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:efecf4de493f2317ddb0f533e565a39cfe2711763654fb27ec316a4bf4019d96
+size 501759848

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ae4a7f05c61a1e072c2978680a7c5b57ca06f3ca71a48e9bbbdac779490193
+size 254028235

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097c45be44fdb7ef34e6a0ba54591adc7c8f8a0f9bb0cbacd1b9803381063a41
+size 14645

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2fa5948d3d1127fc7734c24851dfadb8b68652dc2ac26386fdae7f2387511c5
+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": 0.04199695522074649,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002099847761037325,
+      "grad_norm": 22925.884765625,
+      "learning_rate": 1.9999999999999996e-07,
+      "loss": 9.5004,
+      "step": 10
+    },
+    {
+      "epoch": 0.00419969552207465,
+      "grad_norm": 1589.221435546875,
+      "learning_rate": 1.2e-06,
+      "loss": 8.7173,
+      "step": 20
+    },
+    {
+      "epoch": 0.006299543283111974,
+      "grad_norm": 577.2943115234375,
+      "learning_rate": 2.1999999999999997e-06,
+      "loss": 7.6284,
+      "step": 30
+    },
+    {
+      "epoch": 0.0083993910441493,
+      "grad_norm": 308.8800048828125,
+      "learning_rate": 3.1999999999999994e-06,
+      "loss": 7.2988,
+      "step": 40
+    },
+    {
+      "epoch": 0.010499238805186623,
+      "grad_norm": 458.5738220214844,
+      "learning_rate": 4.2e-06,
+      "loss": 7.1397,
+      "step": 50
+    },
+    {
+      "epoch": 0.012599086566223949,
+      "grad_norm": 2117.726806640625,
+      "learning_rate": 5.199999999999999e-06,
+      "loss": 7.0424,
+      "step": 60
+    },
+    {
+      "epoch": 0.014698934327261274,
+      "grad_norm": 784.7866821289062,
+      "learning_rate": 6.199999999999999e-06,
+      "loss": 6.9896,
+      "step": 70
+    },
+    {
+      "epoch": 0.0167987820882986,
+      "grad_norm": 719.2965087890625,
+      "learning_rate": 7.2e-06,
+      "loss": 6.9514,
+      "step": 80
+    },
+    {
+      "epoch": 0.018898629849335925,
+      "grad_norm": 887.7239379882812,
+      "learning_rate": 8.2e-06,
+      "loss": 6.9188,
+      "step": 90
+    },
+    {
+      "epoch": 0.020998477610373247,
+      "grad_norm": 657.1996459960938,
+      "learning_rate": 9.199999999999998e-06,
+      "loss": 6.9113,
+      "step": 100
+    },
+    {
+      "epoch": 0.023098325371410572,
+      "grad_norm": 1241.19482421875,
+      "learning_rate": 1.02e-05,
+      "loss": 6.8953,
+      "step": 110
+    },
+    {
+      "epoch": 0.025198173132447897,
+      "grad_norm": 411.5585021972656,
+      "learning_rate": 1.12e-05,
+      "loss": 6.8474,
+      "step": 120
+    },
+    {
+      "epoch": 0.027298020893485223,
+      "grad_norm": 1062.7774658203125,
+      "learning_rate": 1.2199999999999998e-05,
+      "loss": 6.8514,
+      "step": 130
+    },
+    {
+      "epoch": 0.029397868654522548,
+      "grad_norm": 148.0970001220703,
+      "learning_rate": 1.3199999999999997e-05,
+      "loss": 6.8698,
+      "step": 140
+    },
+    {
+      "epoch": 0.03149771641555987,
+      "grad_norm": 280.5868835449219,
+      "learning_rate": 1.4199999999999998e-05,
+      "loss": 6.8395,
+      "step": 150
+    },
+    {
+      "epoch": 0.0335975641765972,
+      "grad_norm": 407.1022644042969,
+      "learning_rate": 1.5199999999999998e-05,
+      "loss": 6.8029,
+      "step": 160
+    },
+    {
+      "epoch": 0.035697411937634524,
+      "grad_norm": 166.18153381347656,
+      "learning_rate": 1.6199999999999997e-05,
+      "loss": 6.7946,
+      "step": 170
+    },
+    {
+      "epoch": 0.03779725969867185,
+      "grad_norm": 234.69805908203125,
+      "learning_rate": 1.7199999999999998e-05,
+      "loss": 6.7898,
+      "step": 180
+    },
+    {
+      "epoch": 0.03989710745970917,
+      "grad_norm": 917.2261352539062,
+      "learning_rate": 1.82e-05,
+      "loss": 6.7996,
+      "step": 190
+    },
+    {
+      "epoch": 0.04199695522074649,
+      "grad_norm": 237.35519409179688,
+      "learning_rate": 1.92e-05,
+      "loss": 6.7733,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 21,
+  "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": 1.30684436938752e+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:e4273736f78f1a1a756fad9c1dcb6f595241640fb3898b11c26e020ad95062f5
+size 5201