checkpoint-172/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9985486211901307,
  "eval_steps": 500,
  "global_step": 172,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05805515239477504,
      "grad_norm": 0.600770890712738,
      "learning_rate": 2.9999908009303982e-05,
      "loss": 2.8908,
      "step": 10
    },
    {
      "epoch": 0.11611030478955008,
      "grad_norm": 0.3810243308544159,
      "learning_rate": 2.998887064264453e-05,
      "loss": 2.6786,
      "step": 20
    },
    {
      "epoch": 0.1741654571843251,
      "grad_norm": 0.2603137493133545,
      "learning_rate": 2.9959452370912904e-05,
      "loss": 2.5845,
      "step": 30
    },
    {
      "epoch": 0.23222060957910015,
      "grad_norm": 0.2289140671491623,
      "learning_rate": 2.9911693281561532e-05,
      "loss": 2.4006,
      "step": 40
    },
    {
      "epoch": 0.29027576197387517,
      "grad_norm": 0.18332642316818237,
      "learning_rate": 2.9845658454559736e-05,
      "loss": 2.2503,
      "step": 50
    },
    {
      "epoch": 0.3483309143686502,
      "grad_norm": 0.21847300231456757,
      "learning_rate": 2.9761437873711118e-05,
      "loss": 2.0564,
      "step": 60
    },
    {
      "epoch": 0.40638606676342526,
      "grad_norm": 0.2699638307094574,
      "learning_rate": 2.9659146304035112e-05,
      "loss": 1.8541,
      "step": 70
    },
    {
      "epoch": 0.4644412191582003,
      "grad_norm": 0.17481808364391327,
      "learning_rate": 2.953892313537998e-05,
      "loss": 1.5994,
      "step": 80
    },
    {
      "epoch": 0.5224963715529753,
      "grad_norm": 0.12553584575653076,
      "learning_rate": 2.9400932192480125e-05,
      "loss": 1.4072,
      "step": 90
    },
    {
      "epoch": 0.5805515239477503,
      "grad_norm": 0.12803253531455994,
      "learning_rate": 2.9245361511716764e-05,
      "loss": 1.3509,
      "step": 100
    },
    {
      "epoch": 0.6386066763425254,
      "grad_norm": 0.0883030965924263,
      "learning_rate": 2.907242308488601e-05,
      "loss": 1.3609,
      "step": 110
    },
    {
      "epoch": 0.6966618287373004,
      "grad_norm": 0.08672440052032471,
      "learning_rate": 2.8882352570323616e-05,
      "loss": 1.3838,
      "step": 120
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.08096282929182053,
      "learning_rate": 2.8675408971779997e-05,
      "loss": 1.3488,
      "step": 130
    },
    {
      "epoch": 0.8127721335268505,
      "grad_norm": 0.08677352964878082,
      "learning_rate": 2.8451874285483073e-05,
      "loss": 1.3902,
      "step": 140
    },
    {
      "epoch": 0.8708272859216255,
      "grad_norm": 0.06741151958703995,
      "learning_rate": 2.8212053115869935e-05,
      "loss": 1.319,
      "step": 150
    },
    {
      "epoch": 0.9288824383164006,
      "grad_norm": 0.0820663794875145,
      "learning_rate": 2.7956272260510948e-05,
      "loss": 1.3725,
      "step": 160
    },
    {
      "epoch": 0.9869375907111756,
      "grad_norm": 0.06830213963985443,
      "learning_rate": 2.768488026479187e-05,
      "loss": 1.3809,
      "step": 170
    }
  ],
  "logging_steps": 10,
  "max_steps": 860,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 2.466361865023488e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}