Training in progress, step 15, checkpoint

last-checkpoint/adapter_config.json

@@ -22,10 +22,10 @@
   "target_modules": [
     "o_proj",
     "v_proj",
-    "k_proj",
     "down_proj",
-    "up_proj",
     "gate_proj",
+    "up_proj",
+    "k_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 sha256:9878148640a6b2701734449a5dd6848af54b0d612d8eb174ee6b52eee7ba1a2b
+oid sha256:bf67b44e2474c435f67e089b4aa5e43482ae7ef4a321e6476cc27cfff4b2cf7e
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789296e2aae6020b71c4ecb0490363fca7aab82e522800132180fe75afc353d7
+oid sha256:fedf9f3eb96dc8e2216acb799cce9a385162c8bd915fad167fc6c7b6c2241efa
 size 202110330

last-checkpoint/trainer_state.json

@@ -18,131 +18,131 @@
     {
       "epoch": 0.0035842293906810036,
       "eval_loss": 1.371159315109253,
-      "eval_runtime": 8.0828,
-      "eval_samples_per_second": 58.148,
-      "eval_steps_per_second": 7.299,
+      "eval_runtime": 8.3908,
+      "eval_samples_per_second": 56.014,
+      "eval_steps_per_second": 7.032,
       "step": 1
     },
     {
       "epoch": 0.007168458781362007,
-      "grad_norm": 1.2307049036026,
+      "grad_norm": 1.1762983798980713,
       "learning_rate": 2e-05,
       "loss": 1.2685,
       "step": 2
     },
     {
       "epoch": 0.010752688172043012,
-      "grad_norm": 1.0430188179016113,
+      "grad_norm": 0.999072253704071,
       "learning_rate": 4e-05,
       "loss": 1.1567,
       "step": 3
     },
     {
       "epoch": 0.014336917562724014,
-      "grad_norm": 1.1231369972229004,
+      "grad_norm": 1.0890846252441406,
       "learning_rate": 6e-05,
-      "loss": 1.29,
+      "loss": 1.2905,
       "step": 4
     },
     {
       "epoch": 0.017921146953405017,
-      "grad_norm": 1.1865134239196777,
+      "grad_norm": 1.1394107341766357,
       "learning_rate": 8e-05,
-      "loss": 1.2327,
+      "loss": 1.2343,
       "step": 5
     },
     {
       "epoch": 0.017921146953405017,
-      "eval_loss": 1.304574728012085,
-      "eval_runtime": 8.1943,
-      "eval_samples_per_second": 57.357,
-      "eval_steps_per_second": 7.2,
+      "eval_loss": 1.3072917461395264,
+      "eval_runtime": 8.5738,
+      "eval_samples_per_second": 54.818,
+      "eval_steps_per_second": 6.881,
       "step": 5
     },
     {
       "epoch": 0.021505376344086023,
-      "grad_norm": 1.2747498750686646,
+      "grad_norm": 1.2360237836837769,
       "learning_rate": 0.0001,
-      "loss": 1.4252,
+      "loss": 1.4268,
       "step": 6
     },
     {
       "epoch": 0.025089605734767026,
-      "grad_norm": 0.9193595051765442,
+      "grad_norm": 0.9018695950508118,
       "learning_rate": 0.00012,
-      "loss": 1.0889,
+      "loss": 1.0908,
       "step": 7
     },
     {
       "epoch": 0.02867383512544803,
       "grad_norm": NaN,
       "learning_rate": 0.00012,
-      "loss": 1.4204,
+      "loss": 1.4248,
       "step": 8
     },
     {
       "epoch": 0.03225806451612903,
-      "grad_norm": 0.8832981586456299,
+      "grad_norm": 0.8699414134025574,
       "learning_rate": 0.00014,
-      "loss": 1.1822,
+      "loss": 1.1859,
       "step": 9
     },
     {
       "epoch": 0.035842293906810034,
-      "grad_norm": 0.804837703704834,
+      "grad_norm": 0.7875003218650818,
       "learning_rate": 0.00016,
-      "loss": 1.1865,
+      "loss": 1.1898,
       "step": 10
     },
     {
       "epoch": 0.035842293906810034,
-      "eval_loss": 1.1667453050613403,
-      "eval_runtime": 8.2688,
-      "eval_samples_per_second": 56.84,
-      "eval_steps_per_second": 7.135,
+      "eval_loss": 1.1698945760726929,
+      "eval_runtime": 8.6367,
+      "eval_samples_per_second": 54.419,
+      "eval_steps_per_second": 6.831,
       "step": 10
     },
     {
       "epoch": 0.03942652329749104,
-      "grad_norm": 1.0118783712387085,
+      "grad_norm": 0.9833978414535522,
       "learning_rate": 0.00018,
-      "loss": 1.1729,
+      "loss": 1.1755,
       "step": 11
     },
     {
       "epoch": 0.043010752688172046,
-      "grad_norm": 0.9140554070472717,
+      "grad_norm": 0.890007734298706,
       "learning_rate": 0.0002,
-      "loss": 1.0825,
+      "loss": 1.0835,
       "step": 12
     },
     {
       "epoch": 0.04659498207885305,
-      "grad_norm": 0.9855129718780518,
+      "grad_norm": 0.9671109914779663,
       "learning_rate": 0.00019510565162951537,
-      "loss": 1.1756,
+      "loss": 1.1763,
       "step": 13
     },
     {
       "epoch": 0.05017921146953405,
-      "grad_norm": 0.7907399535179138,
+      "grad_norm": 0.7680312991142273,
       "learning_rate": 0.00018090169943749476,
-      "loss": 1.0081,
+      "loss": 1.007,
       "step": 14
     },
     {
       "epoch": 0.053763440860215055,
-      "grad_norm": 0.809781014919281,
+      "grad_norm": 0.7991800308227539,
       "learning_rate": 0.00015877852522924732,
-      "loss": 0.9997,
+      "loss": 1.0003,
       "step": 15
     },
     {
       "epoch": 0.053763440860215055,
-      "eval_loss": 1.1061427593231201,
-      "eval_runtime": 8.2438,
-      "eval_samples_per_second": 57.012,
-      "eval_steps_per_second": 7.157,
+      "eval_loss": 1.107828140258789,
+      "eval_runtime": 8.6971,
+      "eval_samples_per_second": 54.041,
+      "eval_steps_per_second": 6.784,
       "step": 15
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e50aba904d39c5864e0f36c27d2c58f2cca1afdba552845d8b36d9735033ed
+oid sha256:8ad82ad32525e933af8b9fc0db6dec8e95c1d489a1adc2b0fa6be91ccfcf9268
 size 6712