Training in progress, step 100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec17bc88ac76153637df1b04176014909e961cdf177b910eb472c5e048439bb
+oid sha256:fd961b0e78417f1e80902a52b4b9a133d9724bddd4f50db6ac185504a1aebd52
 size 18516456

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

@@ -13,3 +13,14 @@
 {"current_steps": 45, "total_steps": 3400, "loss": 0.9265, "lr": 2.647058823529412e-05, "epoch": 0.023177955189286635, "percentage": 1.32, "elapsed_time": "0:11:07", "remaining_time": "13:49:36", "throughput": 788.43, "total_tokens": 526384}
 {"current_steps": 50, "total_steps": 3400, "loss": 0.9157, "lr": 2.9411764705882354e-05, "epoch": 0.025753283543651816, "percentage": 1.47, "elapsed_time": "0:12:15", "remaining_time": "13:41:29", "throughput": 795.0, "total_tokens": 584856}
 {"current_steps": 50, "total_steps": 3400, "eval_loss": 0.9191630482673645, "epoch": 0.025753283543651816, "percentage": 1.47, "elapsed_time": "0:12:52", "remaining_time": "14:22:23", "throughput": 757.31, "total_tokens": 584856}
+{"current_steps": 55, "total_steps": 3400, "loss": 0.9009, "lr": 3.235294117647059e-05, "epoch": 0.028328611898016998, "percentage": 1.62, "elapsed_time": "0:14:08", "remaining_time": "14:19:34", "throughput": 758.66, "total_tokens": 643344}
+{"current_steps": 60, "total_steps": 3400, "loss": 0.9063, "lr": 3.529411764705883e-05, "epoch": 0.03090394025238218, "percentage": 1.76, "elapsed_time": "0:15:15", "remaining_time": "14:09:45", "throughput": 766.24, "total_tokens": 701808}
+{"current_steps": 65, "total_steps": 3400, "loss": 0.9031, "lr": 3.8235294117647055e-05, "epoch": 0.03347926860674736, "percentage": 1.91, "elapsed_time": "0:16:23", "remaining_time": "14:01:11", "throughput": 772.9, "total_tokens": 760304}
+{"current_steps": 70, "total_steps": 3400, "loss": 0.8991, "lr": 4.11764705882353e-05, "epoch": 0.036054596961112545, "percentage": 2.06, "elapsed_time": "0:17:31", "remaining_time": "13:53:40", "throughput": 778.67, "total_tokens": 818760}
+{"current_steps": 75, "total_steps": 3400, "loss": 0.9055, "lr": 4.411764705882353e-05, "epoch": 0.03862992531547772, "percentage": 2.21, "elapsed_time": "0:18:38", "remaining_time": "13:46:47", "throughput": 783.98, "total_tokens": 877256}
+{"current_steps": 80, "total_steps": 3400, "loss": 0.9092, "lr": 4.705882352941177e-05, "epoch": 0.04120525366984291, "percentage": 2.35, "elapsed_time": "0:19:46", "remaining_time": "13:40:53", "throughput": 788.45, "total_tokens": 935752}
+{"current_steps": 85, "total_steps": 3400, "loss": 0.9069, "lr": 5e-05, "epoch": 0.043780582024208085, "percentage": 2.5, "elapsed_time": "0:20:53", "remaining_time": "13:35:01", "throughput": 792.91, "total_tokens": 994216}
+{"current_steps": 90, "total_steps": 3400, "loss": 0.8924, "lr": 5.294117647058824e-05, "epoch": 0.04635591037857327, "percentage": 2.65, "elapsed_time": "0:22:02", "remaining_time": "13:30:22", "throughput": 796.26, "total_tokens": 1052704}
+{"current_steps": 95, "total_steps": 3400, "loss": 0.9059, "lr": 5.588235294117647e-05, "epoch": 0.04893123873293845, "percentage": 2.79, "elapsed_time": "0:23:10", "remaining_time": "13:26:06", "throughput": 799.26, "total_tokens": 1111176}
+{"current_steps": 100, "total_steps": 3400, "loss": 0.901, "lr": 5.882352941176471e-05, "epoch": 0.05150656708730363, "percentage": 2.94, "elapsed_time": "0:24:20", "remaining_time": "13:23:15", "throughput": 800.88, "total_tokens": 1169664}
+{"current_steps": 100, "total_steps": 3400, "eval_loss": 0.9077914953231812, "epoch": 0.05150656708730363, "percentage": 2.94, "elapsed_time": "0:24:37", "remaining_time": "13:32:32", "throughput": 791.73, "total_tokens": 1169664}