Upload folder using huggingface_hub

checkpoint-200/adapter_config.json

@@ -33,12 +33,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "gate_proj",
-    "down_proj",
+    "q_proj",
+    "k_proj",
     "v_proj",
     "o_proj",
-    "k_proj",
+    "down_proj",
     "up_proj"
   ],
   "target_parameters": null,

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4d55a4104e38eebca405dd4486abc01e5dc526138f5d6fe9f6019e710a88bb
+size 528550256

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ab6b742fdcf189ee3a2b88d7419b1f60c77156d8bb2601b4d013dd2ef41b1e
+size 1057397963

checkpoint-200/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcff221fe376a4bf36bd6906e8452d332e594495362642b4cc37da03d79a1e34
+oid sha256:b4e31671a48f9cd58f7aa0506207aac3399505fb2f97613873fa5f366e0fd1e8
 size 1465

checkpoint-200/trainer_state.json

@@ -448,25 +448,25 @@
     },
     {
       "epoch": 1.7576099210822997,
-      "eval_loss": 1.4976308345794678,
-      "eval_runtime": 39.5405,
-      "eval_samples_per_second": 4.729,
-      "eval_steps_per_second": 2.377,
+      "eval_loss": 1.4964991807937622,
+      "eval_runtime": 48.3648,
+      "eval_samples_per_second": 3.866,
+      "eval_steps_per_second": 1.944,
       "step": 195
     },
     {
       "epoch": 1.8027057497181511,
-      "grad_norm": 1.6666193914716132e-05,
-      "learning_rate": 3.259962081320084e-07,
-      "loss": 1.4061,
+      "grad_norm": 1.575948772369884e-05,
+      "learning_rate": 3.91304347826087e-06,
+      "loss": 1.4529,
       "step": 200
     },
     {
       "epoch": 1.8027057497181511,
-      "eval_loss": 1.496522307395935,
-      "eval_runtime": 40.1246,
-      "eval_samples_per_second": 4.66,
-      "eval_steps_per_second": 2.343,
+      "eval_loss": 1.486992359161377,
+      "eval_runtime": 46.1615,
+      "eval_samples_per_second": 4.051,
+      "eval_steps_per_second": 2.036,
       "step": 200
     }
   ],
@@ -487,7 +487,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.209136386506752e+16,
+  "total_flos": 6.213149044511539e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b72ba8573ed734a6285768fbde417a7804f6b0e1fd4951476235aa39cc1bc96
+oid sha256:a1c6ee9e73e6fc72e15749b15bb0baa391d3380a7113028297856ba7cbc98304
 size 5841

checkpoint-210/adapter_config.json

@@ -33,12 +33,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "gate_proj",
-    "down_proj",
+    "q_proj",
+    "k_proj",
     "v_proj",
     "o_proj",
-    "k_proj",
+    "down_proj",
     "up_proj"
   ],
   "target_parameters": null,

checkpoint-210/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecacff68af455fbb529438b0827f96309f71400443efdd0a15e0d5a3d49a787
+size 528550256

checkpoint-210/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:524dd5ac65a049fac5cbbb1edc74be19afda74e519424e1933892369df371511
+oid sha256:3a645364045044066373fd0bdbba55cb9e0190b2c1084789d7aedefe6e38f7cf
 size 1057397963

checkpoint-210/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31c77f723e2c44c365a9378e04feb56920e1780c27e61a41d1cc4f8391da730
+oid sha256:0db5f604b9634909dd24be4ffc74e09ba25916453088c45515338d684ec436f3
 size 1465

checkpoint-210/trainer_state.json

@@ -448,48 +448,48 @@
     },
     {
       "epoch": 1.7576099210822997,
-      "eval_loss": 1.4976308345794678,
-      "eval_runtime": 39.5405,
-      "eval_samples_per_second": 4.729,
-      "eval_steps_per_second": 2.377,
+      "eval_loss": 1.4964991807937622,
+      "eval_runtime": 48.3648,
+      "eval_samples_per_second": 3.866,
+      "eval_steps_per_second": 1.944,
       "step": 195
     },
     {
       "epoch": 1.8027057497181511,
-      "grad_norm": 1.6666193914716132e-05,
-      "learning_rate": 3.259962081320084e-07,
-      "loss": 1.4061,
+      "grad_norm": 1.575948772369884e-05,
+      "learning_rate": 3.91304347826087e-06,
+      "loss": 1.4529,
       "step": 200
     },
     {
       "epoch": 1.8027057497181511,
-      "eval_loss": 1.496522307395935,
-      "eval_runtime": 40.1246,
-      "eval_samples_per_second": 4.66,
-      "eval_steps_per_second": 2.343,
+      "eval_loss": 1.486992359161377,
+      "eval_runtime": 46.1615,
+      "eval_samples_per_second": 4.051,
+      "eval_steps_per_second": 2.036,
       "step": 200
     },
     {
       "epoch": 1.8478015783540023,
-      "eval_loss": 1.4957925081253052,
-      "eval_runtime": 39.648,
-      "eval_samples_per_second": 4.717,
-      "eval_steps_per_second": 2.371,
+      "eval_loss": 1.470670461654663,
+      "eval_runtime": 45.9542,
+      "eval_samples_per_second": 4.069,
+      "eval_steps_per_second": 2.046,
       "step": 205
     },
     {
       "epoch": 1.8928974069898534,
-      "grad_norm": 1.6508149201399647e-05,
-      "learning_rate": 1.049289737114273e-07,
-      "loss": 1.479,
+      "grad_norm": 1.8683402231545188e-05,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 1.4523,
       "step": 210
     },
     {
       "epoch": 1.8928974069898534,
-      "eval_loss": 1.4953874349594116,
-      "eval_runtime": 39.5468,
-      "eval_samples_per_second": 4.729,
-      "eval_steps_per_second": 2.377,
+      "eval_loss": 1.4473758935928345,
+      "eval_runtime": 46.0635,
+      "eval_samples_per_second": 4.06,
+      "eval_steps_per_second": 2.041,
       "step": 210
     }
   ],
@@ -510,7 +510,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.522028816940851e+16,
+  "total_flos": 6.519918556481126e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-210/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b72ba8573ed734a6285768fbde417a7804f6b0e1fd4951476235aa39cc1bc96
+oid sha256:a1c6ee9e73e6fc72e15749b15bb0baa391d3380a7113028297856ba7cbc98304
 size 5841