{
  "best_metric": 0.9857142857142858,
  "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset_new/checkpoint-266",
  "epoch": 7.101351351351352,
  "eval_steps": 500,
  "global_step": 296,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 7.813199043273926,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.3171,
      "step": 10
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 7.030215740203857,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.2977,
      "step": 20
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 6.99299430847168,
      "learning_rate": 2e-05,
      "loss": 2.3017,
      "step": 30
    },
    {
      "epoch": 0.12837837837837837,
      "eval_accuracy": 0.11428571428571428,
      "eval_loss": 2.2057487964630127,
      "eval_runtime": 11.4376,
      "eval_samples_per_second": 6.12,
      "eval_steps_per_second": 0.787,
      "step": 38
    },
    {
      "epoch": 1.0067567567567568,
      "grad_norm": 7.603916168212891,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 2.2659,
      "step": 40
    },
    {
      "epoch": 1.0405405405405406,
      "grad_norm": 13.8406400680542,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.1036,
      "step": 50
    },
    {
      "epoch": 1.0743243243243243,
      "grad_norm": 8.632048606872559,
      "learning_rate": 4e-05,
      "loss": 1.9679,
      "step": 60
    },
    {
      "epoch": 1.1081081081081081,
      "grad_norm": 9.114354133605957,
      "learning_rate": 3.8305084745762714e-05,
      "loss": 1.7529,
      "step": 70
    },
    {
      "epoch": 1.1283783783783783,
      "eval_accuracy": 0.45714285714285713,
      "eval_loss": 1.5769890546798706,
      "eval_runtime": 11.5101,
      "eval_samples_per_second": 6.082,
      "eval_steps_per_second": 0.782,
      "step": 76
    },
    {
      "epoch": 2.0135135135135136,
      "grad_norm": 11.52100944519043,
      "learning_rate": 3.6610169491525426e-05,
      "loss": 1.5269,
      "step": 80
    },
    {
      "epoch": 2.0472972972972974,
      "grad_norm": 13.187309265136719,
      "learning_rate": 3.491525423728814e-05,
      "loss": 1.2076,
      "step": 90
    },
    {
      "epoch": 2.081081081081081,
      "grad_norm": 12.104183197021484,
      "learning_rate": 3.322033898305085e-05,
      "loss": 0.8936,
      "step": 100
    },
    {
      "epoch": 2.114864864864865,
      "grad_norm": 7.63131856918335,
      "learning_rate": 3.152542372881356e-05,
      "loss": 0.738,
      "step": 110
    },
    {
      "epoch": 2.1283783783783785,
      "eval_accuracy": 0.7571428571428571,
      "eval_loss": 0.7968592643737793,
      "eval_runtime": 11.5474,
      "eval_samples_per_second": 6.062,
      "eval_steps_per_second": 0.779,
      "step": 114
    },
    {
      "epoch": 3.02027027027027,
      "grad_norm": 11.565006256103516,
      "learning_rate": 2.9830508474576274e-05,
      "loss": 0.6277,
      "step": 120
    },
    {
      "epoch": 3.054054054054054,
      "grad_norm": 6.540169715881348,
      "learning_rate": 2.8135593220338985e-05,
      "loss": 0.4507,
      "step": 130
    },
    {
      "epoch": 3.0878378378378377,
      "grad_norm": 9.234970092773438,
      "learning_rate": 2.6440677966101696e-05,
      "loss": 0.5129,
      "step": 140
    },
    {
      "epoch": 3.1216216216216215,
      "grad_norm": 3.018888235092163,
      "learning_rate": 2.474576271186441e-05,
      "loss": 0.4054,
      "step": 150
    },
    {
      "epoch": 3.1283783783783785,
      "eval_accuracy": 0.8142857142857143,
      "eval_loss": 0.44068485498428345,
      "eval_runtime": 10.5153,
      "eval_samples_per_second": 6.657,
      "eval_steps_per_second": 0.856,
      "step": 152
    },
    {
      "epoch": 4.027027027027027,
      "grad_norm": 4.974002361297607,
      "learning_rate": 2.3050847457627122e-05,
      "loss": 0.3597,
      "step": 160
    },
    {
      "epoch": 4.0608108108108105,
      "grad_norm": 5.819139003753662,
      "learning_rate": 2.1355932203389833e-05,
      "loss": 0.2099,
      "step": 170
    },
