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:a929b752ab438766526ddeb57b3a4ecb4371754b282e45c8f3aac5056cbb6e0a
+size 501888768

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20cb9cbebce1e525c00773c309bd18890d91a1787d822d3225d9fafc113661fa
+size 254046539

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7180a08a7d83da35e8a57b60d042f5daf6593a06012dd02994e752991fe6f585
+size 14645

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3829eb6343ef2e7024661f618446f381872344295e2859c185fcf386144bf924
+size 1383

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d391c9f814a7ddba2fc099f1bbfd00a39fa048e644d7875a5fa391c225bc607
+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": 0.010578512396694216,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005289256198347108,
+      "grad_norm": 11539.134765625,
+      "learning_rate": 2.4e-07,
+      "loss": 17.3129,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010578512396694215,
+      "grad_norm": 1744.7125244140625,
+      "learning_rate": 1.04e-06,
+      "loss": 16.2483,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015867768595041322,
+      "grad_norm": 2114.198486328125,
+      "learning_rate": 1.84e-06,
+      "loss": 15.4478,
+      "step": 30
+    },
+    {
+      "epoch": 0.002115702479338843,
+      "grad_norm": 2165.85546875,
+      "learning_rate": 2.64e-06,
+      "loss": 15.0967,
+      "step": 40
+    },
+    {
+      "epoch": 0.002644628099173554,
+      "grad_norm": 1898.4981689453125,
+      "learning_rate": 3.44e-06,
+      "loss": 14.8865,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031735537190082643,
+      "grad_norm": 1926.602294921875,
+      "learning_rate": 4.24e-06,
+      "loss": 14.7279,
+      "step": 60
+    },
+    {
+      "epoch": 0.0037024793388429752,
+      "grad_norm": 1867.364013671875,
+      "learning_rate": 5.04e-06,
+      "loss": 14.5835,
+      "step": 70
+    },
+    {
+      "epoch": 0.004231404958677686,
+      "grad_norm": 2243.830810546875,
+      "learning_rate": 5.84e-06,
+      "loss": 14.4407,
+      "step": 80
+    },
+    {
+      "epoch": 0.004760330578512397,
+      "grad_norm": 2413.40234375,
+      "learning_rate": 6.640000000000001e-06,
+      "loss": 14.3358,
+      "step": 90
+    },
+    {
+      "epoch": 0.005289256198347108,
+      "grad_norm": 2664.49951171875,
+      "learning_rate": 7.44e-06,
+      "loss": 14.1959,
+      "step": 100
+    },
+    {
+      "epoch": 0.005818181818181818,
+      "grad_norm": 3098.496337890625,
+      "learning_rate": 8.24e-06,
+      "loss": 14.0836,
+      "step": 110
+    },
+    {
+      "epoch": 0.006347107438016529,
+      "grad_norm": 3735.803466796875,
+      "learning_rate": 8.96e-06,
+      "loss": 14.0734,
+      "step": 120
+    },
+    {
+      "epoch": 0.00687603305785124,
+      "grad_norm": 2196.177978515625,
+      "learning_rate": 9.760000000000001e-06,
+      "loss": 13.964,
+      "step": 130
+    },
+    {
+      "epoch": 0.0074049586776859504,
+      "grad_norm": 3840.053466796875,
+      "learning_rate": 1.0480000000000001e-05,
+      "loss": 13.9593,
+      "step": 140
+    },
+    {
+      "epoch": 0.007933884297520661,
+      "grad_norm": 1875.8798828125,
+      "learning_rate": 1.128e-05,
+      "loss": 13.5436,
+      "step": 150
+    },
+    {
+      "epoch": 0.008462809917355372,
+      "grad_norm": 3384.51171875,
+      "learning_rate": 1.2080000000000001e-05,
+      "loss": 13.4371,
+      "step": 160
+    },
+    {
+      "epoch": 0.008991735537190083,
+      "grad_norm": 1160.2091064453125,
+      "learning_rate": 1.288e-05,
+      "loss": 13.3418,
+      "step": 170
+    },
+    {
+      "epoch": 0.009520661157024794,
+      "grad_norm": 983.0501098632812,
+      "learning_rate": 1.3680000000000001e-05,
+      "loss": 13.0806,
+      "step": 180
+    },
+    {
+      "epoch": 0.010049586776859505,
+      "grad_norm": 1017.8507690429688,
+      "learning_rate": 1.4480000000000002e-05,
+      "loss": 13.061,
+      "step": 190
+    },
+    {
+      "epoch": 0.010578512396694216,
+      "grad_norm": 2115.8447265625,
+      "learning_rate": 1.528e-05,
+      "loss": 13.1504,
+      "step": 200
+    }
+  ],
+  "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": 3290406470860800.0,
+  "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 sha256:26f7aa1d4ad8b1e995a5ff471b81bbd6678f0259ea84b481a0ec5af3ad0b3af4
+size 5201