Training in progress, step 300, checkpoint

last-checkpoint/adapter_config.json

@@ -22,8 +22,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj"
+    "k_proj",
+    "q_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 sha256:4afd5de1ba40a667d318a69f8ca1b9640abbb1894e9a31f968505bcc344b6854
+oid sha256:dffb58ead3a8261ad808ac56947c3cd3660dde80949934a70ee4007ecf573495
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b589f7ce6dc8df86706635a4a048b369cefac35fb9420912505e001b6668a2
+oid sha256:b6d510ad6a7aadf1acfd0a7799fb32b8ccdd1d51e237076309c4a4f363e0b0c8
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdcd158786234085082ce38b1824c51dd8c72881220443fc2d1c6f4e031a983
+oid sha256:c84fe26b84a1b82bdd32297a5506f7b0ec5d1b51b65a2f281da22aea31edccd2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf3f988e8fed2daa2e801eb1f19b681872781cf57f0fb7b896e859a12cfe2bb
+oid sha256:6f4c00d522bdde510099aafe1617b13d114dce17a17b44e05876f016f4e4d7af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,125 +1,238 @@
 {
-  "best_metric": 0.7960079908370972,
-  "best_model_checkpoint": "./output/checkpoint-150",
-  "epoch": 6.521739130434782,
+  "best_metric": 0.7312111854553223,
+  "best_model_checkpoint": "./output/checkpoint-300",
+  "epoch": 13.043478260869565,
   "eval_steps": 150,
-  "global_step": 150,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.43478260869565216,
-      "grad_norm": 1.5021412372589111,
+      "grad_norm": 1.5021647214889526,
       "learning_rate": 3e-06,
-      "loss": 0.9061,
+      "loss": 0.9064,
       "step": 10
     },
     {
       "epoch": 0.8695652173913043,
-      "grad_norm": 1.687071442604065,
+      "grad_norm": 1.6793277263641357,
       "learning_rate": 6e-06,
-      "loss": 0.9026,
+      "loss": 0.9024,
       "step": 20
     },
     {
       "epoch": 1.3043478260869565,
-      "grad_norm": 1.7296651601791382,
+      "grad_norm": 1.7296056747436523,
       "learning_rate": 9e-06,
-      "loss": 0.9003,
+      "loss": 0.9,
       "step": 30
     },
     {
       "epoch": 1.7391304347826086,
-      "grad_norm": 1.4536513090133667,
+      "grad_norm": 1.4458602666854858,
       "learning_rate": 1.2e-05,
-      "loss": 0.9093,
+      "loss": 0.9086,
       "step": 40
     },
     {
       "epoch": 2.1739130434782608,
-      "grad_norm": 1.351776361465454,
+      "grad_norm": 1.3516699075698853,
       "learning_rate": 1.5e-05,
-      "loss": 0.8358,
+      "loss": 0.8359,
       "step": 50
     },
     {
       "epoch": 2.608695652173913,
-      "grad_norm": 2.031055212020874,
+      "grad_norm": 2.03114914894104,
       "learning_rate": 1.8e-05,
-      "loss": 0.8894,
+      "loss": 0.8892,
       "step": 60
     },
     {
       "epoch": 3.0434782608695654,
-      "grad_norm": 1.4920436143875122,
+      "grad_norm": 1.4920729398727417,
       "learning_rate": 2.1e-05,
-      "loss": 0.8915,
+      "loss": 0.8913,
       "step": 70
     },
     {
       "epoch": 3.4782608695652173,
-      "grad_norm": 1.729347586631775,
+      "grad_norm": 1.7293280363082886,
       "learning_rate": 2.4e-05,
-      "loss": 0.8237,
+      "loss": 0.8234,
       "step": 80
     },
     {
       "epoch": 3.9130434782608696,
-      "grad_norm": 1.4314346313476562,
+      "grad_norm": 1.4240705966949463,
       "learning_rate": 2.7000000000000002e-05,
       "loss": 0.8529,
       "step": 90
     },
     {
       "epoch": 4.3478260869565215,
-      "grad_norm": 1.3657989501953125,
+      "grad_norm": 1.3656291961669922,
       "learning_rate": 3e-05,
       "loss": 0.8649,
       "step": 100
     },
     {
       "epoch": 4.782608695652174,
-      "grad_norm": 2.1989877223968506,
+      "grad_norm": 2.198136806488037,
       "learning_rate": 2.999999702723963e-05,
       "loss": 0.8227,
       "step": 110
     },
     {
       "epoch": 5.217391304347826,
-      "grad_norm": 1.0724585056304932,
+      "grad_norm": 1.0726988315582275,
       "learning_rate": 2.9999988108959687e-05,
-      "loss": 0.7655,
+      "loss": 0.765,
       "step": 120
     },
     {
       "epoch": 5.6521739130434785,
-      "grad_norm": 1.5675039291381836,
+      "grad_norm": 1.5672078132629395,
       "learning_rate": 2.9999973245163716e-05,
