Update training logs at step 400

training_logs.jsonl

@@ -1,10 +1,18 @@
-{"step": 1, "epoch": 0.14285714285714285, "time": "2026-06-26 19:32:24", "logs": {"loss": 0.8362662196159363, "grad_norm": 8.245688438415527, "learning_rate": 0.0, "epoch": 0.14285714285714285}}
-{"step": 25, "epoch": 3.571428571428571, "time": "2026-06-26 19:32:42", "logs": {"loss": 0.6558732986450195, "grad_norm": 2.779294967651367, "learning_rate": 1.1454397434679022e-06, "epoch": 3.571428571428571}}
-{"step": 28, "epoch": 4.0, "time": "2026-06-26 19:32:44", "logs": {"eval_loss": 0.5602507591247559, "eval_accuracy": 0.9, "eval_precision": 1.0, "eval_recall": 0.875, "eval_f1": 0.9333333333333333, "eval_runtime": 0.1975, "eval_samples_per_second": 50.633, "eval_steps_per_second": 5.063, "epoch": 4.0}}
-{"step": 28, "epoch": 4.0, "time": "2026-06-26 19:32:46", "logs": {"train_runtime": 24.578, "train_samples_per_second": 16.275, "train_steps_per_second": 1.139, "total_flos": 105244422144000.0, "train_loss": 0.6499660504715783, "epoch": 4.0}}
-{"step": 28, "epoch": 4.0, "time": "2026-06-26 19:32:46", "logs": {"eval_loss": 0.5602507591247559, "eval_accuracy": 0.9, "eval_precision": 1.0, "eval_recall": 0.875, "eval_f1": 0.9333333333333333, "eval_runtime": 0.2185, "eval_samples_per_second": 45.757, "eval_steps_per_second": 4.576, "epoch": 4.0}}
-{"step": 1, "epoch": 0.14285714285714285, "time": "2026-06-26 19:43:53", "logs": {"loss": 0.8346311450004578, "grad_norm": 8.198164939880371, "learning_rate": 0.0, "epoch": 0.14285714285714285}}
-{"step": 25, "epoch": 3.571428571428571, "time": "2026-06-26 19:44:12", "logs": {"loss": 0.665327270825704, "grad_norm": 2.6778149604797363, "learning_rate": 1.1454397434679022e-06, "epoch": 3.571428571428571}}
-{"step": 28, "epoch": 4.0, "time": "2026-06-26 19:44:15", "logs": {"eval_loss": 0.5662792921066284, "eval_accuracy": 0.8, "eval_precision": 1.0, "eval_recall": 0.75, "eval_f1": 0.8571428571428571, "eval_runtime": 0.206, "eval_samples_per_second": 48.532, "eval_steps_per_second": 4.853, "epoch": 4.0}}
-{"step": 28, "epoch": 4.0, "time": "2026-06-26 19:44:18", "logs": {"train_runtime": 25.1531, "train_samples_per_second": 15.903, "train_steps_per_second": 1.113, "total_flos": 105244422144000.0, "train_loss": 0.6587884064231601, "epoch": 4.0}}
-{"step": 28, "epoch": 4.0, "time": "2026-06-26 19:44:18", "logs": {"eval_loss": 0.5662792921066284, "eval_accuracy": 0.8, "eval_precision": 1.0, "eval_recall": 0.75, "eval_f1": 0.8571428571428571, "eval_runtime": 0.2602, "eval_samples_per_second": 38.426, "eval_steps_per_second": 3.843, "epoch": 4.0}}
+{"step": 1, "epoch": 0.0008090614886731392, "time": "2026-06-26 20:13:51", "logs": {"loss": 0.748644232749939, "grad_norm": 4.001261234283447, "learning_rate": 0.0, "epoch": 0.0008090614886731392}}
+{"step": 25, "epoch": 0.020226537216828478, "time": "2026-06-26 20:14:10", "logs": {"loss": 0.7263915538787842, "grad_norm": 2.0581886768341064, "learning_rate": 9.716599190283402e-07, "epoch": 0.020226537216828478}}
+{"step": 50, "epoch": 0.040453074433656956, "time": "2026-06-26 20:14:31", "logs": {"loss": 0.7004936218261719, "grad_norm": 3.1348977088928223, "learning_rate": 1.9838056680161946e-06, "epoch": 0.040453074433656956}}
