last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012759170653907496,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004253056884635832,
      "eval_loss": 1.4981176853179932,
      "eval_runtime": 245.4718,
      "eval_samples_per_second": 4.033,
      "eval_steps_per_second": 2.017,
      "step": 1
    },
    {
      "epoch": 0.0012759170653907496,
      "grad_norm": 0.7416582107543945,
      "learning_rate": 6e-05,
      "loss": 1.2658,
      "step": 3
    },
    {
      "epoch": 0.002126528442317916,
      "eval_loss": 1.4587681293487549,
      "eval_runtime": 246.1725,
      "eval_samples_per_second": 4.022,
      "eval_steps_per_second": 2.011,
      "step": 5
    },
    {
      "epoch": 0.002551834130781499,
      "grad_norm": 1.2528460025787354,
      "learning_rate": 0.00012,
      "loss": 1.3591,
      "step": 6
    },
    {
      "epoch": 0.003827751196172249,
      "grad_norm": 0.9704458713531494,
      "learning_rate": 0.00018,
      "loss": 1.2053,
      "step": 9
    },
    {
      "epoch": 0.004253056884635832,
      "eval_loss": 1.316813349723816,
      "eval_runtime": 246.1042,
      "eval_samples_per_second": 4.023,
      "eval_steps_per_second": 2.011,
      "step": 10
    },
    {
      "epoch": 0.005103668261562998,
      "grad_norm": 0.7426415681838989,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.2402,
      "step": 12
    },
    {
      "epoch": 0.006379585326953748,
      "grad_norm": 0.6783424615859985,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.2582,
      "step": 15
    },
    {
      "epoch": 0.006379585326953748,
      "eval_loss": 1.2608532905578613,
      "eval_runtime": 246.365,
      "eval_samples_per_second": 4.018,
      "eval_steps_per_second": 2.009,
      "step": 15
    },
    {
      "epoch": 0.007655502392344498,
      "grad_norm": 0.7505762577056885,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2839,
      "step": 18
    },
    {
      "epoch": 0.008506113769271665,
      "eval_loss": 1.233765959739685,
      "eval_runtime": 246.2301,
      "eval_samples_per_second": 4.021,
      "eval_steps_per_second": 2.01,
      "step": 20
    },
    {
      "epoch": 0.008931419457735247,
      "grad_norm": 0.4921725392341614,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.1052,
      "step": 21
    },
    {
      "epoch": 0.010207336523125997,
      "grad_norm": 1.406823992729187,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.2115,
      "step": 24
    },
    {
      "epoch": 0.01063264221158958,
      "eval_loss": 1.2244946956634521,
      "eval_runtime": 246.2027,
      "eval_samples_per_second": 4.021,
      "eval_steps_per_second": 2.011,
      "step": 25
    },
    {
      "epoch": 0.011483253588516746,
      "grad_norm": 0.5751722455024719,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.1404,
      "step": 27
    },
    {
      "epoch": 0.012759170653907496,
      "grad_norm": 0.6203330159187317,
      "learning_rate": 0.0,
      "loss": 1.2552,
      "step": 30
    },
    {
      "epoch": 0.012759170653907496,
      "eval_loss": 1.2219502925872803,
      "eval_runtime": 246.3094,
      "eval_samples_per_second": 4.019,
      "eval_steps_per_second": 2.01,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3878629964447744e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}