Upload folder using huggingface_hub

checkpoint-100/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-100/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.1"
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e81a0a2c0569c002f3785b852faec95b37e830f83042cc8789ee31117edb37
+size 523296628

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe334b01a23c2374b11c35af4d43ecf138d3de63b6f3fa15cd317b768d66978
+size 253726283

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd7ba6e5f67a7c0db584e10f21a95174e2ab951f6fafb6244212441e8f8209d
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec7dd949d35f48dc8fb27535e4827834a15e6e3a364a22af8ae0bcf2b10765e
+size 1383

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4126f369fa8da2cb59d16fdad6dca8050b919953d85143aa3ba9ddca6cc2cda
+size 1465

checkpoint-100/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-100/trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.005249619402593312,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005249619402593312,
+      "grad_norm": 649.425537109375,
+      "learning_rate": 2.1000000000000002e-06,
+      "loss": 78.31113891601562,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010499238805186625,
+      "grad_norm": 469.9927978515625,
+      "learning_rate": 5.6e-06,
+      "loss": 71.8221435546875,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015748858207779936,
+      "grad_norm": 202.18115234375,
+      "learning_rate": 9.1e-06,
+      "loss": 66.6298828125,
+      "step": 30
+    },
+    {
+      "epoch": 0.002099847761037325,
+      "grad_norm": 170.30665588378906,
+      "learning_rate": 1.26e-05,
+      "loss": 65.17080078125,
+      "step": 40
+    },
+    {
+      "epoch": 0.002624809701296656,
+      "grad_norm": 140.25149536132812,
+      "learning_rate": 1.61e-05,
+      "loss": 63.4235595703125,
+      "step": 50
+    },
+    {
+      "epoch": 0.003149771641555987,
+      "grad_norm": 144.1294708251953,
+      "learning_rate": 1.96e-05,
+      "loss": 62.191094970703126,
+      "step": 60
+    },
+    {
+      "epoch": 0.0036747335818153185,
+      "grad_norm": 135.4667205810547,
+      "learning_rate": 2.3100000000000002e-05,
+      "loss": 61.151849365234376,
+      "step": 70
+    },
+    {
+      "epoch": 0.00419969552207465,
+      "grad_norm": 138.31741333007812,
+      "learning_rate": 2.66e-05,
+      "loss": 60.54093627929687,
+      "step": 80
+    },
+    {
+      "epoch": 0.004724657462333981,
+      "grad_norm": 95.2665023803711,
+      "learning_rate": 3.0099999999999996e-05,
+      "loss": 60.263397216796875,
+      "step": 90
+    },
+    {
+      "epoch": 0.005249619402593312,
+      "grad_norm": Infinity,
+      "learning_rate": 3.3600000000000004e-05,
+      "loss": 60.61234130859375,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 1537952686878720.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4803246c76cbb72f98e283a4fe1207f2b431a3b1a55d9e5de7c9e0bb4cadf427
+size 5137