Upload folder using huggingface_hub

checkpoint-300/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-300/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.1"
+}

checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2abfa03494755c37ff5c82022acb61c23a042898dab67fac7b4da60a7c8977b
+size 501759848

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ea7f3d23b51105263344267ad7f0b7aa4802d3fcdaecf61d0afeb2ac737cd2
+size 254028555

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a436a4d7092d47ae02acb023c1ab674e58b6d89d99b38a311b53ef5939e0a8c9
+size 14645

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb13364774a403779745a17c3836f869672c46523c4bc4724258a055b4087ba
+size 1383

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b85782cfb1341cf535787a1701e7d4b8d1f023d1c1e7158e86978543d2d275
+size 1465

checkpoint-300/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-300/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06299543283111975,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002099847761037325,
+      "grad_norm": 17079.470703125,
+      "learning_rate": 3e-07,
+      "loss": 8.5176,
+      "step": 10
+    },
+    {
+      "epoch": 0.00419969552207465,
+      "grad_norm": 703.8784790039062,
+      "learning_rate": 1.2999999999999998e-06,
+      "loss": 7.9617,
+      "step": 20
+    },
+    {
+      "epoch": 0.006299543283111974,
+      "grad_norm": 225.91131591796875,
+      "learning_rate": 2.2999999999999996e-06,
+      "loss": 7.3752,
+      "step": 30
+    },
+    {
+      "epoch": 0.0083993910441493,
+      "grad_norm": 1157.0888671875,
+      "learning_rate": 3.2999999999999993e-06,
+      "loss": 7.2141,
+      "step": 40
+    },
+    {
+      "epoch": 0.010499238805186623,
+      "grad_norm": 336.49810791015625,
+      "learning_rate": 4.2999999999999995e-06,
+      "loss": 7.0722,
+      "step": 50
+    },
+    {
+      "epoch": 0.012599086566223949,
+      "grad_norm": 540.7726440429688,
+      "learning_rate": 5.3e-06,
+      "loss": 6.9838,
+      "step": 60
+    },
+    {
+      "epoch": 0.014698934327261274,
+      "grad_norm": 1353.6065673828125,
+      "learning_rate": 6.3e-06,
+      "loss": 6.9758,
+      "step": 70
+    },
+    {
+      "epoch": 0.0167987820882986,
+      "grad_norm": 2311.14453125,
+      "learning_rate": 7.299999999999999e-06,
+      "loss": 6.9621,
+      "step": 80
+    },
+    {
+      "epoch": 0.018898629849335925,
+      "grad_norm": 773.8806762695312,
+      "learning_rate": 8.299999999999998e-06,
+      "loss": 6.9078,
+      "step": 90
+    },
+    {
+      "epoch": 0.020998477610373247,
+      "grad_norm": 891.8123168945312,
+      "learning_rate": 9.299999999999999e-06,
+      "loss": 6.9017,
+      "step": 100
+    },
+    {
+      "epoch": 0.023098325371410572,
+      "grad_norm": 960.9219360351562,
+      "learning_rate": 1.03e-05,
+      "loss": 6.8828,
+      "step": 110
+    },
+    {
+      "epoch": 0.025198173132447897,
+      "grad_norm": 946.1056518554688,
+      "learning_rate": 1.1299999999999999e-05,
+      "loss": 6.8413,
+      "step": 120
+    },
+    {
+      "epoch": 0.027298020893485223,
+      "grad_norm": 821.5908813476562,
+      "learning_rate": 1.2299999999999999e-05,
+      "loss": 6.8609,
+      "step": 130
+    },
+    {
+      "epoch": 0.029397868654522548,
+      "grad_norm": 527.0160522460938,
+      "learning_rate": 1.33e-05,
+      "loss": 6.8654,
+      "step": 140
+    },
+    {
+      "epoch": 0.03149771641555987,
+      "grad_norm": 410.8817443847656,
+      "learning_rate": 1.43e-05,
+      "loss": 6.8066,
+      "step": 150
+    },
+    {
+      "epoch": 0.0335975641765972,
+      "grad_norm": 132.47149658203125,
+      "learning_rate": 1.53e-05,
+      "loss": 6.8057,
+      "step": 160
+    },
+    {
+      "epoch": 0.035697411937634524,
+      "grad_norm": 278.36541748046875,
+      "learning_rate": 1.6299999999999996e-05,
+      "loss": 6.7539,
+      "step": 170
+    },
+    {
+      "epoch": 0.03779725969867185,
+      "grad_norm": 126.05323791503906,
+      "learning_rate": 1.7299999999999997e-05,
+      "loss": 6.7514,
+      "step": 180
+    },
+    {
+      "epoch": 0.03989710745970917,
+      "grad_norm": 191.17140197753906,
+      "learning_rate": 1.8299999999999998e-05,
+      "loss": 6.7552,
+      "step": 190
+    },
+    {
+      "epoch": 0.04199695522074649,
+      "grad_norm": 605.2243041992188,
+      "learning_rate": 1.93e-05,
+      "loss": 6.7198,
+      "step": 200
+    },
+    {
+      "epoch": 0.04409680298178382,
+      "grad_norm": 123.91952514648438,
+      "learning_rate": 2.03e-05,
+      "loss": 6.7034,
+      "step": 210
+    },
+    {
+      "epoch": 0.046196650742821144,
+      "grad_norm": 642.62646484375,
+      "learning_rate": 2.1299999999999996e-05,
+      "loss": 6.6899,
+      "step": 220
+    },
+    {
+      "epoch": 0.04829649850385847,
+      "grad_norm": 371.84613037109375,
+      "learning_rate": 2.23e-05,
+      "loss": 6.6559,
+      "step": 230
+    },
+    {
+      "epoch": 0.050396346264895794,
+      "grad_norm": 121.9710922241211,
+      "learning_rate": 2.3299999999999997e-05,
+      "loss": 6.6487,
+      "step": 240
+    },
+    {
+      "epoch": 0.05249619402593312,
+      "grad_norm": 393.8136901855469,
+      "learning_rate": 2.4299999999999998e-05,
+      "loss": 6.6678,
+      "step": 250
+    },
+    {
+      "epoch": 0.054596041786970445,
+      "grad_norm": 139.10740661621094,
+      "learning_rate": 2.53e-05,
+      "loss": 6.6557,
+      "step": 260
+    },
+    {
+      "epoch": 0.05669588954800777,
+      "grad_norm": 97.0140609741211,
+      "learning_rate": 2.63e-05,
+      "loss": 6.6241,
+      "step": 270
+    },
+    {
+      "epoch": 0.058795737309045096,
+      "grad_norm": 151.50413513183594,
+      "learning_rate": 2.7299999999999996e-05,
+      "loss": 6.5866,
+      "step": 280
+    },
+    {
+      "epoch": 0.06089558507008242,
+      "grad_norm": 188.2683868408203,
+      "learning_rate": 2.83e-05,
+      "loss": 6.584,
+      "step": 290
+    },
+    {
+      "epoch": 0.06299543283111975,
+      "grad_norm": 149.62640380859375,
+      "learning_rate": 2.9299999999999997e-05,
+      "loss": 6.5906,
+      "step": 300
+    }
+  ],
+  "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": 1.96087582224384e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c51e387450ebe479893bbb80a73c82daa0e96b07b7c33aa9fe7c7a856907614b
+size 5201