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 sha256:133d7808f85b1f51ce471d1c16f875210114682f9574d0dd295f591fcb4a579f
+size 501759848

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427b930d7ad698ba8d8279e952054d812a53d7bcbe214c3b9fc19e067cf9733e
+size 254028235

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d843b32d5f19351b707f55b56f8e68cbc4e1965665a99570b2ceada519c8ec5
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0fcc2dc47e30e11e8cd21ccb271147223bd41dedc676c096c6d12821502755d
+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": 0.06153609476558594,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006153609476558594,
+      "grad_norm": 25468.8046875,
+      "learning_rate": 1.9999999999999996e-07,
+      "loss": 8.7082,
+      "step": 10
+    },
+    {
+      "epoch": 0.012307218953117188,
+      "grad_norm": 1228.4501953125,
+      "learning_rate": 1.2e-06,
+      "loss": 8.0776,
+      "step": 20
+    },
+    {
+      "epoch": 0.018460828429675783,
+      "grad_norm": 355.1081237792969,
+      "learning_rate": 2.1999999999999997e-06,
+      "loss": 7.2372,
+      "step": 30
+    },
+    {
+      "epoch": 0.024614437906234375,
+      "grad_norm": 255.58433532714844,
+      "learning_rate": 3.1999999999999994e-06,
+      "loss": 6.9725,
+      "step": 40
+    },
+    {
+      "epoch": 0.03076804738279297,
+      "grad_norm": 253.23995971679688,
+      "learning_rate": 4.2e-06,
+      "loss": 6.8585,
+      "step": 50
+    },
+    {
+      "epoch": 0.036921656859351566,
+      "grad_norm": 241.82064819335938,
+      "learning_rate": 5.199999999999999e-06,
+      "loss": 6.7367,
+      "step": 60
+    },
+    {
+      "epoch": 0.043075266335910155,
+      "grad_norm": 229.0261993408203,
+      "learning_rate": 6.199999999999999e-06,
+      "loss": 6.6534,
+      "step": 70
+    },
+    {
+      "epoch": 0.04922887581246875,
+      "grad_norm": 321.6871337890625,
+      "learning_rate": 7.2e-06,
+      "loss": 6.6305,
+      "step": 80
+    },
+    {
+      "epoch": 0.055382485289027346,
+      "grad_norm": 465.00543212890625,
+      "learning_rate": 8.2e-06,
+      "loss": 6.6253,
+      "step": 90
+    },
+    {
+      "epoch": 0.06153609476558594,
+      "grad_norm": 566.6929321289062,
+      "learning_rate": 9.199999999999998e-06,
+      "loss": 6.5724,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 62,
+  "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": 7587180589056000.0,
+  "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 sha256:4183c4264061f851b0692158bc778140daa0082cbcdb75e934ec1d340f04b990
+size 5201