Training in progress, epoch 1

hyperparameters.yaml

@@ -94,7 +94,7 @@ local_rank: 0
 log_level: passive
 log_level_replica: warning
 log_on_each_node: true
-logging_dir: model_runs/donut_experiment_5/runs/May14_14-13-52_ip-172-16-23-1.ec2.internal
+logging_dir: model_runs/donut_experiment_5/runs/May15_14-00-58_ip-172-16-161-151.ec2.internal
 logging_first_step: false
 logging_nan_inf_filter: true
 logging_steps: 100

metrics.jsonl

@@ -1,4 +1 @@
-{"eval_loss": 0.46984946727752686, "eval_bleu": 0.058638588671502775, "eval_precisions": [0.7707006369426752, 0.6956521739130435, 0.6582633053221288, 0.62], "eval_brevity_penalty": 0.08573659052650866, "eval_length_ratio": 0.2893120393120393, "eval_translation_length": 471, "eval_reference_length": 1628, "eval_cer": 0.7660104054123782, "eval_wer": 0.8431764116699929, "eval_runtime": 75.9302, "eval_samples_per_second": 0.751, "eval_steps_per_second": 0.751, "epoch": 1.0}
-{"eval_loss": 0.4197552800178528, "eval_bleu": 0.06425647536525644, "eval_precisions": [0.799163179916318, 0.7315914489311164, 0.6868131868131868, 0.6416938110749185], "eval_brevity_penalty": 0.0901881044262292, "eval_length_ratio": 0.2936117936117936, "eval_translation_length": 478, "eval_reference_length": 1628, "eval_cer": 0.7604681276252823, "eval_wer": 0.8312649598507473, "eval_runtime": 75.4245, "eval_samples_per_second": 0.756, "eval_steps_per_second": 0.756, "epoch": 2.0}
-{"eval_loss": 0.39413073658943176, "eval_bleu": 0.06575803552373187, "eval_precisions": [0.8075313807531381, 0.7387173396674585, 0.7060439560439561, 0.6710097719869706], "eval_brevity_penalty": 0.0901881044262292, "eval_length_ratio": 0.2936117936117936, "eval_translation_length": 478, "eval_reference_length": 1628, "eval_cer": 0.757338139839836, "eval_wer": 0.8282692162386603, "eval_runtime": 75.0128, "eval_samples_per_second": 0.76, "eval_steps_per_second": 0.76, "epoch": 3.0}
-{"eval_loss": 0.39874938130378723, "eval_bleu": 0.06613455502080588, "eval_precisions": [0.8020833333333334, 0.7375886524822695, 0.6994535519125683, 0.6601941747572816], "eval_brevity_penalty": 0.09147709493048638, "eval_length_ratio": 0.29484029484029484, "eval_translation_length": 480, "eval_reference_length": 1628, "eval_cer": 0.7576375295447421, "eval_wer": 0.8280149631962583, "eval_runtime": 75.4844, "eval_samples_per_second": 0.755, "eval_steps_per_second": 0.755, "epoch": 4.0}
+{"eval_loss": 0.5921362638473511, "eval_bleu": 0.049922089313267796, "eval_precisions": [0.7198275862068966, 0.628992628992629, 0.58, 0.5392491467576792], "eval_brevity_penalty": 0.08138041070582977, "eval_length_ratio": 0.28501228501228504, "eval_translation_length": 464, "eval_reference_length": 1628, "eval_cer": 0.7826241357571423, "eval_wer": 0.8602957071465087, "eval_runtime": 171.1871, "eval_samples_per_second": 0.333, "eval_steps_per_second": 0.333, "epoch": 1.0}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab8fa4256c424fd86719c0b81b9de55d0698e7631008b865be8de36d28954ff
+oid sha256:31d7e404dc709278547618b42bdccf00d05578a93779094d18259b6862db6f7e
 size 809103512

runs/May15_14-00-58_ip-172-16-161-151.ec2.internal/events.out.tfevents.1715781659.ip-172-16-161-151.ec2.internal.21020.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9961ccb1773518ecb9e2a23698c204c2566e7cc619c3aeb4641c2adfc467dc1
+size 10206

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f174922ef9c6f989a5cd5dc9a1f3a816e1702cefe0d1a43926ac655d966678eb
-size 5176
+oid sha256:e14f68b5c0e7285d616e63b9fc3d7bab70b3eab22f9d63cc9f22bad4d927bfe0
+size 5240