Upload folder using huggingface_hub

checkpoint-300/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-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:c345bda8e1e00f01fe8df93ffbc628afbdf78aaa35b3f69a0c7142aab42d3d82
+size 542849784

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d385d3859e3e7712fc12ec844900f84c711c5329dee7d80adc461243bb55bce6
+size 273342083

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af64927d11ff5aa2423d08b0b3713eb352c6008df7069557c0533269a97301be
+size 14645

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde406fb39dc0bbced01120a84cbcd1c773bea6ac49dca8cecd1a0e473d9d2af
+size 1383

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d417142d4b873b3ac482614d102a38449931a1bcdb097d70a7a05c35283290
+size 1465

checkpoint-300/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.010404203298132445,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00034680677660441485,
+      "grad_norm": 8.286304473876953,
+      "learning_rate": 2.6999999999999996e-06,
+      "loss": 36.023321533203124,
+      "step": 10
+    },
+    {
+      "epoch": 0.0006936135532088297,
+      "grad_norm": 5.303624153137207,
+      "learning_rate": 5.7e-06,
+      "loss": 35.81325988769531,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010404203298132447,
+      "grad_norm": 14.0803861618042,
+      "learning_rate": 8.7e-06,
+      "loss": 35.61415100097656,
+      "step": 30
+    },
+    {
+      "epoch": 0.0013872271064176594,
+      "grad_norm": 42.10546875,
+      "learning_rate": 1.17e-05,
+      "loss": 35.36910400390625,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017340338830220744,
+      "grad_norm": 43.37276840209961,
+      "learning_rate": 1.47e-05,
+      "loss": 34.86077880859375,
+      "step": 50
+    },
+    {
+      "epoch": 0.0020808406596264893,
+      "grad_norm": Infinity,
+      "learning_rate": 1.7699999999999997e-05,
+      "loss": 34.67452697753906,
+      "step": 60
+    },
+    {
+      "epoch": 0.002427647436230904,
+      "grad_norm": 86.09446716308594,
+      "learning_rate": 2.04e-05,
+      "loss": 34.29078979492188,
+      "step": 70
+    },
+    {
+      "epoch": 0.002774454212835319,
+      "grad_norm": 43.50123977661133,
+      "learning_rate": 2.34e-05,
+      "loss": 33.816766357421876,
+      "step": 80
+    },
+    {
+      "epoch": 0.0031212609894397335,
+      "grad_norm": 104.7258529663086,
+      "learning_rate": 2.6399999999999995e-05,
+      "loss": 33.36159057617188,
+      "step": 90
+    },
+    {
+      "epoch": 0.0034680677660441487,
+      "grad_norm": 66.46515655517578,
+      "learning_rate": 2.91e-05,
+      "loss": 33.181732177734375,
+      "step": 100
+    },
+    {
+      "epoch": 0.0038148745426485635,
+      "grad_norm": 127.66901397705078,
+      "learning_rate": 3.2099999999999994e-05,
+      "loss": 32.83320007324219,
+      "step": 110
+    },
+    {
+      "epoch": 0.004161681319252979,
+      "grad_norm": 71.67156982421875,
+      "learning_rate": 3.51e-05,
+      "loss": 32.48929138183594,
+      "step": 120
+    },
+    {
+      "epoch": 0.004508488095857393,
+      "grad_norm": 76.15655517578125,
+      "learning_rate": 3.81e-05,
+      "loss": 32.10602722167969,
+      "step": 130
+    },
+    {
+      "epoch": 0.004855294872461808,
+      "grad_norm": 38.65349578857422,
+      "learning_rate": 4.11e-05,
+      "loss": 31.449526977539062,
+      "step": 140
+    },
+    {
+      "epoch": 0.005202101649066222,
+      "grad_norm": 59.55622863769531,
+      "learning_rate": 4.4099999999999995e-05,
+      "loss": 31.01339111328125,
+      "step": 150
+    },
+    {
+      "epoch": 0.005548908425670638,
+      "grad_norm": 130.26136779785156,
+      "learning_rate": 4.709999999999999e-05,
+      "loss": 30.92586669921875,
+      "step": 160
+    },
+    {
+      "epoch": 0.005895715202275053,
+      "grad_norm": 77.2778549194336,
+      "learning_rate": 5.01e-05,
+      "loss": 30.492510986328124,
+      "step": 170
+    },
+    {
+      "epoch": 0.006242521978879467,
+      "grad_norm": 29.711563110351562,
+      "learning_rate": 5.309999999999999e-05,
+      "loss": 29.836746215820312,
+      "step": 180
+    },
+    {
+      "epoch": 0.006589328755483882,
+      "grad_norm": 29.891956329345703,
+      "learning_rate": 5.6099999999999995e-05,
+      "loss": 29.291275024414062,
+      "step": 190
+    },
+    {
+      "epoch": 0.006936135532088297,
+      "grad_norm": 30.56305503845215,
+      "learning_rate": 5.91e-05,
+      "loss": 29.14805908203125,
+      "step": 200
+    },
+    {
+      "epoch": 0.007282942308692712,
+      "grad_norm": 29.489208221435547,
+      "learning_rate": 6.209999999999999e-05,
+      "loss": 28.80553283691406,
+      "step": 210
+    },
+    {
+      "epoch": 0.007629749085297127,
+      "grad_norm": 37.147377014160156,
+      "learning_rate": 6.51e-05,
+      "loss": 28.694085693359376,
+      "step": 220
+    },
+    {
+      "epoch": 0.007976555861901541,
+      "grad_norm": 28.496992111206055,
+      "learning_rate": 6.81e-05,
+      "loss": 28.166943359375,
+      "step": 230
+    },
+    {
+      "epoch": 0.008323362638505957,
+      "grad_norm": 29.42328453063965,
+      "learning_rate": 7.11e-05,
+      "loss": 27.878482055664062,
+      "step": 240
+    },
+    {
+      "epoch": 0.008670169415110372,
+      "grad_norm": 27.867637634277344,
+      "learning_rate": 7.41e-05,
+      "loss": 26.99749755859375,
+      "step": 250
+    },
+    {
+      "epoch": 0.009016976191714786,
+      "grad_norm": 29.695758819580078,
+      "learning_rate": 7.709999999999999e-05,
+      "loss": 27.208102416992187,
+      "step": 260
+    },
+    {
+      "epoch": 0.0093637829683192,
+      "grad_norm": 34.605934143066406,
+      "learning_rate": 8.01e-05,
+      "loss": 26.798681640625,
+      "step": 270
+    },
+    {
+      "epoch": 0.009710589744923616,
+      "grad_norm": 35.05394744873047,
+      "learning_rate": 8.31e-05,
+      "loss": 27.192486572265626,
+      "step": 280
+    },
+    {
+      "epoch": 0.01005739652152803,
+      "grad_norm": 19.137067794799805,
+      "learning_rate": 8.609999999999999e-05,
+      "loss": 26.89140930175781,
+      "step": 290
+    },
+    {
+      "epoch": 0.010404203298132445,
+      "grad_norm": 24.543006896972656,
+      "learning_rate": 8.879999999999999e-05,
+      "loss": 26.167477416992188,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1865974048358400.0,
+  "train_batch_size": 4,
+  "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:cbd241599217f087cf90c5afde8d5857bb2c3234f97a197910829d91c3d8c1f7
+size 5137