Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
-    "o_proj",
+    "q_proj",
     "v_proj",
     "down_proj",
-    "q_proj",
-    "up_proj"
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df3c4f1ca07d9487eeae4cdd4d179772c9f28050b7c284fecb0261c95d85250f
+oid sha256:d847474f09d76040ea9a945e5aa072ca85a0825970adc2b5fdcc4e94a928b950
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21e4bb0c28036ed1d2f3636f890837574d0b6055c949c9013e872fe6d9858bca
+oid sha256:2bc832e1d6d58a296221fd7d502797f542b8623e1ae088266b38b7a5c1d67b17
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33506d13deb15f4b59817cb1048b61613518f1ef0883689e9f4785b23e81b15
+oid sha256:69dcafec2603b1c1ced4bbd4d60d2848e0b6db84973c4da004925986c6bce1d9
 size 14512

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.010309278350515464,
-      "grad_norm": 0.7261636853218079,
+      "grad_norm": 0.7860156893730164,
       "learning_rate": 2.0000000000000003e-06,
       "loss": 0.9943,
       "step": 1
@@ -18,69 +18,69 @@
     {
       "epoch": 0.010309278350515464,
       "eval_loss": 0.9863536357879639,
-      "eval_runtime": 11.7218,
-      "eval_samples_per_second": 13.991,
-      "eval_steps_per_second": 1.792,
+      "eval_runtime": 11.8025,
+      "eval_samples_per_second": 13.895,
+      "eval_steps_per_second": 1.779,
       "step": 1
     },
     {
       "epoch": 0.020618556701030927,
-      "grad_norm": 0.6982033252716064,
+      "grad_norm": 0.7550910115242004,
       "learning_rate": 4.000000000000001e-06,
       "loss": 0.9017,
       "step": 2
     },
     {
       "epoch": 0.020618556701030927,
-      "eval_loss": 0.9875333905220032,
-      "eval_runtime": 11.8029,
-      "eval_samples_per_second": 13.895,
-      "eval_steps_per_second": 1.779,
+      "eval_loss": 0.9886725544929504,
+      "eval_runtime": 11.9125,
+      "eval_samples_per_second": 13.767,
+      "eval_steps_per_second": 1.763,
       "step": 2
     },
     {
       "epoch": 0.030927835051546393,
-      "grad_norm": 1.0823779106140137,
+      "grad_norm": 1.1944996118545532,
       "learning_rate": 6e-06,
-      "loss": 1.0974,
+      "loss": 1.1019,
       "step": 3
     },
     {
       "epoch": 0.030927835051546393,
-      "eval_loss": 0.9870172142982483,
-      "eval_runtime": 11.8323,
-      "eval_samples_per_second": 13.86,
-      "eval_steps_per_second": 1.775,
+      "eval_loss": 0.9872242212295532,
+      "eval_runtime": 11.8973,
+      "eval_samples_per_second": 13.785,
+      "eval_steps_per_second": 1.765,
       "step": 3
     },
     {
       "epoch": 0.041237113402061855,
-      "grad_norm": 0.6564100980758667,
+      "grad_norm": 0.7197827696800232,
       "learning_rate": 8.000000000000001e-06,
-      "loss": 0.813,
+      "loss": 0.8137,
       "step": 4
     },
     {
       "epoch": 0.041237113402061855,
-      "eval_loss": 0.9877360463142395,
-      "eval_runtime": 11.8504,
-      "eval_samples_per_second": 13.839,
-      "eval_steps_per_second": 1.772,
+      "eval_loss": 0.9864019751548767,
+      "eval_runtime": 11.966,
+      "eval_samples_per_second": 13.705,
+      "eval_steps_per_second": 1.755,
       "step": 4
     },
     {
       "epoch": 0.05154639175257732,
-      "grad_norm": 0.8452497720718384,
+      "grad_norm": 0.9193218946456909,
       "learning_rate": 1e-05,
-      "loss": 0.9212,
+      "loss": 0.9198,
       "step": 5
     },
     {
       "epoch": 0.05154639175257732,
-      "eval_loss": 0.9856494665145874,
-      "eval_runtime": 11.8911,
-      "eval_samples_per_second": 13.792,
-      "eval_steps_per_second": 1.766,
+      "eval_loss": 0.984832227230072,
+      "eval_runtime": 11.8502,
+      "eval_samples_per_second": 13.839,
+      "eval_steps_per_second": 1.772,
       "step": 5
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aab7569b3377c35eb78eba184a0601d7c745483ceeee6fb9509a33c18bb0950
+oid sha256:d97c4fa40f12b62671931897af867d0478f2095eee9e2b8b99df811f0daadbfa
 size 6712