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": 4032
+}

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 sha256:01add500eef8a7dd424ab074d6c0211792b6ea35378e46986d2e1c1a2460dc8d
+size 483923272

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:694a8416555c7b3b0c58871e86522723fd6a7eee9cae705fa1e1642c887f94dc
+size 245762443

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f117a485cff21d717af2c2d6ee1371f06a9625d9bde4c18c159167cf8bd2886
+size 14645

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2931fa14e239aaef9bdf318d3656a5a1aa4573481c655c08eacc8d1727f88a9
+size 1383

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a589639ba1c962a21780a574f41234aef798e0155ef3d3bf8385cc3a689b83
+size 1465

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "HFCompatibleHybridTokenizer",
+  "vocab_size": 4032,
+  "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": 1.2163809523809523,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.030476190476190476,
+      "grad_norm": 19001.3984375,
+      "learning_rate": 1.9999999999999996e-07,
+      "loss": 11.768,
+      "step": 10
+    },
+    {
+      "epoch": 0.06095238095238095,
+      "grad_norm": 1090.6541748046875,
+      "learning_rate": 1.2e-06,
+      "loss": 10.832,
+      "step": 20
+    },
+    {
+      "epoch": 0.09142857142857143,
+      "grad_norm": 483.8899841308594,
+      "learning_rate": 2.1999999999999997e-06,
+      "loss": 9.7733,
+      "step": 30
+    },
+    {
+      "epoch": 0.1219047619047619,
+      "grad_norm": 310.4847106933594,
+      "learning_rate": 3.1999999999999994e-06,
+      "loss": 9.667,
+      "step": 40
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 312.90118408203125,
+      "learning_rate": 4.2e-06,
+      "loss": 9.4134,
+      "step": 50
+    },
+    {
+      "epoch": 0.18285714285714286,
+      "grad_norm": 225.17079162597656,
+      "learning_rate": 5.199999999999999e-06,
+      "loss": 9.3105,
+      "step": 60
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1866.8404541015625,
+      "learning_rate": 6.199999999999999e-06,
+      "loss": 9.4153,
+      "step": 70
+    },
+    {
+      "epoch": 0.2438095238095238,
+      "grad_norm": 557.7033081054688,
+      "learning_rate": 7.2e-06,
+      "loss": 9.454,
+      "step": 80
+    },
+    {
+      "epoch": 0.2742857142857143,
+      "grad_norm": 573.1474609375,
+      "learning_rate": 8.2e-06,
+      "loss": 9.2006,
+      "step": 90
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 8320.33203125,
+      "learning_rate": 9.199999999999998e-06,
+      "loss": 9.2594,
+      "step": 100
+    },
+    {
+      "epoch": 0.3352380952380952,
+      "grad_norm": 4550.92431640625,
+      "learning_rate": 1.0099999999999998e-05,
+      "loss": 9.174,
+      "step": 110
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "grad_norm": 5021.208984375,
+      "learning_rate": 1.1099999999999999e-05,
+      "loss": 9.08,
+      "step": 120
+    },
+    {
+      "epoch": 0.3961904761904762,
+      "grad_norm": 4049.0517578125,
+      "learning_rate": 1.21e-05,
+      "loss": 9.0038,
+      "step": 130
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 2612.63916015625,
+      "learning_rate": 1.3099999999999998e-05,
+      "loss": 8.8032,
+      "step": 140
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 1136.939697265625,
+      "learning_rate": 1.4099999999999999e-05,
+      "loss": 8.6256,
+      "step": 150
+    },
+    {
+      "epoch": 0.4876190476190476,
+      "grad_norm": 3167.787353515625,
+      "learning_rate": 1.51e-05,
+      "loss": 8.4089,
+      "step": 160
+    },
+    {
+      "epoch": 0.518095238095238,
+      "grad_norm": 2789.38134765625,
+      "learning_rate": 1.61e-05,
+      "loss": 8.5092,
+      "step": 170
+    },
+    {
+      "epoch": 0.5485714285714286,
+      "grad_norm": 852.837158203125,
+      "learning_rate": 1.71e-05,
+      "loss": 8.2976,
+      "step": 180
+    },
+    {
+      "epoch": 0.579047619047619,