    {
      "epoch": 4.094594594594595,
      "grad_norm": 12.941056251525879,
      "learning_rate": 1.9661016949152545e-05,
      "loss": 0.2355,
      "step": 180
    },
    {
      "epoch": 4.128378378378378,
      "grad_norm": 0.7642601728439331,
      "learning_rate": 1.7966101694915256e-05,
      "loss": 0.1165,
      "step": 190
    },
    {
      "epoch": 4.128378378378378,
      "eval_accuracy": 0.8428571428571429,
      "eval_loss": 0.34949493408203125,
      "eval_runtime": 10.8305,
      "eval_samples_per_second": 6.463,
      "eval_steps_per_second": 0.831,
      "step": 190
    },
    {
      "epoch": 5.033783783783784,
      "grad_norm": 14.828243255615234,
      "learning_rate": 1.6271186440677967e-05,
      "loss": 0.2828,
      "step": 200
    },
    {
      "epoch": 5.0675675675675675,
      "grad_norm": 0.2960444986820221,
      "learning_rate": 1.4576271186440678e-05,
      "loss": 0.1411,
      "step": 210
    },
    {
      "epoch": 5.101351351351352,
      "grad_norm": 1.6549774408340454,
      "learning_rate": 1.288135593220339e-05,
      "loss": 0.1328,
      "step": 220
    },
    {
      "epoch": 5.128378378378378,
      "eval_accuracy": 0.9571428571428572,
      "eval_loss": 0.1443941295146942,
      "eval_runtime": 10.5693,
      "eval_samples_per_second": 6.623,
      "eval_steps_per_second": 0.852,
      "step": 228
    },
    {
      "epoch": 6.006756756756757,
      "grad_norm": 0.6144067049026489,
      "learning_rate": 1.1186440677966102e-05,
      "loss": 0.0745,
      "step": 230
    },
    {
      "epoch": 6.04054054054054,
      "grad_norm": 1.5939418077468872,
      "learning_rate": 9.491525423728815e-06,
      "loss": 0.1271,
      "step": 240
    },
    {
      "epoch": 6.074324324324325,
      "grad_norm": 1.3212276697158813,
      "learning_rate": 7.796610169491526e-06,
      "loss": 0.0804,
      "step": 250
    },
    {
      "epoch": 6.108108108108108,
      "grad_norm": 0.2621954083442688,
      "learning_rate": 6.1016949152542385e-06,
      "loss": 0.0875,
      "step": 260
    },
    {
      "epoch": 6.128378378378378,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.08640425652265549,
      "eval_runtime": 10.4854,
      "eval_samples_per_second": 6.676,
      "eval_steps_per_second": 0.858,
      "step": 266
    },
    {
      "epoch": 7.013513513513513,
      "grad_norm": 0.3000829517841339,
      "learning_rate": 4.40677966101695e-06,
      "loss": 0.0622,
      "step": 270
    },
    {
      "epoch": 7.047297297297297,
      "grad_norm": 0.2126113772392273,
      "learning_rate": 2.7118644067796613e-06,
      "loss": 0.0534,
      "step": 280
    },
    {
      "epoch": 7.081081081081081,
      "grad_norm": 0.18285629153251648,
      "learning_rate": 1.016949152542373e-06,
      "loss": 0.0347,
      "step": 290
    },
    {
      "epoch": 7.101351351351352,
      "eval_accuracy": 0.9857142857142858,
      "eval_loss": 0.0650578960776329,
      "eval_runtime": 12.2768,
      "eval_samples_per_second": 5.702,
      "eval_steps_per_second": 0.733,
      "step": 296
    },
    {
      "epoch": 7.101351351351352,
      "step": 296,
      "total_flos": 2.915999166844109e+18,
      "train_loss": 0.7899129955047691,
      "train_runtime": 959.2262,
      "train_samples_per_second": 2.469,
      "train_steps_per_second": 0.309
    },
    {
      "epoch": 7.101351351351352,
      "eval_accuracy": 0.9419354838709677,
      "eval_loss": 0.20170918107032776,
      "eval_runtime": 25.7243,
      "eval_samples_per_second": 6.025,
      "eval_steps_per_second": 0.777,
      "step": 296
    },
    {
      "epoch": 7.101351351351352,
      "eval_accuracy": 0.9419354838709677,
      "eval_loss": 0.20170918107032776,
      "eval_runtime": 26.0431,
      "eval_samples_per_second": 5.952,
      "eval_steps_per_second": 0.768,
      "step": 296
    }
  ],
  "logging_steps": 10,
  "max_steps": 296,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 2.915999166844109e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}