last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0018837318821621056,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020930354246245618,
      "grad_norm": 1.836387276649475,
      "learning_rate": 2e-05,
      "loss": 2.5806,
      "step": 1
    },
    {
      "epoch": 0.00020930354246245618,
      "eval_loss": 2.6074929237365723,
      "eval_runtime": 74.4711,
      "eval_samples_per_second": 27.017,
      "eval_steps_per_second": 13.509,
      "step": 1
    },
    {
      "epoch": 0.00041860708492491236,
      "grad_norm": 1.9787160158157349,
      "learning_rate": 4e-05,
      "loss": 2.5943,
      "step": 2
    },
    {
      "epoch": 0.0006279106273873685,
      "grad_norm": 1.9100641012191772,
      "learning_rate": 6e-05,
      "loss": 2.5517,
      "step": 3
    },
    {
      "epoch": 0.0006279106273873685,
      "eval_loss": 2.589639902114868,
      "eval_runtime": 74.382,
      "eval_samples_per_second": 27.05,
      "eval_steps_per_second": 13.525,
      "step": 3
    },
    {
      "epoch": 0.0008372141698498247,
      "grad_norm": 1.9031531810760498,
      "learning_rate": 8e-05,
      "loss": 2.6434,
      "step": 4
    },
    {
      "epoch": 0.0010465177123122808,
      "grad_norm": 1.8470455408096313,
      "learning_rate": 0.0001,
      "loss": 2.6619,
      "step": 5
    },
    {
      "epoch": 0.001255821254774737,
      "grad_norm": 1.7614034414291382,
      "learning_rate": 0.00012,
      "loss": 2.4174,
      "step": 6
    },
    {
      "epoch": 0.001255821254774737,
      "eval_loss": 2.399675130844116,
      "eval_runtime": 74.5311,
      "eval_samples_per_second": 26.995,
      "eval_steps_per_second": 13.498,
      "step": 6
    },
    {
      "epoch": 0.0014651247972371933,
      "grad_norm": 1.3945518732070923,
      "learning_rate": 0.00014,
      "loss": 2.3177,
      "step": 7
    },
    {
      "epoch": 0.0016744283396996494,
      "grad_norm": 1.2308992147445679,
      "learning_rate": 0.00016,
      "loss": 2.2551,
      "step": 8
    },
    {
      "epoch": 0.0018837318821621056,
      "grad_norm": 1.1053471565246582,
      "learning_rate": 0.00018,
      "loss": 2.4466,
      "step": 9
    },
    {
      "epoch": 0.0018837318821621056,
      "eval_loss": 2.251810312271118,
      "eval_runtime": 74.4683,
      "eval_samples_per_second": 27.018,
      "eval_steps_per_second": 13.509,
      "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": 787653295865856.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}