last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004590080326405712,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005100089251561902,
      "grad_norm": 0.6509891748428345,
      "learning_rate": 2e-05,
      "loss": 0.9055,
      "step": 1
    },
    {
      "epoch": 0.0005100089251561902,
      "eval_loss": 0.9768646955490112,
      "eval_runtime": 31.7786,
      "eval_samples_per_second": 25.992,
      "eval_steps_per_second": 12.996,
      "step": 1
    },
    {
      "epoch": 0.0010200178503123804,
      "grad_norm": 0.6450044512748718,
      "learning_rate": 4e-05,
      "loss": 1.0606,
      "step": 2
    },
    {
      "epoch": 0.0015300267754685707,
      "grad_norm": 0.7204149961471558,
      "learning_rate": 6e-05,
      "loss": 0.8641,
      "step": 3
    },
    {
      "epoch": 0.0015300267754685707,
      "eval_loss": 0.9749890565872192,
      "eval_runtime": 31.7577,
      "eval_samples_per_second": 26.009,
      "eval_steps_per_second": 13.005,
      "step": 3
    },
    {
      "epoch": 0.002040035700624761,
      "grad_norm": 0.6249127984046936,
      "learning_rate": 8e-05,
      "loss": 0.9371,
      "step": 4
    },
    {
      "epoch": 0.0025500446257809514,
      "grad_norm": 0.546884298324585,
      "learning_rate": 0.0001,
      "loss": 0.8757,
      "step": 5
    },
    {
      "epoch": 0.0030600535509371415,
      "grad_norm": 0.7702662944793701,
      "learning_rate": 0.00012,
      "loss": 0.9703,
      "step": 6
    },
    {
      "epoch": 0.0030600535509371415,
      "eval_loss": 0.9503841996192932,
      "eval_runtime": 31.7391,
      "eval_samples_per_second": 26.025,
      "eval_steps_per_second": 13.012,
      "step": 6
    },
    {
      "epoch": 0.0035700624760933316,
      "grad_norm": 0.7128528952598572,
      "learning_rate": 0.00014,
      "loss": 0.8849,
      "step": 7
    },
    {
      "epoch": 0.004080071401249522,
      "grad_norm": 0.8522560000419617,
      "learning_rate": 0.00016,
      "loss": 1.0575,
      "step": 8
    },
    {
      "epoch": 0.004590080326405712,
      "grad_norm": 1.132338523864746,
      "learning_rate": 0.00018,
      "loss": 0.9616,
      "step": 9
    },
    {
      "epoch": 0.004590080326405712,
      "eval_loss": 0.9215655326843262,
      "eval_runtime": 31.7204,
      "eval_samples_per_second": 26.04,
      "eval_steps_per_second": 13.02,
      "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": 900175195275264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}