checkpoint-1500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7001983895437041,
  "eval_steps": 250,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11669973159061735,
      "grad_norm": 0.6994202136993408,
      "learning_rate": 9.805520181836609e-05,
      "loss": 0.478,
      "step": 250
    },
    {
      "epoch": 0.11669973159061735,
      "eval_loss": 0.251759797334671,
      "eval_runtime": 31.9012,
      "eval_samples_per_second": 5.454,
      "eval_steps_per_second": 5.454,
      "step": 250
    },
    {
      "epoch": 0.2333994631812347,
      "grad_norm": 0.49493369460105896,
      "learning_rate": 8.956192175374174e-05,
      "loss": 0.1602,
      "step": 500
    },
    {
      "epoch": 0.2333994631812347,
      "eval_loss": 0.13994424045085907,
      "eval_runtime": 31.9941,
      "eval_samples_per_second": 5.438,
      "eval_steps_per_second": 5.438,
      "step": 500
    },
    {
      "epoch": 0.35009919477185203,
      "grad_norm": 0.4915720224380493,
      "learning_rate": 7.547875537973998e-05,
      "loss": 0.1159,
      "step": 750
    },
    {
      "epoch": 0.35009919477185203,
      "eval_loss": 0.11492624133825302,
      "eval_runtime": 31.9748,
      "eval_samples_per_second": 5.442,
      "eval_steps_per_second": 5.442,
      "step": 750
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 0.3786638677120209,
      "learning_rate": 5.779557819828257e-05,
      "loss": 0.1003,
      "step": 1000
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.09217362850904465,
      "eval_runtime": 31.8976,
      "eval_samples_per_second": 5.455,
      "eval_steps_per_second": 5.455,
      "step": 1000
    },
    {
      "epoch": 0.5834986579530868,
      "grad_norm": 0.5179420113563538,
      "learning_rate": 3.901092783472074e-05,
      "loss": 0.0885,
      "step": 1250
    },
    {
      "epoch": 0.5834986579530868,
      "eval_loss": 0.08533080667257309,
      "eval_runtime": 31.9485,
      "eval_samples_per_second": 5.446,
      "eval_steps_per_second": 5.446,
      "step": 1250
    },
    {
      "epoch": 0.7001983895437041,
      "grad_norm": 0.33462783694267273,
      "learning_rate": 2.1778974138217168e-05,
      "loss": 0.0787,
      "step": 1500
    },
    {
      "epoch": 0.7001983895437041,
      "eval_loss": 0.08074714988470078,
      "eval_runtime": 31.9078,
      "eval_samples_per_second": 5.453,
      "eval_steps_per_second": 5.453,
      "step": 1500
    }
  ],
  "logging_steps": 250,
  "max_steps": 2142,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.485342848505856e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}