Upload folder using huggingface_hub

checkpoint-300/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": 4096
+}

checkpoint-300/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.1"
+}

checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3454e471037adb5a463a4da95519d7e2dbe53262066e986a7b4e8085f0b54dd7
+size 484244528

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679e5026456b29f53d14a0ad06cb8301818ad1ba93369406e9dc94a5cc8a8c57
+size 245864587

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f41083361f32cd305420378189e43e8e292daa01f69a98c10b3e97c6dfed711
+size 14645

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcace22626155bee1bc951084e74570cfa0b6527f8d3ce3887adf71800ffcdf1
+size 1383

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b85782cfb1341cf535787a1701e7d4b8d1f023d1c1e7158e86978543d2d275
+size 1465

checkpoint-300/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "HFCompatibleHybridTokenizer",
+  "vocab_size": 4096,
+  "model_max_length": 512,
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.046152071074189456,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0015384023691396484,
+      "grad_norm": 11396.142578125,
+      "learning_rate": 3e-07,
+      "loss": 8.8759,
+      "step": 10
+    },
+    {
+      "epoch": 0.003076804738279297,
+      "grad_norm": 689.1935424804688,
+      "learning_rate": 1.2999999999999998e-06,
+      "loss": 8.2644,
+      "step": 20
+    },
+    {
+      "epoch": 0.004615207107418946,
+      "grad_norm": 454.8230285644531,
+      "learning_rate": 2.2999999999999996e-06,
+      "loss": 7.2145,
+      "step": 30
+    },
+    {
+      "epoch": 0.006153609476558594,
+      "grad_norm": 169.3773193359375,
+      "learning_rate": 3.2999999999999993e-06,
+      "loss": 6.899,
+      "step": 40
+    },
+    {
+      "epoch": 0.007692011845698243,
+      "grad_norm": 121.77935028076172,
+      "learning_rate": 4.2999999999999995e-06,
+      "loss": 6.7803,
+      "step": 50
+    },
+    {
+      "epoch": 0.009230414214837892,
+      "grad_norm": 1289.1287841796875,
+      "learning_rate": 5.3e-06,
+      "loss": 6.5956,
+      "step": 60
+    },
+    {
+      "epoch": 0.010768816583977539,
+      "grad_norm": 157.25286865234375,
+      "learning_rate": 6.3e-06,
+      "loss": 6.6402,
+      "step": 70
+    },
+    {
+      "epoch": 0.012307218953117188,
+      "grad_norm": 384.85919189453125,
+      "learning_rate": 7.299999999999999e-06,
+      "loss": 6.4978,
+      "step": 80
+    },
+    {
+      "epoch": 0.013845621322256836,
+      "grad_norm": 301.0735778808594,
+      "learning_rate": 8.299999999999998e-06,
+      "loss": 6.3964,
+      "step": 90
+    },
+    {
+      "epoch": 0.015384023691396485,
+      "grad_norm": 226.9570770263672,
+      "learning_rate": 9.299999999999999e-06,
+      "loss": 6.3804,
+      "step": 100
+    },
+    {
+      "epoch": 0.016922426060536132,
+      "grad_norm": 101.4676513671875,
+      "learning_rate": 1.03e-05,
+      "loss": 6.3698,
+      "step": 110
+    },
+    {
+      "epoch": 0.018460828429675783,
+      "grad_norm": 230.73281860351562,
+      "learning_rate": 1.1299999999999999e-05,
+      "loss": 6.4247,
+      "step": 120
+    },
+    {
+      "epoch": 0.01999923079881543,
+      "grad_norm": 124.10091400146484,
+      "learning_rate": 1.2299999999999999e-05,
+      "loss": 6.3109,
+      "step": 130
+    },
+    {
+      "epoch": 0.021537633167955077,
+      "grad_norm": 97.28553009033203,
+      "learning_rate": 1.33e-05,
+      "loss": 6.3895,
+      "step": 140
+    },
+    {
+      "epoch": 0.023076035537094728,
+      "grad_norm": 182.08811950683594,
+      "learning_rate": 1.43e-05,
+      "loss": 6.4089,
+      "step": 150
+    },
+    {
+      "epoch": 0.024614437906234375,
+      "grad_norm": 433.91973876953125,
+      "learning_rate": 1.53e-05,
+      "loss": 6.3014,
+      "step": 160
+    },
+    {
+      "epoch": 0.026152840275374026,
+      "grad_norm": 352.3630065917969,
+      "learning_rate": 1.6299999999999996e-05,
+      "loss": 6.3332,
+      "step": 170
+    },
+    {
+      "epoch": 0.027691242644513673,
+      "grad_norm": 74.03328704833984,
+      "learning_rate": 1.7299999999999997e-05,
+      "loss": 6.315,
+      "step": 180
+    },
+    {
+      "epoch": 0.02922964501365332,
+      "grad_norm": 264.071044921875,
+      "learning_rate": 1.8299999999999998e-05,
+      "loss": 6.3367,
+      "step": 190
+    },
+    {
+      "epoch": 0.03076804738279297,
+      "grad_norm": 92.3805160522461,
+      "learning_rate": 1.93e-05,
+      "loss": 6.306,
+      "step": 200
+    },
+    {
+      "epoch": 0.03230644975193262,
+      "grad_norm": 105.78662872314453,
+      "learning_rate": 2.03e-05,
+      "loss": 6.272,
+      "step": 210
+    },
+    {
+      "epoch": 0.033844852121072265,
+      "grad_norm": 34.507057189941406,
+      "learning_rate": 2.1299999999999996e-05,
+      "loss": 6.2943,
+      "step": 220
+    },
+    {
+      "epoch": 0.035383254490211916,
+      "grad_norm": 29.95108985900879,
+      "learning_rate": 2.23e-05,
+      "loss": 6.2231,
+      "step": 230
+    },
+    {
+      "epoch": 0.036921656859351566,
+      "grad_norm": 105.78109741210938,
+      "learning_rate": 2.3299999999999997e-05,
+      "loss": 6.2223,
+      "step": 240
+    },
+    {
+      "epoch": 0.03846005922849121,
+      "grad_norm": 115.77278900146484,
+      "learning_rate": 2.4299999999999998e-05,
+      "loss": 6.1873,
+      "step": 250
+    },
+    {
+      "epoch": 0.03999846159763086,
+      "grad_norm": 117.57398223876953,
+      "learning_rate": 2.53e-05,
+      "loss": 6.1889,
+      "step": 260
+    },
+    {
+      "epoch": 0.04153686396677051,
+      "grad_norm": 27.769681930541992,
+      "learning_rate": 2.63e-05,
+      "loss": 6.1833,
+      "step": 270
+    },
+    {
+      "epoch": 0.043075266335910155,
+      "grad_norm": 50.23863220214844,
+      "learning_rate": 2.7299999999999996e-05,
+      "loss": 6.1718,
+      "step": 280
+    },
+    {
+      "epoch": 0.044613668705049805,
+      "grad_norm": 16.450408935546875,
+      "learning_rate": 2.83e-05,
+      "loss": 6.0966,
+      "step": 290
+    },
+    {
+      "epoch": 0.046152071074189456,
+      "grad_norm": 28.899629592895508,
+      "learning_rate": 2.9299999999999997e-05,
+      "loss": 6.146,
+      "step": 300
+    }
+  ],
+  "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": 5781011114557440.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe063a25a8755f50ff355c4d7a3fb17af44f79bfac09e4b2672cd081c5200ef0
+size 5201