Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "down_proj",
-    "q_proj",
+    "gate_proj",
     "v_proj",
+    "q_proj",
+    "down_proj",
     "up_proj",
-    "gate_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcfa77e704a64d02fdec392b40a94fb48db317e3c900b1268708b49c323dded4
+oid sha256:e3a01ceb740d08102122da6b511b028ee8d2396427d53cb5e1cacc81f061dc60
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728eec445470e6c3556074d04c3eb74a9573a71fcf7daaa88e905e2fb2d2578e
+oid sha256:03786f759a729f1f35a952d3a54a045233d458322c46721ecdafd30eff8b0e14
 size 160172858

last-checkpoint/trainer_state.json

@@ -18,9 +18,9 @@
     {
       "epoch": 1.396028995522237e-05,
       "eval_loss": 1.870382308959961,
-      "eval_runtime": 1842.0549,
-      "eval_samples_per_second": 8.187,
-      "eval_steps_per_second": 8.187,
+      "eval_runtime": 1878.2928,
+      "eval_samples_per_second": 8.029,
+      "eval_steps_per_second": 8.029,
       "step": 1
     },
     {
@@ -40,14 +40,14 @@
     {
       "epoch": 4.188086986566711e-05,
       "eval_loss": 1.870382308959961,
-      "eval_runtime": 1823.007,
-      "eval_samples_per_second": 8.273,
-      "eval_steps_per_second": 8.273,
+      "eval_runtime": 1814.1651,
+      "eval_samples_per_second": 8.313,
+      "eval_steps_per_second": 8.313,
       "step": 3
     },
     {
       "epoch": 5.584115982088948e-05,
-      "grad_norm": 0.45489802956581116,
+      "grad_norm": 0.47626373171806335,
       "learning_rate": 2e-05,
       "loss": 1.6525,
       "step": 4
@@ -61,17 +61,17 @@
     },
     {
       "epoch": 8.376173973133422e-05,
-      "grad_norm": 0.6043833494186401,
+      "grad_norm": 0.632369339466095,
       "learning_rate": 4e-05,
       "loss": 1.5735,
       "step": 6
     },
     {
       "epoch": 8.376173973133422e-05,
-      "eval_loss": 1.8686633110046387,
-      "eval_runtime": 1822.7895,
-      "eval_samples_per_second": 8.274,
-      "eval_steps_per_second": 8.274,
+      "eval_loss": 1.8685113191604614,
+      "eval_runtime": 1813.0543,
+      "eval_samples_per_second": 8.318,
+      "eval_steps_per_second": 8.318,
       "step": 6
     },
     {
@@ -83,24 +83,24 @@
     },
     {
       "epoch": 0.00011168231964177897,
-      "grad_norm": 0.5930614471435547,
+      "grad_norm": 0.616361141204834,
       "learning_rate": 6e-05,
-      "loss": 1.8795,
+      "loss": 1.8794,
       "step": 8
     },
     {
       "epoch": 0.00012564260959700132,
       "grad_norm": NaN,
       "learning_rate": 6e-05,
-      "loss": 1.6314,
+      "loss": 1.6309,
       "step": 9
     },
     {
       "epoch": 0.00012564260959700132,
-      "eval_loss": 1.862870216369629,
-      "eval_runtime": 1821.1166,
-      "eval_samples_per_second": 8.281,
-      "eval_steps_per_second": 8.281,
+      "eval_loss": 1.8624062538146973,
+      "eval_runtime": 1806.2004,
+      "eval_samples_per_second": 8.35,
+      "eval_steps_per_second": 8.35,
       "step": 9
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e2120fce261a3f11caf9498f0f2c7c47b2d4840984af1e8cfb44d3982cfeb2
+oid sha256:8592505319a0e1bd652dbec69d0ae190ac2673d977246a6c07d54713cd9bce43
 size 6776