| { | |
| "best_metric": 0.0, | |
| "best_model_checkpoint": "videomae-base-finetuned-ElderReact-Sadness/checkpoint-77", | |
| "epoch": 4.189473684210526, | |
| "eval_steps": 500, | |
| "global_step": 380, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 8.733156204223633, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 0.8614, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 2.5065677165985107, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.4565, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 3.9178378582000732, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.6916, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 3.131615161895752, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.4775, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 2.4320406913757324, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 0.5228, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 3.9200363159179688, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.543, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 5.265003204345703, | |
| "learning_rate": 4.5321637426900585e-05, | |
| "loss": 0.4849, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.562191903591156, | |
| "eval_runtime": 1559.6394, | |
| "eval_samples_per_second": 0.51, | |
| "eval_steps_per_second": 0.064, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 7.044685363769531, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.484, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 5.2160563468933105, | |
| "learning_rate": 4.239766081871345e-05, | |
| "loss": 0.5683, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 4.619358539581299, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.4599, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 1.9805103540420532, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.4367, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 8.803659439086914, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.5594, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 2.0656039714813232, | |
| "learning_rate": 3.654970760233918e-05, | |
| "loss": 0.4642, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 3.4128127098083496, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.4347, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 1.4679104089736938, | |
| "learning_rate": 3.362573099415205e-05, | |
| "loss": 0.6142, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5103093385696411, | |
| "eval_runtime": 1584.0126, | |
| "eval_samples_per_second": 0.503, | |
| "eval_steps_per_second": 0.063, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 2.87197208404541, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.386, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 3.87532901763916, | |
| "learning_rate": 3.0701754385964913e-05, | |
| "loss": 0.4474, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 2.707888603210449, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.5089, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 2.239783525466919, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5545, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 5.229273796081543, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.5179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 5.174344062805176, | |
| "learning_rate": 2.485380116959064e-05, | |
| "loss": 0.4611, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 8.643746376037598, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.5094, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 2.9545063972473145, | |
| "learning_rate": 2.1929824561403507e-05, | |
| "loss": 0.3716, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5194397568702698, | |
| "eval_runtime": 1491.9026, | |
| "eval_samples_per_second": 0.534, | |
| "eval_steps_per_second": 0.067, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "grad_norm": 1.3416327238082886, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.3645, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "grad_norm": 3.5003273487091064, | |
| "learning_rate": 1.9005847953216373e-05, | |
| "loss": 0.4325, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 2.262181043624878, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.4698, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "grad_norm": 4.914053916931152, | |
| "learning_rate": 1.608187134502924e-05, | |
| "loss": 0.4821, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "grad_norm": 1.7723067998886108, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.5028, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 2.144120454788208, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 0.4522, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "grad_norm": 8.266680717468262, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.5747, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5140724778175354, | |
| "eval_runtime": 1509.3663, | |
| "eval_samples_per_second": 0.527, | |
| "eval_steps_per_second": 0.066, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "grad_norm": 1.3488402366638184, | |
| "learning_rate": 1.023391812865497e-05, | |
| "loss": 0.4201, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "grad_norm": 5.935779094696045, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.4379, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "grad_norm": 5.667685508728027, | |
| "learning_rate": 7.3099415204678366e-06, | |
| "loss": 0.5889, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "grad_norm": 2.8014166355133057, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.3455, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "grad_norm": 2.801328659057617, | |
| "learning_rate": 4.3859649122807014e-06, | |
| "loss": 0.4534, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "grad_norm": 1.3298965692520142, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.3722, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 1.345963716506958, | |
| "learning_rate": 1.4619883040935671e-06, | |
| "loss": 0.5017, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "grad_norm": 3.070298671722412, | |
| "learning_rate": 0.0, | |
| "loss": 0.5651, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5184840559959412, | |
| "eval_runtime": 1440.3381, | |
| "eval_samples_per_second": 0.553, | |
| "eval_steps_per_second": 0.069, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "step": 380, | |
| "total_flos": 3.783052093636215e+18, | |
| "train_loss": 0.4941942767093056, | |
| "train_runtime": 18908.6056, | |
| "train_samples_per_second": 0.161, | |
| "train_steps_per_second": 0.02 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5602521896362305, | |
| "eval_runtime": 1292.4629, | |
| "eval_samples_per_second": 0.58, | |
| "eval_steps_per_second": 0.073, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.5602522492408752, | |
| "eval_runtime": 1096.1841, | |
| "eval_samples_per_second": 0.684, | |
| "eval_steps_per_second": 0.086, | |
| "step": 380 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 380, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 3.783052093636215e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |