Training in progress, step 14, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "down_proj",
-    "v_proj",
     "o_proj",
-    "k_proj",
     "gate_proj",
+    "k_proj",
+    "v_proj",
+    "up_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:fbe91a1e7a9e8806479c94af4880c2bb3c8d967af4f9dc73111e3c41db3e4a27
+oid sha256:feeaefd251f02f422e5dc6eadd4cbe7770795c8751d2ce9e40026a86116ffce2
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6fe8c2c68b2a1531e08e4d28dbb67886db0ccbc640acf215e58a6c7cb96f039
+oid sha256:d07a5e857a9079e109033a494fff4433c3ce4156f9dca7fddf6fa3769955254d
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d7f00ec176b642ec567832ed7aebee44eb0aaa14876171d0750a87c94306030
+oid sha256:375cdd7ee13bf1e7c71cd45ce4a1ff0e16f11d5b854e85da1a07d9c05b445f24
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b2b7320b3325477d1a1c4f088efd5e12b26559cbc85b98bc73afac1c90ec058
+oid sha256:a798b360b7f185b7033ff4bad3a189bb7aa074d36e79555a2d99759059b64c93
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd01ddd4691e6318db0624fc7f170f0df5a10315ed9db786331d9a78925d9c57
+oid sha256:ce4b42ef37ef2745a957a7616be82f6f50f83d7319671d5f1de35717a5a177be
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c808e6a6a241aef069b3c838619267c6fbde9f050151e8a70a9afe3cbad62482
+oid sha256:e06470b7675e4574eb9536be30c42fbd8b33083282a7d6588136def8808e4563
 size 15024

last-checkpoint/trainer_state.json

@@ -10,108 +10,108 @@
   "log_history": [
     {
       "epoch": 0.2222222222222222,
-      "grad_norm": 0.17398317158222198,
+      "grad_norm": 0.17190293967723846,
       "learning_rate": 9.874639560909117e-05,
       "loss": 0.8215,
       "step": 1
     },
     {
       "epoch": 0.2222222222222222,
-      "eval_loss": 0.9823926687240601,
-      "eval_runtime": 0.8845,
-      "eval_samples_per_second": 33.919,
-      "eval_steps_per_second": 4.523,
+      "eval_loss": 0.9819098711013794,
+      "eval_runtime": 1.8124,
+      "eval_samples_per_second": 16.552,
+      "eval_steps_per_second": 2.207,
       "step": 1
     },
     {
       "epoch": 0.4444444444444444,
-      "grad_norm": 0.19333340227603912,
+      "grad_norm": 0.191148579120636,
       "learning_rate": 9.504844339512095e-05,
-      "loss": 0.8185,
+      "loss": 0.8189,
       "step": 2
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 0.20087279379367828,
+      "grad_norm": 0.2025042325258255,
       "learning_rate": 8.90915741234015e-05,
-      "loss": 0.9266,
+      "loss": 0.9278,
       "step": 3
     },
     {
       "epoch": 0.8888888888888888,
-      "grad_norm": 0.13123652338981628,
+      "grad_norm": 0.13297100365161896,
       "learning_rate": 8.117449009293668e-05,
-      "loss": 0.7505,
+      "loss": 0.7514,
       "step": 4
     },
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 0.19573189318180084,
+      "grad_norm": 0.19530025124549866,
       "learning_rate": 7.169418695587791e-05,
-      "loss": 1.2223,
+      "loss": 1.2238,
       "step": 5
     },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 0.132665753364563,
+      "grad_norm": 0.13223180174827576,
       "learning_rate": 6.112604669781572e-05,
-      "loss": 0.7468,
+      "loss": 0.7471,
       "step": 6
     },
     {
       "epoch": 1.5555555555555556,
-      "grad_norm": 0.12373827397823334,
+      "grad_norm": 0.12357468158006668,
       "learning_rate": 5e-05,
-      "loss": 0.6952,
+      "loss": 0.6953,
       "step": 7
     },
     {
       "epoch": 1.7777777777777777,
-      "grad_norm": 0.11204627901315689,
+      "grad_norm": 0.11169826984405518,
       "learning_rate": 3.887395330218429e-05,
-      "loss": 0.7634,
+      "loss": 0.7635,
       "step": 8
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.1433575302362442,
+      "grad_norm": 0.14295947551727295,
       "learning_rate": 2.8305813044122097e-05,
-      "loss": 0.7388,
+      "loss": 0.7394,
       "step": 9
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 0.09788352996110916,
+      "grad_norm": 0.09722330421209335,
       "learning_rate": 1.8825509907063327e-05,
-      "loss": 0.6522,
+      "loss": 0.6525,
       "step": 10
     },
     {
       "epoch": 2.4444444444444446,
-      "grad_norm": 0.09559472650289536,
+      "grad_norm": 0.09481758624315262,
       "learning_rate": 1.090842587659851e-05,
-      "loss": 0.7127,
+      "loss": 0.7131,
       "step": 11
     },
     {
       "epoch": 2.6666666666666665,
-      "grad_norm": 0.09474680572748184,
+      "grad_norm": 0.09451146423816681,
       "learning_rate": 4.951556604879048e-06,
-      "loss": 0.6954,
+      "loss": 0.6958,
       "step": 12
     },
     {
       "epoch": 2.888888888888889,
-      "grad_norm": 0.09361825883388519,
+      "grad_norm": 0.09294182807207108,
       "learning_rate": 1.2536043909088191e-06,
-      "loss": 0.6649,
+      "loss": 0.665,
       "step": 13
     },
     {
       "epoch": 3.111111111111111,
-      "grad_norm": 0.1547682285308838,
+      "grad_norm": 0.15370355546474457,
       "learning_rate": 0.0,
-      "loss": 1.1236,
+      "loss": 1.1239,
       "step": 14
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9599259b3a8ed0257e4ba7c92f50f5987d4afeb6ceb047a196d86595b584caf
+oid sha256:15b1e63507204285c0a761c74cdac18925cae1de1cbc6b88fb00aeb9357a1e79
 size 6776