End of training

README.md

@@ -4,23 +4,16 @@ tags:
 - generated_from_trainer
 base_model: liuhaotian/llava-v1.5-13b
 model-index:
-- name: llava_13b_exact_location_name_synthetic
+- name: liuhaotian/llava-v1.5-13b_1.0
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# llava_13b_exact_location_name_synthetic
+# liuhaotian/llava-v1.5-13b_1.0
 
-This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_2.0](https://huggingface.co/liuhaotian/llava-v1.5-13b_2.0) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 0.2209
-- eval_runtime: 55.1656
-- eval_samples_per_second: 15.716
-- eval_steps_per_second: 0.508
-- epoch: 1.0
-- step: 28
+This model is a fine-tuned version of [liuhaotian/llava-v1.5-13b_1.0](https://huggingface.co/liuhaotian/llava-v1.5-13b_1.0) on an unknown dataset.
 
 ## Model description
 
@@ -50,7 +43,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 2.0
+- num_epochs: 10.0
 
 ### Framework versions
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
-    "gate_proj",
-    "up_proj",
     "q_proj",
-    "down_proj",
     "o_proj",
-    "v_proj"
+    "gate_proj",
+    "up_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5411dae2e1c74192ad746e7850b567ea81e74ac5ab615f27792ff9fe3c0e5923
+oid sha256:67294656e681be2e83da3526407b218831e97f6f3e4e74c6beeb7c4425892eef
 size 1001466944

