Upload folder using huggingface_hub

checkpoint-400/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_tagless",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 16,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
+  "vocab_size": 8192
+}

checkpoint-400/generation_config.json

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

checkpoint-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc71a31a63d86dd38a940d41a4e5bb560223893d597b8592cf571ba863e8926
+size 501888768

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508ae5d7c40594c496d1ca4ad559001e531d2a53091f12b75e0c35eb5f04050b
+size 254046859

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feddbd711a1283a01bd764487918c0d9dbcb55710578ac8ae7bfb7117ebc93bd
+size 14645

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6af6768bd9c8acf8905c484e9b3f46893ab9cb12cf6d32c42039e4f8b337a168
+size 1383

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff4459b8feb01c399a0ce4139e41489fe3742a5bbdeaf7f42d5a56b4d62b91a5
+size 1465

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "HFCompatibleHybridTokenizer",
+  "vocab_size": 8192,
+  "model_max_length": 512,
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

checkpoint-400/trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.02115702479338843,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005289256198347108,
+      "grad_norm": 14983.798828125,
+      "learning_rate": 2.4e-07,
+      "loss": 17.1865,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010578512396694215,
+      "grad_norm": 2818.19287109375,
+      "learning_rate": 1.04e-06,
+      "loss": 16.2669,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015867768595041322,
+      "grad_norm": 2148.98486328125,
+      "learning_rate": 1.84e-06,
+      "loss": 15.5605,
+      "step": 30
+    },
+    {
+      "epoch": 0.002115702479338843,
+      "grad_norm": 2309.862548828125,
+      "learning_rate": 2.64e-06,
+      "loss": 15.2203,
+      "step": 40
+    },
+    {
+      "epoch": 0.002644628099173554,
+      "grad_norm": 2205.408935546875,
+      "learning_rate": 3.44e-06,
+      "loss": 14.9347,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031735537190082643,
+      "grad_norm": 2530.3701171875,
+      "learning_rate": 4.24e-06,
+      "loss": 14.8024,
+      "step": 60
+    },
+    {
+      "epoch": 0.0037024793388429752,
+      "grad_norm": 1678.7281494140625,
+      "learning_rate": 5.04e-06,
+      "loss": 14.6196,
+      "step": 70
+    },
+    {
+      "epoch": 0.004231404958677686,
+      "grad_norm": 2254.43798828125,
+      "learning_rate": 5.84e-06,
+      "loss": 14.4786,
+      "step": 80
+    },
+    {
+      "epoch": 0.004760330578512397,
+      "grad_norm": 2226.012939453125,
+      "learning_rate": 6.640000000000001e-06,
+      "loss": 14.3674,
+      "step": 90
+    },
+    {
+      "epoch": 0.005289256198347108,
+      "grad_norm": 2211.912353515625,
+      "learning_rate": 7.44e-06,
+      "loss": 14.1906,
+      "step": 100
+    },
+    {
+      "epoch": 0.005818181818181818,
+      "grad_norm": 3070.8232421875,
+      "learning_rate": 8.24e-06,
+      "loss": 14.1344,
+      "step": 110
+    },
+    {
+      "epoch": 0.006347107438016529,
+      "grad_norm": 2257.41455078125,
+      "learning_rate": 9.04e-06,
+      "loss": 14.0681,
+      "step": 120
+    },
+    {
+      "epoch": 0.00687603305785124,
+      "grad_norm": 2274.346435546875,
+      "learning_rate": 9.84e-06,
+      "loss": 13.9746,
+      "step": 130
+    },
+    {
+      "epoch": 0.0074049586776859504,
+      "grad_norm": 2632.0341796875,
+      "learning_rate": 1.064e-05,
+      "loss": 13.9974,
+      "step": 140
+    },
+    {
+      "epoch": 0.007933884297520661,
+      "grad_norm": 1979.03857421875,
+      "learning_rate": 1.144e-05,
+      "loss": 13.6573,
+      "step": 150
+    },
+    {
+      "epoch": 0.008462809917355372,
+      "grad_norm": 1911.6646728515625,
+      "learning_rate": 1.216e-05,
+      "loss": 13.5115,
+      "step": 160
+    },
+    {
+      "epoch": 0.008991735537190083,
+      "grad_norm": 1221.2379150390625,
+      "learning_rate": 1.296e-05,
+      "loss": 13.4189,
+      "step": 170
+    },
+    {
+      "epoch": 0.009520661157024794,
