Training in progress, step 100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a1dc75a4969cd4402c49224cdbeb8259d9c8645a8db3aac5f2374a463b3078
+oid sha256:88adf62b811dddbfbc65ae98eba00efe66665471856295c0f658fa870638b53c
 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

@@ -9,3 +9,14 @@
 {"current_steps": 45, "total_steps": 716, "loss": 0.9076, "lr": 6.25e-05, "epoch": 0.1256544502617801, "percentage": 6.28, "elapsed_time": "0:18:43", "remaining_time": "4:39:18", "throughput": 624.36, "total_tokens": 701720}
 {"current_steps": 50, "total_steps": 716, "loss": 0.9039, "lr": 6.944444444444444e-05, "epoch": 0.13961605584642234, "percentage": 6.98, "elapsed_time": "0:20:37", "remaining_time": "4:34:45", "throughput": 630.02, "total_tokens": 779728}
 {"current_steps": 50, "total_steps": 716, "eval_loss": 0.9039102792739868, "epoch": 0.13961605584642234, "percentage": 6.98, "elapsed_time": "0:21:52", "remaining_time": "4:51:23", "throughput": 594.04, "total_tokens": 779728}
+{"current_steps": 55, "total_steps": 716, "loss": 0.8983, "lr": 7.638888888888889e-05, "epoch": 0.15357766143106458, "percentage": 7.68, "elapsed_time": "0:23:55", "remaining_time": "4:47:37", "throughput": 597.32, "total_tokens": 857728}
+{"current_steps": 60, "total_steps": 716, "loss": 0.9115, "lr": 8.333333333333334e-05, "epoch": 0.16753926701570682, "percentage": 8.38, "elapsed_time": "0:25:50", "remaining_time": "4:42:35", "throughput": 603.37, "total_tokens": 935680}
+{"current_steps": 65, "total_steps": 716, "loss": 0.9022, "lr": 9.027777777777779e-05, "epoch": 0.18150087260034903, "percentage": 9.08, "elapsed_time": "0:27:45", "remaining_time": "4:38:01", "throughput": 608.6, "total_tokens": 1013664}
+{"current_steps": 70, "total_steps": 716, "loss": 0.8981, "lr": 9.722222222222223e-05, "epoch": 0.19546247818499127, "percentage": 9.78, "elapsed_time": "0:29:40", "remaining_time": "4:33:53", "throughput": 613.04, "total_tokens": 1091656}
+{"current_steps": 75, "total_steps": 716, "loss": 0.9067, "lr": 9.999464569905628e-05, "epoch": 0.2094240837696335, "percentage": 10.47, "elapsed_time": "0:31:34", "remaining_time": "4:29:52", "throughput": 617.35, "total_tokens": 1169664}
+{"current_steps": 80, "total_steps": 716, "loss": 0.9075, "lr": 9.99619291237835e-05, "epoch": 0.22338568935427575, "percentage": 11.17, "elapsed_time": "0:33:29", "remaining_time": "4:26:17", "throughput": 620.81, "total_tokens": 1247672}
+{"current_steps": 85, "total_steps": 716, "loss": 0.8964, "lr": 9.989949002448076e-05, "epoch": 0.23734729493891799, "percentage": 11.87, "elapsed_time": "0:35:24", "remaining_time": "4:22:54", "throughput": 623.85, "total_tokens": 1325640}
+{"current_steps": 90, "total_steps": 716, "loss": 0.9128, "lr": 9.980736554638366e-05, "epoch": 0.2513089005235602, "percentage": 12.57, "elapsed_time": "0:37:18", "remaining_time": "4:19:32", "throughput": 626.98, "total_tokens": 1403688}
+{"current_steps": 95, "total_steps": 716, "loss": 0.8991, "lr": 9.968561049466214e-05, "epoch": 0.26527050610820246, "percentage": 13.27, "elapsed_time": "0:39:13", "remaining_time": "4:16:27", "throughput": 629.44, "total_tokens": 1481664}
+{"current_steps": 100, "total_steps": 716, "loss": 0.9033, "lr": 9.953429730181653e-05, "epoch": 0.2792321116928447, "percentage": 13.97, "elapsed_time": "0:41:08", "remaining_time": "4:13:23", "throughput": 631.9, "total_tokens": 1559632}
+{"current_steps": 100, "total_steps": 716, "eval_loss": 0.9009457230567932, "epoch": 0.2792321116928447, "percentage": 13.97, "elapsed_time": "0:41:55", "remaining_time": "4:18:15", "throughput": 620.01, "total_tokens": 1559632}