Upload folder using huggingface_hub

checkpoint-100/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-100/generation_config.json

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

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5893545f18a10ae4fa44747d8ff1c6ebcc1536af0b8c369c2b0ceba91d3f3e0
+size 492457480

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a47067f84a9919a807cf1b20777e6011a3c0154df4e1c63327e22f84d768c3c
+size 250761995

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43e93896c9dae064ca0ff7fd28d303571cf6c1fe79d2d68f7b8ee0fcf007f52c
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c67871b8673bdd87f360d9f1c6dc0223826dd34d380dfe4aee8c6342961529c8
+size 1383

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e410b1dc3acada561f6ff7304c8a44eb98a5cb11dd7f3416f2746c13f89b6bd4
+size 1465

checkpoint-100/trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0011665191505990805,
+  "eval_steps": 500,
+  "global_step": 100,
+  "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
+    }
+  ],
+  "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": 902002033999872.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

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