+      "grad_norm": 3195.60400390625,
+      "learning_rate": 1.81e-05,
+      "loss": 8.015,
+      "step": 190
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "grad_norm": 1504.184814453125,
+      "learning_rate": 1.9099999999999997e-05,
+      "loss": 7.8722,
+      "step": 200
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1651.9476318359375,
+      "learning_rate": 2.01e-05,
+      "loss": 7.7998,
+      "step": 210
+    },
+    {
+      "epoch": 0.6704761904761904,
+      "grad_norm": 1374.2181396484375,
+      "learning_rate": 2.1099999999999998e-05,
+      "loss": 7.7693,
+      "step": 220
+    },
+    {
+      "epoch": 0.700952380952381,
+      "grad_norm": 5336.3330078125,
+      "learning_rate": 2.21e-05,
+      "loss": 7.6378,
+      "step": 230
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "grad_norm": 2519.78173828125,
+      "learning_rate": 2.31e-05,
+      "loss": 7.71,
+      "step": 240
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 2713.69921875,
+      "learning_rate": 2.41e-05,
+      "loss": 7.6609,
+      "step": 250
+    },
+    {
+      "epoch": 0.7923809523809524,
+      "grad_norm": 3746.745361328125,
+      "learning_rate": 2.5099999999999997e-05,
+      "loss": 7.4668,
+      "step": 260
+    },
+    {
+      "epoch": 0.8228571428571428,
+      "grad_norm": 1610.9803466796875,
+      "learning_rate": 2.6099999999999997e-05,
+      "loss": 7.3347,
+      "step": 270
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 639.0009765625,
+      "learning_rate": 2.7099999999999998e-05,
+      "loss": 7.3286,
+      "step": 280
+    },
+    {
+      "epoch": 0.8838095238095238,
+      "grad_norm": 2618.20263671875,
+      "learning_rate": 2.8099999999999995e-05,
+      "loss": 7.296,
+      "step": 290
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 3252.7421875,
+      "learning_rate": 2.91e-05,
+      "loss": 7.0725,
+      "step": 300
+    },
+    {
+      "epoch": 0.9447619047619048,
+      "grad_norm": 4246.71435546875,
+      "learning_rate": 3.0099999999999996e-05,
+      "loss": 7.3166,
+      "step": 310
+    },
+    {
+      "epoch": 0.9752380952380952,
+      "grad_norm": 2218.63720703125,
+      "learning_rate": 3.11e-05,
+      "loss": 7.0924,
+      "step": 320
+    },
+    {
+      "epoch": 1.003047619047619,
+      "grad_norm": 2834.141357421875,
+      "learning_rate": 3.2099999999999994e-05,
+      "loss": 6.8622,
+      "step": 330
+    },
+    {
+      "epoch": 1.0335238095238095,
+      "grad_norm": 3740.896240234375,
+      "learning_rate": 3.31e-05,
+      "loss": 6.9755,
+      "step": 340
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 783.5746459960938,
+      "learning_rate": 3.4099999999999995e-05,
+      "loss": 6.9616,
+      "step": 350
+    },
+    {
+      "epoch": 1.0944761904761904,
+      "grad_norm": 1153.624755859375,
+      "learning_rate": 3.51e-05,
+      "loss": 6.9227,
+      "step": 360
+    },
+    {
+      "epoch": 1.124952380952381,
+      "grad_norm": 4491.00634765625,
+      "learning_rate": 3.6099999999999997e-05,
+      "loss": 6.9063,
+      "step": 370
+    },
+    {
+      "epoch": 1.1554285714285715,
+      "grad_norm": 1424.7935791015625,
+      "learning_rate": 3.7099999999999994e-05,
+      "loss": 6.877,
+      "step": 380
+    },
+    {
+      "epoch": 1.1859047619047618,
+      "grad_norm": 1928.0592041015625,
+      "learning_rate": 3.81e-05,
+      "loss": 6.8588,
+      "step": 390
+    },
+    {
+      "epoch": 1.2163809523809523,
+      "grad_norm": 1208.5244140625,
+      "learning_rate": 3.9099999999999995e-05,
+      "loss": 6.6404,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 50000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 152,
+  "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": 8088298937155584.0,
+  "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:f5d62b58803f3df91cbb2dc55e80cd5e08feec723ef6772fad70777790cbe8a5
+size 5201