Training in progress, step 700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a040fdacc28b9de2977636cd1c1956bffb7f97df44e5bd2640662f6a98fa674b
+oid sha256:2cc88a9133bd30e9f761aeca11737097aa2bc75e291ca7a8f1b1b21cc4ee3a5a
 size 29034840

tokenizer_config.json

@@ -137,6 +137,7 @@
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
+  "processor_class": "Qwen2VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

trainer_log.jsonl

@@ -145,3 +145,14 @@
 {"current_steps": 645, "total_steps": 3400, "loss": 0.6111, "lr": 9.475816456775313e-05, "epoch": 0.1661086788565542, "percentage": 18.97, "elapsed_time": "0:14:35", "remaining_time": "1:02:19", "throughput": 7734.51, "total_tokens": 6771256}
 {"current_steps": 650, "total_steps": 3400, "loss": 0.5959, "lr": 9.464925117963133e-05, "epoch": 0.1673963430337368, "percentage": 19.12, "elapsed_time": "0:16:07", "remaining_time": "1:08:11", "throughput": 7056.83, "total_tokens": 6824008}
 {"current_steps": 650, "total_steps": 3400, "eval_loss": 0.5542036890983582, "epoch": 0.1673963430337368, "percentage": 19.12, "elapsed_time": "0:17:15", "remaining_time": "1:13:02", "throughput": 6587.43, "total_tokens": 6824008}
+{"current_steps": 655, "total_steps": 3400, "loss": 0.5344, "lr": 9.453928183013385e-05, "epoch": 0.1686840072109194, "percentage": 19.26, "elapsed_time": "0:18:55", "remaining_time": "1:19:19", "throughput": 6053.33, "total_tokens": 6875432}
+{"current_steps": 660, "total_steps": 3400, "loss": 0.56, "lr": 9.442825912005202e-05, "epoch": 0.16997167138810199, "percentage": 19.41, "elapsed_time": "0:20:27", "remaining_time": "1:24:57", "throughput": 5642.47, "total_tokens": 6927768}
+{"current_steps": 665, "total_steps": 3400, "loss": 0.5701, "lr": 9.431618567508933e-05, "epoch": 0.17125933556528458, "percentage": 19.56, "elapsed_time": "0:21:58", "remaining_time": "1:30:24", "throughput": 5292.74, "total_tokens": 6980544}
+{"current_steps": 670, "total_steps": 3400, "loss": 0.5604, "lr": 9.420306414579925e-05, "epoch": 0.17254699974246718, "percentage": 19.71, "elapsed_time": "0:23:32", "remaining_time": "1:35:53", "throughput": 4980.28, "total_tokens": 7032584}
+{"current_steps": 675, "total_steps": 3400, "loss": 0.5763, "lr": 9.408889720752266e-05, "epoch": 0.17383466391964975, "percentage": 19.85, "elapsed_time": "0:25:03", "remaining_time": "1:41:09", "throughput": 4712.79, "total_tokens": 7085048}
+{"current_steps": 680, "total_steps": 3400, "loss": 0.5962, "lr": 9.397368756032445e-05, "epoch": 0.17512232809683234, "percentage": 20.0, "elapsed_time": "0:26:35", "remaining_time": "1:46:21", "throughput": 4474.29, "total_tokens": 7137952}
+{"current_steps": 685, "total_steps": 3400, "loss": 0.5935, "lr": 9.385743792892982e-05, "epoch": 0.17640999227401494, "percentage": 20.15, "elapsed_time": "0:28:03", "remaining_time": "1:51:13", "throughput": 4270.71, "total_tokens": 7190584}
+{"current_steps": 690, "total_steps": 3400, "loss": 0.5267, "lr": 9.374015106265968e-05, "epoch": 0.17769765645119753, "percentage": 20.29, "elapsed_time": "0:29:33", "remaining_time": "1:56:04", "throughput": 4084.88, "total_tokens": 7243440}
+{"current_steps": 695, "total_steps": 3400, "loss": 0.5351, "lr": 9.362182973536569e-05, "epoch": 0.17898532062838013, "percentage": 20.44, "elapsed_time": "0:31:00", "remaining_time": "2:00:42", "throughput": 3920.82, "total_tokens": 7295568}
+{"current_steps": 700, "total_steps": 3400, "loss": 0.5014, "lr": 9.35024767453647e-05, "epoch": 0.1802729848055627, "percentage": 20.59, "elapsed_time": "0:32:28", "remaining_time": "2:05:16", "throughput": 3770.1, "total_tokens": 7347040}
+{"current_steps": 700, "total_steps": 3400, "eval_loss": 0.5440100431442261, "epoch": 0.1802729848055627, "percentage": 20.59, "elapsed_time": "0:33:07", "remaining_time": "2:07:47", "throughput": 3695.91, "total_tokens": 7347040}