Training in progress, epoch 3

metrics.jsonl

@@ -1,2 +1,3 @@
 {"eval_loss": 2.091798782348633, "eval_bleu": 0.06996470821651866, "eval_precisions": [0.625, 0.5714285714285714, 0.5, 0.4], "eval_brevity_penalty": 0.1353352832366127, "eval_length_ratio": 0.3333333333333333, "eval_translation_length": 8, "eval_reference_length": 24, "eval_cer": 0.8050847457627118, "eval_wer": 0.9411764705882353, "eval_runtime": 1.2872, "eval_samples_per_second": 0.777, "eval_steps_per_second": 0.777, "epoch": 1.0}
 {"eval_loss": 1.6558915376663208, "eval_bleu": 0.06996470821651866, "eval_precisions": [0.625, 0.5714285714285714, 0.5, 0.4], "eval_brevity_penalty": 0.1353352832366127, "eval_length_ratio": 0.3333333333333333, "eval_translation_length": 8, "eval_reference_length": 24, "eval_cer": 0.8135593220338984, "eval_wer": 0.9411764705882353, "eval_runtime": 1.2813, "eval_samples_per_second": 0.78, "eval_steps_per_second": 0.78, "epoch": 2.0}
+{"eval_loss": 1.6591044664382935, "eval_bleu": 0.06996470821651866, "eval_precisions": [0.625, 0.5714285714285714, 0.5, 0.4], "eval_brevity_penalty": 0.1353352832366127, "eval_length_ratio": 0.3333333333333333, "eval_translation_length": 8, "eval_reference_length": 24, "eval_cer": 0.8050847457627118, "eval_wer": 0.9411764705882353, "eval_runtime": 1.2944, "eval_samples_per_second": 0.773, "eval_steps_per_second": 0.773, "epoch": 3.0}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6f79a077f7d4667c1a6c1fefe29842e87f4093bda0ed81e7bf9612b9f306fd
+oid sha256:fb469c24698ef3b51c262c4293e4994bc6ad03e826cd647ff0b89dc22642c311
 size 809103512

runs/May15_19-25-12_ip-172-16-161-151.ec2.internal/events.out.tfevents.1715801113.ip-172-16-161-151.ec2.internal.21020.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe4c2c4cbd436f867e51efce584e2f3d31b3c1e5500d9e0dcdf873e1778666d
-size 11489
+oid sha256:d06f9764ce35525bf94e1d2b21e46e11269e36c8a94080c17365a72559784e73
+size 12772