Training in progress, step 525, checkpoint

last-checkpoint/adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "v_proj",
+    "down_proj",
     "k_proj",
-    "o_proj",
     "up_proj",
-    "down_proj",
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "gate_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cea3c8ef0c20ac5c7064464590e6eef40731a1cd849dfa141568fb7a4d03c6e
+oid sha256:49eb6649e2274b02d328f72a794bc7eab49ea2afa9e5177abb89e6bdcb67b5e4
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c52cd1d2167dd41de29c42e86dd4fbb033029e2161c9429d73882d09abe4736
+oid sha256:d57e25f58ff1fa6d753d6a1dbefb4091585054520e08933d5556e19de1668929
 size 21506325

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:004c6cf8c75cf21d98d37334b5f18898a61555d4c3bf916f050eabd9c214bf85
+oid sha256:184a8c32c5a60652447eaf994156244275cb645dd3472230ece015c8f72b2491
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7272727272727273,
+  "epoch": 0.9545454545454546,
   "eval_steps": 300,
-  "global_step": 400,
+  "global_step": 525,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -168,6 +168,56 @@
       "mean_token_accuracy": 0.9314557152986527,
       "num_tokens": 3680638.0,
       "step": 400
+    },
+    {
+      "entropy": 0.211444590985775,
+      "epoch": 0.7727272727272727,
+      "grad_norm": 0.33696606755256653,
+      "learning_rate": 0.0002,
+      "loss": 0.2138,
+      "mean_token_accuracy": 0.9305079692602157,
+      "num_tokens": 246907.0,
+      "step": 425
+    },
+    {
+      "entropy": 0.2034035588800907,
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.2776103913784027,
+      "learning_rate": 0.0002,
+      "loss": 0.205,
+      "mean_token_accuracy": 0.9340596944093704,
+      "num_tokens": 491107.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.20198263928294183,
+      "epoch": 0.8636363636363636,
+      "grad_norm": 0.2613779902458191,
+      "learning_rate": 0.0002,
+      "loss": 0.2046,
+      "mean_token_accuracy": 0.9333311957120896,
+      "num_tokens": 736913.0,
+      "step": 475
+    },
+    {
+      "entropy": 0.19453272923827172,
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.2954370677471161,
+      "learning_rate": 0.0002,
+      "loss": 0.198,
+      "mean_token_accuracy": 0.9352397722005844,
+      "num_tokens": 981351.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.19829959146678447,
+      "epoch": 0.9545454545454546,
+      "grad_norm": 0.25840431451797485,
+      "learning_rate": 0.0002,
+      "loss": 0.1992,
+      "mean_token_accuracy": 0.9348948985338211,
+      "num_tokens": 1226716.0,
+      "step": 525
     }
   ],
   "logging_steps": 25,
@@ -187,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.483559954625331e+16,
+  "total_flos": 7.203650548006912e+16,
   "train_batch_size": 3,
   "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:f81338ff956e9b40cae3af19655b5440963e1f86777dc882b1fa550d0186dcd1
+oid sha256:8e9dd78fafbdde44e0f278b929472178a449375b56fb77fab30d30a5d733013a
 size 6865