Training in progress, step 300, checkpoint

last-checkpoint/adapter_config.json

@@ -16,8 +16,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:867173bcaddd4298f59f7d72b16f31a68f27518e15f271a9040271ca66f6319e
+oid sha256:1c8b46775cd1518360b0322d9acadb985d980bc6360007c1b29cefe44d9dd337
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4b1d6ed1999ea1b1bbcec41b01bea8534d890f34f41175ccb3137f2d3ef69cc
-size 25222277
+oid sha256:f4b65442bbf6d1467cc9417ee8a2d402be15409442f366e77e6f6ef6d1af2390
+size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85658496e06077f87b750aeb031c8edf46d72979c48ec879f8596b632cba3381
+oid sha256:8cfb045d2aace0aa6b48f6b2659a883d08eab7c39a2384b021a9dd36bdce66b0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1465147733688354,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.1323238611221313,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.4,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 10.395,
       "eval_steps_per_second": 1.303,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 0.9916,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.1323238611221313,
+      "eval_runtime": 186.616,
+      "eval_samples_per_second": 10.342,
+      "eval_steps_per_second": 1.297,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.8242451495747584e+16,
+  "total_flos": 4.242711954033869e+16,
   "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:ef6793b9c786624948fe20bfafe4d99e555c2e1c3dcf3c8e95e0213265b53906
+oid sha256:a44655c832d56011e28a0581b59475c0dfdadb4c68de0ecc5ac3364c1002507d
 size 4283