{
  "best_metric": 0.793597304128054,
  "best_model_checkpoint": "MCG-NJU/videomae-base-finetuned-TikHaram/checkpoint-120",
  "epoch": 9.084745762711865,
  "eval_steps": 500,
  "global_step": 295,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 5.0345001220703125,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.3726,
      "step": 10
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 6.756855487823486,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.3354,
      "step": 20
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 10.93206787109375,
      "learning_rate": 5e-05,
      "loss": 1.1179,
      "step": 30
    },
    {
      "epoch": 0.1016949152542373,
      "eval_accuracy": 0.6857624262847515,
      "eval_loss": 0.9409521222114563,
      "eval_runtime": 1237.8509,
      "eval_samples_per_second": 0.959,
      "eval_steps_per_second": 0.12,
      "step": 30
    },
    {
      "epoch": 1.0338983050847457,
      "grad_norm": 7.3327813148498535,
      "learning_rate": 4.811320754716982e-05,
      "loss": 0.8248,
      "step": 40
    },
    {
      "epoch": 1.0677966101694916,
      "grad_norm": 10.208086967468262,
      "learning_rate": 4.6226415094339625e-05,
      "loss": 0.759,
      "step": 50
    },
    {
      "epoch": 1.1016949152542372,
      "grad_norm": 2.690416097640991,
      "learning_rate": 4.433962264150944e-05,
      "loss": 0.6162,
      "step": 60
    },
    {
      "epoch": 1.1016949152542372,
      "eval_accuracy": 0.7497893850042123,
      "eval_loss": 0.6875647902488708,
      "eval_runtime": 1167.6728,
      "eval_samples_per_second": 1.017,
      "eval_steps_per_second": 0.128,
      "step": 60
    },
    {
      "epoch": 2.0338983050847457,
      "grad_norm": 8.078776359558105,
      "learning_rate": 4.245283018867925e-05,
      "loss": 0.5685,
      "step": 70
    },
    {
      "epoch": 2.0677966101694913,
      "grad_norm": 4.468865871429443,
      "learning_rate": 4.0566037735849064e-05,
      "loss": 0.4638,
      "step": 80
    },
    {
      "epoch": 2.1016949152542375,
      "grad_norm": 4.634223937988281,
      "learning_rate": 3.867924528301887e-05,
      "loss": 0.5604,
      "step": 90
    },
    {
      "epoch": 2.1016949152542375,
      "eval_accuracy": 0.7363100252737995,
      "eval_loss": 0.6748067140579224,
      "eval_runtime": 1179.8147,
      "eval_samples_per_second": 1.006,
      "eval_steps_per_second": 0.126,
      "step": 90
    },
    {
      "epoch": 3.0338983050847457,
      "grad_norm": 1.432814359664917,
      "learning_rate": 3.679245283018868e-05,
      "loss": 0.4324,
      "step": 100
    },
    {
      "epoch": 3.0677966101694913,
      "grad_norm": 8.20600700378418,
      "learning_rate": 3.490566037735849e-05,
      "loss": 0.3613,
      "step": 110
    },
    {
      "epoch": 3.1016949152542375,
      "grad_norm": 5.8781514167785645,
      "learning_rate": 3.30188679245283e-05,
      "loss": 0.3628,
      "step": 120
    },
    {
      "epoch": 3.1016949152542375,
      "eval_accuracy": 0.793597304128054,
      "eval_loss": 0.6228342056274414,
      "eval_runtime": 1039.6898,
      "eval_samples_per_second": 1.142,
      "eval_steps_per_second": 0.143,
      "step": 120
    },
    {
      "epoch": 4.033898305084746,
      "grad_norm": 5.754726886749268,
      "learning_rate": 3.113207547169811e-05,
      "loss": 0.2648,
      "step": 130
    },
    {
      "epoch": 4.067796610169491,
      "grad_norm": 4.939706325531006,
      "learning_rate": 2.9245283018867926e-05,
      "loss": 0.2436,
      "step": 140
    },
    {
      "epoch": 4.101694915254237,
      "grad_norm": 1.7757413387298584,
      "learning_rate": 2.7358490566037738e-05,
      "loss": 0.2861,
      "step": 150
    },
    {
      "epoch": 4.101694915254237,
      "eval_accuracy": 0.7422072451558551,
      "eval_loss": 0.7411791682243347,
      "eval_runtime": 1006.166,
      "eval_samples_per_second": 1.18,
      "eval_steps_per_second": 0.148,
      "step": 150
    },
    {
      "epoch": 5.033898305084746,
      "grad_norm": 9.85596752166748,
      "learning_rate": 2.547169811320755e-05,
      "loss": 0.1681,
      "step": 160
    },
    {
      "epoch": 5.067796610169491,
      "grad_norm": 5.040333271026611,
      "learning_rate": 2.358490566037736e-05,
      "loss": 0.3501,
      "step": 170