       "loss": 0.7413,
       "step": 130
     },
     {
       "epoch": 6.086956521739131,
-      "grad_norm": 1.9068934917449951,
+      "grad_norm": 1.9071016311645508,
       "learning_rate": 2.99999524358576e-05,
-      "loss": 0.7653,
+      "loss": 0.7655,
       "step": 140
     },
     {
       "epoch": 6.521739130434782,
-      "grad_norm": 1.121341586112976,
+      "grad_norm": 1.1219961643218994,
       "learning_rate": 2.9999925681049593e-05,
       "loss": 0.7855,
       "step": 150
     },
     {
       "epoch": 6.521739130434782,
-      "eval_loss": 0.7960079908370972,
-      "eval_runtime": 0.4677,
-      "eval_samples_per_second": 21.382,
-      "eval_steps_per_second": 21.382,
+      "eval_loss": 0.7960985898971558,
+      "eval_runtime": 0.5137,
+      "eval_samples_per_second": 19.465,
+      "eval_steps_per_second": 19.465,
       "step": 150
+    },
+    {
+      "epoch": 6.956521739130435,
+      "grad_norm": 1.5404783487319946,
+      "learning_rate": 2.9999892980750297e-05,
+      "loss": 0.6588,
+      "step": 160
+    },
+    {
+      "epoch": 7.391304347826087,
+      "grad_norm": 1.3464210033416748,
+      "learning_rate": 2.9999854334972675e-05,
+      "loss": 0.739,
+      "step": 170
+    },
+    {
+      "epoch": 7.826086956521739,
+      "grad_norm": 1.7264870405197144,
+      "learning_rate": 2.999980974373204e-05,
+      "loss": 0.7292,
+      "step": 180
+    },
+    {
+      "epoch": 8.26086956521739,
+      "grad_norm": 1.5393368005752563,
+      "learning_rate": 2.9999759207046075e-05,
+      "loss": 0.6244,
+      "step": 190
+    },
+    {
+      "epoch": 8.695652173913043,
+      "grad_norm": 1.7342770099639893,
+      "learning_rate": 2.9999702724934804e-05,
+      "loss": 0.6764,
+      "step": 200
+    },
+    {
+      "epoch": 9.130434782608695,
+      "grad_norm": 1.0416548252105713,
+      "learning_rate": 2.999964029742062e-05,
+      "loss": 0.6521,
+      "step": 210
+    },
+    {
+      "epoch": 9.565217391304348,
+      "grad_norm": 1.2193585634231567,
+      "learning_rate": 2.9999571924528263e-05,
+      "loss": 0.5592,
+      "step": 220
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.5286610126495361,
+      "learning_rate": 2.9999497606284837e-05,
+      "loss": 0.756,
+      "step": 230
+    },
+    {
+      "epoch": 10.434782608695652,
+      "grad_norm": 1.427451252937317,
+      "learning_rate": 2.9999417342719796e-05,
+      "loss": 0.7118,
+      "step": 240
+    },
+    {
+      "epoch": 10.869565217391305,
+      "grad_norm": 0.9794074296951294,
+      "learning_rate": 2.9999331133864956e-05,
+      "loss": 0.5897,
+      "step": 250
+    },
+    {
+      "epoch": 11.304347826086957,
+      "grad_norm": 1.194082260131836,
+      "learning_rate": 2.9999238979754485e-05,
+      "loss": 0.6548,
+      "step": 260
+    },
+    {
+      "epoch": 11.73913043478261,
+      "grad_norm": 1.0489437580108643,
+      "learning_rate": 2.999914088042492e-05,
+      "loss": 0.6474,
+      "step": 270
+    },
+    {
+      "epoch": 12.173913043478262,
+      "grad_norm": 1.3105570077896118,
+      "learning_rate": 2.9999036835915132e-05,
+      "loss": 0.5936,
+      "step": 280
+    },
+    {
+      "epoch": 12.608695652173914,
+      "grad_norm": 1.0830979347229004,
+      "learning_rate": 2.9998926846266365e-05,
+      "loss": 0.6328,
+      "step": 290
+    },
+    {
+      "epoch": 13.043478260869565,
+      "grad_norm": 1.3943493366241455,
+      "learning_rate": 2.9998810911522213e-05,
+      "loss": 0.5806,
+      "step": 300
+    },
+    {
+      "epoch": 13.043478260869565,
+      "eval_loss": 0.7312111854553223,
+      "eval_runtime": 0.6239,
+      "eval_samples_per_second": 16.028,
+      "eval_steps_per_second": 16.028,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -139,7 +252,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3894839614291968.0,
+  "total_flos": 7724643094462464.0,
   "train_batch_size": 4,
   "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:a4e26a07b48ab9f4eeb67e7d951dfa1f71b1fc6e6c955372cec1a3c50fa8b9a2
+oid sha256:0c84fd1341bca21f546fb34f0984c2737ed54e8dbbe2ce01666781675b951db1
 size 5368