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:b72370dd4da30b981f5d6a6bcd9e1f17efa3967c09315450e4c13684f2eecaa6
+size 501888768

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6976e81ffb2bb3cbb8af28078d56e7006adf4a56d0124a63a504b80db4ef3622
+size 254046859

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a3442c4fd41d8b988cc37376dea9f5c74252a071385a61b2a6228ea9697ce7
+size 14645

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cea68c01b3915d688bd58a3f25233c15d121454691c758b6d2f9c05adc499abf
+size 1383

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3a19044d6621549c1b46da092c80bf658910ef6873650417cec22826a82e947
+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": 7458.9189453125,
+      "learning_rate": 1.6e-07,
+      "loss": 16.4424,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010578512396694215,
+      "grad_norm": 2789.625,
+      "learning_rate": 9.6e-07,
+      "loss": 15.6542,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015867768595041322,
+      "grad_norm": 2489.71142578125,
+      "learning_rate": 1.76e-06,
+      "loss": 15.1573,
+      "step": 30
+    },
+    {
+      "epoch": 0.002115702479338843,
+      "grad_norm": 2955.32568359375,
+      "learning_rate": 2.56e-06,
+      "loss": 14.8308,
+      "step": 40
+    },
+    {
+      "epoch": 0.002644628099173554,
+      "grad_norm": 2157.26318359375,
+      "learning_rate": 3.36e-06,
+      "loss": 14.6636,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031735537190082643,
+      "grad_norm": 2898.47314453125,
+      "learning_rate": 4.16e-06,
+      "loss": 14.5921,
+      "step": 60
+    },
+    {
+      "epoch": 0.0037024793388429752,
+      "grad_norm": 2458.47607421875,
+      "learning_rate": 4.96e-06,
+      "loss": 14.501,
+      "step": 70
+    },
+    {
+      "epoch": 0.004231404958677686,
+      "grad_norm": 2568.217529296875,
+      "learning_rate": 5.76e-06,
+      "loss": 14.3649,
+      "step": 80
+    },
+    {
+      "epoch": 0.004760330578512397,
+      "grad_norm": 2298.6142578125,
+      "learning_rate": 6.560000000000001e-06,
+      "loss": 14.2622,
+      "step": 90
+    },
+    {
+      "epoch": 0.005289256198347108,
+      "grad_norm": 2145.729248046875,
+      "learning_rate": 7.36e-06,
+      "loss": 14.1271,
+      "step": 100
+    },
+    {
+      "epoch": 0.005818181818181818,
+      "grad_norm": 2116.720458984375,
+      "learning_rate": 8.160000000000001e-06,
+      "loss": 14.0036,
+      "step": 110
+    },
+    {
+      "epoch": 0.006347107438016529,
+      "grad_norm": 1847.9112548828125,
+      "learning_rate": 8.96e-06,
+      "loss": 13.8998,
+      "step": 120
+    },
+    {
+      "epoch": 0.00687603305785124,
+      "grad_norm": 1758.4593505859375,
+      "learning_rate": 9.760000000000001e-06,
+      "loss": 13.8227,
+      "step": 130
+    },
+    {
+      "epoch": 0.0074049586776859504,
+      "grad_norm": 3267.474365234375,
+      "learning_rate": 1.056e-05,
+      "loss": 13.7623,
+      "step": 140
+    },
+    {
+      "epoch": 0.007933884297520661,
+      "grad_norm": 1531.384521484375,
+      "learning_rate": 1.1360000000000001e-05,
+      "loss": 13.5285,
+      "step": 150
+    },
+    {
+      "epoch": 0.008462809917355372,
+      "grad_norm": 1631.8902587890625,
+      "learning_rate": 1.216e-05,
+      "loss": 13.3848,
+      "step": 160
+    },
+    {
+      "epoch": 0.008991735537190083,
+      "grad_norm": 1016.30419921875,
+      "learning_rate": 1.296e-05,
+      "loss": 13.3074,
+      "step": 170
+    },
+    {
+      "epoch": 0.009520661157024794,
+      "grad_norm": 1558.402099609375,
+      "learning_rate": 1.376e-05,
+      "loss": 13.121,
+      "step": 180
+    },
+    {
+      "epoch": 0.010049586776859505,
+      "grad_norm": 1313.5159912109375,
+      "learning_rate": 1.4560000000000001e-05,
+      "loss": 12.9932,
+      "step": 190
+    },
+    {
+      "epoch": 0.010578512396694216,
+      "grad_norm": 1270.5982666015625,
+      "learning_rate": 1.536e-05,
+      "loss": 13.0639,
+      "step": 200
+    },
+    {
+      "epoch": 0.011107438016528925,
+      "grad_norm": 866.6194458007812,
+      "learning_rate": 1.616e-05,
+      "loss": 13.0773,
+      "step": 210
+    },
+    {
+      "epoch": 0.011636363636363636,
+      "grad_norm": 1080.3182373046875,
+      "learning_rate": 1.696e-05,
+      "loss": 12.9607,
+      "step": 220
+    },
+    {
+      "epoch": 0.012165289256198347,
+      "grad_norm": 1044.58740234375,
+      "learning_rate": 1.7760000000000003e-05,
+      "loss": 12.7768,
+      "step": 230
+    },
+    {
+      "epoch": 0.012694214876033057,
+      "grad_norm": 1139.590576171875,
+      "learning_rate": 1.856e-05,
+      "loss": 12.565,
+      "step": 240
+    },
+    {
+      "epoch": 0.013223140495867768,
+      "grad_norm": 1116.9873046875,
+      "learning_rate": 1.936e-05,
+      "loss": 12.6404,
+      "step": 250
+    },
+    {
+      "epoch": 0.01375206611570248,
+      "grad_norm": 2548.608642578125,
+      "learning_rate": 2.016e-05,
+      "loss": 12.4778,
+      "step": 260
+    },
+    {
+      "epoch": 0.01428099173553719,
+      "grad_norm": 1183.2412109375,
+      "learning_rate": 2.0960000000000003e-05,
+      "loss": 12.4691,
+      "step": 270
+    },
+    {
+      "epoch": 0.014809917355371901,
+      "grad_norm": 635.5205688476562,
+      "learning_rate": 2.176e-05,
+      "loss": 12.3107,
+      "step": 280
+    },
+    {
+      "epoch": 0.015338842975206612,
+      "grad_norm": 851.1377563476562,
+      "learning_rate": 2.256e-05,
+      "loss": 12.1444,
+      "step": 290
+    },
+    {
+      "epoch": 0.015867768595041323,
+      "grad_norm": 587.5467529296875,
+      "learning_rate": 2.336e-05,
+      "loss": 12.2068,
+      "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": 5050474674585600.0,
+  "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:b9349b20a7a64da01434fede7e7e7e228a954cd591ba627d75e5e86ca536410c
+size 5201