Training in progress, step 99, checkpoint

last-checkpoint/adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "Wqkv",
     "out_proj",
+    "Wqkv",
     "layer"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff3dba4ded2fdf628b0c9bd810333742a4ada5e95901002fce7ac0ae675ad29
+oid sha256:802a01c1ed23b73188902d952f4f15ea954fee5824fd44125d5ad95cd36945ef
 size 5752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3599abb1c1bbafb5cf23e547962c6be67eff25d97cbb4fc116adeba928bd6c31
+oid sha256:1ee63e5cf5d7064f73e2b1c77aada83b8d7d19728003dd8eb4163a75837779be
 size 15814

last-checkpoint/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.30745341614906835,
+  "epoch": 0.15396578538102643,
   "eval_steps": 50,
   "global_step": 99,
   "is_hyper_param_search": false,
@@ -9,45 +9,45 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.003105590062111801,
+      "epoch": 0.0015552099533437014,
       "eval_loss": 11.5,
-      "eval_runtime": 0.794,
-      "eval_samples_per_second": 341.322,
-      "eval_steps_per_second": 21.411,
+      "eval_runtime": 0.9095,
+      "eval_samples_per_second": 297.968,
+      "eval_steps_per_second": 37.383,
       "step": 1
     },
     {
-      "epoch": 0.062111801242236024,
-      "grad_norm": 5.816050361318048e-06,
+      "epoch": 0.03110419906687403,
+      "grad_norm": 6.635740191995865e-06,
       "learning_rate": 0.0005,
       "loss": 11.5,
       "step": 20
     },
     {
-      "epoch": 0.12422360248447205,
-      "grad_norm": 5.217343641561456e-06,
+      "epoch": 0.06220839813374806,
+      "grad_norm": 1.2428505215211771e-05,
       "learning_rate": 0.00042501051864235636,
       "loss": 11.5,
       "step": 40
     },
     {
-      "epoch": 0.15527950310559005,
+      "epoch": 0.07776049766718507,
       "eval_loss": 11.5,
-      "eval_runtime": 0.9798,
-      "eval_samples_per_second": 276.6,
-      "eval_steps_per_second": 17.351,
+      "eval_runtime": 0.8873,
+      "eval_samples_per_second": 305.428,
+      "eval_steps_per_second": 38.319,
       "step": 50
     },
     {
-      "epoch": 0.18633540372670807,
-      "grad_norm": 6.795597983000334e-06,
+      "epoch": 0.09331259720062209,
+      "grad_norm": 1.2873988453065977e-05,
       "learning_rate": 0.00024502945308373244,
       "loss": 11.5,
       "step": 60
     },
     {
-      "epoch": 0.2484472049689441,
-      "grad_norm": 7.33325032342691e-06,
+      "epoch": 0.12441679626749612,
+      "grad_norm": 1.2784214959538076e-05,
       "learning_rate": 6.803029740762648e-05,
       "loss": 11.5,
       "step": 80
@@ -70,8 +70,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 3944729935872.0,
-  "train_batch_size": 16,
+  "total_flos": 1972364967936.0,
+  "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca3e4660f8a5a3e2a0a6131d1b2056bbc7e9740103969e0f2d007680d31942d
+oid sha256:df6d97d90dddbe76304ec413367b35d93d0004cea3ab128ff75bc30a5753a0c7
 size 6776