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 sha256:62219c7b48f400f23c3a49a4bb87a4f9b5da43ca016235ba2aec10f06129451a
+size 501911880

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0bfcc9cbba7ef519a6f354e064bf3f8454eca1f568c2684989e8415d34ffce8
+size 254046539

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228aca2cbc060d55776c078f59b285dec9965a084958773bc060010786a50e21
+size 14645

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e0b88b2b21c7f4038a5aad3901f12945cd7b739d9dd969a776161241b8f6ec0
+size 1383

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:678503feeb6707b61d9e6c001443b3742e932d2acc6afc1e7414605fe01f80bf
+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": 2042.0159912109375,
+      "learning_rate": 3.2e-07,
+      "loss": 8.126,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010578512396694215,
+      "grad_norm": 132.607666015625,
+      "learning_rate": 1.12e-06,
+      "loss": 8.0108,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015867768595041322,
+      "grad_norm": 117.4473876953125,
+      "learning_rate": 1.92e-06,
+      "loss": 7.8388,
+      "step": 30
+    },
+    {
+      "epoch": 0.002115702479338843,
+      "grad_norm": 58.00923538208008,
+      "learning_rate": 2.72e-06,
+      "loss": 7.7671,
+      "step": 40
+    },
+    {
+      "epoch": 0.002644628099173554,
+      "grad_norm": 62.31724166870117,
+      "learning_rate": 3.52e-06,
+      "loss": 7.821,
+      "step": 50
+    },
+    {
+      "epoch": 0.0031735537190082643,
+      "grad_norm": 99.75863647460938,
+      "learning_rate": 4.32e-06,
+      "loss": 7.6772,
+      "step": 60
+    },
+    {
+      "epoch": 0.0037024793388429752,
+      "grad_norm": 337.9526672363281,
+      "learning_rate": 5.12e-06,
+      "loss": 7.8172,
+      "step": 70
+    },
+    {
+      "epoch": 0.004231404958677686,
+      "grad_norm": 95.75334167480469,
+      "learning_rate": 5.920000000000001e-06,
+      "loss": 7.6801,
+      "step": 80
+    },
+    {
+      "epoch": 0.004760330578512397,
+      "grad_norm": 589.1984252929688,
+      "learning_rate": 6.72e-06,
+      "loss": 7.7462,
+      "step": 90
+    },
+    {
+      "epoch": 0.005289256198347108,
+      "grad_norm": 115.37745666503906,
+      "learning_rate": 7.520000000000001e-06,
+      "loss": 7.5665,
+      "step": 100
+    },
+    {
+      "epoch": 0.005818181818181818,
+      "grad_norm": 104.31098937988281,
+      "learning_rate": 8.32e-06,
+      "loss": 7.6031,
+      "step": 110
+    },
+    {
+      "epoch": 0.006347107438016529,
+      "grad_norm": 357.35272216796875,
+      "learning_rate": 9.12e-06,
+      "loss": 7.6829,
+      "step": 120
+    },
+    {
+      "epoch": 0.00687603305785124,
+      "grad_norm": 299.00555419921875,
+      "learning_rate": 9.92e-06,
+      "loss": 7.6717,
+      "step": 130
+    },
+    {
+      "epoch": 0.0074049586776859504,
+      "grad_norm": 593.5489501953125,
+      "learning_rate": 1.072e-05,
+      "loss": 7.6622,
+      "step": 140
+    },
+    {
+      "epoch": 0.007933884297520661,
+      "grad_norm": 174.9026336669922,
+      "learning_rate": 1.152e-05,
+      "loss": 7.595,
+      "step": 150
+    },
+    {
+      "epoch": 0.008462809917355372,
+      "grad_norm": 199.49935913085938,
+      "learning_rate": 1.232e-05,
+      "loss": 7.5791,
+      "step": 160
+    },
+    {
+      "epoch": 0.008991735537190083,
+      "grad_norm": 557.2059936523438,
+      "learning_rate": 1.3120000000000001e-05,
+      "loss": 7.7285,
+      "step": 170
+    },
+    {
+      "epoch": 0.009520661157024794,
+      "grad_norm": 333.83441162109375,
+      "learning_rate": 1.3919999999999999e-05,
+      "loss": 7.6101,
+      "step": 180
+    },
+    {
+      "epoch": 0.010049586776859505,
+      "grad_norm": 213.27163696289062,
+      "learning_rate": 1.472e-05,
+      "loss": 7.6139,
+      "step": 190
+    },
+    {
+      "epoch": 0.010578512396694216,
+      "grad_norm": 192.46920776367188,
+      "learning_rate": 1.552e-05,
+      "loss": 7.4358,
+      "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": 3486447461990400.0,
+  "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 sha256:15fcfa1bbe0f7d96538cf17908c1e0f3298cf826d4ee288e67e22815d92829e3
+size 5137