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 sha256:888cf2d77a09147a353e03c8b6196d64bddbf4076068b983c13965e099182a6f
+size 501888768

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e626241b1ae73911b75dfcee18c73e0bb9d1ebb52f8767c02f1cd0b138fc12d
+size 254046859

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056f8757a18a32a56889abcc9edfcec8f850e35375032835b0b5797ad89d5f11
+size 14645

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35bdbd6735eb5a02dcefed3ce598561c037f46534fa7155618f8b22a86aa9947
+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": 0.012767994892802044,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0004255998297600681,
+      "grad_norm": 5634.16845703125,
+      "learning_rate": 2.4e-07,
+      "loss": 14.1264,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008511996595201362,
+      "grad_norm": 2312.5771484375,
+      "learning_rate": 1.04e-06,
+      "loss": 13.2905,
+      "step": 20
+    },
+    {
+      "epoch": 0.0012767994892802044,
+      "grad_norm": 2110.1591796875,
+      "learning_rate": 1.84e-06,
+      "loss": 12.6236,
+      "step": 30
+    },
+    {
+      "epoch": 0.0017023993190402723,
+      "grad_norm": 1493.8431396484375,
+      "learning_rate": 2.64e-06,
+      "loss": 12.3954,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021279991488003403,
+      "grad_norm": 1430.7598876953125,
+      "learning_rate": 3.44e-06,
+      "loss": 12.265,
+      "step": 50
+    },
+    {
+      "epoch": 0.0025535989785604087,
+      "grad_norm": 2192.621826171875,
+      "learning_rate": 4.24e-06,
+      "loss": 12.018,
+      "step": 60
+    },
+    {
+      "epoch": 0.0029791988083204767,
+      "grad_norm": 1678.5159912109375,
+      "learning_rate": 5.04e-06,
+      "loss": 11.8932,
+      "step": 70
+    },
+    {
+      "epoch": 0.0034047986380805447,
+      "grad_norm": 1261.883056640625,
+      "learning_rate": 5.84e-06,
+      "loss": 11.8077,
+      "step": 80
+    },
+    {
+      "epoch": 0.0038303984678406127,
+      "grad_norm": 1710.3070068359375,
+      "learning_rate": 6.640000000000001e-06,
+      "loss": 11.6841,
+      "step": 90
+    },
+    {
+      "epoch": 0.004255998297600681,
+      "grad_norm": 2306.063232421875,
+      "learning_rate": 7.44e-06,
+      "loss": 11.5426,
+      "step": 100
+    },
+    {
+      "epoch": 0.004681598127360749,
+      "grad_norm": 2158.360107421875,
+      "learning_rate": 8.24e-06,
+      "loss": 11.4863,
+      "step": 110
+    },
+    {
+      "epoch": 0.0051071979571208174,
+      "grad_norm": 2058.938232421875,
+      "learning_rate": 9.04e-06,
+      "loss": 11.5044,
+      "step": 120
+    },
+    {
+      "epoch": 0.005532797786880885,
+      "grad_norm": 2320.1376953125,
+      "learning_rate": 9.84e-06,
+      "loss": 11.4696,
+      "step": 130
+    },
+    {
+      "epoch": 0.005958397616640953,
+      "grad_norm": 3147.455078125,
+      "learning_rate": 1.064e-05,
+      "loss": 11.2994,
+      "step": 140
+    },
+    {
+      "epoch": 0.006383997446401022,
+      "grad_norm": 1930.887451171875,
+      "learning_rate": 1.144e-05,
+      "loss": 11.2686,
+      "step": 150
+    },
+    {
+      "epoch": 0.006809597276161089,
+      "grad_norm": 3005.495361328125,
+      "learning_rate": 1.224e-05,
+      "loss": 11.2556,
+      "step": 160
+    },
+    {
+      "epoch": 0.007235197105921158,
+      "grad_norm": 1587.324462890625,
+      "learning_rate": 1.3039999999999999e-05,
+      "loss": 11.1593,
+      "step": 170
+    },
+    {
+      "epoch": 0.007660796935681225,
+      "grad_norm": 1496.0810546875,
+      "learning_rate": 1.384e-05,
+      "loss": 11.0329,
+      "step": 180
+    },
+    {
+      "epoch": 0.008086396765441295,
+      "grad_norm": 2397.255615234375,
+      "learning_rate": 1.4560000000000001e-05,
+      "loss": 11.0514,
+      "step": 190
+    },
+    {
+      "epoch": 0.008511996595201361,
+      "grad_norm": 3627.1494140625,
+      "learning_rate": 1.536e-05,
+      "loss": 10.9684,
+      "step": 200
+    },
+    {
+      "epoch": 0.00893759642496143,
+      "grad_norm": 1078.9390869140625,
+      "learning_rate": 1.616e-05,
+      "loss": 11.0077,
+      "step": 210
+    },
+    {
+      "epoch": 0.009363196254721498,
+      "grad_norm": 1400.2003173828125,
+      "learning_rate": 1.696e-05,
+      "loss": 10.7138,
+      "step": 220
+    },
+    {
+      "epoch": 0.009788796084481566,
+      "grad_norm": 880.6416015625,
+      "learning_rate": 1.7760000000000003e-05,
+      "loss": 10.4564,
+      "step": 230
+    },
+    {
+      "epoch": 0.010214395914241635,
+      "grad_norm": 888.9507446289062,
+      "learning_rate": 1.856e-05,
+      "loss": 10.4699,
+      "step": 240
+    },
+    {
+      "epoch": 0.010639995744001702,
+      "grad_norm": 604.7562255859375,
+      "learning_rate": 1.936e-05,
+      "loss": 10.5335,
+      "step": 250
+    },
+    {
+      "epoch": 0.01106559557376177,
+      "grad_norm": 885.2161865234375,
+      "learning_rate": 2.016e-05,
+      "loss": 10.3258,
+      "step": 260
+    },
+    {
+      "epoch": 0.011491195403521838,
+      "grad_norm": 689.9547729492188,
+      "learning_rate": 2.0960000000000003e-05,
+      "loss": 10.3034,
+      "step": 270
+    },
+    {
+      "epoch": 0.011916795233281907,
+      "grad_norm": 1086.3548583984375,
+      "learning_rate": 2.176e-05,
+      "loss": 10.121,
+      "step": 280
+    },
+    {
+      "epoch": 0.012342395063041975,
+      "grad_norm": 728.9247436523438,
+      "learning_rate": 2.256e-05,
+      "loss": 9.9983,
+      "step": 290
+    },
+    {
+      "epoch": 0.012767994892802044,
+      "grad_norm": 931.4705200195312,
+      "learning_rate": 2.336e-05,
+      "loss": 10.1502,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 426,
+  "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": 4405008815308800.0,
+  "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 sha256:297139a11e797886df97214381a888b42a0b5caa8afc09face8a71d0e1d36fd7
+size 5201