Upload folder using huggingface_hub

checkpoint-200/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": 8192
+}

checkpoint-200/generation_config.json

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

checkpoint-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d37f9561e608e2be88c46cacc051676fb800d1c1b8a078fb6e3846dfcd0a27
+size 501759848

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ee6bea04fe299f130891d659ca9ad4b71fbc13b446f1d45e099a4f42cc82a9
+size 254028235

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab2a826b84cc6133088c31084f6486de05c0ba924651b9d87697aac1afc8d5d1
+size 14645

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4179e2d0ffcb46dd1f54b945c169392202b450b28112e11201c0043c75b7a439
+size 1383

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60090a1c05b2cbb4c4f334a421c4e1db1cbe84af8ad9d62fd5dcc182fa70daf7
+size 1465

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "tokenizer_class": "HFCompatibleHybridTokenizer",
+  "vocab_size": 8192,
+  "model_max_length": 512,
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.12307218953117188,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006153609476558594,
+      "grad_norm": 26290.87109375,
+      "learning_rate": 1.9999999999999996e-07,
+      "loss": 8.2122,
+      "step": 10
+    },
+    {
+      "epoch": 0.012307218953117188,
+      "grad_norm": 1750.26953125,
+      "learning_rate": 1.2e-06,
+      "loss": 7.6386,
+      "step": 20
+    },
+    {
+      "epoch": 0.018460828429675783,
+      "grad_norm": 235.5290985107422,
+      "learning_rate": 2.1999999999999997e-06,
+      "loss": 7.0511,
+      "step": 30
+    },
+    {
+      "epoch": 0.024614437906234375,
+      "grad_norm": 317.7790222167969,
+      "learning_rate": 3.1999999999999994e-06,
+      "loss": 6.889,
+      "step": 40
+    },
+    {
+      "epoch": 0.03076804738279297,
+      "grad_norm": 906.6453247070312,
+      "learning_rate": 4.2e-06,
+      "loss": 6.8145,
+      "step": 50
+    },
+    {
+      "epoch": 0.036921656859351566,
+      "grad_norm": 1056.044189453125,
+      "learning_rate": 5.199999999999999e-06,
+      "loss": 6.7193,
+      "step": 60
+    },
+    {
+      "epoch": 0.043075266335910155,
+      "grad_norm": 830.0984497070312,
+      "learning_rate": 6.199999999999999e-06,
+      "loss": 6.6406,
+      "step": 70
+    },
+    {
+      "epoch": 0.04922887581246875,
+      "grad_norm": 259.50299072265625,
+      "learning_rate": 7.2e-06,
+      "loss": 6.6149,
+      "step": 80
+    },
+    {
+      "epoch": 0.055382485289027346,
+      "grad_norm": 143.87599182128906,
+      "learning_rate": 8.2e-06,
+      "loss": 6.6122,
+      "step": 90
+    },
+    {
+      "epoch": 0.06153609476558594,
+      "grad_norm": 435.93017578125,
+      "learning_rate": 9.199999999999998e-06,
+      "loss": 6.5612,
+      "step": 100
+    },
+    {
+      "epoch": 0.06768970424214453,
+      "grad_norm": 557.260498046875,
+      "learning_rate": 1.02e-05,
+      "loss": 6.5083,
+      "step": 110
+    },
+    {
+      "epoch": 0.07384331371870313,
+      "grad_norm": 291.8673095703125,
+      "learning_rate": 1.12e-05,
+      "loss": 6.5365,
+      "step": 120
+    },
+    {
+      "epoch": 0.07999692319526172,
+      "grad_norm": 434.8012390136719,
+      "learning_rate": 1.2199999999999998e-05,
+      "loss": 6.5229,
+      "step": 130
+    },
+    {
+      "epoch": 0.08615053267182031,
+      "grad_norm": 1767.30908203125,
+      "learning_rate": 1.3199999999999997e-05,
+      "loss": 6.4961,
+      "step": 140
+    },
+    {
+      "epoch": 0.09230414214837891,
+      "grad_norm": 548.34228515625,
+      "learning_rate": 1.4199999999999998e-05,
+      "loss": 6.5135,
+      "step": 150
+    },
+    {
+      "epoch": 0.0984577516249375,
+      "grad_norm": 212.0412139892578,
+      "learning_rate": 1.5199999999999998e-05,
+      "loss": 6.47,
+      "step": 160
+    },
+    {
+      "epoch": 0.1046113611014961,
+      "grad_norm": 220.91732788085938,
+      "learning_rate": 1.6199999999999997e-05,
+      "loss": 6.4492,
+      "step": 170
+    },
+    {
+      "epoch": 0.11076497057805469,
+      "grad_norm": 275.8125305175781,
+      "learning_rate": 1.7199999999999998e-05,
+      "loss": 6.5087,
+      "step": 180
+    },
+    {
+      "epoch": 0.11691858005461328,
+      "grad_norm": 205.40353393554688,
+      "learning_rate": 1.82e-05,
+      "loss": 6.4695,
+      "step": 190
+    },
+    {
+      "epoch": 0.12307218953117188,
+      "grad_norm": 170.36024475097656,
+      "learning_rate": 1.92e-05,
+      "loss": 6.4184,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 62,
+  "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": 1.517794510848e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d8a04beb8e0a03960173726e811f1b8582eccdf1b28b006a6664bc6f7605bb
+size 5201