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 sha256:9b21db77f9cb07b992c113f29466f2305c5b4cea138a47e8670a010c337df56b
+size 501759848

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323a8353f4eff47f05aa6a28ed9ba52a7a2a746dfaf7e8b13c0e1c6c731d5e2e
+size 254028235

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c5b58d3f7e7471f2198ee6b21dea68e420c91a02bec101ad01e42ce6256886
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a572468c945e796bc85d83657570c70a9437f9012394a3c5c1b8396c4e5a364
+size 1383

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f690b2d36e27acd1338eddb359cde82c85c32e6852269bedc125d5340c18ccd2
+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": 0.020998477610373247,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002099847761037325,
+      "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
+    }
+  ],
+  "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": 6566118827212800.0,
+  "train_batch_size": 16,
+  "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:e4273736f78f1a1a756fad9c1dcb6f595241640fb3898b11c26e020ad95062f5
+size 5201