Upload folder using huggingface_hub

checkpoint-1000/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.18.0",
+  "use_cache": false,
+  "vocab_size": 16384
+}

checkpoint-1000/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 1,
+  "transformers_version": "5.18.0",
+  "use_cache": true
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f693ae492a5a9358fc98b1ffe8c4712a20021fa0d7647ff804d1f21630c1bf6
+size 201369672

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af8f93b929b6260e088a22a5203ad66065cacc6f420cac7ad3ce614ff8f2656
+size 402787851

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-1000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+size 1383

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8083cb28f9178670969e8954135f0609f0eac2102b31887abccd667da0fb9cf
+size 1465

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.625,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03125,
+      "grad_norm": 1.527620792388916,
+      "learning_rate": 4.755e-05,
+      "loss": 8.730679321289063,
+      "step": 50
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 1.0522923469543457,
+      "learning_rate": 4.5050000000000004e-05,
+      "loss": 7.81984375,
+      "step": 100
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 0.9898874163627625,
+      "learning_rate": 4.2550000000000004e-05,
+      "loss": 7.370440673828125,
+      "step": 150
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.8935964703559875,
+      "learning_rate": 4.0050000000000004e-05,
+      "loss": 7.193408813476562,
+      "step": 200
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.9063679575920105,
+      "learning_rate": 3.7550000000000005e-05,
+      "loss": 7.081380615234375,
+      "step": 250
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 1.0553767681121826,
+      "learning_rate": 3.505e-05,
+      "loss": 7.03900634765625,
+      "step": 300
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 1.1848763227462769,
+      "learning_rate": 3.2550000000000005e-05,
+      "loss": 6.9334521484375,
+      "step": 350
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.0184597969055176,
+      "learning_rate": 3.0050000000000002e-05,
+      "loss": 6.876171264648438,
+      "step": 400
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 1.2478649616241455,
+      "learning_rate": 2.7550000000000002e-05,
+      "loss": 6.834779052734375,
+      "step": 450
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 1.175338625907898,
+      "learning_rate": 2.5050000000000002e-05,
+      "loss": 6.7814111328125,
+      "step": 500
+    },
+    {
+      "epoch": 0.34375,
+      "grad_norm": 1.1923964023590088,
+      "learning_rate": 2.2550000000000003e-05,
+      "loss": 6.735855712890625,
+      "step": 550
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 1.3196032047271729,
+      "learning_rate": 2.0050000000000003e-05,
+      "loss": 6.695497436523437,
+      "step": 600
+    },
+    {
+      "epoch": 0.40625,
+      "grad_norm": 1.6262001991271973,
+      "learning_rate": 1.755e-05,
+      "loss": 6.66811767578125,
+      "step": 650
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 1.2989777326583862,
+      "learning_rate": 1.505e-05,
+      "loss": 6.630078735351563,
+      "step": 700
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 1.3588811159133911,
+      "learning_rate": 1.255e-05,
+      "loss": 6.63123291015625,
+      "step": 750
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.2979592084884644,
+      "learning_rate": 1.005e-05,
+      "loss": 6.598649291992188,
+      "step": 800
+    },
+    {
+      "epoch": 0.53125,
+      "grad_norm": 1.324408769607544,
+      "learning_rate": 7.55e-06,
+      "loss": 6.595721435546875,
+      "step": 850
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 1.4655917882919312,
+      "learning_rate": 5.050000000000001e-06,
+      "loss": 6.617113037109375,
+      "step": 900
+    },
+    {
+      "epoch": 0.59375,
+      "grad_norm": 1.500761866569519,
+      "learning_rate": 2.55e-06,
+      "loss": 6.571935424804687,
+      "step": 950
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 1.2903245687484741,
+      "learning_rate": 5.0000000000000004e-08,
+      "loss": 6.574727783203125,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 515503030272000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9182e13b9d566cb1f1336008814e6901596a5e9dfd02b13e584a9347a4cbf315
+size 5201

config.json

@@ -1,41 +1,32 @@
 {
-  "model_name": "Agron",
-  "architecture": "AgronMultiAgent",
-  "model_type": "agent_system",
-  "learn_from_scratch": true,
-  "recursive_self_improvement": true,
-  "agents": [
-    {
-      "name": "ExploitAgent",
-      "role": "exploitation"
-    },
-    {
-      "name": "AnalysisAgent",
-      "role": "analysis"
-    },
-    {
-      "name": "ReconAgent",
-      "role": "surface-mapping"
-    },
-    {
-      "name": "VulnAgent",
-      "role": "vulnerability-research"
-    },
-    {
-      "name": "DefenseAgent",
-      "role": "defense"
-    }
+  "architectures": [
+    "LlamaForCausalLM"
   ],
-  "bootstrap": {
-    "empty_memory": true,
-    "seed_rules_only": true,
-    "validation_required": true
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
   },
-  "license": "MIT",
-  "domain": "cybersecurity-only",
-  "tasks": [
-    "exploitation",
-    "analysis",
-    "parallel-spawn"
-  ]
-}
+  "tie_word_embeddings": false,
+  "transformers_version": "5.18.0",
+  "use_cache": false,
+  "vocab_size": 16384
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b155095fbff2b4d29dca17d1a18255c7959eee172a311dc733229e1ec2e713
-size 33567880
+oid sha256:1f693ae492a5a9358fc98b1ffe8c4712a20021fa0d7647ff804d1f21630c1bf6
+size 201369672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3dcb6da6e65c4a3e82f2d94267cceacfb3edb68a4bec4bbb9ced406fc2d5dc
+oid sha256:9182e13b9d566cb1f1336008814e6901596a5e9dfd02b13e584a9347a4cbf315
 size 5201