last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0029996250468691415,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00029996250468691414,
      "grad_norm": 0.5346159338951111,
      "learning_rate": 2e-05,
      "loss": 1.3403,
      "step": 1
    },
    {
      "epoch": 0.0005999250093738283,
      "grad_norm": 0.5412738919258118,
      "learning_rate": 4e-05,
      "loss": 1.3097,
      "step": 2
    },
    {
      "epoch": 0.0008998875140607424,
      "grad_norm": 0.4987219572067261,
      "learning_rate": 6e-05,
      "loss": 1.3042,
      "step": 3
    },
    {
      "epoch": 0.0008998875140607424,
      "eval_loss": 1.3808029890060425,
      "eval_runtime": 111.1218,
      "eval_samples_per_second": 12.635,
      "eval_steps_per_second": 6.317,
      "step": 3
    },
    {
      "epoch": 0.0011998500187476566,
      "grad_norm": 0.5031708478927612,
      "learning_rate": 8e-05,
      "loss": 1.3172,
      "step": 4
    },
    {
      "epoch": 0.0014998125234345708,
      "grad_norm": 0.6353933215141296,
      "learning_rate": 0.0001,
      "loss": 1.3887,
      "step": 5
    },
    {
      "epoch": 0.0017997750281214847,
      "grad_norm": 0.5398218631744385,
      "learning_rate": 0.00012,
      "loss": 1.1691,
      "step": 6
    },
    {
      "epoch": 0.0017997750281214847,
      "eval_loss": 1.3009066581726074,
      "eval_runtime": 94.0427,
      "eval_samples_per_second": 14.929,
      "eval_steps_per_second": 7.465,
      "step": 6
    },
    {
      "epoch": 0.002099737532808399,
      "grad_norm": 0.6405991911888123,
      "learning_rate": 0.00014,
      "loss": 1.2792,
      "step": 7
    },
    {
      "epoch": 0.002399700037495313,
      "grad_norm": 0.6479175686836243,
      "learning_rate": 0.00016,
      "loss": 1.1775,
      "step": 8
    },
    {
      "epoch": 0.0026996625421822273,
      "grad_norm": 0.5565217733383179,
      "learning_rate": 0.00018,
      "loss": 1.0312,
      "step": 9
    },
    {
      "epoch": 0.0026996625421822273,
      "eval_loss": 1.0326220989227295,
      "eval_runtime": 96.9065,
      "eval_samples_per_second": 14.488,
      "eval_steps_per_second": 7.244,
      "step": 9
    },
    {
      "epoch": 0.0029996250468691415,
      "grad_norm": 0.5226589441299438,
      "learning_rate": 0.0002,
      "loss": 0.9901,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3257466271825920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}