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:a807e89e75de0f6ec5814d1285465776f5ee1ca3cd0e4136761fdb710b6cb6d0
+size 501755480

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f33e1f6de370145e431c33a2e8a0304d4bbd2e2f90ad90399997c70d0f1641b0
+size 254028555

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b808243ef02c3a2d3019a40ba1120742141ec60059dc52d647c5aa1fe0daf5b
+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": 0.06153609476558594,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0015384023691396484,
+      "grad_norm": 15216.6796875,
+      "learning_rate": 1.9999999999999996e-07,
+      "loss": 7.628,
+      "step": 10
+    },
+    {
+      "epoch": 0.003076804738279297,
+      "grad_norm": 539.3572387695312,
+      "learning_rate": 1.2e-06,
+      "loss": 7.3644,
+      "step": 20
+    },
+    {
+      "epoch": 0.004615207107418946,
+      "grad_norm": 496.3940734863281,
+      "learning_rate": 2.1999999999999997e-06,
+      "loss": 7.0137,
+      "step": 30
+    },
+    {
+      "epoch": 0.006153609476558594,
+      "grad_norm": 110.5931396484375,
+      "learning_rate": 3.1999999999999994e-06,
+      "loss": 6.9299,
+      "step": 40
+    },
+    {
+      "epoch": 0.007692011845698243,
+      "grad_norm": 442.7750549316406,
+      "learning_rate": 4.2e-06,
+      "loss": 6.88,
+      "step": 50
+    },
+    {
+      "epoch": 0.009230414214837892,
+      "grad_norm": 285.75390625,
+      "learning_rate": 5.199999999999999e-06,
+      "loss": 6.7252,
+      "step": 60
+    },
+    {
+      "epoch": 0.010768816583977539,
+      "grad_norm": 238.201416015625,
+      "learning_rate": 6.199999999999999e-06,
+      "loss": 6.7641,
+      "step": 70
+    },
+    {
+      "epoch": 0.012307218953117188,
+      "grad_norm": 203.7633514404297,
+      "learning_rate": 7.2e-06,
+      "loss": 6.6961,
+      "step": 80
+    },
+    {
+      "epoch": 0.013845621322256836,
+      "grad_norm": 537.8616943359375,
+      "learning_rate": 8.2e-06,
+      "loss": 6.5996,
+      "step": 90
+    },
+    {
+      "epoch": 0.015384023691396485,
+      "grad_norm": 643.6299438476562,
+      "learning_rate": 9.199999999999998e-06,
+      "loss": 6.5856,
+      "step": 100
+    },
+    {
+      "epoch": 0.016922426060536132,
+      "grad_norm": 679.996337890625,
+      "learning_rate": 1.02e-05,
+      "loss": 6.599,
+      "step": 110
+    },
+    {
+      "epoch": 0.018460828429675783,
+      "grad_norm": 452.3795471191406,
+      "learning_rate": 1.12e-05,
+      "loss": 6.6354,
+      "step": 120
+    },
+    {
+      "epoch": 0.01999923079881543,
+      "grad_norm": 117.24376678466797,
+      "learning_rate": 1.2199999999999998e-05,
+      "loss": 6.5363,
+      "step": 130
+    },
+    {
+      "epoch": 0.021537633167955077,
+      "grad_norm": 145.65036010742188,
+      "learning_rate": 1.3199999999999997e-05,
+      "loss": 6.5564,
+      "step": 140
+    },
+    {
+      "epoch": 0.023076035537094728,
+      "grad_norm": 178.4263458251953,
+      "learning_rate": 1.4199999999999998e-05,
+      "loss": 6.5828,
+      "step": 150
+    },
+    {
+      "epoch": 0.024614437906234375,
+      "grad_norm": 174.7183837890625,
+      "learning_rate": 1.5199999999999998e-05,
+      "loss": 6.4821,
+      "step": 160
+    },
+    {
+      "epoch": 0.026152840275374026,
+      "grad_norm": 145.78704833984375,
+      "learning_rate": 1.6199999999999997e-05,
+      "loss": 6.4711,
+      "step": 170
+    },
+    {
+      "epoch": 0.027691242644513673,
+      "grad_norm": 217.81866455078125,
+      "learning_rate": 1.7199999999999998e-05,
+      "loss": 6.4947,
+      "step": 180
+    },
+    {
+      "epoch": 0.02922964501365332,
+      "grad_norm": 105.79635620117188,
+      "learning_rate": 1.82e-05,
+      "loss": 6.4997,
+      "step": 190
+    },
+    {
+      "epoch": 0.03076804738279297,
