Upload folder using huggingface_hub

checkpoint-500/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-500/generation_config.json

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

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13a1fa1c89df8befb8576f78edbffff4af11792c7eefb6616e5c3ea921d7c1a
+size 501911880

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00696ebf4cb24ef5b32f87f4b1625c89e5c5780085eafb138b92d27cd89d699d
+size 254046859

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92df83ba94f8c9b6d68f6408304e9ba87b3385af850ed42a08b9709b08226317
+size 14645

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8434ea412811a4c8e6bccd144af12ba43d57ba4ccf2f40980f4dbc77dc194b
+size 1383

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c016689534dd706c86d62a4ceb7891f14852bbadb3eaf96578fcd1aac6842bc3
+size 1465

checkpoint-500/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-500/trainer_state.json

@@ -0,0 +1,384 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.026446280991735537,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005289256198347108,
+      "grad_norm": 2042.0159912109375,
+      "learning_rate": 3.2e-07,
+      "loss": 8.126,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010578512396694215,
+      "grad_norm": 132.607666015625,
+      "learning_rate": 1.12e-06,
+      "loss": 8.0108,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015867768595041322,
+      "grad_norm": 117.4473876953125,
+      "learning_rate": 1.92e-06,
+      "loss": 7.8388,
+      "step": 30
+    },
+    {
+      "epoch": 0.002115702479338843,
+      "grad_norm": 58.00923538208008,
+      "learning_rate": 2.72e-06,
+      "loss": 7.7671,
+      "step": 40
+    },
+    {
+      "epoch": 0.002644628099173554,
+      "grad_norm": 62.31724166870117,
+      "learning_rate": 3.52e-06,
+      "loss": 7.821,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031735537190082643,
+      "grad_norm": 99.75863647460938,
+      "learning_rate": 4.32e-06,
+      "loss": 7.6772,
+      "step": 60
+    },
+    {
+      "epoch": 0.0037024793388429752,
+      "grad_norm": 337.9526672363281,
+      "learning_rate": 5.12e-06,
+      "loss": 7.8172,
+      "step": 70
+    },
+    {
+      "epoch": 0.004231404958677686,
+      "grad_norm": 95.75334167480469,
+      "learning_rate": 5.920000000000001e-06,
+      "loss": 7.6801,
+      "step": 80
+    },
+    {
+      "epoch": 0.004760330578512397,
+      "grad_norm": 589.1984252929688,
+      "learning_rate": 6.72e-06,
+      "loss": 7.7462,
+      "step": 90
+    },
+    {
+      "epoch": 0.005289256198347108,
+      "grad_norm": 115.37745666503906,
+      "learning_rate": 7.520000000000001e-06,
+      "loss": 7.5665,
+      "step": 100
+    },
+    {
+      "epoch": 0.005818181818181818,
+      "grad_norm": 104.31098937988281,
+      "learning_rate": 8.32e-06,
+      "loss": 7.6031,
+      "step": 110
+    },
+    {
+      "epoch": 0.006347107438016529,
+      "grad_norm": 357.35272216796875,
+      "learning_rate": 9.12e-06,
+      "loss": 7.6829,
+      "step": 120
+    },
+    {
+      "epoch": 0.00687603305785124,
+      "grad_norm": 299.00555419921875,
+      "learning_rate": 9.92e-06,
+      "loss": 7.6717,
+      "step": 130
+    },
+    {
+      "epoch": 0.0074049586776859504,
+      "grad_norm": 593.5489501953125,
+      "learning_rate": 1.072e-05,
+      "loss": 7.6622,
+      "step": 140
+    },
+    {
+      "epoch": 0.007933884297520661,
+      "grad_norm": 174.9026336669922,
+      "learning_rate": 1.152e-05,
+      "loss": 7.595,
+      "step": 150
+    },
+    {
+      "epoch": 0.008462809917355372,
+      "grad_norm": 199.49935913085938,
+      "learning_rate": 1.232e-05,
+      "loss": 7.5791,
+      "step": 160
+    },
+    {
+      "epoch": 0.008991735537190083,
+      "grad_norm": 557.2059936523438,
+      "learning_rate": 1.3120000000000001e-05,
+      "loss": 7.7285,
+      "step": 170
+    },
+    {
+      "epoch": 0.009520661157024794,
+      "grad_norm": 333.83441162109375,
+      "learning_rate": 1.3919999999999999e-05,
+      "loss": 7.6101,
+      "step": 180
+    },
+    {
+      "epoch": 0.010049586776859505,
+      "grad_norm": 213.27163696289062,
+      "learning_rate": 1.472e-05,
+      "loss": 7.6139,
+      "step": 190
+    },
+    {
+      "epoch": 0.010578512396694216,
+      "grad_norm": 192.46920776367188,
+      "learning_rate": 1.552e-05,
+      "loss": 7.4358,
+      "step": 200
+    },
+    {
+      "epoch": 0.011107438016528925,
+      "grad_norm": 369.1148986816406,
+      "learning_rate": 1.6320000000000003e-05,
+      "loss": 7.4565,
+      "step": 210
+    },
+    {
+      "epoch": 0.011636363636363636,
+      "grad_norm": 244.7185821533203,
+      "learning_rate": 1.712e-05,
+      "loss": 7.3962,
+      "step": 220
+    },
+    {
+      "epoch": 0.012165289256198347,
+      "grad_norm": 308.51544189453125,
+      "learning_rate": 1.792e-05,
