diogopaes10's picture
Training in progress, step 500
f182806
raw
history blame
8.82 kB
{
"best_metric": 0.9424768686294556,
"best_model_checkpoint": "diogopaes10/012-microsoft-deberta-v3-base-finetuned-yahoo-8000_2000/checkpoint-500",
"epoch": 2.0,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.9984e-05,
"loss": 2.308,
"step": 1
},
{
"epoch": 0.2,
"learning_rate": 1.9200000000000003e-05,
"loss": 2.2963,
"step": 50
},
{
"epoch": 0.2,
"eval_accuracy": 0.2015,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.807334899902344,
"eval_f1": 0.12984294240667255,
"eval_gpu_ram_allocated": 2.0898146629333496,
"eval_gpu_ram_cached": 25.845703125,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 48,
"eval_loss": 2.2150378227233887,
"eval_precision": 0.20897251377917925,
"eval_recall": 0.2015,
"eval_runtime": 2.4064,
"eval_samples_per_second": 831.127,
"eval_steps_per_second": 26.181,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.9806594848632812,
"step": 50
},
{
"epoch": 0.4,
"learning_rate": 1.8400000000000003e-05,
"loss": 1.8843,
"step": 100
},
{
"epoch": 0.4,
"eval_accuracy": 0.592,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.80740737915039,
"eval_f1": 0.5588381140615875,
"eval_gpu_ram_allocated": 2.0897889137268066,
"eval_gpu_ram_cached": 25.84765625,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 49,
"eval_loss": 1.4590158462524414,
"eval_precision": 0.6417526665901784,
"eval_recall": 0.592,
"eval_runtime": 2.4022,
"eval_samples_per_second": 832.564,
"eval_steps_per_second": 26.226,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.9979324340820312,
"step": 100
},
{
"epoch": 0.6,
"learning_rate": 1.7616000000000002e-05,
"loss": 1.3348,
"step": 150
},
{
"epoch": 0.6,
"eval_accuracy": 0.668,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.80740737915039,
"eval_f1": 0.6613366784391611,
"eval_gpu_ram_allocated": 2.089787483215332,
"eval_gpu_ram_cached": 25.85546875,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 49,
"eval_loss": 1.180911660194397,
"eval_precision": 0.6736430562605106,
"eval_recall": 0.668,
"eval_runtime": 2.3835,
"eval_samples_per_second": 839.093,
"eval_steps_per_second": 26.431,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.983623504638672,
"step": 150
},
{
"epoch": 0.8,
"learning_rate": 1.6816e-05,
"loss": 1.1501,
"step": 200
},
{
"epoch": 0.8,
"eval_accuracy": 0.695,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.807422637939453,
"eval_f1": 0.6929220794455174,
"eval_gpu_ram_allocated": 2.0897974967956543,
"eval_gpu_ram_cached": 25.85546875,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 51,
"eval_loss": 1.0483959913253784,
"eval_precision": 0.6981404124535453,
"eval_recall": 0.695,
"eval_runtime": 2.3606,
"eval_samples_per_second": 847.255,
"eval_steps_per_second": 26.689,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.9695281982421875,
"step": 200
},
{
"epoch": 1.0,
"learning_rate": 1.6016e-05,
"loss": 1.0842,
"step": 250
},
{
"epoch": 1.0,
"eval_accuracy": 0.6905,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.80750274658203,
"eval_f1": 0.6825102140466686,
"eval_gpu_ram_allocated": 2.0897974967956543,
"eval_gpu_ram_cached": 25.85546875,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 50,
"eval_loss": 1.0264948606491089,
"eval_precision": 0.6893511728014889,
"eval_recall": 0.6905,
"eval_runtime": 2.3931,
"eval_samples_per_second": 835.746,
"eval_steps_per_second": 26.326,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.975543975830078,
"step": 250
},
{
"epoch": 1.2,
"learning_rate": 1.5216000000000001e-05,
"loss": 0.8618,
"step": 300
},
{
"epoch": 1.2,
"eval_accuracy": 0.704,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.807506561279297,
"eval_f1": 0.70238565521567,
"eval_gpu_ram_allocated": 2.0897774696350098,
"eval_gpu_ram_cached": 25.85546875,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 50,
"eval_loss": 0.9903561472892761,
"eval_precision": 0.7048361105844692,
"eval_recall": 0.704,
"eval_runtime": 2.3588,
"eval_samples_per_second": 847.898,
"eval_steps_per_second": 26.709,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.97076416015625,
"step": 300
},
{
"epoch": 1.4,
"learning_rate": 1.4416e-05,
"loss": 0.9329,
"step": 350
},
{
"epoch": 1.4,
"eval_accuracy": 0.686,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.807571411132812,
"eval_f1": 0.6824952585178898,
"eval_gpu_ram_allocated": 2.089780330657959,
"eval_gpu_ram_cached": 25.85546875,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 48,
"eval_loss": 0.9927061796188354,
"eval_precision": 0.6938911551302326,
"eval_recall": 0.686,
"eval_runtime": 2.3815,
"eval_samples_per_second": 839.799,
"eval_steps_per_second": 26.454,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.9594879150390625,
"step": 350
},
{
"epoch": 1.6,
"learning_rate": 1.3616e-05,
"loss": 0.9053,
"step": 400
},
{
"epoch": 1.6,
"eval_accuracy": 0.705,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.807575225830078,
"eval_f1": 0.702067821848656,
"eval_gpu_ram_allocated": 2.089798927307129,
"eval_gpu_ram_cached": 25.85546875,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 48,
"eval_loss": 0.9795323610305786,
"eval_precision": 0.7048247100554489,
"eval_recall": 0.705,
"eval_runtime": 2.405,
"eval_samples_per_second": 831.614,
"eval_steps_per_second": 26.196,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.9837112426757812,
"step": 400
},
{
"epoch": 1.8,
"learning_rate": 1.2816000000000002e-05,
"loss": 0.9173,
"step": 450
},
{
"epoch": 1.8,
"eval_accuracy": 0.709,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.807697296142578,
"eval_f1": 0.702389340359417,
"eval_gpu_ram_allocated": 2.089791774749756,
"eval_gpu_ram_cached": 25.85546875,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 48,
"eval_loss": 0.9748538136482239,
"eval_precision": 0.7139968646595424,
"eval_recall": 0.709,
"eval_runtime": 2.4003,
"eval_samples_per_second": 833.243,
"eval_steps_per_second": 26.247,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.9850807189941406,
"step": 450
},
{
"epoch": 2.0,
"learning_rate": 1.2016000000000002e-05,
"loss": 0.9189,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.718,
"eval_disk_space_total": 78.1898422241211,
"eval_disk_space_used": 24.807697296142578,
"eval_f1": 0.7137748110894239,
"eval_gpu_ram_allocated": 2.0897889137268066,
"eval_gpu_ram_cached": 25.85546875,
"eval_gpu_ram_total": 39.56402587890625,
"eval_gpu_utilization": 48,
"eval_loss": 0.9424768686294556,
"eval_precision": 0.718404095887314,
"eval_recall": 0.718,
"eval_runtime": 2.381,
"eval_samples_per_second": 839.978,
"eval_steps_per_second": 26.459,
"eval_system_ram_total": 83.48073959350586,
"eval_system_ram_used": 3.994873046875,
"step": 500
}
],
"max_steps": 1250,
"num_train_epochs": 5,
"total_flos": 965391777104256.0,
"trial_name": null,
"trial_params": null
}