Upload folder using huggingface_hub

checkpoint-100/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_16k",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 16,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
+  "vocab_size": 16384
+}

checkpoint-100/generation_config.json

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

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7979469c1b8322bf042db8ab5f1fc487b3582adcd76be70afd974fdf70c3a6f2
+size 543870712

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8459324bcb8fba31c67a6d1d53cb22fdb4033998d9f15d07c27ea93ab02c46
+size 276872523

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab9f8aeb7f748e68e01490ef0408ff0b13e57bb0d8b7659d152c232ff49dfbe
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b43b0032748a5307b63a7e500c1f42f50866ec8b02362cb76d9f786b67be3b75
+size 1383

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd96bf354448cb97767043df3a463cc4b9a80a47a7e591703725b5039c8b4972
+size 1465

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "HFCompatibleLinguisticTokenizer",
+  "vocab_size": 16384,
+  "model_max_length": 512,
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0002925152656404256,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.925152656404256e-05,
+      "grad_norm": 44.091312408447266,
+      "learning_rate": 4.1999999999999995e-07,
+      "loss": 9.3692,
+      "step": 10
+    },
+    {
+      "epoch": 5.850305312808512e-05,
+      "grad_norm": 44.14885711669922,
+      "learning_rate": 1.0199999999999998e-06,
+      "loss": 9.3095,
+      "step": 20
+    },
+    {
+      "epoch": 8.775457969212769e-05,
+      "grad_norm": 71.31829071044922,
+      "learning_rate": 1.62e-06,
+      "loss": 9.2848,
+      "step": 30
+    },
+    {
+      "epoch": 0.00011700610625617024,
+      "grad_norm": 44.88148498535156,
+      "learning_rate": 2.22e-06,
+      "loss": 9.3214,
+      "step": 40
+    },
+    {
+      "epoch": 0.0001462576328202128,
+      "grad_norm": 71.73838806152344,
+      "learning_rate": 2.8199999999999997e-06,
+      "loss": 9.2992,
+      "step": 50
+    },
+    {
+      "epoch": 0.00017550915938425538,
+      "grad_norm": 63.85468292236328,
+      "learning_rate": 3.42e-06,
+      "loss": 9.3034,
+      "step": 60
+    },
+    {
+      "epoch": 0.00020476068594829793,
+      "grad_norm": 47.08655548095703,
+      "learning_rate": 4.02e-06,
+      "loss": 9.2972,
+      "step": 70
+    },
+    {
+      "epoch": 0.00023401221251234048,
+      "grad_norm": 46.76586151123047,
+      "learning_rate": 4.62e-06,
+      "loss": 9.282,
+      "step": 80
+    },
+    {
+      "epoch": 0.00026326373907638306,
+      "grad_norm": 68.871826171875,
+      "learning_rate": 5.219999999999999e-06,
+      "loss": 9.2683,
+      "step": 90
+    },
+    {
+      "epoch": 0.0002925152656404256,
+      "grad_norm": 40.276512145996094,
+      "learning_rate": 5.819999999999999e-06,
+      "loss": 9.2803,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 292394772480000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:345930ddfb53788d81724f387da0e4c9b3054879aaa61b84767ee1042bc4803a
+size 5201