{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9915254237288136,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025423728813559324,
      "grad_norm": 0.0730147390450625,
      "learning_rate": 1.25e-06,
      "loss": 0.4558,
      "step": 1
    },
    {
      "epoch": 0.1271186440677966,
      "grad_norm": 0.06534838050795798,
      "learning_rate": 6.25e-06,
      "loss": 0.4283,
      "step": 5
    },
    {
      "epoch": 0.2542372881355932,
      "grad_norm": 0.07880361896680486,
      "learning_rate": 9.979871469976197e-06,
      "loss": 0.4333,
      "step": 10
    },
    {
      "epoch": 0.3813559322033898,
      "grad_norm": 0.06167813403187308,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.3957,
      "step": 15
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 0.056345965720785644,
      "learning_rate": 9.292243968009332e-06,
      "loss": 0.3871,
      "step": 20
    },
    {
      "epoch": 0.635593220338983,
      "grad_norm": 0.05709095573219508,
      "learning_rate": 8.613974319136959e-06,
      "loss": 0.4074,
      "step": 25
    },
    {
      "epoch": 0.7627118644067796,
      "grad_norm": 0.05325720652524892,
      "learning_rate": 7.754484907260513e-06,
      "loss": 0.3923,
      "step": 30
    },
    {
      "epoch": 0.8898305084745762,
      "grad_norm": 0.06496552156375579,
      "learning_rate": 6.7568741204067145e-06,
      "loss": 0.3506,
      "step": 35
    },
    {
      "epoch": 0.9915254237288136,
      "eval_loss": 0.42708608508110046,
      "eval_runtime": 28.3391,
      "eval_samples_per_second": 19.373,
      "eval_steps_per_second": 4.87,
      "step": 39
    },
    {
      "epoch": 1.0254237288135593,
      "grad_norm": 0.11980842959729002,
      "learning_rate": 5.671166329088278e-06,
      "loss": 0.4393,
      "step": 40
    },
    {
      "epoch": 1.152542372881356,
      "grad_norm": 0.05843339680839595,
      "learning_rate": 4.551803455482833e-06,
      "loss": 0.3204,
      "step": 45
    },
    {
      "epoch": 1.2796610169491525,
      "grad_norm": 0.054919903247120906,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.3555,
      "step": 50
    },
    {
      "epoch": 1.4067796610169492,
      "grad_norm": 0.07085936292685689,
      "learning_rate": 2.43550361297047e-06,
      "loss": 0.3271,
      "step": 55
    },
    {
      "epoch": 1.5338983050847457,
      "grad_norm": 0.06803901954956897,
      "learning_rate": 1.544686755065677e-06,
      "loss": 0.3118,
      "step": 60
    },
    {
      "epoch": 1.6610169491525424,
      "grad_norm": 0.06855321202228915,
      "learning_rate": 8.271337313934869e-07,
      "loss": 0.2804,
      "step": 65
    },
    {
      "epoch": 1.788135593220339,
      "grad_norm": 0.06749004000856927,
      "learning_rate": 3.18825646801314e-07,
      "loss": 0.2871,
      "step": 70
    },
    {
      "epoch": 1.9152542372881356,
      "grad_norm": 0.06909307377658395,
      "learning_rate": 4.52511911603265e-08,
      "loss": 0.2896,
      "step": 75
    },
    {
      "epoch": 1.9915254237288136,
      "eval_loss": 0.43976882100105286,
      "eval_runtime": 28.393,
      "eval_samples_per_second": 19.336,
      "eval_steps_per_second": 4.86,
      "step": 78
    },
    {
      "epoch": 1.9915254237288136,
      "step": 78,
      "total_flos": 2.0040717157217075e+17,
      "train_loss": 0.3583613080091966,
      "train_runtime": 1046.9285,
      "train_samples_per_second": 3.603,
      "train_steps_per_second": 0.075
    }
  ],
  "logging_steps": 5,
  "max_steps": 78,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0040717157217075e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}