update slot resume pointers for step 496

slots/12/checkpoint-501/config.json

@@ -1,24 +0,0 @@
-{
-  "architectures": [
-    "TwinyForCausalLM"
-  ],
-  "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": "twiny",
-  "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/12/checkpoint-501/trainer_state.json

@@ -1,216 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.026222506604695713,
-  "eval_steps": 500,
-  "global_step": 501,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 2.617016627215141e-05,
-      "grad_norm": 122.33340454101562,
-      "learning_rate": 5e-05,
-      "loss": 419.9996032714844,
-      "step": 1
-    },
-    {
-      "epoch": 0.0005234033254430282,
-      "grad_norm": 90.82410430908203,
-      "learning_rate": 4.999999511980259e-05,
-      "loss": 428.18197471217104,
-      "step": 20
-    },
-    {
-      "epoch": 0.0010468066508860564,
-      "grad_norm": 59.52641296386719,
-      "learning_rate": 4.999997943828395e-05,
-      "loss": 366.3947265625,
-      "step": 40
-    },
-    {
-      "epoch": 0.0015702099763290846,
-      "grad_norm": 41.61277389526367,
-      "learning_rate": 4.999995294193233e-05,
-      "loss": 325.6545166015625,
-      "step": 60
-    },
-    {
-      "epoch": 0.0020936133017721128,
-      "grad_norm": 46.67556381225586,
-      "learning_rate": 4.999991563075919e-05,
-      "loss": 310.3648193359375,
-      "step": 80
-    },
-    {
-      "epoch": 0.002617016627215141,
-      "grad_norm": 47.65824890136719,
-      "learning_rate": 4.999986750478065e-05,
-      "loss": 303.49443359375,
-      "step": 100
-    },
-    {
-      "epoch": 0.003140419952658169,
-      "grad_norm": 62.748138427734375,
-      "learning_rate": 4.999980856401755e-05,
-      "loss": 322.389990234375,
-      "step": 120
-    },
-    {
-      "epoch": 0.007327646556202395,
-      "grad_norm": 48.20169448852539,
-      "learning_rate": 4.999895523943923e-05,
-      "loss": 288.82497336647725,
-      "step": 140
-    },
-    {
-      "epoch": 0.008374453207088451,
-      "grad_norm": 68.66603088378906,
-      "learning_rate": 4.99986329623214e-05,
-      "loss": 293.87509765625,
-      "step": 160
-    },
-    {
-      "epoch": 0.009421259857974507,
-      "grad_norm": 61.69401931762695,
-      "learning_rate": 4.999826742820622e-05,
-      "loss": 324.10361328125,
-      "step": 180
-    },
-    {
-      "epoch": 0.010468066508860565,
-      "grad_norm": 56.778385162353516,
-      "learning_rate": 4.999785863772618e-05,
-      "loss": 274.875537109375,
-      "step": 200
-    },
-    {
-      "epoch": 0.01151487315974662,
-      "grad_norm": 71.3816146850586,
-      "learning_rate": 4.999740659158865e-05,
-      "loss": 281.357080078125,
-      "step": 220
-    },
-    {
-      "epoch": 0.012561679810632677,
-      "grad_norm": 75.08697509765625,
-      "learning_rate": 4.9996911290575844e-05,
-      "loss": 263.852783203125,
-      "step": 240
-    },
-    {
-      "epoch": 0.013608486461518732,
-      "grad_norm": 53.91341781616211,
-      "learning_rate": 4.999637273554481e-05,
-      "loss": 258.546630859375,
-      "step": 260
-    },
-    {
-      "epoch": 0.01465529311240479,
-      "grad_norm": 56.39162063598633,
-      "learning_rate": 4.9995790927427446e-05,
-      "loss": 270.5470703125,
-      "step": 280
-    },
-    {
-      "epoch": 0.015702099763290844,
-      "grad_norm": 62.93777084350586,
-      "learning_rate": 4.99951658672305e-05,
-      "loss": 252.8383056640625,
-      "step": 300
-    },
-    {
-      "epoch": 0.016748906414176902,
-      "grad_norm": 61.51578903198242,
-      "learning_rate": 4.9994497556035567e-05,
-      "loss": 287.8167724609375,
-      "step": 320
-    },
-    {
-      "epoch": 0.01779571306506296,
-      "grad_norm": 62.75235366821289,
-      "learning_rate": 4.9993785994999074e-05,
-      "loss": 258.673779296875,
-      "step": 340
-    },
-    {
-      "epoch": 0.018842519715949014,
-      "grad_norm": 56.2258186340332,
-      "learning_rate": 4.999303118535229e-05,
-      "loss": 252.9609375,
-      "step": 360
-    },
-    {
-      "epoch": 0.01988932636683507,
-      "grad_norm": 54.998130798339844,
-      "learning_rate": 4.9992233128401314e-05,
-      "loss": 241.9411376953125,
-      "step": 380
-    },
-    {
-      "epoch": 0.02093613301772113,
-      "grad_norm": 63.37522888183594,
-      "learning_rate": 4.999139182552709e-05,
-      "loss": 249.7280517578125,
-      "step": 400
-    },
-    {
-      "epoch": 0.021982939668607183,
-      "grad_norm": 60.007144927978516,
-      "learning_rate": 4.9990507278185374e-05,
-      "loss": 236.941015625,
-      "step": 420
-    },
-    {
-      "epoch": 0.02302974631949324,
-      "grad_norm": 66.06304168701172,
-      "learning_rate": 4.998957948790677e-05,
-      "loss": 240.55878363715277,
-      "step": 440
-    },
-    {
-      "epoch": 0.0240765529703793,
-      "grad_norm": 68.9736099243164,
-      "learning_rate": 4.998860845629671e-05,
-      "loss": 247.988720703125,
-      "step": 460
-    },
-    {
-      "epoch": 0.025123359621265353,
-      "grad_norm": 61.50578308105469,
-      "learning_rate": 4.998759418503544e-05,
-      "loss": 233.025537109375,
-      "step": 480
-    },
-    {
-      "epoch": 0.02617016627215141,
-      "grad_norm": 54.96660614013672,
-      "learning_rate": 4.998653667587801e-05,
-      "loss": 243.004736328125,
-      "step": 500
-    }
-  ],
-  "logging_steps": 20,
-  "max_steps": 47765,
-  "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": 519043089991680.0,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

slots/12/latest.json

@@ -1 +1 @@
-{"worker_id": "slot:12", "checkpoint": "slots/12/checkpoint-501", "step": 501, "updated_at": 1776388785}
+{"worker_id": "slot:12", "checkpoint": "slots/12/checkpoint-496", "step": 496, "updated_at": 1776389539}