformers_version": "4.46.3"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72b6839175448b42b75cbd438db44b3e5d02930e0743702306c34f98ac0fa5f
+size 308136760

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539ce5476fb69655a06eb00a2f29e3969e68492bb697eea0f7435081a22fe382
+size 615914507

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:831263f9ef5ec285b9e5d2658a1638c8c02e0ceaf7c1db5598c75929cd9476f8
+size 14645

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b284c429fa62a5741342f8cb3659b3fe09612846a6822ac911645e81c7ecb6ec
+size 1465

last-checkpoint/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9129bf81ef9d5fcc1797ea3061e789dc5f9e5602786b0490238d207d4219e0f5
+size 790473

last-checkpoint/special_tokens_map.json

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

last-checkpoint/target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0a52318dac3247455ec889eb3bd8da9bdf234974be8b9b0f99ad5378f474c9
+size 706659

last-checkpoint/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
+    },
+    "64109": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "mul",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,96 @@
+{
+  "best_metric": 0.36743368487194655,
+  "best_model_checkpoint": "/content/marianmt-santali-sanlish-to-bangla/checkpoint-194",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 194,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 42.4873046875,
+      "learning_rate": 1.0721649484536084e-06,
+      "loss": 8.0222,
+      "step": 30
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 36.22905731201172,
+      "learning_rate": 2.309278350515464e-06,
+      "loss": 6.6412,
+      "step": 60
+    },
+    {
+      "epoch": 0.4639175257731959,
+      "grad_norm": 16.503164291381836,
+      "learning_rate": 3.54639175257732e-06,
+      "loss": 4.5054,
+      "step": 90
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 12.453246116638184,
+      "learning_rate": 4.783505154639176e-06,
+      "loss": 3.1932,
+      "step": 120
+    },
+    {
+      "epoch": 0.7731958762886598,
+      "grad_norm": 12.397629737854004,
+      "learning_rate": 6.020618556701031e-06,
+      "loss": 2.9572,
+      "step": 150
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 12.388405799865723,
+      "learning_rate": 7.257731958762887e-06,
+      "loss": 2.892,
+      "step": 180
+    },
+    {
+      "epoch": 1.0,
+      "eval_bertscore": 0.713106596716945,
+      "eval_bleu": 0.36743368487194655,
+      "eval_chrf": 10.498730872940474,
+      "eval_loss": 2.5750420093536377,
+      "eval_meteor": 0.0286107362704522,
+      "eval_runtime": 34.3517,
+      "eval_samples_per_second": 5.618,
+      "eval_steps_per_second": 0.728,
+      "step": 194
+    }
+  ],
+  "logging_steps": 30,
+  "max_steps": 4850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 10531533422592.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e31c1c20d42437db55f916a392450dbc7427a0f4a051779e553f5d316c80bed
+size 5969