checkpoint-150/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3177966101694915,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0211864406779661,
      "grad_norm": 2.184818744659424,
      "learning_rate": 9e-05,
      "loss": 2.2934,
      "step": 10
    },
    {
      "epoch": 0.0423728813559322,
      "grad_norm": 2.2629222869873047,
      "learning_rate": 9.816326530612245e-05,
      "loss": 2.2189,
      "step": 20
    },
    {
      "epoch": 0.0635593220338983,
      "grad_norm": 2.3219990730285645,
      "learning_rate": 9.612244897959184e-05,
      "loss": 2.1761,
      "step": 30
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": 1.970227837562561,
      "learning_rate": 9.408163265306123e-05,
      "loss": 2.1154,
      "step": 40
    },
    {
      "epoch": 0.1059322033898305,
      "grad_norm": 2.4447333812713623,
      "learning_rate": 9.204081632653062e-05,
      "loss": 2.0372,
      "step": 50
    },
    {
      "epoch": 0.1271186440677966,
      "grad_norm": 1.99861741065979,
      "learning_rate": 9e-05,
      "loss": 2.0285,
      "step": 60
    },
    {
      "epoch": 0.1483050847457627,
      "grad_norm": 2.0891239643096924,
      "learning_rate": 8.79591836734694e-05,
      "loss": 2.012,
      "step": 70
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 2.4882593154907227,
      "learning_rate": 8.591836734693878e-05,
      "loss": 1.9419,
      "step": 80
    },
    {
      "epoch": 0.1906779661016949,
      "grad_norm": 2.932203769683838,
      "learning_rate": 8.387755102040816e-05,
      "loss": 1.9201,
      "step": 90
    },
    {
      "epoch": 0.211864406779661,
      "grad_norm": 2.5325565338134766,
      "learning_rate": 8.183673469387756e-05,
      "loss": 1.9257,
      "step": 100
    },
    {
      "epoch": 0.2330508474576271,
      "grad_norm": 2.3659908771514893,
      "learning_rate": 7.979591836734695e-05,
      "loss": 1.8988,
      "step": 110
    },
    {
      "epoch": 0.2542372881355932,
      "grad_norm": 2.7854678630828857,
      "learning_rate": 7.775510204081632e-05,
      "loss": 1.8925,
      "step": 120
    },
    {
      "epoch": 0.2754237288135593,
      "grad_norm": 3.742159366607666,
      "learning_rate": 7.571428571428571e-05,
      "loss": 1.8514,
      "step": 130
    },
    {
      "epoch": 0.2966101694915254,
      "grad_norm": 2.687325954437256,
      "learning_rate": 7.36734693877551e-05,
      "loss": 1.8296,
      "step": 140
    },
    {
      "epoch": 0.3177966101694915,
      "grad_norm": 2.8193745613098145,
      "learning_rate": 7.163265306122449e-05,
      "loss": 1.8542,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1386538625826816.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}