Upload folder using huggingface_hub

README.md

@@ -18,7 +18,6 @@ base_model: Qwen/Qwen-7B
 
 
 - **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
@@ -77,7 +76,7 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
 [More Information Needed]
 
@@ -108,7 +107,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Dataset Card if possible. -->
+<!-- This should link to a Data Card if possible. -->
 
 [More Information Needed]
 

adapter_config.json

@@ -8,7 +8,7 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
@@ -17,13 +17,13 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "down_proj",
-    "q_proj",
+    "k_proj",
+    "v_proj",
     "gate_proj",
+    "q_proj",
+    "lm_head",
     "o_proj",
-    "v_proj",
-    "k_proj",
-    "lm_head"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9efca0a41b1fa0a7d2c73a7c0668d7fdd266dbc38b22073b3785ec1a03d107
+oid sha256:e03393f30be6aabf595239c99982eb0834fc0e03b87b1be304f49b2e1adac248
 size 4994175

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e7334e269ed3f118133b4e9a64cbdd8962344cc1a926a089fc1f3a3aaa49ce
+oid sha256:ca6bf3778c5a5dbfd5eb20342f741f20dfcb3e7f387f57f5e2b7141f7576e46b
 size 2506975

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb21a3129c20b585a208f88d463aa0b3f24c0c1cd36c5d747317950a557c052
+oid sha256:2ecd26e0c4b589f9cc8af39ffd4ca0913eaa05895d20110af3d5ab7e80d59877
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37b925d914a427f9d777adc61a9630c02045830538343e941aba5fd083fe36b9
+oid sha256:933395f7fd252489a558205952ea72f3d20cc20b5ccab7087d643266a68fdfff
 size 627

trainer_state.json

@@ -1,75 +1,169 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21447721179624665,
-  "eval_steps": 20,
-  "global_step": 80,
+  "epoch": 1.0621348911311737,
+  "eval_steps": 500,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.05,
+      "epoch": 0.04,
       "learning_rate": 1.9393939393939395e-05,
-      "loss": 2.0524,
+      "loss": 1.9406,
       "step": 20
     },
     {
-      "epoch": 0.05,
-      "eval_loss": 2.070744514465332,
-      "eval_runtime": 124.4779,
-      "eval_samples_per_second": 2.635,
-      "eval_steps_per_second": 1.318,
-      "step": 20
-    },
-    {
-      "epoch": 0.11,
+      "epoch": 0.08,
       "learning_rate": 1.8585858585858588e-05,
-      "loss": 2.059,
+      "loss": 1.9925,
       "step": 40
     },
     {
-      "epoch": 0.11,
-      "eval_loss": 2.068726062774658,
-      "eval_runtime": 124.4655,
-      "eval_samples_per_second": 2.635,
-      "eval_steps_per_second": 1.318,
-      "step": 40
-    },
-    {
-      "epoch": 0.16,
+      "epoch": 0.13,
       "learning_rate": 1.7777777777777777e-05,
-      "loss": 2.0337,
+      "loss": 1.9952,
       "step": 60
     },
     {
-      "epoch": 0.16,
-      "eval_loss": 2.066453218460083,
-      "eval_runtime": 124.4729,
-      "eval_samples_per_second": 2.635,
-      "eval_steps_per_second": 1.318,
-      "step": 60
-    },
-    {
-      "epoch": 0.21,
+      "epoch": 0.17,
       "learning_rate": 1.6969696969696972e-05,
-      "loss": 2.0875,
+      "loss": 1.9616,
       "step": 80
     },
     {
       "epoch": 0.21,
-      "eval_loss": 2.063451051712036,
-      "eval_runtime": 124.438,
-      "eval_samples_per_second": 2.636,
-      "eval_steps_per_second": 1.318,
-      "step": 80
+      "learning_rate": 1.616161616161616e-05,
+      "loss": 2.0246,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.5353535353535354e-05,
+      "loss": 1.9661,
+      "step": 120
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.4545454545454546e-05,
+      "loss": 1.9318,
+      "step": 140
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.3737373737373739e-05,
+      "loss": 1.9104,
+      "step": 160
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.2929292929292931e-05,
+      "loss": 1.9786,
+      "step": 180
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 1.9611,
+      "step": 200
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1313131313131314e-05,
+      "loss": 1.9473,
+      "step": 220
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.0505050505050507e-05,
+      "loss": 1.9428,
+      "step": 240
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.696969696969698e-06,
+      "loss": 1.899,
+      "step": 260
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.9273,
+      "step": 280
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.08080808080808e-06,
+      "loss": 1.9628,
+      "step": 300
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.9621,
+      "step": 320
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 6.464646464646466e-06,
+      "loss": 1.949,
+      "step": 340
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.656565656565657e-06,
+      "loss": 1.9522,
+      "step": 360
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.848484848484849e-06,
+      "loss": 1.9618,
+      "step": 380
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.04040404040404e-06,
+      "loss": 1.9464,
+      "step": 400
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.232323232323233e-06,
+      "loss": 1.9332,
+      "step": 420
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.4242424242424244e-06,
+      "loss": 1.9209,
+      "step": 440
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.6161616161616164e-06,
+      "loss": 1.9663,
+      "step": 460
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 8.080808080808082e-07,
+      "loss": 1.9469,
+      "step": 480
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0,
+      "loss": 1.947,
+      "step": 500
     }
   ],
   "logging_steps": 20,
   "max_steps": 500,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 3.037389329006592e+16,
+  "total_flos": 1.89836833062912e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3180999a8d8b01de32f6df7932aa3def96692646eef435d7c634bd0d994fee56
+oid sha256:314fddf569f46a3933ef800aa8a159837c4220c59256ba35a8c9aa88331d62c3
 size 4027