Upload folder using huggingface_hub

checkpoint-100/config.json

@@ -0,0 +1,16 @@
+{
+  "architectures": [
+    "FastHyperNet125mForCausalLM"
+  ],
+  "dtype": "float32",
+  "hidden_size": 768,
+  "hyperbolic_dim": 64,
+  "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-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 sha256:63fafbf61cb57df8973df5dbe23c8f0715ab153809f6bf7db5d1820489b04797
+size 543424784

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89fc01b4a9e8dac676bb1fc3df4c8c8246740cb65fabddff0af7b60feea0b49a
+size 273341635

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a94b25a5c4a6faa3e13f3e099460591671eb104c1f9eaf67b689bb2b04973a
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:950e08b42b334d0e3771882f1de7912ce395d219cf34337634b8de428d68d62e
+size 1383

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a1a81c4083e59a561a40526e9b105b936319bdcc650ed27d7a0170232b4a87
+size 1465

checkpoint-100/trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.006936135532088297,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006936135532088297,
+      "grad_norm": 80.97769927978516,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 39.45225219726562,
+      "step": 10
+    },
+    {
+      "epoch": 0.0013872271064176594,
+      "grad_norm": 69.19830322265625,
+      "learning_rate": 6.25e-06,
+      "loss": 38.231222534179686,
+      "step": 20
+    },
+    {
+      "epoch": 0.0020808406596264893,
+      "grad_norm": 55.03429412841797,
+      "learning_rate": 1.0416666666666666e-05,
+      "loss": 37.07829284667969,
+      "step": 30
+    },
+    {
+      "epoch": 0.002774454212835319,
+      "grad_norm": 36.03839874267578,
+      "learning_rate": 1.4583333333333333e-05,
+      "loss": 35.945098876953125,
+      "step": 40
+    },
+    {
+      "epoch": 0.0034680677660441487,
+      "grad_norm": 48.63792419433594,
+      "learning_rate": 1.875e-05,
+      "loss": 34.40289306640625,
+      "step": 50
+    },
+    {
+      "epoch": 0.004161681319252979,
+      "grad_norm": 41.98967361450195,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 33.45003662109375,
+      "step": 60
+    },
+    {
+      "epoch": 0.004855294872461808,
+      "grad_norm": 81.57576751708984,
+      "learning_rate": 2.7083333333333335e-05,
+      "loss": 32.02000427246094,
+      "step": 70
+    },
+    {
+      "epoch": 0.005548908425670638,
+      "grad_norm": 60.575645446777344,
+      "learning_rate": 3.125e-05,
+      "loss": 30.74504699707031,
+      "step": 80
+    },
+    {
+      "epoch": 0.006242521978879467,
+      "grad_norm": 61.149410247802734,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 29.49912109375,
+      "step": 90
+    },
+    {
+      "epoch": 0.006936135532088297,
+      "grad_norm": 69.96782684326172,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 28.152670288085936,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "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": 1086932082032640.0,
+  "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 sha256:49f3e14a77c081da7c71dab3b3b7c4ec1dede30e28c9fb753d87e3fc83f88ec1
+size 5137