+      "grad_norm": 86.61837768554688,
+      "learning_rate": 1.92e-05,
+      "loss": 6.4604,
+      "step": 200
+    },
+    {
+      "epoch": 0.03230644975193262,
+      "grad_norm": 102.03221893310547,
+      "learning_rate": 2.0199999999999996e-05,
+      "loss": 6.4451,
+      "step": 210
+    },
+    {
+      "epoch": 0.033844852121072265,
+      "grad_norm": 93.15425109863281,
+      "learning_rate": 2.12e-05,
+      "loss": 6.4653,
+      "step": 220
+    },
+    {
+      "epoch": 0.035383254490211916,
+      "grad_norm": 120.66065979003906,
+      "learning_rate": 2.2199999999999998e-05,
+      "loss": 6.3898,
+      "step": 230
+    },
+    {
+      "epoch": 0.036921656859351566,
+      "grad_norm": 108.00463104248047,
+      "learning_rate": 2.3199999999999998e-05,
+      "loss": 6.3907,
+      "step": 240
+    },
+    {
+      "epoch": 0.03846005922849121,
+      "grad_norm": 129.6912841796875,
+      "learning_rate": 2.42e-05,
+      "loss": 6.3551,
+      "step": 250
+    },
+    {
+      "epoch": 0.03999846159763086,
+      "grad_norm": 66.96916961669922,
+      "learning_rate": 2.52e-05,
+      "loss": 6.3443,
+      "step": 260
+    },
+    {
+      "epoch": 0.04153686396677051,
+      "grad_norm": 44.31541061401367,
+      "learning_rate": 2.6199999999999996e-05,
+      "loss": 6.3372,
+      "step": 270
+    },
+    {
+      "epoch": 0.043075266335910155,
+      "grad_norm": 21.828279495239258,
+      "learning_rate": 2.72e-05,
+      "loss": 6.3368,
+      "step": 280
+    },
+    {
+      "epoch": 0.044613668705049805,
+      "grad_norm": 38.62431716918945,
+      "learning_rate": 2.8199999999999998e-05,
+      "loss": 6.2708,
+      "step": 290
+    },
+    {
+      "epoch": 0.046152071074189456,
+      "grad_norm": 28.7634334564209,
+      "learning_rate": 2.9199999999999995e-05,
+      "loss": 6.3324,
+      "step": 300
+    },
+    {
+      "epoch": 0.0476904734433291,
+      "grad_norm": 29.64866065979004,
+      "learning_rate": 3.02e-05,
+      "loss": 6.329,
+      "step": 310
+    },
+    {
+      "epoch": 0.04922887581246875,
+      "grad_norm": 27.20194435119629,
+      "learning_rate": 3.119999999999999e-05,
+      "loss": 6.2864,
+      "step": 320
+    },
+    {
+      "epoch": 0.0507672781816084,
+      "grad_norm": 24.59855079650879,
+      "learning_rate": 3.22e-05,
+      "loss": 6.2371,
+      "step": 330
+    },
+    {
+      "epoch": 0.05230568055074805,
+      "grad_norm": 32.6953239440918,
+      "learning_rate": 3.3199999999999994e-05,
+      "loss": 6.2824,
+      "step": 340
+    },
+    {
+      "epoch": 0.053844082919887695,
+      "grad_norm": 36.308067321777344,
+      "learning_rate": 3.42e-05,
+      "loss": 6.2977,
+      "step": 350
+    },
+    {
+      "epoch": 0.055382485289027346,
+      "grad_norm": 25.23465347290039,
+      "learning_rate": 3.5199999999999995e-05,
+      "loss": 6.3222,
+      "step": 360
+    },
+    {
+      "epoch": 0.056920887658166996,
+      "grad_norm": 47.594947814941406,
+      "learning_rate": 3.62e-05,
+      "loss": 6.2513,
+      "step": 370
+    },
+    {
+      "epoch": 0.05845929002730664,
+      "grad_norm": 44.8812370300293,
+      "learning_rate": 3.7199999999999996e-05,
+      "loss": 6.2244,
+      "step": 380
+    },
+    {
+      "epoch": 0.05999769239644629,
+      "grad_norm": 22.950286865234375,
+      "learning_rate": 3.8199999999999993e-05,
+      "loss": 6.1613,
+      "step": 390
+    },
+    {
+      "epoch": 0.06153609476558594,
+      "grad_norm": 23.65997314453125,
+      "learning_rate": 3.919999999999999e-05,
+      "loss": 6.1839,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 16,
+  "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": 7669252594483200.0,
+  "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 sha256:62417cc687938b852957f7012ea833e7979cfe3f532b1c8c4b1c41687231ccf6
+size 5201