Upload folder using huggingface_hub

checkpoint-300/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-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 sha256:7d70d4c29259580e725f9a72a1c8a7bcae74959f81a4e4cab04315f1372c3772
+size 501888768

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab0a2f5f65b11ac13644b9e3a2c9c03691b5621feec01de027e77fe5d2a6f0a7
+size 254046859

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c49a49678d52974b8d745a5196a1f2dbf8c6b4bc44b2a9e86ed79a0107e7c6
+size 14645

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d16baab2a19519d751adba800238fbcacdeaeaa5af8b2df0d35fce7cdfae7c1
+size 1383

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f349f26c0a3abe0bf43cc21aa29c67848a6de4bb4be3e486385e7979d4b0ce
+size 1465

checkpoint-300/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-300/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.015867768595041323,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005289256198347108,
+      "grad_norm": 9168.4580078125,
+      "learning_rate": 2.4e-07,
+      "loss": 16.6978,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010578512396694215,
+      "grad_norm": 2087.102783203125,
+      "learning_rate": 1.04e-06,
+      "loss": 15.7625,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015867768595041322,
+      "grad_norm": 2472.9306640625,
+      "learning_rate": 1.84e-06,
+      "loss": 15.1353,
+      "step": 30
+    },
+    {
+      "epoch": 0.002115702479338843,
+      "grad_norm": 2254.28271484375,
+      "learning_rate": 2.64e-06,
+      "loss": 14.9132,
+      "step": 40
+    },
+    {
+      "epoch": 0.002644628099173554,
+      "grad_norm": 2219.509521484375,
+      "learning_rate": 3.44e-06,
+      "loss": 14.6851,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031735537190082643,
+      "grad_norm": 2151.2685546875,
+      "learning_rate": 4.24e-06,
+      "loss": 14.5536,
+      "step": 60
+    },
+    {
+      "epoch": 0.0037024793388429752,
+      "grad_norm": 2181.529052734375,
+      "learning_rate": 5.04e-06,
+      "loss": 14.489,
+      "step": 70
+    },
+    {
+      "epoch": 0.004231404958677686,
+      "grad_norm": 2351.65869140625,
+      "learning_rate": 5.84e-06,
+      "loss": 14.3607,
+      "step": 80
+    },
+    {
+      "epoch": 0.004760330578512397,
+      "grad_norm": 1830.1292724609375,
+      "learning_rate": 6.640000000000001e-06,
+      "loss": 14.3096,
+      "step": 90
+    },
+    {
+      "epoch": 0.005289256198347108,
+      "grad_norm": 2534.877197265625,
+      "learning_rate": 7.44e-06,
+      "loss": 14.1419,
+      "step": 100
+    },
+    {
+      "epoch": 0.005818181818181818,
+      "grad_norm": 3552.001708984375,
+      "learning_rate": 8.24e-06,
+      "loss": 13.9957,
+      "step": 110
+    },
+    {
+      "epoch": 0.006347107438016529,
+      "grad_norm": 1729.5421142578125,
+      "learning_rate": 8.96e-06,
+      "loss": 13.9384,
+      "step": 120
+    },
+    {
+      "epoch": 0.00687603305785124,
+      "grad_norm": 1677.7344970703125,
+      "learning_rate": 9.760000000000001e-06,
+      "loss": 13.8056,
+      "step": 130
+    },
+    {
+      "epoch": 0.0074049586776859504,
+      "grad_norm": 1419.7279052734375,
+      "learning_rate": 1.056e-05,
+      "loss": 13.5914,
+      "step": 140
+    },
+    {
+      "epoch": 0.007933884297520661,
+      "grad_norm": 1191.801025390625,
+      "learning_rate": 1.1360000000000001e-05,
+      "loss": 13.4104,
+      "step": 150
+    },
+    {
+      "epoch": 0.008462809917355372,
+      "grad_norm": 1145.3717041015625,
+      "learning_rate": 1.216e-05,
+      "loss": 13.4135,
+      "step": 160
+    },
+    {
+      "epoch": 0.008991735537190083,
+      "grad_norm": 1149.420654296875,
+      "learning_rate": 1.296e-05,
+      "loss": 13.3217,
+      "step": 170
+    },
+    {
+      "epoch": 0.009520661157024794,
+      "grad_norm": 690.7573852539062,
+      "learning_rate": 1.376e-05,
+      "loss": 13.2032,
+      "step": 180
+    },
+    {
+      "epoch": 0.010049586776859505,
+      "grad_norm": 783.4169311523438,
+      "learning_rate": 1.4560000000000001e-05,
+      "loss": 13.2695,
+      "step": 190
+    },
+    {
+      "epoch": 0.010578512396694216,
+      "grad_norm": 2450.64501953125,
+      "learning_rate": 1.536e-05,
+      "loss": 13.204,
+      "step": 200
+    },
+    {
+      "epoch": 0.011107438016528925,
+      "grad_norm": 1024.4141845703125,
+      "learning_rate": 1.616e-05,
+      "loss": 13.1314,
+      "step": 210
+    },
+    {
+      "epoch": 0.011636363636363636,
+      "grad_norm": 1143.5775146484375,
+      "learning_rate": 1.696e-05,
+      "loss": 13.0375,
+      "step": 220
+    },
+    {
+      "epoch": 0.012165289256198347,
+      "grad_norm": 1500.1324462890625,
+      "learning_rate": 1.7760000000000003e-05,
+      "loss": 12.7867,
+      "step": 230
+    },
+    {
+      "epoch": 0.012694214876033057,
+      "grad_norm": Infinity,
+      "learning_rate": 1.856e-05,
+      "loss": 12.6831,
+      "step": 240
+    },
+    {
+      "epoch": 0.013223140495867768,
+      "grad_norm": 1573.1968994140625,
+      "learning_rate": 1.9280000000000002e-05,
+      "loss": 12.6766,
+      "step": 250
+    },
+    {
+      "epoch": 0.01375206611570248,
+      "grad_norm": 1723.42138671875,
+      "learning_rate": 2.008e-05,
+      "loss": 12.5227,
+      "step": 260
+    },
+    {
+      "epoch": 0.01428099173553719,
+      "grad_norm": 1796.69970703125,
+      "learning_rate": 2.0880000000000003e-05,
+      "loss": 12.5479,
+      "step": 270
+    },
+    {
+      "epoch": 0.014809917355371901,
+      "grad_norm": 925.7263793945312,
+      "learning_rate": 2.168e-05,
+      "loss": 12.3445,
+      "step": 280
+    },
+    {
+      "epoch": 0.015338842975206612,
+      "grad_norm": 657.2308959960938,
+      "learning_rate": 2.248e-05,
+      "loss": 12.2945,
+      "step": 290
+    },
+    {
+      "epoch": 0.015867768595041323,
+      "grad_norm": 1082.7481689453125,
+      "learning_rate": 2.328e-05,
+      "loss": 12.3474,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 529,
+  "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": 4837947603763200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1367cd21fd22f3d4b48b4d242f8055c422120aecc23f0740b94b9e27d61b91
+size 5201