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 sha256:76617ad0a8735c7d1c6f80f664adbfdc328cf6bdda46646a856c897767d501db
+size 501759848

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0b5f0c0617366487866f731b3a2e0f7f55f9ab00317088cd9e91c345e496c2
+size 254028555

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fbbd01b7f35459c3b4e0e752391da1b0481879fcbddb78fc341114fa44cdd18
+size 14645

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca7f49fa8e5b7b36f5a7b879d2c054308a7f330b78c207e7de66d4d9a23df71f
+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": 0.08399391044149299,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002099847761037325,
+      "grad_norm": 22925.884765625,
+      "learning_rate": 1.9999999999999996e-07,
+      "loss": 9.5004,
+      "step": 10
+    },
+    {
+      "epoch": 0.00419969552207465,
+      "grad_norm": 1589.221435546875,
+      "learning_rate": 1.2e-06,
+      "loss": 8.7173,
+      "step": 20
+    },
+    {
+      "epoch": 0.006299543283111974,
+      "grad_norm": 577.2943115234375,
+      "learning_rate": 2.1999999999999997e-06,
+      "loss": 7.6284,
+      "step": 30
+    },
+    {
+      "epoch": 0.0083993910441493,
+      "grad_norm": 308.8800048828125,
+      "learning_rate": 3.1999999999999994e-06,
+      "loss": 7.2988,
+      "step": 40
+    },
+    {
+      "epoch": 0.010499238805186623,
+      "grad_norm": 458.5738220214844,
+      "learning_rate": 4.2e-06,
+      "loss": 7.1397,
+      "step": 50
+    },
+    {
+      "epoch": 0.012599086566223949,
+      "grad_norm": 2117.726806640625,
+      "learning_rate": 5.199999999999999e-06,
+      "loss": 7.0424,
+      "step": 60
+    },
+    {
+      "epoch": 0.014698934327261274,
+      "grad_norm": 784.7866821289062,
+      "learning_rate": 6.199999999999999e-06,
+      "loss": 6.9896,
+      "step": 70
+    },
+    {
+      "epoch": 0.0167987820882986,
+      "grad_norm": 719.2965087890625,
+      "learning_rate": 7.2e-06,
+      "loss": 6.9514,
+      "step": 80
+    },
+    {
+      "epoch": 0.018898629849335925,
+      "grad_norm": 887.7239379882812,
+      "learning_rate": 8.2e-06,
+      "loss": 6.9188,
+      "step": 90
+    },
+    {
+      "epoch": 0.020998477610373247,
+      "grad_norm": 657.1996459960938,
+      "learning_rate": 9.199999999999998e-06,
+      "loss": 6.9113,
+      "step": 100
+    },
+    {
+      "epoch": 0.023098325371410572,
+      "grad_norm": 1241.19482421875,
+      "learning_rate": 1.02e-05,
+      "loss": 6.8953,
+      "step": 110
+    },
+    {
+      "epoch": 0.025198173132447897,
+      "grad_norm": 411.5585021972656,
+      "learning_rate": 1.12e-05,
+      "loss": 6.8474,
+      "step": 120
+    },
+    {
+      "epoch": 0.027298020893485223,
+      "grad_norm": 1062.7774658203125,
+      "learning_rate": 1.2199999999999998e-05,
+      "loss": 6.8514,
+      "step": 130
+    },
+    {
+      "epoch": 0.029397868654522548,
+      "grad_norm": 148.0970001220703,
+      "learning_rate": 1.3199999999999997e-05,
+      "loss": 6.8698,
+      "step": 140
+    },
+    {
+      "epoch": 0.03149771641555987,
+      "grad_norm": 280.5868835449219,
+      "learning_rate": 1.4199999999999998e-05,
+      "loss": 6.8395,
+      "step": 150
+    },
+    {
+      "epoch": 0.0335975641765972,
+      "grad_norm": 407.1022644042969,
+      "learning_rate": 1.5199999999999998e-05,
+      "loss": 6.8029,
+      "step": 160
+    },
+    {
+      "epoch": 0.035697411937634524,
+      "grad_norm": 166.18153381347656,
+      "learning_rate": 1.6199999999999997e-05,
+      "loss": 6.7946,
+      "step": 170
+    },
+    {
+      "epoch": 0.03779725969867185,
+      "grad_norm": 234.69805908203125,
+      "learning_rate": 1.7199999999999998e-05,
+      "loss": 6.7898,
+      "step": 180
+    },
+    {
+      "epoch": 0.03989710745970917,
+      "grad_norm": 917.2261352539062,
+      "learning_rate": 1.82e-05,
+      "loss": 6.7996,
