finetuned-model-16-full/checkpoint-576/trainer_state.json

{
  "best_global_step": 448,
  "best_metric": 0.10987533628940582,
  "best_model_checkpoint": "./finetuned-model-16-full\\checkpoint-448",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 576,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7889546351084813,
      "grad_norm": 0.21714453399181366,
      "learning_rate": 4.603174603174603e-05,
      "loss": 0.5977,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.1679154932498932,
      "eval_runtime": 449.444,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.556,
      "step": 64
    },
    {
      "epoch": 1.5680473372781065,
      "grad_norm": 0.13297569751739502,
      "learning_rate": 4.2063492063492065e-05,
      "loss": 0.1177,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.13711020350456238,
      "eval_runtime": 448.5722,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.557,
      "step": 128
    },
    {
      "epoch": 2.3471400394477318,
      "grad_norm": 0.11708807200193405,
      "learning_rate": 3.809523809523809e-05,
      "loss": 0.0936,
      "step": 150
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.12583088874816895,
      "eval_runtime": 449.2291,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.557,
      "step": 192
    },
    {
      "epoch": 3.126232741617357,
      "grad_norm": 0.13195854425430298,
      "learning_rate": 3.412698412698413e-05,
      "loss": 0.0876,
      "step": 200
    },
    {
      "epoch": 3.9151873767258385,
      "grad_norm": 0.1334521323442459,
      "learning_rate": 3.0158730158730158e-05,
      "loss": 0.0773,
      "step": 250
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.11675416678190231,
      "eval_runtime": 447.9794,
      "eval_samples_per_second": 0.558,
      "eval_steps_per_second": 0.558,
      "step": 256
    },
    {
      "epoch": 4.6942800788954635,
      "grad_norm": 0.1745067685842514,
      "learning_rate": 2.6190476190476192e-05,
      "loss": 0.0715,
      "step": 300
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.11324296146631241,
      "eval_runtime": 449.3754,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.556,
      "step": 320
    },
    {
      "epoch": 5.4733727810650885,
      "grad_norm": 0.14304669201374054,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.0678,
      "step": 350
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.11094386130571365,
      "eval_runtime": 448.7599,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.557,
      "step": 384
    },
    {
      "epoch": 6.252465483234714,
      "grad_norm": 0.20627053081989288,
      "learning_rate": 1.8253968253968254e-05,
      "loss": 0.0628,
      "step": 400
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.10987533628940582,
      "eval_runtime": 446.2745,
      "eval_samples_per_second": 0.56,
      "eval_steps_per_second": 0.56,
      "step": 448
    },
    {
      "epoch": 7.031558185404339,
      "grad_norm": 0.18030017614364624,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.0578,
      "step": 450
    },
    {
      "epoch": 7.82051282051282,
      "grad_norm": 0.20803600549697876,
      "learning_rate": 1.0317460317460318e-05,
      "loss": 0.0563,
      "step": 500
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.11132891476154327,
      "eval_runtime": 449.0806,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.557,
      "step": 512
    },
    {
      "epoch": 8.599605522682445,
      "grad_norm": 0.2382732778787613,
      "learning_rate": 6.349206349206349e-06,
      "loss": 0.0518,
      "step": 550
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.11033967137336731,
      "eval_runtime": 447.1892,
      "eval_samples_per_second": 0.559,
      "eval_steps_per_second": 0.559,
      "step": 576
    }
  ],
  "logging_steps": 50,
  "max_steps": 630,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.2377604877018726e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}