last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0007736112603416783,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.595680670463093e-05,
      "grad_norm": 18.537153244018555,
      "learning_rate": 2e-05,
      "loss": 16.756,
      "step": 1
    },
    {
      "epoch": 0.00017191361340926185,
      "grad_norm": 17.885053634643555,
      "learning_rate": 4e-05,
      "loss": 17.2255,
      "step": 2
    },
    {
      "epoch": 0.0002578704201138928,
      "grad_norm": 15.5270357131958,
      "learning_rate": 6e-05,
      "loss": 15.8191,
      "step": 3
    },
    {
      "epoch": 0.0002578704201138928,
      "eval_loss": 4.119691848754883,
      "eval_runtime": 156.4833,
      "eval_samples_per_second": 31.307,
      "eval_steps_per_second": 15.657,
      "step": 3
    },
    {
      "epoch": 0.0003438272268185237,
      "grad_norm": 19.30111312866211,
      "learning_rate": 8e-05,
      "loss": 18.3316,
      "step": 4
    },
    {
      "epoch": 0.00042978403352315463,
      "grad_norm": 16.91377067565918,
      "learning_rate": 0.0001,
      "loss": 16.5025,
      "step": 5
    },
    {
      "epoch": 0.0005157408402277856,
      "grad_norm": 19.309635162353516,
      "learning_rate": 0.00012,
      "loss": 17.6309,
      "step": 6
    },
    {
      "epoch": 0.0005157408402277856,
      "eval_loss": 3.652055025100708,
      "eval_runtime": 156.6802,
      "eval_samples_per_second": 31.268,
      "eval_steps_per_second": 15.637,
      "step": 6
    },
    {
      "epoch": 0.0006016976469324165,
      "grad_norm": 17.67934226989746,
      "learning_rate": 0.00014,
      "loss": 14.5922,
      "step": 7
    },
    {
      "epoch": 0.0006876544536370474,
      "grad_norm": 21.108476638793945,
      "learning_rate": 0.00016,
      "loss": 14.2659,
      "step": 8
    },
    {
      "epoch": 0.0007736112603416783,
      "grad_norm": 17.110633850097656,
      "learning_rate": 0.00018,
      "loss": 11.7024,
      "step": 9
    },
    {
      "epoch": 0.0007736112603416783,
      "eval_loss": 2.6825897693634033,
      "eval_runtime": 148.9963,
      "eval_samples_per_second": 32.88,
      "eval_steps_per_second": 16.443,
      "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": 268889078366208.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}