+      "grad_norm": 1295.5301513671875,
+      "learning_rate": 1.376e-05,
+      "loss": 13.1649,
+      "step": 180
+    },
+    {
+      "epoch": 0.010049586776859505,
+      "grad_norm": 1181.076904296875,
+      "learning_rate": 1.4480000000000002e-05,
+      "loss": 13.0769,
+      "step": 190
+    },
+    {
+      "epoch": 0.010578512396694216,
+      "grad_norm": 1546.213623046875,
+      "learning_rate": 1.528e-05,
+      "loss": 12.981,
+      "step": 200
+    },
+    {
+      "epoch": 0.011107438016528925,
+      "grad_norm": 1649.0814208984375,
+      "learning_rate": 1.6080000000000002e-05,
+      "loss": 12.9791,
+      "step": 210
+    },
+    {
+      "epoch": 0.011636363636363636,
+      "grad_norm": 1149.5986328125,
+      "learning_rate": 1.688e-05,
+      "loss": 12.9944,
+      "step": 220
+    },
+    {
+      "epoch": 0.012165289256198347,
+      "grad_norm": 1094.528564453125,
+      "learning_rate": 1.7680000000000004e-05,
+      "loss": 12.712,
+      "step": 230
+    },
+    {
+      "epoch": 0.012694214876033057,
+      "grad_norm": 1151.943603515625,
+      "learning_rate": 1.848e-05,
+      "loss": 12.7007,
+      "step": 240
+    },
+    {
+      "epoch": 0.013223140495867768,
+      "grad_norm": 756.9489135742188,
+      "learning_rate": 1.9280000000000002e-05,
+      "loss": 12.6777,
+      "step": 250
+    },
+    {
+      "epoch": 0.01375206611570248,
+      "grad_norm": 1089.9005126953125,
+      "learning_rate": 2.008e-05,
+      "loss": 12.551,
+      "step": 260
+    },
+    {
+      "epoch": 0.01428099173553719,
+      "grad_norm": 1578.2489013671875,
+      "learning_rate": 2.0880000000000003e-05,
+      "loss": 12.6069,
+      "step": 270
+    },
+    {
+      "epoch": 0.014809917355371901,
+      "grad_norm": 622.3321533203125,
+      "learning_rate": 2.168e-05,
+      "loss": 12.4807,
+      "step": 280
+    },
+    {
+      "epoch": 0.015338842975206612,
+      "grad_norm": 653.3980712890625,
+      "learning_rate": 2.248e-05,
+      "loss": 12.2924,
+      "step": 290
+    },
+    {
+      "epoch": 0.015867768595041323,
+      "grad_norm": 580.5093994140625,
+      "learning_rate": 2.328e-05,
+      "loss": 12.2673,
+      "step": 300
+    },
+    {
+      "epoch": 0.016396694214876033,
+      "grad_norm": 870.7935791015625,
+      "learning_rate": 2.408e-05,
+      "loss": 11.8822,
+      "step": 310
+    },
+    {
+      "epoch": 0.016925619834710744,
+      "grad_norm": 451.5616760253906,
+      "learning_rate": 2.488e-05,
+      "loss": 11.7939,
+      "step": 320
+    },
+    {
+      "epoch": 0.017454545454545455,
+      "grad_norm": 1039.074462890625,
+      "learning_rate": 2.5679999999999998e-05,
+      "loss": 11.7623,
+      "step": 330
+    },
+    {
+      "epoch": 0.017983471074380166,
+      "grad_norm": 826.6625366210938,
+      "learning_rate": 2.648e-05,
+      "loss": 11.5301,
+      "step": 340
+    },
+    {
+      "epoch": 0.018512396694214877,
+      "grad_norm": 375.2585144042969,
+      "learning_rate": 2.728e-05,
+      "loss": 11.6941,
+      "step": 350
+    },
+    {
+      "epoch": 0.019041322314049588,
+      "grad_norm": 535.522705078125,
+      "learning_rate": 2.8080000000000002e-05,
+      "loss": 11.3719,
+      "step": 360
+    },
+    {
+      "epoch": 0.0195702479338843,
+      "grad_norm": 608.0570678710938,
+      "learning_rate": 2.888e-05,
+      "loss": 11.2682,
+      "step": 370
+    },
+    {
+      "epoch": 0.02009917355371901,
+      "grad_norm": 678.4328002929688,
+      "learning_rate": 2.9680000000000004e-05,
+      "loss": 11.3097,
+      "step": 380
+    },
+    {
+      "epoch": 0.02062809917355372,
+      "grad_norm": 567.5283203125,
+      "learning_rate": 3.0480000000000003e-05,
+      "loss": 11.2014,
+      "step": 390
+    },
+    {
+      "epoch": 0.02115702479338843,
+      "grad_norm": 382.2688293457031,
+      "learning_rate": 3.1280000000000005e-05,
+      "loss": 10.9673,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 529,
+  "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": 6693348355276800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5623a138829268598233d481b5532c5c6b7e4686976472a3d219e1ab580f03e5
+size 5201