Upload folder using huggingface_hub

checkpoint-300/config.json

@@ -0,0 +1,17 @@
+{
+  "architectures": [
+    "FastHyperNet125mForCausalLM"
+  ],
+  "dtype": "float32",
+  "hidden_size": 768,
+  "hyperbolic_dim": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 512,
+  "model_type": "fasthypernet_125m_8k",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 16,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
+  "vocab_size": 8192
+}

checkpoint-300/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.1"
+}

checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0179e2ae53c6a2f233a3763b591e38f3c8b7a808f16542e0d14b5ffe12a18e6d
+size 492457480

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c5df1d26900a7b99e2f55b0ab969b1ee16f8c7c46fc219120cce580c3f822b
+size 250762315

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fd37d20a160b97bf2f2b3f8d3d7d59f6ea8c886e967cd6369f4ab9b5da1022
+size 14645

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad73af13a1722b92e0c44c8869d24f52eb0593c021502a90944ab514bde616f3
+size 1383

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7cdee8a8dc143e885d59afaa2c449c315ee53e1e588ffa3e5425276e062bb59
+size 1465

checkpoint-300/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0034995574517972415,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00011665191505990805,
+      "grad_norm": 36.77709197998047,
+      "learning_rate": 4.8e-07,
+      "loss": 8.7532,
+      "step": 10
+    },
+    {
+      "epoch": 0.0002333038301198161,
+      "grad_norm": 27.75691795349121,
+      "learning_rate": 1.0799999999999998e-06,
+      "loss": 8.7454,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003499557451797241,
+      "grad_norm": 28.70688247680664,
+      "learning_rate": 1.6799999999999998e-06,
+      "loss": 8.7275,
+      "step": 30
+    },
+    {
+      "epoch": 0.0004666076602396322,
+      "grad_norm": 30.075843811035156,
+      "learning_rate": 2.2799999999999998e-06,
+      "loss": 8.7324,
+      "step": 40
+    },
+    {
+      "epoch": 0.0005832595752995402,
+      "grad_norm": 24.32572364807129,
+      "learning_rate": 2.8799999999999995e-06,
+      "loss": 8.7301,
+      "step": 50
+    },
+    {
+      "epoch": 0.0006999114903594483,
+      "grad_norm": 20.42615509033203,
+      "learning_rate": 3.4799999999999993e-06,
+      "loss": 8.7192,
+      "step": 60
+    },
+    {
+      "epoch": 0.0008165634054193564,
+      "grad_norm": 21.43255043029785,
+      "learning_rate": 4.079999999999999e-06,
+      "loss": 8.7223,
+      "step": 70
+    },
+    {
+      "epoch": 0.0009332153204792644,
+      "grad_norm": 15.917525291442871,
+      "learning_rate": 4.679999999999999e-06,
+      "loss": 8.7192,
+      "step": 80
+    },
+    {
+      "epoch": 0.0010498672355391725,
+      "grad_norm": 18.44275665283203,
+      "learning_rate": 5.28e-06,
+      "loss": 8.7243,
+      "step": 90
+    },
+    {
+      "epoch": 0.0011665191505990805,
+      "grad_norm": 23.859643936157227,
+      "learning_rate": 5.88e-06,
+      "loss": 8.7202,
+      "step": 100
+    },
+    {
+      "epoch": 0.0012831710656589885,
+      "grad_norm": 25.342121124267578,
+      "learning_rate": 6.48e-06,
+      "loss": 8.7108,
+      "step": 110
+    },
+    {
+      "epoch": 0.0013998229807188965,
+      "grad_norm": 31.435964584350586,
+      "learning_rate": 7.079999999999999e-06,