+      "step": 190
+    },
+    {
+      "epoch": 0.04199695522074649,
+      "grad_norm": 237.35519409179688,
+      "learning_rate": 1.92e-05,
+      "loss": 6.7733,
+      "step": 200
+    },
+    {
+      "epoch": 0.04409680298178382,
+      "grad_norm": 49.55766296386719,
+      "learning_rate": 2.0199999999999996e-05,
+      "loss": 6.7318,
+      "step": 210
+    },
+    {
+      "epoch": 0.046196650742821144,
+      "grad_norm": 152.66554260253906,
+      "learning_rate": 2.12e-05,
+      "loss": 6.6867,
+      "step": 220
+    },
+    {
+      "epoch": 0.04829649850385847,
+      "grad_norm": 284.306640625,
+      "learning_rate": 2.2199999999999998e-05,
+      "loss": 6.6555,
+      "step": 230
+    },
+    {
+      "epoch": 0.050396346264895794,
+      "grad_norm": 127.93234252929688,
+      "learning_rate": 2.3199999999999998e-05,
+      "loss": 6.6263,
+      "step": 240
+    },
+    {
+      "epoch": 0.05249619402593312,
+      "grad_norm": 119.77033996582031,
+      "learning_rate": 2.42e-05,
+      "loss": 6.649,
+      "step": 250
+    },
+    {
+      "epoch": 0.054596041786970445,
+      "grad_norm": 389.56536865234375,
+      "learning_rate": 2.52e-05,
+      "loss": 6.6383,
+      "step": 260
+    },
+    {
+      "epoch": 0.05669588954800777,
+      "grad_norm": 427.01580810546875,
+      "learning_rate": 2.6199999999999996e-05,
+      "loss": 6.593,
+      "step": 270
+    },
+    {
+      "epoch": 0.058795737309045096,
+      "grad_norm": 222.83114624023438,
+      "learning_rate": 2.72e-05,
+      "loss": 6.5701,
+      "step": 280
+    },
+    {
+      "epoch": 0.06089558507008242,
+      "grad_norm": 92.09854125976562,
+      "learning_rate": 2.8199999999999998e-05,
+      "loss": 6.5495,
+      "step": 290
+    },
+    {
+      "epoch": 0.06299543283111975,
+      "grad_norm": 137.1016082763672,
+      "learning_rate": 2.9199999999999995e-05,
+      "loss": 6.5433,
+      "step": 300
+    },
+    {
+      "epoch": 0.06509528059215706,
+      "grad_norm": 165.11099243164062,
+      "learning_rate": 3.02e-05,
+      "loss": 6.5528,
+      "step": 310
+    },
+    {
+      "epoch": 0.0671951283531944,
+      "grad_norm": 193.72972106933594,
+      "learning_rate": 3.119999999999999e-05,
+      "loss": 6.4983,
+      "step": 320
+    },
+    {
+      "epoch": 0.06929497611423172,
+      "grad_norm": 168.2730255126953,
+      "learning_rate": 3.22e-05,
+      "loss": 6.4875,
+      "step": 330
+    },
+    {
+      "epoch": 0.07139482387526905,
+      "grad_norm": 204.45751953125,
+      "learning_rate": 3.3199999999999994e-05,
+      "loss": 6.4667,
+      "step": 340
+    },
+    {
+      "epoch": 0.07349467163630637,
+      "grad_norm": 200.1185302734375,
+      "learning_rate": 3.42e-05,
+      "loss": 6.4163,
+      "step": 350
+    },
+    {
+      "epoch": 0.0755945193973437,
+      "grad_norm": 212.8289337158203,
+      "learning_rate": 3.5199999999999995e-05,
+      "loss": 6.4009,
+      "step": 360
+    },
+    {
+      "epoch": 0.07769436715838102,
+      "grad_norm": 67.6531982421875,
+      "learning_rate": 3.62e-05,
+      "loss": 6.3942,
+      "step": 370
+    },
+    {
+      "epoch": 0.07979421491941834,
+      "grad_norm": 103.08153533935547,
+      "learning_rate": 3.7199999999999996e-05,
+      "loss": 6.37,
+      "step": 380
+    },
+    {
+      "epoch": 0.08189406268045567,
+      "grad_norm": 155.30517578125,
+      "learning_rate": 3.8199999999999993e-05,
+      "loss": 6.3541,
+      "step": 390
+    },
+    {
+      "epoch": 0.08399391044149299,
+      "grad_norm": 78.574462890625,
+      "learning_rate": 3.919999999999999e-05,
+      "loss": 6.331,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 21,
+  "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": 2.60705846759424e+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:e4273736f78f1a1a756fad9c1dcb6f595241640fb3898b11c26e020ad95062f5
+size 5201