+      "loss": 7.4273,
+      "step": 230
+    },
+    {
+      "epoch": 0.012694214876033057,
+      "grad_norm": 208.3214569091797,
+      "learning_rate": 1.872e-05,
+      "loss": 7.3567,
+      "step": 240
+    },
+    {
+      "epoch": 0.013223140495867768,
+      "grad_norm": 121.53463745117188,
+      "learning_rate": 1.9520000000000003e-05,
+      "loss": 7.4131,
+      "step": 250
+    },
+    {
+      "epoch": 0.01375206611570248,
+      "grad_norm": 124.09678649902344,
+      "learning_rate": 2.032e-05,
+      "loss": 7.426,
+      "step": 260
+    },
+    {
+      "epoch": 0.01428099173553719,
+      "grad_norm": 237.53346252441406,
+      "learning_rate": 2.112e-05,
+      "loss": 7.377,
+      "step": 270
+    },
+    {
+      "epoch": 0.014809917355371901,
+      "grad_norm": 174.61985778808594,
+      "learning_rate": 2.192e-05,
+      "loss": 7.3773,
+      "step": 280
+    },
+    {
+      "epoch": 0.015338842975206612,
+      "grad_norm": 86.74190521240234,
+      "learning_rate": 2.2720000000000003e-05,
+      "loss": 7.3686,
+      "step": 290
+    },
+    {
+      "epoch": 0.015867768595041323,
+      "grad_norm": 123.0051498413086,
+      "learning_rate": 2.3520000000000002e-05,
+      "loss": 7.363,
+      "step": 300
+    },
+    {
+      "epoch": 0.016396694214876033,
+      "grad_norm": 149.46461486816406,
+      "learning_rate": 2.432e-05,
+      "loss": 7.3321,
+      "step": 310
+    },
+    {
+      "epoch": 0.016925619834710744,
+      "grad_norm": 129.9262237548828,
+      "learning_rate": 2.512e-05,
+      "loss": 7.3589,
+      "step": 320
+    },
+    {
+      "epoch": 0.017454545454545455,
+      "grad_norm": 287.2998962402344,
+      "learning_rate": 2.592e-05,
+      "loss": 7.3022,
+      "step": 330
+    },
+    {
+      "epoch": 0.017983471074380166,
+      "grad_norm": 149.36317443847656,
+      "learning_rate": 2.672e-05,
+      "loss": 7.1559,
+      "step": 340
+    },
+    {
+      "epoch": 0.018512396694214877,
+      "grad_norm": 133.55393981933594,
+      "learning_rate": 2.752e-05,
+      "loss": 7.2833,
+      "step": 350
+    },
+    {
+      "epoch": 0.019041322314049588,
+      "grad_norm": 111.75740814208984,
+      "learning_rate": 2.8320000000000003e-05,
+      "loss": 7.0669,
+      "step": 360
+    },
+    {
+      "epoch": 0.0195702479338843,
+      "grad_norm": 108.92760467529297,
+      "learning_rate": 2.9120000000000002e-05,
+      "loss": 7.2586,
+      "step": 370
+    },
+    {
+      "epoch": 0.02009917355371901,
+      "grad_norm": 160.08486938476562,
+      "learning_rate": 2.9920000000000005e-05,
+      "loss": 7.2912,
+      "step": 380
+    },
+    {
+      "epoch": 0.02062809917355372,
+      "grad_norm": 115.86800384521484,
+      "learning_rate": 3.072e-05,
+      "loss": 7.1553,
+      "step": 390
+    },
+    {
+      "epoch": 0.02115702479338843,
+      "grad_norm": 131.96246337890625,
+      "learning_rate": 3.1519999999999996e-05,
+      "loss": 7.0865,
+      "step": 400
+    },
+    {
+      "epoch": 0.021685950413223142,
+      "grad_norm": 175.23385620117188,
+      "learning_rate": 3.232e-05,
+      "loss": 7.1718,
+      "step": 410
+    },
+    {
+      "epoch": 0.02221487603305785,
+      "grad_norm": 130.51516723632812,
+      "learning_rate": 3.312e-05,
+      "loss": 7.1449,
+      "step": 420
+    },
+    {
+      "epoch": 0.02274380165289256,
+      "grad_norm": 142.1250762939453,
+      "learning_rate": 3.392e-05,
+      "loss": 7.0811,
+      "step": 430
+    },
+    {
+      "epoch": 0.02327272727272727,
+      "grad_norm": 93.60326385498047,
+      "learning_rate": 3.472e-05,
+      "loss": 7.0511,
+      "step": 440
+    },
+    {
+      "epoch": 0.023801652892561982,
+      "grad_norm": 85.3148193359375,
+      "learning_rate": 3.5520000000000006e-05,
+      "loss": 7.057,
+      "step": 450
+    },
+    {
+      "epoch": 0.024330578512396693,
+      "grad_norm": 77.96083068847656,
+      "learning_rate": 3.6320000000000005e-05,
+      "loss": 7.0768,
+      "step": 460
+    },
+    {
+      "epoch": 0.024859504132231404,
+      "grad_norm": 64.50347900390625,
+      "learning_rate": 3.712e-05,
+      "loss": 7.0468,
+      "step": 470
+    },
+    {
+      "epoch": 0.025388429752066115,
+      "grad_norm": 89.8930892944336,
+      "learning_rate": 3.792e-05,
+      "loss": 6.9279,
+      "step": 480
+    },
+    {
+      "epoch": 0.025917355371900826,
+      "grad_norm": 103.4708251953125,
+      "learning_rate": 3.872e-05,
+      "loss": 6.8665,
+      "step": 490
+    },
+    {
+      "epoch": 0.026446280991735537,
+      "grad_norm": 96.82048034667969,
+      "learning_rate": 3.952e-05,
+      "loss": 6.9254,
+      "step": 500
+    }
+  ],
+  "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": 8700349361356800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15fcfa1bbe0f7d96538cf17908c1e0f3298cf826d4ee288e67e22815d92829e3
+size 5137