+{"step": 75, "epoch": 0.06067961165048544, "time": "2026-06-26 20:14:51", "logs": {"loss": 0.6983621978759765, "grad_norm": 7.536289215087891, "learning_rate": 2.995951417004049e-06, "epoch": 0.06067961165048544}}
+{"step": 100, "epoch": 0.08090614886731391, "time": "2026-06-26 20:15:13", "logs": {"loss": 0.6408506774902344, "grad_norm": 5.387710094451904, "learning_rate": 4.008097165991903e-06, "epoch": 0.08090614886731391}}
+{"step": 125, "epoch": 0.1011326860841424, "time": "2026-06-26 20:15:35", "logs": {"loss": 0.5292000961303711, "grad_norm": 4.4866790771484375, "learning_rate": 5.020242914979757e-06, "epoch": 0.1011326860841424}}
+{"step": 150, "epoch": 0.12135922330097088, "time": "2026-06-26 20:15:59", "logs": {"loss": 0.4315451049804688, "grad_norm": 5.9393534660339355, "learning_rate": 6.0323886639676124e-06, "epoch": 0.12135922330097088}}
+{"step": 175, "epoch": 0.14158576051779936, "time": "2026-06-26 20:16:22", "logs": {"loss": 0.3674881362915039, "grad_norm": 4.814444065093994, "learning_rate": 7.044534412955466e-06, "epoch": 0.14158576051779936}}
+{"step": 200, "epoch": 0.16181229773462782, "time": "2026-06-26 20:16:44", "logs": {"loss": 0.29549776077270506, "grad_norm": 2.463817834854126, "learning_rate": 8.056680161943322e-06, "epoch": 0.16181229773462782}}
+{"step": 225, "epoch": 0.1820388349514563, "time": "2026-06-26 20:17:07", "logs": {"loss": 0.19513965606689454, "grad_norm": 1.6270427703857422, "learning_rate": 9.068825910931175e-06, "epoch": 0.1820388349514563}}
+{"step": 250, "epoch": 0.2022653721682848, "time": "2026-06-26 20:17:30", "logs": {"loss": 0.258267822265625, "grad_norm": 15.206025123596191, "learning_rate": 1.008097165991903e-05, "epoch": 0.2022653721682848}}
+{"step": 275, "epoch": 0.22249190938511326, "time": "2026-06-26 20:17:53", "logs": {"loss": 0.3252030563354492, "grad_norm": 5.6893134117126465, "learning_rate": 1.1093117408906884e-05, "epoch": 0.22249190938511326}}
+{"step": 300, "epoch": 0.24271844660194175, "time": "2026-06-26 20:18:15", "logs": {"loss": 0.2558871841430664, "grad_norm": 15.90676498413086, "learning_rate": 1.2105263157894737e-05, "epoch": 0.24271844660194175}}
+{"step": 325, "epoch": 0.26294498381877024, "time": "2026-06-26 20:18:38", "logs": {"loss": 0.20428178787231446, "grad_norm": 1.5257281064987183, "learning_rate": 1.3117408906882592e-05, "epoch": 0.26294498381877024}}
+{"step": 350, "epoch": 0.28317152103559873, "time": "2026-06-26 20:19:01", "logs": {"loss": 0.2579817008972168, "grad_norm": 20.172571182250977, "learning_rate": 1.4129554655870446e-05, "epoch": 0.28317152103559873}}
+{"step": 375, "epoch": 0.30339805825242716, "time": "2026-06-26 20:19:24", "logs": {"loss": 0.3013817977905273, "grad_norm": 0.42674902081489563, "learning_rate": 1.5141700404858302e-05, "epoch": 0.30339805825242716}}
+{"step": 400, "epoch": 0.32362459546925565, "time": "2026-06-26 20:19:46", "logs": {"loss": 0.22500619888305665, "grad_norm": 0.6443495750427246, "learning_rate": 1.6153846153846154e-05, "epoch": 0.32362459546925565}}
+{"step": 400, "epoch": 0.32362459546925565, "time": "2026-06-26 20:20:21", "logs": {"eval_loss": 0.16199301183223724, "eval_accuracy": 0.9560384032339565, "eval_precision": 0.9539936102236422, "eval_recall": 0.9900530503978779, "eval_f1": 0.9716889033517735, "eval_runtime": 34.745, "eval_samples_per_second": 56.958, "eval_steps_per_second": 3.569, "epoch": 0.32362459546925565}}