Upload 11 files

adapter_config.json

@@ -22,13 +22,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "down_proj",
+    "up_proj",
     "k_proj",
-    "o_proj",
-    "gate_proj",
     "v_proj",
-    "down_proj",
-    "up_proj"
+    "q_proj",
+    "o_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d25bd789cb6a991749b606e6126dc74f7b177cc51ed8921f27f9a294bb85af7
+oid sha256:4dc8aa54d7ed4f0bac4ecf79b025a2486e0aea959b10810fbb080d1d9681f26c
 size 1688269144

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e5ea8cf168db24796b4fcc1d6c4e2aac01c9d190754134ab71ac48372857fd3
+oid sha256:f106c50469490163ec8a353566a5b56f18c15b310ee0ec7ab962cd5e71b7654b
 size 3376693690

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dc60aa4f1516382130d3b0c554410962bfb86d0526269c324fa5af80178a2bf
+oid sha256:e12ea3f9366ef57150f27ea3fc624ec4159be0bd810bddd4151068ba523c2758
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a220e59f16a9e8b90ff15e2b6bb0773b2c7243b48eb780bbeab8facd90f9af
+oid sha256:e59adef78c7c9f732efc8743c19c366429ad673c8ab6ce5449196f188d915d5e
 size 1064

trainer_state.json

@@ -1,107 +1,99 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.995488721804511,
-  "eval_steps": 332,
-  "global_step": 996,
+  "epoch": 1.995967741935484,
+  "eval_steps": 495,
+  "global_step": 990,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.3,
-      "grad_norm": 0.7148292660713196,
+      "epoch": 0.2,
+      "grad_norm": 0.7123413681983948,
       "learning_rate": 0.0002,
-      "loss": 1.0358,
+      "loss": 0.9903,
       "step": 100
     },
     {
-      "epoch": 0.6,
-      "grad_norm": 0.6553963422775269,
+      "epoch": 0.4,
+      "grad_norm": 0.5445395112037659,
       "learning_rate": 0.0002,
-      "loss": 0.5404,
+      "loss": 0.5847,
       "step": 200
     },
     {
-      "epoch": 0.9,
-      "grad_norm": 0.414563924074173,
+      "epoch": 0.6,
+      "grad_norm": 0.5527735948562622,
       "learning_rate": 0.0002,
-      "loss": 0.3174,
+      "loss": 0.4054,
       "step": 300
     },
     {
-      "epoch": 1.0,
-      "eval_loss": 0.22190843522548676,
-      "eval_runtime": 246.2313,
-      "eval_samples_per_second": 9.601,
-      "eval_steps_per_second": 2.4,
-      "step": 332
-    },
-    {
-      "epoch": 1.2,
-      "grad_norm": 0.18883414566516876,
+      "epoch": 0.81,
+      "grad_norm": 0.3411148190498352,
       "learning_rate": 0.0002,
-      "loss": 0.1946,
+      "loss": 0.2877,
       "step": 400
     },
     {
-      "epoch": 1.5,
-      "grad_norm": 0.17923474311828613,
+      "epoch": 1.0,
+      "eval_loss": 0.1955450177192688,
+      "eval_runtime": 459.2044,
+      "eval_samples_per_second": 7.681,
+      "eval_steps_per_second": 1.921,
+      "step": 495
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.21418581902980804,
       "learning_rate": 0.0002,
-      "loss": 0.1477,
+      "loss": 0.215,
       "step": 500
     },
     {
-      "epoch": 1.8,
-      "grad_norm": 0.1587008535861969,
+      "epoch": 1.21,
+      "grad_norm": 0.2143397480249405,
       "learning_rate": 0.0002,
-      "loss": 0.1267,
+      "loss": 0.1507,
       "step": 600
     },
     {
-      "epoch": 2.0,
-      "eval_loss": 0.1259666383266449,
-      "eval_runtime": 259.3726,
-      "eval_samples_per_second": 9.114,
-      "eval_steps_per_second": 2.279,
-      "step": 664
-    },
-    {
-      "epoch": 2.11,
-      "grad_norm": 0.12644633650779724,
+      "epoch": 1.41,
+      "grad_norm": 0.20695798099040985,
       "learning_rate": 0.0002,
-      "loss": 0.1041,
+      "loss": 0.1356,
       "step": 700
     },
     {
-      "epoch": 2.41,
-      "grad_norm": 0.12423792481422424,
+      "epoch": 1.61,
+      "grad_norm": 0.1783648580312729,
       "learning_rate": 0.0002,
-      "loss": 0.0852,
+      "loss": 0.123,
       "step": 800
     },
     {
-      "epoch": 2.71,
-      "grad_norm": 0.12744352221488953,
+      "epoch": 1.81,
+      "grad_norm": 0.1991637796163559,
       "learning_rate": 0.0002,
-      "loss": 0.0839,
+      "loss": 0.1129,
       "step": 900
     },
     {
-      "epoch": 3.0,
-      "eval_loss": 0.11405616998672485,
-      "eval_runtime": 336.0805,
-      "eval_samples_per_second": 7.034,
-      "eval_steps_per_second": 1.759,
-      "step": 996
+      "epoch": 2.0,
+      "eval_loss": 0.11679410934448242,
+      "eval_runtime": 436.9065,
+      "eval_samples_per_second": 8.073,
+      "eval_steps_per_second": 2.019,
+      "step": 990
     }
   ],
   "logging_steps": 100,
   "max_steps": 1000,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
-  "save_steps": 332,
-  "total_flos": 1.337637124630315e+18,
+  "num_train_epochs": 3,
+  "save_steps": 495,
+  "total_flos": 1.2763485559860756e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67b85754e2cdb450cb9c03739b6f5f65f89a56fce079ae737ddc4e37f06e2a5f
-size 4920
+oid sha256:4d2b30c5bde8e8e19a714de47b14083d5036183c4b876f302bdc5b8b5d525453
+size 4984