Upload folder using huggingface_hub

adapter_config.json

@@ -12,18 +12,18 @@
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 10,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
-    "o_proj",
     "v_proj",
+    "lm_head",
     "gate_proj",
+    "q_proj",
+    "k_proj",
     "up_proj",
-    "lm_head",
-    "down_proj"
+    "down_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e656ad14e1d76b0391a061c1797fbf326c79c057f1731672e11cb75b6a6e1fa6
-size 106462933
+oid sha256:76d801ea8704901b08aee34b31db2a65164205ce78bda431afb1ad2040968879
+size 85202645

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6393c7ed447f7a3f01c6918424051ce72b5a6b770778a57372124a39168a7cfe
-size 53769383
+oid sha256:1b1b062a9026cdff22918215afa1e701a5c5018c5d07cd951ec0ec341229660b
+size 43126695

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46da827e165696189c34c2493b211d8adc8abaffc57cfa6ca30d52808eb30a0e
+oid sha256:d6ed61af62f500446a510a2dd0027dc95c613e9d4678794729df15c9c15f0581
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08342e596f9ce0d2810a89135af8758741c90d0421d3905ccfac5d85179e1963
+oid sha256:490ec907d63ee4b432e03215897359bdad5d7a21cb4e01a81d706b7a66b06a7e
 size 627

trainer_state.json

@@ -1,137 +1,83 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9446693657219973,
+  "epoch": 1.9323671497584543,
   "eval_steps": 50,
-  "global_step": 700,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.07,
-      "eval_loss": 1.4132792949676514,
-      "eval_runtime": 24.6579,
-      "eval_samples_per_second": 4.056,
-      "eval_steps_per_second": 0.527,
+      "epoch": 0.24,
+      "eval_loss": 1.0984270572662354,
+      "eval_runtime": 21.1382,
+      "eval_samples_per_second": 7.664,
+      "eval_steps_per_second": 0.993,
       "step": 50
     },
     {
-      "epoch": 0.13,
-      "eval_loss": 1.3802086114883423,
-      "eval_runtime": 24.6958,
-      "eval_samples_per_second": 4.049,
-      "eval_steps_per_second": 0.526,
+      "epoch": 0.48,
+      "eval_loss": 1.0866656303405762,
+      "eval_runtime": 21.1298,
+      "eval_samples_per_second": 7.667,
+      "eval_steps_per_second": 0.994,
       "step": 100
     },
     {
-      "epoch": 0.2,
-      "eval_loss": 1.3620883226394653,
-      "eval_runtime": 24.6721,
-      "eval_samples_per_second": 4.053,
-      "eval_steps_per_second": 0.527,
+      "epoch": 0.72,
+      "eval_loss": 1.0614020824432373,
+      "eval_runtime": 21.1356,
+      "eval_samples_per_second": 7.665,
+      "eval_steps_per_second": 0.994,
       "step": 150
     },
     {
-      "epoch": 0.27,
-      "eval_loss": 1.34859037399292,
-      "eval_runtime": 24.7313,
-      "eval_samples_per_second": 4.043,
-      "eval_steps_per_second": 0.526,
+      "epoch": 0.97,
+      "eval_loss": 1.0404683351516724,
+      "eval_runtime": 21.1305,
+      "eval_samples_per_second": 7.667,
+      "eval_steps_per_second": 0.994,
       "step": 200
     },
     {
-      "epoch": 0.34,
-      "eval_loss": 1.3401516675949097,
-      "eval_runtime": 24.6981,
-      "eval_samples_per_second": 4.049,
-      "eval_steps_per_second": 0.526,
+      "epoch": 1.21,
+      "eval_loss": 1.062158465385437,
+      "eval_runtime": 21.14,
+      "eval_samples_per_second": 7.663,
+      "eval_steps_per_second": 0.993,
       "step": 250
     },
     {
-      "epoch": 0.4,
-      "eval_loss": 1.3350552320480347,
-      "eval_runtime": 24.7526,
-      "eval_samples_per_second": 4.04,
-      "eval_steps_per_second": 0.525,
+      "epoch": 1.45,
+      "eval_loss": 1.0509228706359863,
+      "eval_runtime": 21.1314,
+      "eval_samples_per_second": 7.666,
+      "eval_steps_per_second": 0.994,
       "step": 300
     },
     {
-      "epoch": 0.47,
-      "eval_loss": 1.3288078308105469,
-      "eval_runtime": 24.7114,
-      "eval_samples_per_second": 4.047,
-      "eval_steps_per_second": 0.526,
+      "epoch": 1.69,
+      "eval_loss": 1.03497314453125,
+      "eval_runtime": 21.1338,
+      "eval_samples_per_second": 7.665,
+      "eval_steps_per_second": 0.994,
       "step": 350
     },
     {
-      "epoch": 0.54,
-      "eval_loss": 1.3192832469940186,
-      "eval_runtime": 24.7246,
-      "eval_samples_per_second": 4.045,
-      "eval_steps_per_second": 0.526,
+      "epoch": 1.93,
+      "eval_loss": 1.0270304679870605,
+      "eval_runtime": 21.1332,
+      "eval_samples_per_second": 7.666,
+      "eval_steps_per_second": 0.994,
       "step": 400
-    },
-    {
-      "epoch": 0.61,
-      "eval_loss": 1.3144173622131348,
-      "eval_runtime": 24.6861,
-      "eval_samples_per_second": 4.051,
-      "eval_steps_per_second": 0.527,
-      "step": 450
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 7.224606580829757e-06,
-      "loss": 1.3853,
-      "step": 500
-    },
-    {
-      "epoch": 0.67,
-      "eval_loss": 1.3092302083969116,
-      "eval_runtime": 24.7017,
-      "eval_samples_per_second": 4.048,
-      "eval_steps_per_second": 0.526,
-      "step": 500
-    },
-    {
-      "epoch": 0.74,
-      "eval_loss": 1.303202509880066,
-      "eval_runtime": 24.6861,
-      "eval_samples_per_second": 4.051,
-      "eval_steps_per_second": 0.527,
-      "step": 550
-    },
-    {
-      "epoch": 0.81,
-      "eval_loss": 1.29935884475708,
-      "eval_runtime": 24.6791,
-      "eval_samples_per_second": 4.052,
-      "eval_steps_per_second": 0.527,
-      "step": 600
-    },
-    {
-      "epoch": 0.88,
-      "eval_loss": 1.2970906496047974,
-      "eval_runtime": 24.7065,
-      "eval_samples_per_second": 4.048,
-      "eval_steps_per_second": 0.526,
-      "step": 650
-    },
-    {
-      "epoch": 0.94,
-      "eval_loss": 1.2959811687469482,
-      "eval_runtime": 24.7115,
-      "eval_samples_per_second": 4.047,
-      "eval_steps_per_second": 0.526,
-      "step": 700
     }
   ],
   "logging_steps": 500,
-  "max_steps": 700,
-  "num_train_epochs": 1,
-  "save_steps": 50,
-  "total_flos": 4.49645833728e+16,
+  "max_steps": 2000,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 1.2821409870336e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:127d5f0e7e6f41442f9837e46f4f0568cb2b6b2eb071d6ef7a98e02aadc0d78d
+oid sha256:3a9b20d48ed28f5d1fcc2ffbef76d52e9379516adac2d305ede51ee83eb93f99
 size 4027