Upload folder using huggingface_hub

slots/0/checkpoint-282/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "MinixForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "hidden_dropout": 0.0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 128,
+  "model_type": "minix",
+  "neftune_alpha": 0.0,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 3,
+  "qk_norm": true,
+  "rezero_init": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

slots/0/checkpoint-282/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7587efb55eedd76d4d59a8528416609c62bb3e8e0a3c963c7425a0570f8cad82
+size 233203620

slots/0/checkpoint-282/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:995c0105a206b56d2815386a49c42f93bd6191364d4e6845dc7d95777bec7c89
+size 466419638

slots/0/checkpoint-282/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1971a7f5a4b2dbf37c7eaedcc9ddd90b7f2853c5557f35719c1a2082903b821
+size 14455

slots/0/checkpoint-282/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f3a0fea04086aba89b8caef79ae7bc110e7d961a10b25a5401d3eebe3b06e8
+size 1465

slots/0/checkpoint-282/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.018301260158578473,
+  "eval_steps": 500,
+  "global_step": 282,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 6.489808566871798e-05,
+      "grad_norm": 109.46859741210938,
+      "learning_rate": 5e-05,
+      "loss": 421.4660949707031,
+      "step": 1
+    },
+    {
+      "epoch": 0.0012979617133743598,
+      "grad_norm": 88.54906463623047,
+      "learning_rate": 4.999996998926224e-05,
+      "loss": 390.39101048519734,
+      "step": 20
+    },
+    {
+      "epoch": 0.0025959234267487197,
+      "grad_norm": 60.599815368652344,
+      "learning_rate": 4.999987355594792e-05,
+      "loss": 341.1005126953125,
+      "step": 40
+    },
+    {
+      "epoch": 0.003893885140123079,
+      "grad_norm": 42.03083419799805,
+      "learning_rate": 4.999971061718136e-05,
+      "loss": 318.29091796875,
+      "step": 60
+    },
+    {
+      "epoch": 0.005191846853497439,
+      "grad_norm": 34.96514129638672,
+      "learning_rate": 4.999948117339598e-05,
+      "loss": 305.076220703125,
+      "step": 80
+    },
+    {
+      "epoch": 0.006489808566871798,
+      "grad_norm": 37.357093811035156,
+      "learning_rate": 4.9999185225202174e-05,
+      "loss": 298.5962890625,
+      "step": 100
+    },
+    {
+      "epoch": 0.007787770280246158,
+      "grad_norm": 43.13069152832031,
+      "learning_rate": 4.999882277338722e-05,
+      "loss": 291.7892578125,
+      "step": 120
+    },
+    {
+      "epoch": 0.009085731993620519,
+      "grad_norm": 43.607086181640625,
+      "learning_rate": 4.9998393818915336e-05,
+      "loss": 283.4513671875,
+      "step": 140
+    },
+    {
+      "epoch": 0.010383693706994879,
+      "grad_norm": 45.93403625488281,
+      "learning_rate": 4.999789836292764e-05,
+      "loss": 279.384619140625,
+      "step": 160
+    },
+    {
+      "epoch": 0.011681655420369237,
+      "grad_norm": 42.242095947265625,
+      "learning_rate": 4.9997336406742147e-05,
+      "loss": 272.4620849609375,
+      "step": 180
+    },
+    {
+      "epoch": 0.012979617133743597,
+      "grad_norm": 45.98979187011719,
+      "learning_rate": 4.99967079518538e-05,
+      "loss": 273.69755859375,
+      "step": 200
+    },
+    {
+      "epoch": 0.014277578847117956,
+      "grad_norm": 43.22636413574219,
+      "learning_rate": 4.999601299993443e-05,
+      "loss": 269.176513671875,
+      "step": 220
+    },
+    {
+      "epoch": 0.015575540560492316,
+      "grad_norm": 48.822811126708984,
+      "learning_rate": 4.9995251552832775e-05,
+      "loss": 278.3380859375,
+      "step": 240
+    },
+    {
+      "epoch": 0.016873502273866678,
+      "grad_norm": 43.93081283569336,
+      "learning_rate": 4.999442361257446e-05,
+      "loss": 267.6831787109375,
+      "step": 260
+    },
+    {
+      "epoch": 0.018171463987241038,
+      "grad_norm": 39.47734832763672,
+      "learning_rate": 4.9993529181361986e-05,
+      "loss": 253.4231689453125,
+      "step": 280
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 38523,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 292155990773760.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

slots/0/checkpoint-282/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836dfb13cdcae1876ff32684eefa6b1c7850dd96d7540d28415116d6d69ea1df
+size 5201