Training in progress, step 100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e12077c4de756051187fe883bbe791e075fa6dd40da0f431483dcb0a6e10bc64
+oid sha256:7dcd3cc1733beba0d2cfe024b5800ccbcc1ab26ea9926cf8c4f3b88a8198614e
 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": 3400, "loss": 1.4659, "lr": 2.647058823529412e-05, "epoch": 0.011588977594643318, "percentage": 1.32, "elapsed_time": "0:14:34", "remaining_time": "18:06:24", "throughput": 540.69, "total_tokens": 472728}
 {"current_steps": 50, "total_steps": 3400, "loss": 1.3506, "lr": 2.9411764705882354e-05, "epoch": 0.012876641771825908, "percentage": 1.47, "elapsed_time": "0:16:03", "remaining_time": "17:56:24", "throughput": 544.27, "total_tokens": 524648}
 {"current_steps": 50, "total_steps": 3400, "eval_loss": 1.1727452278137207, "epoch": 0.012876641771825908, "percentage": 1.47, "elapsed_time": "0:17:10", "remaining_time": "19:10:27", "throughput": 509.24, "total_tokens": 524648}
+{"current_steps": 55, "total_steps": 3400, "loss": 1.1455, "lr": 3.235294117647059e-05, "epoch": 0.014164305949008499, "percentage": 1.62, "elapsed_time": "0:18:46", "remaining_time": "19:01:52", "throughput": 511.73, "total_tokens": 576472}
+{"current_steps": 60, "total_steps": 3400, "loss": 0.9971, "lr": 3.529411764705883e-05, "epoch": 0.01545197012619109, "percentage": 1.76, "elapsed_time": "0:20:15", "remaining_time": "18:48:02", "throughput": 516.56, "total_tokens": 628056}
+{"current_steps": 65, "total_steps": 3400, "loss": 0.9073, "lr": 3.8235294117647055e-05, "epoch": 0.01673963430337368, "percentage": 1.91, "elapsed_time": "0:21:44", "remaining_time": "18:35:51", "throughput": 521.45, "total_tokens": 680448}
+{"current_steps": 70, "total_steps": 3400, "loss": 0.8386, "lr": 4.11764705882353e-05, "epoch": 0.018027298480556272, "percentage": 2.06, "elapsed_time": "0:23:19", "remaining_time": "18:29:19", "throughput": 524.37, "total_tokens": 733664}
+{"current_steps": 75, "total_steps": 3400, "loss": 0.7827, "lr": 4.411764705882353e-05, "epoch": 0.01931496265773886, "percentage": 2.21, "elapsed_time": "0:24:51", "remaining_time": "18:22:18", "throughput": 526.93, "total_tokens": 786096}
+{"current_steps": 80, "total_steps": 3400, "loss": 0.7814, "lr": 4.705882352941177e-05, "epoch": 0.020602626834921454, "percentage": 2.35, "elapsed_time": "0:26:25", "remaining_time": "18:16:38", "throughput": 528.66, "total_tokens": 838192}
+{"current_steps": 85, "total_steps": 3400, "loss": 0.7297, "lr": 5e-05, "epoch": 0.021890291012104043, "percentage": 2.5, "elapsed_time": "0:27:54", "remaining_time": "18:08:20", "throughput": 531.61, "total_tokens": 890112}
+{"current_steps": 90, "total_steps": 3400, "loss": 0.7894, "lr": 5.294117647058824e-05, "epoch": 0.023177955189286635, "percentage": 2.65, "elapsed_time": "0:29:24", "remaining_time": "18:01:48", "throughput": 534.58, "total_tokens": 943472}
+{"current_steps": 95, "total_steps": 3400, "loss": 0.7758, "lr": 5.588235294117647e-05, "epoch": 0.024465619366469224, "percentage": 2.79, "elapsed_time": "0:30:52", "remaining_time": "17:54:11", "throughput": 538.09, "total_tokens": 996872}
+{"current_steps": 100, "total_steps": 3400, "loss": 0.7577, "lr": 5.882352941176471e-05, "epoch": 0.025753283543651816, "percentage": 2.94, "elapsed_time": "0:32:21", "remaining_time": "17:47:53", "throughput": 540.69, "total_tokens": 1049816}
+{"current_steps": 100, "total_steps": 3400, "eval_loss": 0.7517351508140564, "epoch": 0.025753283543651816, "percentage": 2.94, "elapsed_time": "0:33:00", "remaining_time": "18:09:13", "throughput": 530.1, "total_tokens": 1049816}