last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0004148995021205975,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.6099944680066385e-05,
      "grad_norm": 76.13255310058594,
      "learning_rate": 2e-05,
      "loss": 6.8489,
      "step": 1
    },
    {
      "epoch": 4.6099944680066385e-05,
      "eval_loss": 1.8310697078704834,
      "eval_runtime": 2413.4248,
      "eval_samples_per_second": 1.892,
      "eval_steps_per_second": 1.892,
      "step": 1
    },
    {
      "epoch": 9.219988936013277e-05,
      "grad_norm": 65.25715637207031,
      "learning_rate": 4e-05,
      "loss": 4.1512,
      "step": 2
    },
    {
      "epoch": 0.00013829983404019914,
      "grad_norm": 38.44824981689453,
      "learning_rate": 6e-05,
      "loss": 4.524,
      "step": 3
    },
    {
      "epoch": 0.00013829983404019914,
      "eval_loss": 1.7453240156173706,
      "eval_runtime": 2385.7879,
      "eval_samples_per_second": 1.914,
      "eval_steps_per_second": 1.914,
      "step": 3
    },
    {
      "epoch": 0.00018439977872026554,
      "grad_norm": 56.332122802734375,
      "learning_rate": 8e-05,
      "loss": 8.9046,
      "step": 4
    },
    {
      "epoch": 0.0002304997234003319,
      "grad_norm": 40.86722946166992,
      "learning_rate": 0.0001,
      "loss": 4.3963,
      "step": 5
    },
    {
      "epoch": 0.0002765996680803983,
      "grad_norm": 37.40678024291992,
      "learning_rate": 0.00012,
      "loss": 3.531,
      "step": 6
    },
    {
      "epoch": 0.0002765996680803983,
      "eval_loss": 0.9802604913711548,
      "eval_runtime": 2405.8344,
      "eval_samples_per_second": 1.898,
      "eval_steps_per_second": 1.898,
      "step": 6
    },
    {
      "epoch": 0.0003226996127604647,
      "grad_norm": 68.54777526855469,
      "learning_rate": 0.00014,
      "loss": 3.5579,
      "step": 7
    },
    {
      "epoch": 0.0003687995574405311,
      "grad_norm": 37.80275344848633,
      "learning_rate": 0.00016,
      "loss": 6.1531,
      "step": 8
    },
    {
      "epoch": 0.0004148995021205975,
      "grad_norm": 25.41352081298828,
      "learning_rate": 0.00018,
      "loss": 2.361,
      "step": 9
    },
    {
      "epoch": 0.0004148995021205975,
      "eval_loss": 0.9192412495613098,
      "eval_runtime": 2377.3456,
      "eval_samples_per_second": 1.921,
      "eval_steps_per_second": 1.921,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5133769962946560.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}