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:d0d4f50b4cfd9e2ea0c01a20af0e05650e511ebc9161235443e598b219270a41
+size 501759848

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cbd4a5b844a306f1b54d9c78142554cab5fed18ae6d82e5f1009838d7094520
+size 254028235

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097c45be44fdb7ef34e6a0ba54591adc7c8f8a0f9bb0cbacd1b9803381063a41
+size 14645

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a871f91401a0bd517d31d61a5fd51ea6df5bf7fd306387cba6f306497b3414d2
+size 1383

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39153e61f589f1aa26a556a4b6cc87338b4c93748d9ebb98d9f5b5c1a28b7cf
+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": 0.04199695522074649,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002099847761037325,
+      "grad_norm": 19872.2890625,
+      "learning_rate": 3e-07,
+      "loss": 8.7939,
+      "step": 10
+    },
+    {
+      "epoch": 0.00419969552207465,
+      "grad_norm": 1458.198974609375,
+      "learning_rate": 1.2999999999999998e-06,
+      "loss": 8.1117,
+      "step": 20
+    },
+    {
+      "epoch": 0.006299543283111974,
+      "grad_norm": 297.6234130859375,
+      "learning_rate": 2.2999999999999996e-06,
+      "loss": 7.3977,
+      "step": 30
+    },
+    {
+      "epoch": 0.0083993910441493,
+      "grad_norm": 426.92987060546875,
+      "learning_rate": 3.2999999999999993e-06,
+      "loss": 7.2069,
+      "step": 40
+    },
+    {
+      "epoch": 0.010499238805186623,
+      "grad_norm": 474.7532653808594,
+      "learning_rate": 4.2999999999999995e-06,
+      "loss": 7.08,
+      "step": 50
+    },
+    {
+      "epoch": 0.012599086566223949,
+      "grad_norm": 1569.4381103515625,
+      "learning_rate": 5.3e-06,
+      "loss": 7.0092,
+      "step": 60
+    },
+    {
+      "epoch": 0.014698934327261274,
+      "grad_norm": 1407.21142578125,
+      "learning_rate": 6.3e-06,
+      "loss": 6.9929,
+      "step": 70
+    },
+    {
+      "epoch": 0.0167987820882986,
+      "grad_norm": 500.49493408203125,
+      "learning_rate": 7.299999999999999e-06,
+      "loss": 6.9501,
+      "step": 80
+    },
+    {
+      "epoch": 0.018898629849335925,
+      "grad_norm": 442.69537353515625,
+      "learning_rate": 8.299999999999998e-06,
+      "loss": 6.9001,
+      "step": 90
+    },
+    {
+      "epoch": 0.020998477610373247,
+      "grad_norm": 1423.2950439453125,
+      "learning_rate": 9.299999999999999e-06,
+      "loss": 6.9037,
+      "step": 100
+    },
+    {
+      "epoch": 0.023098325371410572,
+      "grad_norm": 448.7774963378906,
+      "learning_rate": 1.03e-05,
+      "loss": 6.8732,
+      "step": 110
+    },
+    {
+      "epoch": 0.025198173132447897,
+      "grad_norm": 711.8992919921875,
+      "learning_rate": 1.1299999999999999e-05,
+      "loss": 6.8381,
+      "step": 120
+    },
+    {
+      "epoch": 0.027298020893485223,
+      "grad_norm": 884.006591796875,
+      "learning_rate": 1.2299999999999999e-05,
+      "loss": 6.8462,
+      "step": 130
+    },
+    {
+      "epoch": 0.029397868654522548,
+      "grad_norm": 96.5859375,
+      "learning_rate": 1.33e-05,
+      "loss": 6.8433,
+      "step": 140
+    },
+    {
+      "epoch": 0.03149771641555987,
+      "grad_norm": 91.52490997314453,
+      "learning_rate": 1.43e-05,
+      "loss": 6.8171,
+      "step": 150
+    },
+    {
+      "epoch": 0.0335975641765972,
+      "grad_norm": 354.9374084472656,
+      "learning_rate": 1.53e-05,
+      "loss": 6.7899,
+      "step": 160
+    },
+    {
+      "epoch": 0.035697411937634524,
+      "grad_norm": 189.09506225585938,
+      "learning_rate": 1.6299999999999996e-05,
+      "loss": 6.7456,
+      "step": 170
+    },
+    {
+      "epoch": 0.03779725969867185,
+      "grad_norm": 170.39376831054688,
+      "learning_rate": 1.7299999999999997e-05,
+      "loss": 6.7505,
+      "step": 180
+    },
+    {
+      "epoch": 0.03989710745970917,
+      "grad_norm": 193.9166259765625,
+      "learning_rate": 1.8299999999999998e-05,
+      "loss": 6.752,
+      "step": 190
+    },
+    {
+      "epoch": 0.04199695522074649,
+      "grad_norm": 336.08624267578125,
+      "learning_rate": 1.93e-05,
+      "loss": 6.7015,
+      "step": 200
+    }
+  ],
+  "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": 1.30684436938752e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000c64b2f44395822e8bf59265f8e6e5d085b71ae5ccbb8b496fbe6f256940c8
+size 5201