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 sha256:1b0ee3e2eab5b29488ab4c9afa6c09bfc52f4539d17b358c681e5b596bd2aeaa
+size 501755480

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9fb6469af38bafb2f7ff6630775d162931b15216bd9622eec3890b5568dc2f
+size 254028235

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e18d1a0a8905bf76046fbd57bd2a92ee690f1537b119955a5c97c83aacbff90
+size 14645

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb22dbede66ad7a98c11fb496813e1803325871e2016e5d29a056027d8f91089
+size 1383

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4740c83a8d487f8c66d35ee96265fa1587e3e5fb469c8ea471a63e194c9897c
+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": 0.010499376599514405,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005249688299757202,
+      "grad_norm": 4051.18359375,
+      "learning_rate": 9e-07,
+      "loss": 7.93,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010499376599514404,
+      "grad_norm": 111.26915740966797,
+      "learning_rate": 3.899999999999999e-06,
+      "loss": 7.7273,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015749064899271605,
+      "grad_norm": 176.40713500976562,
+      "learning_rate": 6.899999999999999e-06,
+      "loss": 7.5271,
+      "step": 30
+    },
+    {
+      "epoch": 0.002099875319902881,
+      "grad_norm": 668.3442993164062,
+      "learning_rate": 9.9e-06,
+      "loss": 7.6155,
+      "step": 40
+    },
+    {
+      "epoch": 0.002624844149878601,
+      "grad_norm": 171.85369873046875,
+      "learning_rate": 1.2899999999999998e-05,
+      "loss": 7.4873,
+      "step": 50
+    },
+    {
+      "epoch": 0.003149812979854321,
+      "grad_norm": 477.1031494140625,
+      "learning_rate": 1.5899999999999997e-05,
+      "loss": 7.4295,
+      "step": 60
+    },
+    {
+      "epoch": 0.0036747818098300414,
+      "grad_norm": 256.7841491699219,
+      "learning_rate": 1.89e-05,
+      "loss": 7.3037,
+      "step": 70
+    },
+    {
+      "epoch": 0.004199750639805762,
+      "grad_norm": 240.86167907714844,
+      "learning_rate": 2.1899999999999997e-05,
+      "loss": 7.3488,
+      "step": 80
+    },
+    {
+      "epoch": 0.0047247194697814816,
+      "grad_norm": 151.8752899169922,
+      "learning_rate": 2.49e-05,
+      "loss": 7.1664,
+      "step": 90
+    },
+    {
+      "epoch": 0.005249688299757202,
+      "grad_norm": 92.41702270507812,
+      "learning_rate": 2.7899999999999997e-05,
+      "loss": 7.2001,
+      "step": 100
+    },
+    {
+      "epoch": 0.005774657129732922,
+      "grad_norm": 125.6628189086914,
+      "learning_rate": 3.09e-05,
+      "loss": 7.1956,
+      "step": 110
+    },
+    {
+      "epoch": 0.006299625959708642,
+      "grad_norm": 105.1700210571289,
+      "learning_rate": 3.39e-05,
+      "loss": 7.2136,
+      "step": 120
+    },
+    {
+      "epoch": 0.006824594789684363,
+      "grad_norm": 95.49678039550781,
+      "learning_rate": 3.6899999999999996e-05,
+      "loss": 7.2046,
+      "step": 130
+    },
+    {
+      "epoch": 0.007349563619660083,
+      "grad_norm": 70.33267974853516,
+      "learning_rate": 3.99e-05,
+      "loss": 7.0895,
+      "step": 140
+    },
+    {
+      "epoch": 0.007874532449635803,
+      "grad_norm": 42.994972229003906,
+      "learning_rate": 4.289999999999999e-05,
+      "loss": 7.1157,
+      "step": 150
+    },
+    {
+      "epoch": 0.008399501279611523,
+      "grad_norm": 87.23907470703125,
+      "learning_rate": 4.59e-05,
+      "loss": 7.1537,
+      "step": 160
+    },
+    {
+      "epoch": 0.008924470109587244,
+      "grad_norm": 53.14045333862305,
+      "learning_rate": 4.8899999999999996e-05,
+      "loss": 7.0126,
+      "step": 170
+    },
+    {
+      "epoch": 0.009449438939562963,
+      "grad_norm": 44.222225189208984,
+      "learning_rate": 5.1899999999999994e-05,
+      "loss": 7.1067,
+      "step": 180
+    },
+    {
+      "epoch": 0.009974407769538684,
+      "grad_norm": 65.67877197265625,
+      "learning_rate": 5.489999999999999e-05,
+      "loss": 7.0359,
+      "step": 190
+    },
+    {
+      "epoch": 0.010499376599514405,
+      "grad_norm": 34.80784225463867,
+      "learning_rate": 5.79e-05,
+      "loss": 7.0124,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 10000000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 525,
+  "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": 2988639533875200.0,
+  "train_batch_size": 8,
+  "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:a40bbf14bc866e7549dd7e35b2f1efa93574f3325f7dcb8eac5341e7f4b4f035
+size 5201