    },
    {
      "epoch": 5.101694915254237,
      "grad_norm": 7.130555629730225,
      "learning_rate": 2.1698113207547172e-05,
      "loss": 0.213,
      "step": 180
    },
    {
      "epoch": 5.101694915254237,
      "eval_accuracy": 0.7666385846672283,
      "eval_loss": 0.6355797052383423,
      "eval_runtime": 1155.5919,
      "eval_samples_per_second": 1.027,
      "eval_steps_per_second": 0.129,
      "step": 180
    },
    {
      "epoch": 6.033898305084746,
      "grad_norm": 3.2904608249664307,
      "learning_rate": 1.9811320754716984e-05,
      "loss": 0.1472,
      "step": 190
    },
    {
      "epoch": 6.067796610169491,
      "grad_norm": 2.7492494583129883,
      "learning_rate": 1.7924528301886792e-05,
      "loss": 0.1845,
      "step": 200
    },
    {
      "epoch": 6.101694915254237,
      "grad_norm": 1.3256348371505737,
      "learning_rate": 1.6037735849056604e-05,
      "loss": 0.1428,
      "step": 210
    },
    {
      "epoch": 6.101694915254237,
      "eval_accuracy": 0.7590564448188711,
      "eval_loss": 0.6791483163833618,
      "eval_runtime": 1101.1588,
      "eval_samples_per_second": 1.078,
      "eval_steps_per_second": 0.135,
      "step": 210
    },
    {
      "epoch": 7.033898305084746,
      "grad_norm": 1.3044459819793701,
      "learning_rate": 1.4150943396226415e-05,
      "loss": 0.1269,
      "step": 220
    },
    {
      "epoch": 7.067796610169491,
      "grad_norm": 1.1943762302398682,
      "learning_rate": 1.2264150943396227e-05,
      "loss": 0.057,
      "step": 230
    },
    {
      "epoch": 7.101694915254237,
      "grad_norm": 20.165433883666992,
      "learning_rate": 1.0377358490566038e-05,
      "loss": 0.1536,
      "step": 240
    },
    {
      "epoch": 7.101694915254237,
      "eval_accuracy": 0.7523167649536647,
      "eval_loss": 0.7612273097038269,
      "eval_runtime": 1207.276,
      "eval_samples_per_second": 0.983,
      "eval_steps_per_second": 0.123,
      "step": 240
    },
    {
      "epoch": 8.033898305084746,
      "grad_norm": 0.7759658694267273,
      "learning_rate": 8.49056603773585e-06,
      "loss": 0.0919,
      "step": 250
    },
    {
      "epoch": 8.067796610169491,
      "grad_norm": 0.4191964268684387,
      "learning_rate": 6.60377358490566e-06,
      "loss": 0.2008,
      "step": 260
    },
    {
      "epoch": 8.101694915254237,
      "grad_norm": 0.7120205760002136,
      "learning_rate": 4.716981132075472e-06,
      "loss": 0.1594,
      "step": 270
    },
    {
      "epoch": 8.101694915254237,
      "eval_accuracy": 0.7624262847514743,
      "eval_loss": 0.7678460478782654,
      "eval_runtime": 1195.7328,
      "eval_samples_per_second": 0.993,
      "eval_steps_per_second": 0.125,
      "step": 270
    },
    {
      "epoch": 9.033898305084746,
      "grad_norm": 3.204578161239624,
      "learning_rate": 2.830188679245283e-06,
      "loss": 0.1085,
      "step": 280
    },
    {
      "epoch": 9.067796610169491,
      "grad_norm": 2.541273355484009,
      "learning_rate": 9.433962264150943e-07,
      "loss": 0.1056,
      "step": 290
    },
    {
      "epoch": 9.084745762711865,
      "eval_accuracy": 0.7657961246840775,
      "eval_loss": 0.7785321474075317,
      "eval_runtime": 1147.1184,
      "eval_samples_per_second": 1.035,
      "eval_steps_per_second": 0.13,
      "step": 295
    },
    {
      "epoch": 9.084745762711865,
      "step": 295,
      "total_flos": 2.8959057571998597e+18,
      "train_loss": 0.4020373065592879,
      "train_runtime": 14069.0887,
      "train_samples_per_second": 0.168,
      "train_steps_per_second": 0.021
    },
    {
      "epoch": 9.084745762711865,
      "eval_accuracy": 0.6756505576208178,
      "eval_loss": 0.875449001789093,
      "eval_runtime": 932.4911,
      "eval_samples_per_second": 1.154,
      "eval_steps_per_second": 0.145,
      "step": 295
    },
    {
      "epoch": 9.084745762711865,
      "eval_accuracy": 0.6756505576208178,
      "eval_loss": 0.8754490613937378,
      "eval_runtime": 924.3,
      "eval_samples_per_second": 1.164,
      "eval_steps_per_second": 0.146,
      "step": 295
    }
  ],
  "logging_steps": 10,
  "max_steps": 295,
  "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": 2.8959057571998597e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}