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 sha256:8b1f5fb4b5b7662feac73db16b15177b189872138f95698f1a9b1f862d216e00
+size 501759848

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb64e37ca108637a86280f15c467aedb8102b19a275dac0685ac9abfdba72ad6
+size 254028555

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c59e0ca9edabab78440af19aaf9d032bcb5072819d82562fa255cb7b86c6b9f9
+size 14645

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:203122e4bc844922324a7566f33d2d87cd58645589524a7d686fd6afbdbf4b0b
+size 1383

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b7c1b664d6b318bceef21e46397787622c46c950e75d4a0ef6b572c4898ce55
+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": 0.24614437906234377,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006153609476558594,
+      "grad_norm": 26290.87109375,
+      "learning_rate": 1.9999999999999996e-07,
+      "loss": 8.2122,
+      "step": 10
+    },
+    {
+      "epoch": 0.012307218953117188,
+      "grad_norm": 1750.26953125,
+      "learning_rate": 1.2e-06,
+      "loss": 7.6386,
+      "step": 20
+    },
+    {
+      "epoch": 0.018460828429675783,
+      "grad_norm": 235.5290985107422,
+      "learning_rate": 2.1999999999999997e-06,
+      "loss": 7.0511,
+      "step": 30
+    },
+    {
+      "epoch": 0.024614437906234375,
+      "grad_norm": 317.7790222167969,
+      "learning_rate": 3.1999999999999994e-06,
+      "loss": 6.889,
+      "step": 40
+    },
+    {
+      "epoch": 0.03076804738279297,
+      "grad_norm": 906.6453247070312,
+      "learning_rate": 4.2e-06,
+      "loss": 6.8145,
+      "step": 50
+    },
+    {
+      "epoch": 0.036921656859351566,
+      "grad_norm": 1056.044189453125,
+      "learning_rate": 5.199999999999999e-06,
+      "loss": 6.7193,
+      "step": 60
+    },
+    {
+      "epoch": 0.043075266335910155,
+      "grad_norm": 830.0984497070312,
+      "learning_rate": 6.199999999999999e-06,
+      "loss": 6.6406,
+      "step": 70
+    },
+    {
+      "epoch": 0.04922887581246875,
+      "grad_norm": 259.50299072265625,
+      "learning_rate": 7.2e-06,
+      "loss": 6.6149,
+      "step": 80
+    },
+    {
+      "epoch": 0.055382485289027346,
+      "grad_norm": 143.87599182128906,
+      "learning_rate": 8.2e-06,
+      "loss": 6.6122,
+      "step": 90
+    },
+    {
+      "epoch": 0.06153609476558594,
+      "grad_norm": 435.93017578125,
+      "learning_rate": 9.199999999999998e-06,
+      "loss": 6.5612,
+      "step": 100
+    },
+    {
+      "epoch": 0.06768970424214453,
+      "grad_norm": 557.260498046875,
+      "learning_rate": 1.02e-05,
+      "loss": 6.5083,
+      "step": 110
+    },
+    {
+      "epoch": 0.07384331371870313,
+      "grad_norm": 291.8673095703125,
+      "learning_rate": 1.12e-05,
+      "loss": 6.5365,
+      "step": 120
+    },
+    {
+      "epoch": 0.07999692319526172,
+      "grad_norm": 434.8012390136719,
+      "learning_rate": 1.2199999999999998e-05,
+      "loss": 6.5229,
+      "step": 130
+    },
+    {
+      "epoch": 0.08615053267182031,
+      "grad_norm": 1767.30908203125,
+      "learning_rate": 1.3199999999999997e-05,
+      "loss": 6.4961,
+      "step": 140
+    },
+    {
+      "epoch": 0.09230414214837891,
+      "grad_norm": 548.34228515625,
+      "learning_rate": 1.4199999999999998e-05,
+      "loss": 6.5135,
+      "step": 150
+    },
+    {
+      "epoch": 0.0984577516249375,
+      "grad_norm": 212.0412139892578,
+      "learning_rate": 1.5199999999999998e-05,
+      "loss": 6.47,
+      "step": 160
+    },
+    {
+      "epoch": 0.1046113611014961,
+      "grad_norm": 220.91732788085938,
+      "learning_rate": 1.6199999999999997e-05,
+      "loss": 6.4492,
+      "step": 170
+    },
+    {
+      "epoch": 0.11076497057805469,
+      "grad_norm": 275.8125305175781,
+      "learning_rate": 1.7199999999999998e-05,
+      "loss": 6.5087,
+      "step": 180
+    },
+    {
+      "epoch": 0.11691858005461328,
+      "grad_norm": 205.40353393554688,
