trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5923566878980893,
  "eval_steps": 7000,
  "global_step": 56000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19904458598726116,
      "grad_norm": 0.03612709417939186,
      "learning_rate": 9.948820017059994e-06,
      "loss": 0.0087,
      "step": 7000
    },
    {
      "epoch": 0.19904458598726116,
      "eval_loss": 0.0026995299849659204,
      "eval_runtime": 305.8094,
      "eval_samples_per_second": 229.999,
      "eval_steps_per_second": 28.75,
      "step": 7000
    },
    {
      "epoch": 0.3980891719745223,
      "grad_norm": 1.6214265997405164e-05,
      "learning_rate": 8.900350699819912e-06,
      "loss": 0.0026,
      "step": 14000
    },
    {
      "epoch": 0.3980891719745223,
      "eval_loss": 0.001954245613887906,
      "eval_runtime": 330.9357,
      "eval_samples_per_second": 212.537,
      "eval_steps_per_second": 26.567,
      "step": 14000
    },
    {
      "epoch": 0.5971337579617835,
      "grad_norm": 0.0028366802725940943,
      "learning_rate": 7.794856402641308e-06,
      "loss": 0.0014,
      "step": 21000
    },
    {
      "epoch": 0.5971337579617835,
      "eval_loss": 0.0018354407511651516,
      "eval_runtime": 310.0088,
      "eval_samples_per_second": 226.884,
      "eval_steps_per_second": 28.36,
      "step": 21000
    },
    {
      "epoch": 0.7961783439490446,
      "grad_norm": 0.000240739289438352,
      "learning_rate": 6.689520078354555e-06,
      "loss": 0.0014,
      "step": 28000
    },
    {
      "epoch": 0.7961783439490446,
      "eval_loss": 0.0013708125334233046,
      "eval_runtime": 302.71,
      "eval_samples_per_second": 232.354,
      "eval_steps_per_second": 29.044,
      "step": 28000
    },
    {
      "epoch": 0.9952229299363057,
      "grad_norm": 6.373108772095293e-05,
      "learning_rate": 5.5841837540678024e-06,
      "loss": 0.0013,
      "step": 35000
    },
    {
      "epoch": 0.9952229299363057,
      "eval_loss": 0.001039660070091486,
      "eval_runtime": 303.8852,
      "eval_samples_per_second": 231.456,
      "eval_steps_per_second": 28.932,
      "step": 35000
    },
    {
      "epoch": 1.194267515923567,
      "grad_norm": 0.0001592708140378818,
      "learning_rate": 4.478847429781049e-06,
      "loss": 0.0008,
      "step": 42000
    },
    {
      "epoch": 1.194267515923567,
      "eval_loss": 0.0009645811514928937,
      "eval_runtime": 302.4576,
      "eval_samples_per_second": 232.548,
      "eval_steps_per_second": 29.069,
      "step": 42000
    },
    {
      "epoch": 1.393312101910828,
      "grad_norm": 9.89227119134739e-05,
      "learning_rate": 3.373195159710594e-06,
      "loss": 0.0005,
      "step": 49000
    },
    {
      "epoch": 1.393312101910828,
      "eval_loss": 0.0009661925723776221,
      "eval_runtime": 309.9354,
      "eval_samples_per_second": 226.938,
      "eval_steps_per_second": 28.367,
      "step": 49000
    },
    {
      "epoch": 1.5923566878980893,
      "grad_norm": 0.00025980532518588006,
      "learning_rate": 2.2678588354238415e-06,
      "loss": 0.0003,
      "step": 56000
    },
    {
      "epoch": 1.5923566878980893,
      "eval_loss": 0.0009464903851039708,
      "eval_runtime": 304.9907,
      "eval_samples_per_second": 230.617,
      "eval_steps_per_second": 28.827,
      "step": 56000
    }
  ],
  "logging_steps": 7000,
  "max_steps": 70336,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}