checkpoint-108/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.917808219178082,
  "eval_steps": 9,
  "global_step": 108,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4931506849315068,
      "grad_norm": 0.10725488513708115,
      "learning_rate": 4e-05,
      "loss": 1.419,
      "step": 9
    },
    {
      "epoch": 0.4931506849315068,
      "eval_runtime": 28.5255,
      "eval_samples_per_second": 2.209,
      "eval_steps_per_second": 1.122,
      "step": 9
    },
    {
      "epoch": 0.9863013698630136,
      "grad_norm": 0.15689760446548462,
      "learning_rate": 4e-05,
      "loss": 1.344,
      "step": 18
    },
    {
      "epoch": 0.9863013698630136,
      "eval_runtime": 28.4389,
      "eval_samples_per_second": 2.215,
      "eval_steps_per_second": 1.125,
      "step": 18
    },
    {
      "epoch": 1.4794520547945205,
      "grad_norm": 0.19748298823833466,
      "learning_rate": 4e-05,
      "loss": 1.3077,
      "step": 27
    },
    {
      "epoch": 1.4794520547945205,
      "eval_runtime": 28.4449,
      "eval_samples_per_second": 2.215,
      "eval_steps_per_second": 1.125,
      "step": 27
    },
    {
      "epoch": 1.9726027397260273,
      "grad_norm": 0.2421897053718567,
      "learning_rate": 4e-05,
      "loss": 1.1656,
      "step": 36
    },
    {
      "epoch": 1.9726027397260273,
      "eval_runtime": 28.4768,
      "eval_samples_per_second": 2.212,
      "eval_steps_per_second": 1.124,
      "step": 36
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.30667445063591003,
      "learning_rate": 4e-05,
      "loss": 1.0709,
      "step": 45
    },
    {
      "epoch": 2.4657534246575343,
      "eval_runtime": 28.4429,
      "eval_samples_per_second": 2.215,
      "eval_steps_per_second": 1.125,
      "step": 45
    },
    {
      "epoch": 2.958904109589041,
      "grad_norm": 0.43574613332748413,
      "learning_rate": 4e-05,
      "loss": 0.9364,
      "step": 54
    },
    {
      "epoch": 2.958904109589041,
      "eval_runtime": 28.42,
      "eval_samples_per_second": 2.217,
      "eval_steps_per_second": 1.126,
      "step": 54
    },
    {
      "epoch": 3.452054794520548,
      "grad_norm": 0.5465545058250427,
      "learning_rate": 4e-05,
      "loss": 0.7984,
      "step": 63
    },
    {
      "epoch": 3.452054794520548,
      "eval_runtime": 28.395,
      "eval_samples_per_second": 2.219,
      "eval_steps_per_second": 1.127,
      "step": 63
    },
    {
      "epoch": 3.9452054794520546,
      "grad_norm": 0.3935684561729431,
      "learning_rate": 4e-05,
      "loss": 0.6656,
      "step": 72
    },
    {
      "epoch": 3.9452054794520546,
      "eval_runtime": 28.3262,
      "eval_samples_per_second": 2.224,
      "eval_steps_per_second": 1.13,
      "step": 72
    },
    {
      "epoch": 4.438356164383562,
      "grad_norm": 0.2613831162452698,
      "learning_rate": 4e-05,
      "loss": 0.6008,
      "step": 81
    },
    {
      "epoch": 4.438356164383562,
      "eval_runtime": 28.3252,
      "eval_samples_per_second": 2.224,
      "eval_steps_per_second": 1.13,
      "step": 81
    },
    {
      "epoch": 4.931506849315069,
      "grad_norm": 0.3327048718929291,
      "learning_rate": 4e-05,
      "loss": 0.5703,
      "step": 90
    },
    {
      "epoch": 4.931506849315069,
      "eval_runtime": 28.3611,
      "eval_samples_per_second": 2.221,
      "eval_steps_per_second": 1.128,
      "step": 90
    },
    {
      "epoch": 5.424657534246576,
      "grad_norm": 0.26965251564979553,
      "learning_rate": 4e-05,
      "loss": 0.5243,
      "step": 99
    },
    {
      "epoch": 5.424657534246576,
      "eval_runtime": 28.3252,
      "eval_samples_per_second": 2.224,
      "eval_steps_per_second": 1.13,
      "step": 99
    },
    {
      "epoch": 5.917808219178082,
      "grad_norm": 0.2745685577392578,
      "learning_rate": 4e-05,
      "loss": 0.5232,
      "step": 108
    },
    {
      "epoch": 5.917808219178082,
      "eval_runtime": 28.3761,
      "eval_samples_per_second": 2.22,
      "eval_steps_per_second": 1.128,
      "step": 108
    }
  ],
  "logging_steps": 9,
  "max_steps": 108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 8.763528609792e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}