trainer_state.json

@@ -17,49 +17,49 @@
     {
       "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 1.2004,
+      "loss": 1.2012,
       "step": 2
     },
     {
       "epoch": 0.11,
       "learning_rate": 0.0002,
-      "loss": 1.1709,
+      "loss": 1.1717,
       "step": 3
     },
     {
       "epoch": 0.14,
       "learning_rate": 0.0002,
-      "loss": 1.0756,
+      "loss": 1.0755,
       "step": 4
     },
     {
       "epoch": 0.18,
       "learning_rate": 0.0002,
-      "loss": 1.039,
+      "loss": 1.0384,
       "step": 5
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 0.9718,
+      "loss": 0.9714,
       "step": 6
     },
     {
       "epoch": 0.25,
       "learning_rate": 0.0002,
-      "loss": 0.922,
+      "loss": 0.9222,
       "step": 7
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 0.9097,
+      "loss": 0.909,
       "step": 8
     },
     {
       "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 0.8924,
+      "loss": 0.8922,
       "step": 9
     },
     {
@@ -71,303 +71,303 @@
     {
       "epoch": 0.39,
       "learning_rate": 0.0002,
-      "loss": 0.8296,
+      "loss": 0.8293,
       "step": 11
     },
     {
       "epoch": 0.43,
       "learning_rate": 0.0002,
-      "loss": 0.7891,
+      "loss": 0.7898,
       "step": 12
     },
     {
       "epoch": 0.46,
       "learning_rate": 0.0002,
-      "loss": 0.7679,
+      "loss": 0.768,
       "step": 13
     },
     {
       "epoch": 0.5,
       "learning_rate": 0.0002,
-      "loss": 0.723,
+      "loss": 0.7237,
       "step": 14
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 0.7228,
+      "loss": 0.7225,
       "step": 15
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 0.6779,
+      "loss": 0.6761,
       "step": 16
     },
     {
       "epoch": 0.61,
       "learning_rate": 0.0002,
-      "loss": 0.5896,
+      "loss": 0.5894,
       "step": 17
     },
     {
       "epoch": 0.64,
       "learning_rate": 0.0002,
-      "loss": 0.6516,
+      "loss": 0.651,
       "step": 18
     },
     {
       "epoch": 0.68,
       "learning_rate": 0.0002,
-      "loss": 0.5621,
+      "loss": 0.5618,
       "step": 19
     },
     {
       "epoch": 0.71,
       "learning_rate": 0.0002,
-      "loss": 0.6197,
+      "loss": 0.6188,
       "step": 20
     },
     {
       "epoch": 0.75,
       "learning_rate": 0.0002,
-      "loss": 0.4754,
+      "loss": 0.4751,
       "step": 21
     },
     {
       "epoch": 0.79,
       "learning_rate": 0.0002,
-      "loss": 0.4386,
+      "loss": 0.439,
       "step": 22
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 0.4126,
+      "loss": 0.4123,
       "step": 23
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 0.3274,
+      "loss": 0.3256,
       "step": 24
     },
     {
       "epoch": 0.89,
       "learning_rate": 0.0002,
-      "loss": 0.3908,
+      "loss": 0.3866,
       "step": 25
     },
     {
       "epoch": 0.93,
       "learning_rate": 0.0002,
-      "loss": 0.3058,
+      "loss": 0.3048,
       "step": 26
     },
     {
       "epoch": 0.96,
       "learning_rate": 0.0002,
-      "loss": 0.3605,
+      "loss": 0.361,
       "step": 27
     },
     {
       "epoch": 1.0,
       "learning_rate": 0.0002,
-      "loss": 0.2814,
+      "loss": 0.2796,
       "step": 28
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.22194796800613403,
-      "eval_runtime": 56.9155,
-      "eval_samples_per_second": 15.233,
-      "eval_steps_per_second": 0.492,
+      "eval_loss": 0.22090579569339752,
+      "eval_runtime": 55.1656,
+      "eval_samples_per_second": 15.716,
+      "eval_steps_per_second": 0.508,
       "step": 28
     },
     {
       "epoch": 1.04,
       "learning_rate": 0.0002,
-      "loss": 0.2038,
+      "loss": 0.202,
       "step": 29
     },
     {
       "epoch": 1.07,
       "learning_rate": 0.0002,
-      "loss": 0.2133,
+      "loss": 0.2117,
       "step": 30
     },
     {
       "epoch": 1.11,
       "learning_rate": 0.0002,
-      "loss": 0.1911,
+      "loss": 0.1917,
       "step": 31
     },
     {
       "epoch": 1.14,
       "learning_rate": 0.0002,
-      "loss": 0.1707,
+      "loss": 0.1686,
       "step": 32
     },
     {
       "epoch": 1.18,
       "learning_rate": 0.0002,
-      "loss": 0.1928,
+      "loss": 0.1938,
       "step": 33
     },
     {
       "epoch": 1.21,
       "learning_rate": 0.0002,
-      "loss": 0.1678,
+      "loss": 0.1667,
       "step": 34
     },
     {
       "epoch": 1.25,
       "learning_rate": 0.0002,
-      "loss": 0.2044,
+      "loss": 0.2046,
       "step": 35
     },
     {
       "epoch": 1.29,
       "learning_rate": 0.0002,
-      "loss": 0.1367,
+      "loss": 0.1348,
       "step": 36
     },
     {
       "epoch": 1.32,
       "learning_rate": 0.0002,
-      "loss": 0.1395,
+      "loss": 0.1376,
       "step": 37
     },
     {
       "epoch": 1.36,
       "learning_rate": 0.0002,
-      "loss": 0.0845,
+      "loss": 0.0836,
       "step": 38
     },
     {
       "epoch": 1.39,
       "learning_rate": 0.0002,
-      "loss": 0.093,
+      "loss": 0.0931,
       "step": 39
     },
     {
       "epoch": 1.43,
       "learning_rate": 0.0002,
-      "loss": 0.1559,
+      "loss": 0.1543,
       "step": 40
     },
     {
       "epoch": 1.46,
       "learning_rate": 0.0002,
-      "loss": 0.1009,
+      "loss": 0.0985,
       "step": 41
     },
     {
       "epoch": 1.5,
       "learning_rate": 0.0002,
-      "loss": 0.0909,
+      "loss": 0.0891,
       "step": 42
     },
     {
       "epoch": 1.54,
       "learning_rate": 0.0002,
-      "loss": 0.1177,
+      "loss": 0.1181,
       "step": 43
     },
     {
       "epoch": 1.57,
       "learning_rate": 0.0002,
-      "loss": 0.1206,
+      "loss": 0.1194,
       "step": 44
     },
     {
       "epoch": 1.61,
       "learning_rate": 0.0002,
-      "loss": 0.062,
+      "loss": 0.0609,
       "step": 45
     },
     {
       "epoch": 1.64,
       "learning_rate": 0.0002,
-      "loss": 0.0648,
+      "loss": 0.0644,
       "step": 46
     },
     {
       "epoch": 1.68,
       "learning_rate": 0.0002,
-      "loss": 0.0793,
+      "loss": 0.0791,
       "step": 47
     },
     {
       "epoch": 1.71,
       "learning_rate": 0.0002,
-      "loss": 0.1064,
+      "loss": 0.1023,
       "step": 48
     },
     {
       "epoch": 1.75,
       "learning_rate": 0.0002,
-      "loss": 0.0924,
+      "loss": 0.0922,
       "step": 49
     },
     {
       "epoch": 1.79,
       "learning_rate": 0.0002,
-      "loss": 0.0518,
+      "loss": 0.0534,
       "step": 50
     },
     {
       "epoch": 1.82,
       "learning_rate": 0.0002,
-      "loss": 0.1159,
+      "loss": 0.1168,
       "step": 51
     },
     {
       "epoch": 1.86,
       "learning_rate": 0.0002,
-      "loss": 0.0479,
+      "loss": 0.0473,
       "step": 52
     },
     {
       "epoch": 1.89,
       "learning_rate": 0.0002,
-      "loss": 0.1041,
+      "loss": 0.1019,
       "step": 53
     },
     {
       "epoch": 1.93,
       "learning_rate": 0.0002,
-      "loss": 0.1483,
+      "loss": 0.1488,
       "step": 54
     },
     {
       "epoch": 1.96,
       "learning_rate": 0.0002,
-      "loss": 0.0986,
+      "loss": 0.1002,
       "step": 55
     },
     {
       "epoch": 2.0,
       "learning_rate": 0.0002,
-      "loss": 0.0352,
+      "loss": 0.0347,
       "step": 56
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.03910892829298973,
-      "eval_runtime": 56.8268,
-      "eval_samples_per_second": 15.257,
-      "eval_steps_per_second": 0.493,
+      "eval_loss": 0.03905528038740158,
+      "eval_runtime": 55.2135,
+      "eval_samples_per_second": 15.703,
+      "eval_steps_per_second": 0.507,
       "step": 56
     },
     {
       "epoch": 2.0,
       "step": 56,
       "total_flos": 1.65447188707541e+17,
-      "train_loss": 0.42645503600527135,
-      "train_runtime": 568.7271,
-      "train_samples_per_second": 3.049,
-      "train_steps_per_second": 0.098
+      "train_loss": 0.4258737172266202,
+      "train_runtime": 620.5334,
+      "train_samples_per_second": 2.794,
+      "train_steps_per_second": 0.09
     }
   ],
   "logging_steps": 1.0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca823d71f9f1dfe99c4c12b322baa8687b341261d17a6a38a37d4ca0be5ed1d7
+oid sha256:916f5d701e6ee4989937509630b933bc38f9bbd0f859c786e9046ea2551d2f15
 size 6840