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_linguistic",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 16,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
+  "vocab_size": 8192
+}

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:ed1bf77bce4b67e61c7dd13aa4c922bac38840008d3b402e6235491ddcfb3494
+size 508157712

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1257b3a1f7cb732f201a359de3f4f7a0b3f4e14ba2c6d21e05cd744699deecb
+size 258736843

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc25f164ea850ce98776c38e5a387aeb3947263d4af6908e944ff609314c2ba0
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d15f80eff8e7aa3a49c0408f3d31fa2e6e9e75a2fbae063b0cc83bfa545cc3d7
+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": 8192,
+  "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": 0.0013795315455754113,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00013795315455754112,
+      "grad_norm": 53.4421272277832,
+      "learning_rate": 4.1999999999999995e-07,
+      "loss": 8.6569,
+      "step": 10
+    },
+    {
+      "epoch": 0.00027590630911508224,
+      "grad_norm": 57.65703582763672,
+      "learning_rate": 1.0199999999999998e-06,
+      "loss": 8.6391,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004138594636726234,
+      "grad_norm": 93.79612731933594,
+      "learning_rate": 1.62e-06,
+      "loss": 8.6097,
+      "step": 30
+    },
+    {
+      "epoch": 0.0005518126182301645,
+      "grad_norm": 133.8379669189453,
+      "learning_rate": 2.22e-06,
+      "loss": 8.5995,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006897657727877056,
+      "grad_norm": 99.24571228027344,
+      "learning_rate": 2.8199999999999997e-06,
+      "loss": 8.5699,
+      "step": 50
+    },
+    {
+      "epoch": 0.0008277189273452468,
+      "grad_norm": 155.49118041992188,
+      "learning_rate": 3.42e-06,
+      "loss": 8.5516,
+      "step": 60
+    },
+    {
+      "epoch": 0.0009656720819027878,
+      "grad_norm": 118.79692840576172,
+      "learning_rate": 4.02e-06,
+      "loss": 8.5331,
+      "step": 70
+    },
+    {
+      "epoch": 0.001103625236460329,
+      "grad_norm": 88.51729583740234,
+      "learning_rate": 4.62e-06,
+      "loss": 8.5212,
+      "step": 80
+    },
+    {
+      "epoch": 0.0012415783910178701,
+      "grad_norm": 117.01810455322266,
+      "learning_rate": 5.219999999999999e-06,
+      "loss": 8.5007,
+      "step": 90
+    },
+    {
+      "epoch": 0.0013795315455754113,
+      "grad_norm": 104.06542205810547,
+      "learning_rate": 5.819999999999999e-06,
+      "loss": 8.4948,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 138,
+  "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": 1527705471172608.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:336d6c305ed5ab5d43d372ffb91cb30e0040bca808dc3ebbd882977601a96740
+size 5201