+      "loss": 8.7104,
+      "step": 120
+    },
+    {
+      "epoch": 0.0015164748957788047,
+      "grad_norm": 28.961843490600586,
+      "learning_rate": 7.68e-06,
+      "loss": 8.7152,
+      "step": 130
+    },
+    {
+      "epoch": 0.0016331268108387127,
+      "grad_norm": 34.92390060424805,
+      "learning_rate": 8.279999999999999e-06,
+      "loss": 8.7094,
+      "step": 140
+    },
+    {
+      "epoch": 0.0017497787258986207,
+      "grad_norm": 33.02936553955078,
+      "learning_rate": 8.88e-06,
+      "loss": 8.6974,
+      "step": 150
+    },
+    {
+      "epoch": 0.0018664306409585287,
+      "grad_norm": 32.488067626953125,
+      "learning_rate": 9.48e-06,
+      "loss": 8.6996,
+      "step": 160
+    },
+    {
+      "epoch": 0.0019830825560184367,
+      "grad_norm": 23.191457748413086,
+      "learning_rate": 1.0079999999999998e-05,
+      "loss": 8.7105,
+      "step": 170
+    },
+    {
+      "epoch": 0.002099734471078345,
+      "grad_norm": 106.55644226074219,
+      "learning_rate": 1.068e-05,
+      "loss": 8.6988,
+      "step": 180
+    },
+    {
+      "epoch": 0.0022163863861382528,
+      "grad_norm": 38.405574798583984,
+      "learning_rate": 1.1279999999999999e-05,
+      "loss": 8.7015,
+      "step": 190
+    },
+    {
+      "epoch": 0.002333038301198161,
+      "grad_norm": 12.893147468566895,
+      "learning_rate": 1.188e-05,
+      "loss": 8.6945,
+      "step": 200
+    },
+    {
+      "epoch": 0.002449690216258069,
+      "grad_norm": 98.10584259033203,
+      "learning_rate": 1.2479999999999999e-05,
+      "loss": 8.6942,
+      "step": 210
+    },
+    {
+      "epoch": 0.002566342131317977,
+      "grad_norm": 14.490903854370117,
+      "learning_rate": 1.3079999999999998e-05,
+      "loss": 8.6946,
+      "step": 220
+    },
+    {
+      "epoch": 0.002682994046377885,
+      "grad_norm": 13.219086647033691,
+      "learning_rate": 1.368e-05,
+      "loss": 8.7053,
+      "step": 230
+    },
+    {
+      "epoch": 0.002799645961437793,
+      "grad_norm": 16.4891357421875,
+      "learning_rate": 1.428e-05,
+      "loss": 8.6833,
+      "step": 240
+    },
+    {
+      "epoch": 0.0029162978764977012,
+      "grad_norm": 20.30918312072754,
+      "learning_rate": 1.4879999999999998e-05,
+      "loss": 8.6788,
+      "step": 250
+    },
+    {
+      "epoch": 0.0030329497915576095,
+      "grad_norm": 47.12828063964844,
+      "learning_rate": 1.5419999999999998e-05,
+      "loss": 8.6797,
+      "step": 260
+    },
+    {
+      "epoch": 0.0031496017066175172,
+      "grad_norm": 13.309244155883789,
+      "learning_rate": 1.602e-05,
+      "loss": 8.6818,
+      "step": 270
+    },
+    {
+      "epoch": 0.0032662536216774255,
+      "grad_norm": 20.72736358642578,
+      "learning_rate": 1.6619999999999997e-05,
+      "loss": 8.6939,
+      "step": 280
+    },
+    {
+      "epoch": 0.0033829055367373333,
+      "grad_norm": 13.736023902893066,
+      "learning_rate": 1.7219999999999998e-05,
+      "loss": 8.6678,
+      "step": 290
+    },
+    {
+      "epoch": 0.0034995574517972415,
+      "grad_norm": 19.503042221069336,
+      "learning_rate": 1.782e-05,
+      "loss": 8.6681,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2705289374121984.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b170d18889101cba0d6a5dd19192f31549fbb1b1fc60a4d9f3703761083c42
+size 5201