| { | |
| "best_metric": 1.5166430473327637, | |
| "best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected/checkpoint-2000", | |
| "epoch": 2.4968789013732833, | |
| "global_step": 18000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5.533980582524272e-05, | |
| "loss": 2.3123, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_exact_match": 0.3041855393390371, | |
| "eval_loss": 1.5166430473327637, | |
| "eval_rouge1": 0.5067136517111104, | |
| "eval_rouge2": 0.24081725256234615, | |
| "eval_rougeL": 0.506502054347064, | |
| "eval_runtime": 165.2083, | |
| "eval_samples_per_second": 144.327, | |
| "eval_steps_per_second": 1.507, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 9.943053223333577e-05, | |
| "loss": 1.3707, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_exact_match": 0.29290387518872674, | |
| "eval_loss": 1.5657806396484375, | |
| "eval_rouge1": 0.4950482401384949, | |
| "eval_rouge2": 0.22613374150081544, | |
| "eval_rougeL": 0.49478029159516457, | |
| "eval_runtime": 162.5745, | |
| "eval_samples_per_second": 146.665, | |
| "eval_steps_per_second": 1.532, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.651018471198073e-05, | |
| "loss": 1.2334, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_exact_match": 0.3253648716658279, | |
| "eval_loss": 1.5264997482299805, | |
| "eval_rouge1": 0.531867219960122, | |
| "eval_rouge2": 0.25865030861885435, | |
| "eval_rougeL": 0.5313541147701524, | |
| "eval_runtime": 167.7297, | |
| "eval_samples_per_second": 142.157, | |
| "eval_steps_per_second": 1.485, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 9.358983719062569e-05, | |
| "loss": 1.1394, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "eval_exact_match": 0.3172705921825197, | |
| "eval_loss": 1.6098668575286865, | |
| "eval_rouge1": 0.507425024161823, | |
| "eval_rouge2": 0.2482872472913446, | |
| "eval_rougeL": 0.5069841743495872, | |
| "eval_runtime": 166.4039, | |
| "eval_samples_per_second": 143.29, | |
| "eval_steps_per_second": 1.496, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 9.066948966927065e-05, | |
| "loss": 1.0699, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_exact_match": 0.32087736956886426, | |
| "eval_loss": 1.5405367612838745, | |
| "eval_rouge1": 0.5257435158783685, | |
| "eval_rouge2": 0.2513617731408373, | |
| "eval_rougeL": 0.5253820138123132, | |
| "eval_runtime": 166.5276, | |
| "eval_samples_per_second": 143.183, | |
| "eval_steps_per_second": 1.495, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.775060232167628e-05, | |
| "loss": 1.0402, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_exact_match": 0.310476430129173, | |
| "eval_loss": 1.6315388679504395, | |
| "eval_rouge1": 0.5041999610588694, | |
| "eval_rouge2": 0.23111610343932948, | |
| "eval_rougeL": 0.5037586055646353, | |
| "eval_runtime": 166.2206, | |
| "eval_samples_per_second": 143.448, | |
| "eval_steps_per_second": 1.498, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 8.483025480032124e-05, | |
| "loss": 1.0186, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_exact_match": 0.3139154504277806, | |
| "eval_loss": 1.6186127662658691, | |
| "eval_rouge1": 0.5068008383486242, | |
| "eval_rouge2": 0.231322858719689, | |
| "eval_rougeL": 0.5061156690587016, | |
| "eval_runtime": 165.85, | |
| "eval_samples_per_second": 143.768, | |
| "eval_steps_per_second": 1.501, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 8.191136745272688e-05, | |
| "loss": 0.9368, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "eval_exact_match": 0.318906223787955, | |
| "eval_loss": 1.6294344663619995, | |
| "eval_rouge1": 0.5072474931474986, | |
| "eval_rouge2": 0.2326535102579398, | |
| "eval_rougeL": 0.5071239367268146, | |
| "eval_runtime": 165.6048, | |
| "eval_samples_per_second": 143.981, | |
| "eval_steps_per_second": 1.504, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 7.899248010513252e-05, | |
| "loss": 0.9162, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_exact_match": 0.3142090253313202, | |
| "eval_loss": 1.6406846046447754, | |
| "eval_rouge1": 0.5094524045798439, | |
| "eval_rouge2": 0.23439332329304746, | |
| "eval_rougeL": 0.5087577538678478, | |
| "eval_runtime": 164.3561, | |
| "eval_samples_per_second": 145.075, | |
| "eval_steps_per_second": 1.515, | |
| "step": 18000 | |
| } | |
| ], | |
| "max_steps": 72090, | |
| "num_train_epochs": 10, | |
| "total_flos": 2.3384627141935104e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |