summarizer/tmp_multilingual_results/checkpoint-1500/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.639344262295082,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0546448087431694,
      "grad_norm": 2.1467645168304443,
      "learning_rate": 0.0004973224043715847,
      "loss": 5.4078,
      "step": 50
    },
    {
      "epoch": 0.1092896174863388,
      "grad_norm": 0.8721267580986023,
      "learning_rate": 0.0004945901639344262,
      "loss": 1.2654,
      "step": 100
    },
    {
      "epoch": 0.16393442622950818,
      "grad_norm": 0.8103071451187134,
      "learning_rate": 0.0004918579234972678,
      "loss": 1.0538,
      "step": 150
    },
    {
      "epoch": 0.2185792349726776,
      "grad_norm": 1.3929318189620972,
      "learning_rate": 0.0004891256830601093,
      "loss": 1.0236,
      "step": 200
    },
    {
      "epoch": 0.273224043715847,
      "grad_norm": 0.970960259437561,
      "learning_rate": 0.00048639344262295083,
      "loss": 1.075,
      "step": 250
    },
    {
      "epoch": 0.32786885245901637,
      "grad_norm": 0.9727946519851685,
      "learning_rate": 0.00048366120218579234,
      "loss": 1.0434,
      "step": 300
    },
    {
      "epoch": 0.3825136612021858,
      "grad_norm": 0.6411604285240173,
      "learning_rate": 0.0004809289617486339,
      "loss": 0.9285,
      "step": 350
    },
    {
      "epoch": 0.4371584699453552,
      "grad_norm": 0.8864787817001343,
      "learning_rate": 0.0004781967213114754,
      "loss": 0.9315,
      "step": 400
    },
    {
      "epoch": 0.4918032786885246,
      "grad_norm": 0.8886504173278809,
      "learning_rate": 0.0004754644808743169,
      "loss": 0.8818,
      "step": 450
    },
    {
      "epoch": 0.546448087431694,
      "grad_norm": 0.7289233803749084,
      "learning_rate": 0.0004727322404371585,
      "loss": 0.92,
      "step": 500
    },
    {
      "epoch": 0.6010928961748634,
      "grad_norm": 1.0301029682159424,
      "learning_rate": 0.00047,
      "loss": 0.8222,
      "step": 550
    },
    {
      "epoch": 0.6557377049180327,
      "grad_norm": 0.808475136756897,
      "learning_rate": 0.00046726775956284155,
      "loss": 0.8767,
      "step": 600
    },
    {
      "epoch": 0.7103825136612022,
      "grad_norm": 0.8232861161231995,
      "learning_rate": 0.0004645355191256831,
      "loss": 0.835,
      "step": 650
    },
    {
      "epoch": 0.7650273224043715,
      "grad_norm": 0.9552908539772034,
      "learning_rate": 0.0004618032786885246,
      "loss": 0.8203,
      "step": 700
    },
    {
      "epoch": 0.819672131147541,
      "grad_norm": 0.7888686656951904,
      "learning_rate": 0.00045907103825136613,
      "loss": 0.8296,
      "step": 750
    },
    {
      "epoch": 0.8743169398907104,
      "grad_norm": 0.7473599910736084,
      "learning_rate": 0.0004563387978142077,
      "loss": 0.7801,
      "step": 800
    },
    {
      "epoch": 0.9289617486338798,
      "grad_norm": 0.8543986678123474,
      "learning_rate": 0.0004536065573770492,
      "loss": 0.9248,
      "step": 850
    },
    {
      "epoch": 0.9836065573770492,
      "grad_norm": 0.7910193204879761,
      "learning_rate": 0.0004508743169398907,
      "loss": 0.8386,
      "step": 900
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6989373564720154,
      "eval_runtime": 35.1236,
      "eval_samples_per_second": 23.175,
      "eval_steps_per_second": 2.904,
      "step": 915
    },
    {
      "epoch": 1.0382513661202186,
      "grad_norm": 1.1451815366744995,
      "learning_rate": 0.00044814207650273227,
      "loss": 0.7198,
      "step": 950
    },
    {
      "epoch": 1.092896174863388,
      "grad_norm": 0.7096536755561829,
      "learning_rate": 0.0004454098360655738,
      "loss": 0.7374,
      "step": 1000
    },
    {
      "epoch": 1.1475409836065573,
      "grad_norm": 0.8436596393585205,
      "learning_rate": 0.0004426775956284153,
      "loss": 0.7471,
      "step": 1050
    },
    {
      "epoch": 1.2021857923497268,
      "grad_norm": 0.8844044208526611,
      "learning_rate": 0.00043994535519125685,
      "loss": 0.7072,
      "step": 1100
    },
    {
      "epoch": 1.2568306010928962,
      "grad_norm": 0.9547187089920044,
      "learning_rate": 0.00043721311475409836,
      "loss": 0.7618,
      "step": 1150
    },
    {
      "epoch": 1.3114754098360657,
      "grad_norm": 0.8470160961151123,
      "learning_rate": 0.00043448087431693987,
      "loss": 0.7719,
      "step": 1200
    },
    {
      "epoch": 1.366120218579235,
      "grad_norm": 0.8797179460525513,
      "learning_rate": 0.00043174863387978143,
      "loss": 0.7172,
      "step": 1250
    },
    {
      "epoch": 1.4207650273224044,
      "grad_norm": 0.6831291317939758,
      "learning_rate": 0.00042901639344262294,
      "loss": 0.7254,
      "step": 1300
    },
    {
      "epoch": 1.4754098360655736,
      "grad_norm": 0.7458399534225464,
      "learning_rate": 0.00042628415300546445,
      "loss": 0.7219,
      "step": 1350
    },
    {
      "epoch": 1.530054644808743,
      "grad_norm": 0.7829724550247192,
      "learning_rate": 0.000423551912568306,
      "loss": 0.6969,
      "step": 1400
    },
    {
      "epoch": 1.5846994535519126,
      "grad_norm": 0.914277970790863,
      "learning_rate": 0.0004208196721311475,
      "loss": 0.7088,
      "step": 1450
    },
    {
      "epoch": 1.639344262295082,
      "grad_norm": 0.9189252853393555,
      "learning_rate": 0.00041808743169398913,
      "loss": 0.7574,
      "step": 1500
    }
  ],
  "logging_steps": 50,
  "max_steps": 9150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2230686056448000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}