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_16k",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 16,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
+  "vocab_size": 16384
+}

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:a4116cf63f3377424260b78c124d94105a0f28f1c163b3a57e54def5446b4104
+size 543870712

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dafa5ede514f4f00296cea2c9a74a410ba73e4e7631b03975132c56517f19ff
+size 276872907

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e4f902c8906d623a114c0c367bef3954414e2be4936e32e48f1634a18a8291
+size 14645

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:042bec69325cffd026bbe8e7d33a18e1c2c76d1fe7ec21ff3bbfd51714aa90e9
+size 1383

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc86464e62c82ee7b5d292eda3c31d3ee68398f148ca7b653d19857053d32294
+size 1465

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "HFCompatibleLinguisticTokenizer",
+  "vocab_size": 16384,
+  "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": 0.0013830302192102898,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.4575755480257244e-05,
+      "grad_norm": 38.12546920776367,
+      "learning_rate": 4.8e-07,
+      "loss": 9.3097,
+      "step": 10
+    },
+    {
+      "epoch": 6.915151096051449e-05,
+      "grad_norm": 31.766887664794922,
+      "learning_rate": 1.0799999999999998e-06,
+      "loss": 9.293,
+      "step": 20
+    },
+    {
+      "epoch": 0.00010372726644077173,
+      "grad_norm": 48.67866897583008,
+      "learning_rate": 1.6799999999999998e-06,
+      "loss": 9.2784,
+      "step": 30
+    },
+    {
+      "epoch": 0.00013830302192102898,
+      "grad_norm": 33.25461959838867,
+      "learning_rate": 2.2799999999999998e-06,
+      "loss": 9.2793,
+      "step": 40
+    },
+    {
+      "epoch": 0.00017287877740128623,
+      "grad_norm": 35.62735366821289,
+      "learning_rate": 2.8799999999999995e-06,
+      "loss": 9.2657,
+      "step": 50
+    },
+    {
+      "epoch": 0.00020745453288154345,
+      "grad_norm": 43.818328857421875,
+      "learning_rate": 3.4799999999999993e-06,
+      "loss": 9.2616,
+      "step": 60
+    },
+    {
+      "epoch": 0.0002420302883618007,
+      "grad_norm": 43.82963943481445,
+      "learning_rate": 4.079999999999999e-06,
+      "loss": 9.2633,
+      "step": 70
+    },
+    {
+      "epoch": 0.00027660604384205796,
+      "grad_norm": 57.38799285888672,
+      "learning_rate": 4.679999999999999e-06,
+      "loss": 9.2308,
+      "step": 80
+    },
+    {
+      "epoch": 0.0003111817993223152,
+      "grad_norm": 44.78755187988281,
+      "learning_rate": 5.28e-06,
+      "loss": 9.2083,
+      "step": 90
+    },
+    {
+      "epoch": 0.00034575755480257246,
+      "grad_norm": 40.440338134765625,
+      "learning_rate": 5.88e-06,
+      "loss": 9.2418,
+      "step": 100
+    },
+    {
+      "epoch": 0.00038033331028282965,
+      "grad_norm": 36.28009033203125,
+      "learning_rate": 6.48e-06,
+      "loss": 9.2208,
+      "step": 110
+    },
+    {
+      "epoch": 0.0004149090657630869,
+      "grad_norm": 42.1943473815918,
+      "learning_rate": 7.079999999999999e-06,
+      "loss": 9.2197,
+      "step": 120
+    },
+    {
+      "epoch": 0.00044948482124334416,
+      "grad_norm": 37.897483825683594,
+      "learning_rate": 7.68e-06,
+      "loss": 9.2271,
+      "step": 130
+    },
+    {
+      "epoch": 0.0004840605767236014,
+      "grad_norm": 33.77066421508789,
+      "learning_rate": 8.279999999999999e-06,
+      "loss": 9.2311,
+      "step": 140
+    },
+    {
+      "epoch": 0.0005186363322038587,
+      "grad_norm": 34.798553466796875,
+      "learning_rate": 8.88e-06,
+      "loss": 9.2079,
+      "step": 150
+    },
+    {
+      "epoch": 0.0005532120876841159,
+      "grad_norm": 39.236812591552734,
+      "learning_rate": 9.48e-06,
+      "loss": 9.2186,
+      "step": 160
+    },
+    {
+      "epoch": 0.0005877878431643732,
+      "grad_norm": 37.878868103027344,
+      "learning_rate": 1.0079999999999998e-05,
+      "loss": 9.2176,
+      "step": 170
+    },
+    {
+      "epoch": 0.0006223635986446304,
+      "grad_norm": 64.34676361083984,
