Upload 11 files

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.04766274616122246,
+    "eval_runtime": 30.6769,
+    "eval_samples_per_second": 15.614,
+    "eval_steps_per_second": 1.956,
+    "total_flos": 4140685831357440.0,
+    "train_loss": 0.10683462303953574,
+    "train_runtime": 2456.6799,
+    "train_samples_per_second": 8.817,
+    "train_steps_per_second": 0.277
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "5.9.0",
+  "use_cache": false,
+  "vocab_size": 49152
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.04766274616122246,
+    "eval_runtime": 30.6769,
+    "eval_samples_per_second": 15.614,
+    "eval_steps_per_second": 1.956
+}

foresight_train_config.json

@@ -0,0 +1,24 @@
+{
+  "base_model": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "dataset_name": "rogue-security/prompt-injections-benchmark",
+  "output_dir": "./foresight-135m",
+  "test_split_ratio": 0.1,
+  "seed": 42,
+  "num_epochs": 5,
+  "per_device_train_batch_size": 4,
+  "per_device_eval_batch_size": 8,
+  "gradient_accumulation_steps": 8,
+  "learning_rate": 2e-05,
+  "weight_decay": 0.01,
+  "warmup_ratio": 0.05,
+  "lr_scheduler_type": "cosine",
+  "max_grad_norm": 1.0,
+  "max_seq_len": 512,
+  "logging_steps": 25,
+  "eval_steps": 100,
+  "save_steps": 200,
+  "save_total_limit": 2,
+  "load_best_model_at_end": true,
+  "metric_for_best_model": "eval_loss",
+  "greater_is_better": false
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "5.9.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f05f69066a07e82e2516393623032a5d20ef4b196714d15351b8a7c7419a46
+size 538090408

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 4140685831357440.0,
+    "train_loss": 0.10683462303953574,
+    "train_runtime": 2456.6799,
+    "train_samples_per_second": 8.817,
+    "train_steps_per_second": 0.277
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b833e77b8291cbb21fbf87f339a7174bcc7fb98fad88ebc0cf1d4963a4a0cd3
+size 5265