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 sha256:024176efc16d0705d2286e781a17e0800adfd5d0d7829f3089fc744f74aa769f
+size 501911880

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6fdcb0739ecfc2ca1ab0513faa75dd0906c3346467454912d974e325c9fc6ac
+size 254431981

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58e018f8871872b60e06284743811f932f4f2ef1045c94f180d946f6ec4f8b9d
+size 14645

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4b5ae02588e6b631725983040ddfcc019305b73190233742439d7a13c11a92
+size 1383

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8515c7a0314d5be547eec5f17aed50a033ee61d960615c864781e60454a426
+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": 0.005289256198347108,
+  "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": 641.732177734375,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 8.8563,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010578512396694215,
+      "grad_norm": 167.62478637695312,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 8.669,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015867768595041322,
+      "grad_norm": 132.942138671875,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 8.4099,
+      "step": 30
+    },
+    {
+      "epoch": 0.002115702479338843,
+      "grad_norm": 87.03181457519531,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 8.3399,
+      "step": 40
+    },
+    {
+      "epoch": 0.002644628099173554,
+      "grad_norm": 83.94163513183594,
+      "learning_rate": 3.6e-06,
+      "loss": 8.4131,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031735537190082643,
+      "grad_norm": 224.91473388671875,
+      "learning_rate": 4.4e-06,
+      "loss": 8.1753,
+      "step": 60
+    },
+    {
+      "epoch": 0.0037024793388429752,
+      "grad_norm": 316.9183044433594,
+      "learning_rate": 5.2e-06,
+      "loss": 8.411,
+      "step": 70
+    },
+    {
+      "epoch": 0.004231404958677686,
+      "grad_norm": 344.9347839355469,
+      "learning_rate": 6e-06,
+      "loss": 8.2236,
+      "step": 80
+    },
+    {
+      "epoch": 0.004760330578512397,
+      "grad_norm": 131.94554138183594,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 8.2993,
+      "step": 90
+    },
+    {
+      "epoch": 0.005289256198347108,
+      "grad_norm": 187.1765594482422,
+      "learning_rate": 7.6e-06,
+      "loss": 8.0748,
+      "step": 100
+    },
+    {
+      "epoch": 0.005818181818181818,
+      "grad_norm": 185.48715209960938,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 8.0531,
+      "step": 110
+    },
+    {
+      "epoch": 0.006347107438016529,
+      "grad_norm": 292.0998840332031,
+      "learning_rate": 9.2e-06,
+      "loss": 8.1898,
+      "step": 120
+    },
+    {
+      "epoch": 0.00687603305785124,
+      "grad_norm": 236.91464233398438,
+      "learning_rate": 1e-05,
+      "loss": 8.0968,
+      "step": 130
+    },
+    {
+      "epoch": 0.0074049586776859504,
+      "grad_norm": 276.836669921875,
+      "learning_rate": 1.08e-05,
+      "loss": 8.0387,
+      "step": 140
+    },
+    {
+      "epoch": 0.007933884297520661,
+      "grad_norm": 226.5710906982422,
+      "learning_rate": 1.16e-05,
+      "loss": 7.9954,
+      "step": 150
+    },
+    {
+      "epoch": 0.008462809917355372,
+      "grad_norm": 341.735595703125,
+      "learning_rate": 1.232e-05,
+      "loss": 7.9396,
+      "step": 160
+    },
+    {
+      "epoch": 0.008991735537190083,
+      "grad_norm": 215.15040588378906,
+      "learning_rate": 1.3120000000000001e-05,
+      "loss": 8.0838,
+      "step": 170
+    },
+    {
+      "epoch": 0.009520661157024794,
+      "grad_norm": 314.2020263671875,
+      "learning_rate": 1.3919999999999999e-05,
+      "loss": 7.9612,
+      "step": 180
+    },
+    {
+      "epoch": 0.010049586776859505,
+      "grad_norm": 1104.496826171875,
+      "learning_rate": 1.472e-05,
+      "loss": 7.8864,
+      "step": 190
+    },
+    {
+      "epoch": 0.010578512396694216,
+      "grad_norm": 114.84138488769531,
+      "learning_rate": 1.552e-05,
+      "loss": 7.7783,
+      "step": 200
+    },
+    {
+      "epoch": 0.0005289256198347108,
+      "grad_norm": 298.0364685058594,
+      "learning_rate": 1.6320000000000003e-05,
+      "loss": 7.7893,
+      "step": 210
+    },
+    {
+      "epoch": 0.0010578512396694215,
+      "grad_norm": 215.82244873046875,
+      "learning_rate": 1.712e-05,
+      "loss": 7.779,
+      "step": 220
+    },
+    {
+      "epoch": 0.0015867768595041322,
+      "grad_norm": 247.94859313964844,
+      "learning_rate": 1.792e-05,
+      "loss": 7.6925,
+      "step": 230
+    },
+    {
+      "epoch": 0.002115702479338843,
+      "grad_norm": 97.73837280273438,
+      "learning_rate": 1.872e-05,
+      "loss": 7.6725,
+      "step": 240
+    },
+    {
+      "epoch": 0.002644628099173554,
+      "grad_norm": 141.45123291015625,
+      "learning_rate": 1.9520000000000003e-05,
+      "loss": 7.7421,
+      "step": 250
+    },
+    {
+      "epoch": 0.0031735537190082643,
+      "grad_norm": 200.86509704589844,
+      "learning_rate": 2.032e-05,
+      "loss": 7.5497,
+      "step": 260
+    },
+    {
+      "epoch": 0.0037024793388429752,
+      "grad_norm": 185.7206268310547,
+      "learning_rate": 2.112e-05,
+      "loss": 7.7364,
+      "step": 270
+    },
+    {
+      "epoch": 0.004231404958677686,
+      "grad_norm": 101.28189086914062,
+      "learning_rate": 2.192e-05,
+      "loss": 7.5938,
+      "step": 280
+    },
+    {
+      "epoch": 0.004760330578512397,
+      "grad_norm": 330.9864807128906,
+      "learning_rate": 2.2720000000000003e-05,
+      "loss": 7.6908,
+      "step": 290
+    },
+    {
+      "epoch": 0.005289256198347108,
+      "grad_norm": 148.31687927246094,
+      "learning_rate": 2.3520000000000002e-05,
+      "loss": 7.5153,
+      "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": 5097782555443200.0,
+  "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 sha256:05cb5d668e12b91a46e597433b8a814a5107ab9e663d3ff34f9f7bdba2b54572
+size 5201