+      "learning_rate": 1.068e-05,
+      "loss": 9.2086,
+      "step": 180
+    },
+    {
+      "epoch": 0.0006569393541248877,
+      "grad_norm": 35.60507583618164,
+      "learning_rate": 1.1279999999999999e-05,
+      "loss": 9.2045,
+      "step": 190
+    },
+    {
+      "epoch": 0.0006915151096051449,
+      "grad_norm": 45.516971588134766,
+      "learning_rate": 1.188e-05,
+      "loss": 9.2144,
+      "step": 200
+    },
+    {
+      "epoch": 0.0007260908650854022,
+      "grad_norm": 33.20392608642578,
+      "learning_rate": 1.2479999999999999e-05,
+      "loss": 9.1846,
+      "step": 210
+    },
+    {
+      "epoch": 0.0007606666205656593,
+      "grad_norm": 33.04153060913086,
+      "learning_rate": 1.3019999999999999e-05,
+      "loss": 9.1875,
+      "step": 220
+    },
+    {
+      "epoch": 0.0007952423760459166,
+      "grad_norm": 29.512754440307617,
+      "learning_rate": 1.362e-05,
+      "loss": 9.1849,
+      "step": 230
+    },
+    {
+      "epoch": 0.0008298181315261738,
+      "grad_norm": 24.111255645751953,
+      "learning_rate": 1.4219999999999998e-05,
+      "loss": 9.2074,
+      "step": 240
+    },
+    {
+      "epoch": 0.0008643938870064311,
+      "grad_norm": 36.84242630004883,
+      "learning_rate": 1.4819999999999999e-05,
+      "loss": 9.1818,
+      "step": 250
+    },
+    {
+      "epoch": 0.0008989696424866883,
+      "grad_norm": 22.629037857055664,
+      "learning_rate": 1.5419999999999998e-05,
+      "loss": 9.1991,
+      "step": 260
+    },
+    {
+      "epoch": 0.0009335453979669456,
+      "grad_norm": 28.257951736450195,
+      "learning_rate": 1.602e-05,
+      "loss": 9.1579,
+      "step": 270
+    },
+    {
+      "epoch": 0.0009681211534472028,
+      "grad_norm": 26.29328155517578,
+      "learning_rate": 1.6619999999999997e-05,
+      "loss": 9.1753,
+      "step": 280
+    },
+    {
+      "epoch": 0.00100269690892746,
+      "grad_norm": 30.55463981628418,
+      "learning_rate": 1.7219999999999998e-05,
+      "loss": 9.1663,
+      "step": 290
+    },
+    {
+      "epoch": 0.0010372726644077173,
+      "grad_norm": 30.852642059326172,
+      "learning_rate": 1.782e-05,
+      "loss": 9.1624,
+      "step": 300
+    },
+    {
+      "epoch": 0.0010718484198879745,
+      "grad_norm": 30.8385009765625,
+      "learning_rate": 1.842e-05,
+      "loss": 9.1754,
+      "step": 310
+    },
+    {
+      "epoch": 0.0011064241753682318,
+      "grad_norm": 16.846324920654297,
+      "learning_rate": 1.9019999999999997e-05,
+      "loss": 9.1774,
+      "step": 320
+    },
+    {
+      "epoch": 0.001140999930848489,
+      "grad_norm": 26.020891189575195,
+      "learning_rate": 1.962e-05,
+      "loss": 9.1461,
+      "step": 330
+    },
+    {
+      "epoch": 0.0011755756863287463,
+      "grad_norm": 24.087093353271484,
+      "learning_rate": 2.022e-05,
+      "loss": 9.1698,
+      "step": 340
+    },
+    {
+      "epoch": 0.0012101514418090035,
+      "grad_norm": 22.612030029296875,
+      "learning_rate": 2.082e-05,
+      "loss": 9.1564,
+      "step": 350
+    },
+    {
+      "epoch": 0.0012447271972892608,
+      "grad_norm": 24.23309898376465,
+      "learning_rate": 2.1419999999999998e-05,
+      "loss": 9.1407,
+      "step": 360
+    },
+    {
+      "epoch": 0.001279302952769518,
+      "grad_norm": 19.798912048339844,
+      "learning_rate": 2.202e-05,
+      "loss": 9.1916,
+      "step": 370
+    },
+    {
+      "epoch": 0.0013138787082497753,
+      "grad_norm": 17.621305465698242,
+      "learning_rate": 2.2619999999999997e-05,
+      "loss": 9.1724,
+      "step": 380
+    },
+    {
+      "epoch": 0.0013484544637300325,
+      "grad_norm": 19.028974533081055,
+      "learning_rate": 2.3219999999999998e-05,
+      "loss": 9.1416,
+      "step": 390
+    },
+    {
+      "epoch": 0.0013830302192102898,
+      "grad_norm": 15.816458702087402,
+      "learning_rate": 2.382e-05,
+      "loss": 9.1704,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1276491534336000.0,
+  "train_batch_size": 4,
+  "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:a746fe2aa9d502223795e2f6a42a0bba1c746d65b90cdeab7a9a789b02ea1695
+size 5201