Initial model release

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|bn|>": 50257,
+  "<|en|>": 50258
+}

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}

checkpoint-6/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|bn|>": 50257,
+  "<|en|>": 50258
+}

checkpoint-6/chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}

checkpoint-6/config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50259
+}

checkpoint-6/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.57.3"
+}

checkpoint-6/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e315c2eb6cd582ed3518caa8d01f377c1f423cd2c09be62743143f50203582
+size 497780352

checkpoint-6/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e502242ed60a36d0ab6c6e6021dcab65f5e5c543abc6d12c5df1468aa5ec3e10
+size 995650490

checkpoint-6/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbf11243288a5c23a3ff457eb797018d98049d17a92086a1b2f6131f32cc6fa6
+size 13990

checkpoint-6/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f450fb7193d2d51b6164e9ffad490bd758c04a6df6f06f69f56e9cbf8bf9761
+size 1064

checkpoint-6/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-6/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|bn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|en|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-6/trainer_state.json

@@ -0,0 +1,33 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [],
+  "logging_steps": 100,
+  "max_steps": 6,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2547597312000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a81f867659ac5799522b5174cccbcb92f30688e80e2d6642edf31c7578466f
+size 5368

config.json

@@ -0,0 +1,38 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 50259
+}

eval_metrics.json

@@ -0,0 +1,7 @@
+{
+  "eval_loss": 27.3120174407959,
+  "eval_runtime": 3.2068,
+  "eval_samples_per_second": 0.312,
+  "eval_steps_per_second": 0.312,
+  "epoch": 3.0
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "4.57.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9e315c2eb6cd582ed3518caa8d01f377c1f423cd2c09be62743143f50203582
+size 497780352

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|bn|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50258": {
+      "content": "<|en|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a81f867659ac5799522b5174cccbcb92f30688e80e2d6642edf31c7578466f
+size 5368

training_args.json

@@ -0,0 +1,18 @@
+{
+  "train_data": "datasets/processed/final/train.jsonl",
+  "val_data": "datasets/processed/final/val.jsonl",
+  "model_name_or_path": "microsoft/DialoGPT-small",
+  "output_dir": "models/bilingual-lm/",
+  "max_length": 128,
+  "batch_size": 8,
+  "num_epochs": 3,
+  "learning_rate": 5e-05,
+  "weight_decay": 0.01,
+  "warmup_steps": 500,
+  "gradient_accumulation_steps": 1,
+  "max_grad_norm": 1.0,
+  "seed": 42,
+  "max_train_samples": null,
+  "max_val_samples": null,
+  "fp16": false
+}

training_metrics.json

@@ -0,0 +1,8 @@
+{
+  "train_runtime": 68.3283,
+  "train_samples_per_second": 0.571,
+  "train_steps_per_second": 0.088,
+  "total_flos": 2547597312000.0,
+  "train_loss": 25.982961018880207,
+  "epoch": 3.0
+}