Training in progress, step 50

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "AdaptLLM/biomed-Qwen2-VL-2B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*patch_embed).*(?:fc2|q_proj|up_proj|v_proj|gate_proj|k_proj|qkv|down_proj|fc1|o_proj|proj).*",
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5610e17b54fbe21915de6f88fbef454251e0c97d074cc7f742ad36050f74199f
+size 29034840

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,11 @@
+{"current_steps": 5, "total_steps": 720, "loss": 2.8851, "lr": 6.944444444444445e-06, "epoch": 0.013888888888888888, "percentage": 0.69, "elapsed_time": "0:03:14", "remaining_time": "7:44:07", "throughput": 400.25, "total_tokens": 77944}
+{"current_steps": 10, "total_steps": 720, "loss": 2.8741, "lr": 1.388888888888889e-05, "epoch": 0.027777777777777776, "percentage": 1.39, "elapsed_time": "0:05:10", "remaining_time": "6:06:57", "throughput": 502.64, "total_tokens": 155872}
+{"current_steps": 15, "total_steps": 720, "loss": 2.3696, "lr": 2.0833333333333336e-05, "epoch": 0.041666666666666664, "percentage": 2.08, "elapsed_time": "0:07:06", "remaining_time": "5:34:07", "throughput": 548.35, "total_tokens": 233896}
+{"current_steps": 20, "total_steps": 720, "loss": 1.383, "lr": 2.777777777777778e-05, "epoch": 0.05555555555555555, "percentage": 2.78, "elapsed_time": "0:09:01", "remaining_time": "5:16:08", "throughput": 575.53, "total_tokens": 311912}
+{"current_steps": 25, "total_steps": 720, "loss": 0.948, "lr": 3.472222222222222e-05, "epoch": 0.06944444444444445, "percentage": 3.47, "elapsed_time": "0:10:58", "remaining_time": "5:04:55", "throughput": 592.47, "total_tokens": 389912}
+{"current_steps": 30, "total_steps": 720, "loss": 0.9201, "lr": 4.166666666666667e-05, "epoch": 0.08333333333333333, "percentage": 4.17, "elapsed_time": "0:12:53", "remaining_time": "4:56:41", "throughput": 604.48, "total_tokens": 467848}
+{"current_steps": 35, "total_steps": 720, "loss": 0.9244, "lr": 4.8611111111111115e-05, "epoch": 0.09722222222222222, "percentage": 4.86, "elapsed_time": "0:14:49", "remaining_time": "4:50:04", "throughput": 613.82, "total_tokens": 545864}
+{"current_steps": 40, "total_steps": 720, "loss": 0.9158, "lr": 5.555555555555556e-05, "epoch": 0.1111111111111111, "percentage": 5.56, "elapsed_time": "0:16:45", "remaining_time": "4:44:58", "throughput": 620.25, "total_tokens": 623832}
+{"current_steps": 45, "total_steps": 720, "loss": 0.9065, "lr": 6.25e-05, "epoch": 0.125, "percentage": 6.25, "elapsed_time": "0:18:42", "remaining_time": "4:40:31", "throughput": 625.51, "total_tokens": 701864}
+{"current_steps": 50, "total_steps": 720, "loss": 0.9013, "lr": 6.944444444444444e-05, "epoch": 0.1388888888888889, "percentage": 6.94, "elapsed_time": "0:20:38", "remaining_time": "4:36:38", "throughput": 629.57, "total_tokens": 779840}
+{"current_steps": 50, "total_steps": 720, "eval_loss": 0.9147798418998718, "epoch": 0.1388888888888889, "percentage": 6.94, "elapsed_time": "0:21:55", "remaining_time": "4:53:52", "throughput": 592.65, "total_tokens": 779840}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae1f2f88db7ed48f6bd7b609c8d1a0011f4c2a12f13011280474cb269b33af9
+size 7352