+      "learning_rate": 1.82e-05,
+      "loss": 6.4695,
+      "step": 190
+    },
+    {
+      "epoch": 0.12307218953117188,
+      "grad_norm": 170.36024475097656,
+      "learning_rate": 1.92e-05,
+      "loss": 6.4184,
+      "step": 200
+    },
+    {
+      "epoch": 0.12922579900773049,
+      "grad_norm": 240.3199462890625,
+      "learning_rate": 2.0199999999999996e-05,
+      "loss": 6.4329,
+      "step": 210
+    },
+    {
+      "epoch": 0.13537940848428906,
+      "grad_norm": 508.4911193847656,
+      "learning_rate": 2.12e-05,
+      "loss": 6.3826,
+      "step": 220
+    },
+    {
+      "epoch": 0.14153301796084766,
+      "grad_norm": 117.4170150756836,
+      "learning_rate": 2.2199999999999998e-05,
+      "loss": 6.394,
+      "step": 230
+    },
+    {
+      "epoch": 0.14768662743740626,
+      "grad_norm": 76.04037475585938,
+      "learning_rate": 2.3199999999999998e-05,
+      "loss": 6.3696,
+      "step": 240
+    },
+    {
+      "epoch": 0.15384023691396484,
+      "grad_norm": 243.4922332763672,
+      "learning_rate": 2.42e-05,
+      "loss": 6.3843,
+      "step": 250
+    },
+    {
+      "epoch": 0.15999384639052344,
+      "grad_norm": 84.42725372314453,
+      "learning_rate": 2.52e-05,
+      "loss": 6.3401,
+      "step": 260
+    },
+    {
+      "epoch": 0.16614745586708204,
+      "grad_norm": 119.90478515625,
+      "learning_rate": 2.6199999999999996e-05,
+      "loss": 6.3586,
+      "step": 270
+    },
+    {
+      "epoch": 0.17230106534364062,
+      "grad_norm": 101.67578125,
+      "learning_rate": 2.72e-05,
+      "loss": 6.3315,
+      "step": 280
+    },
+    {
+      "epoch": 0.17845467482019922,
+      "grad_norm": 64.19589233398438,
+      "learning_rate": 2.8199999999999998e-05,
+      "loss": 6.3033,
+      "step": 290
+    },
+    {
+      "epoch": 0.18460828429675782,
+      "grad_norm": 43.22764205932617,
+      "learning_rate": 2.9199999999999995e-05,
+      "loss": 6.3065,
+      "step": 300
+    },
+    {
+      "epoch": 0.1907618937733164,
+      "grad_norm": 70.01463317871094,
+      "learning_rate": 3.02e-05,
+      "loss": 6.3044,
+      "step": 310
+    },
+    {
+      "epoch": 0.196915503249875,
+      "grad_norm": 48.240699768066406,
+      "learning_rate": 3.119999999999999e-05,
+      "loss": 6.2598,
+      "step": 320
+    },
+    {
+      "epoch": 0.2030691127264336,
+      "grad_norm": 59.44075012207031,
+      "learning_rate": 3.22e-05,
+      "loss": 6.2607,
+      "step": 330
+    },
+    {
+      "epoch": 0.2092227222029922,
+      "grad_norm": 61.2050666809082,
+      "learning_rate": 3.3199999999999994e-05,
+      "loss": 6.2497,
+      "step": 340
+    },
+    {
+      "epoch": 0.21537633167955078,
+      "grad_norm": 60.02091598510742,
+      "learning_rate": 3.42e-05,
+      "loss": 6.2319,
+      "step": 350
+    },
+    {
+      "epoch": 0.22152994115610938,
+      "grad_norm": 41.094627380371094,
+      "learning_rate": 3.5199999999999995e-05,
+      "loss": 6.219,
+      "step": 360
+    },
+    {
+      "epoch": 0.22768355063266799,
+      "grad_norm": 64.33719635009766,
+      "learning_rate": 3.62e-05,
+      "loss": 6.2147,
+      "step": 370
+    },
+    {
+      "epoch": 0.23383716010922656,
+      "grad_norm": 62.03013610839844,
+      "learning_rate": 3.7199999999999996e-05,
+      "loss": 6.1763,
+      "step": 380
+    },
+    {
+      "epoch": 0.23999076958578516,
+      "grad_norm": 181.71493530273438,
+      "learning_rate": 3.8199999999999993e-05,
+      "loss": 6.1753,
+      "step": 390
+    },
+    {
+      "epoch": 0.24614437906234377,
+      "grad_norm": 80.83346557617188,
+      "learning_rate": 3.919999999999999e-05,
+      "loss": 6.1614,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 62,
+  "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": 3.03139582316544e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d8a04beb8e0a03960173726e811f1b8582eccdf1b28b006a6664bc6f7605bb
+size 5201