Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35820b18cb2d1840f01298abaa2a6ee2d1da18435d42aa5d26681751a1378e1c
+oid sha256:44a96603bd8eee4cf918c9772a26520b8760099bd8f4cd2de014624bf4fa4c7f
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e724a055f269185a0e46082ca9a545eaf1f95d0e10536516c1a0c1dc261b97
+oid sha256:b4fd2108d49d07e4d7bee6998e7ecb19e375ff49d05de755c3a44b4b5c6c6dc5
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f76c4c2dca19bfb0a463693a0e409b44510488650d816e566bccd2a2851e9524
+oid sha256:5feb56512e955691dc9bb9a1e37b9dd590e06a961d7d94560b679e2730b03194
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0b9a1e2fa3da24e9af8b74787d70ff4c95d9bc9b74eeab135df0350a00b462
+oid sha256:8cf3f988e8fed2daa2e801eb1f19b681872781cf57f0fb7b896e859a12cfe2bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,447 +1,157 @@
 {
-  "best_metric": 0.7164942026138306,
-  "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 19.565217391304348,
+  "best_metric": 0.7962104678153992,
+  "best_model_checkpoint": "./output/checkpoint-150",
+  "epoch": 6.521739130434782,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.43478260869565216,
-      "grad_norm": 1.4944251775741577,
+      "grad_norm": 1.5021581649780273,
       "learning_rate": 3e-06,
-      "loss": 0.9061,
+      "loss": 0.9064,
       "step": 10
     },
     {
       "epoch": 0.8695652173913043,
-      "grad_norm": 1.6870940923690796,
+      "grad_norm": 1.6793084144592285,
       "learning_rate": 6e-06,
-      "loss": 0.9025,
+      "loss": 0.9027,
       "step": 20
     },
     {
       "epoch": 1.3043478260869565,
-      "grad_norm": 1.7296459674835205,
+      "grad_norm": 1.7296501398086548,
       "learning_rate": 9e-06,
-      "loss": 0.9002,
+      "loss": 0.9003,
       "step": 30
     },
     {
       "epoch": 1.7391304347826086,
-      "grad_norm": 1.445741057395935,
+      "grad_norm": 1.4458428621292114,
       "learning_rate": 1.2e-05,
-      "loss": 0.9088,
+      "loss": 0.9092,
       "step": 40
     },
     {
       "epoch": 2.1739130434782608,
-      "grad_norm": 1.3440334796905518,
+      "grad_norm": 1.351685643196106,
       "learning_rate": 1.5e-05,
-      "loss": 0.8357,
+      "loss": 0.8363,
       "step": 50
     },
     {
       "epoch": 2.608695652173913,
-      "grad_norm": 2.0310230255126953,
+      "grad_norm": 2.0312559604644775,
       "learning_rate": 1.8e-05,
-      "loss": 0.8895,
+      "loss": 0.8894,
       "step": 60
     },
     {
       "epoch": 3.0434782608695654,
-      "grad_norm": 1.4844013452529907,
+      "grad_norm": 1.4843778610229492,
       "learning_rate": 2.1e-05,
-      "loss": 0.8912,
+      "loss": 0.8913,
       "step": 70
     },
     {
       "epoch": 3.4782608695652173,
-      "grad_norm": 1.7371524572372437,
+      "grad_norm": 1.729393720626831,
       "learning_rate": 2.4e-05,
-      "loss": 0.8235,
+      "loss": 0.8231,
       "step": 80
     },
     {
       "epoch": 3.9130434782608696,
-      "grad_norm": 1.424216866493225,
+      "grad_norm": 1.4239307641983032,
       "learning_rate": 2.7000000000000002e-05,
-      "loss": 0.8529,
+      "loss": 0.8528,
       "step": 90
     },
     {
       "epoch": 4.3478260869565215,
-      "grad_norm": 1.3736321926116943,
+      "grad_norm": 1.3656258583068848,
       "learning_rate": 3e-05,
-      "loss": 0.8648,
+      "loss": 0.865,
       "step": 100
     },
     {
       "epoch": 4.782608695652174,
-      "grad_norm": 2.198913335800171,
+      "grad_norm": 2.198690176010132,
       "learning_rate": 2.999999702723963e-05,
-      "loss": 0.8222,
+      "loss": 0.8228,
       "step": 110
     },
     {
       "epoch": 5.217391304347826,
-      "grad_norm": 1.072839379310608,
+      "grad_norm": 1.0728951692581177,
       "learning_rate": 2.9999988108959687e-05,
       "loss": 0.7655,
       "step": 120
     },
     {
       "epoch": 5.6521739130434785,
-      "grad_norm": 1.5597290992736816,
+      "grad_norm": 1.5677502155303955,
       "learning_rate": 2.9999973245163716e-05,
       "loss": 0.7412,
       "step": 130
     },
     {
       "epoch": 6.086956521739131,
-      "grad_norm": 1.9144600629806519,
+      "grad_norm": 1.9072229862213135,
       "learning_rate": 2.99999524358576e-05,
-      "loss": 0.7656,
+      "loss": 0.7657,
       "step": 140
     },
     {
       "epoch": 6.521739130434782,
-      "grad_norm": 1.1224875450134277,
+      "grad_norm": 1.1221002340316772,
       "learning_rate": 2.9999925681049593e-05,
-      "loss": 0.7859,
+      "loss": 0.7857,
       "step": 150
     },
     {
       "epoch": 6.521739130434782,
-      "eval_loss": 0.7959539294242859,
-      "eval_runtime": 0.5133,
-      "eval_samples_per_second": 19.482,
-      "eval_steps_per_second": 19.482,
+      "eval_loss": 0.7962104678153992,
+      "eval_runtime": 0.4685,
+      "eval_samples_per_second": 21.344,
+      "eval_steps_per_second": 21.344,
       "step": 150
     },
     {
       "epoch": 6.521739130434782,
-      "eval_loss": 0.8609360456466675,
-      "eval_runtime": 0.4466,
-      "eval_samples_per_second": 22.392,
-      "eval_steps_per_second": 22.392,
+      "eval_loss": 0.8606523275375366,
+      "eval_runtime": 0.3993,
+      "eval_samples_per_second": 25.042,
+      "eval_steps_per_second": 25.042,
       "step": 150
     },
     {
       "epoch": 6.521739130434782,
-      "eval_loss": 0.7959539294242859,
-      "eval_runtime": 0.4435,
-      "eval_samples_per_second": 22.55,
-      "eval_steps_per_second": 22.55,
+      "eval_loss": 0.7962104678153992,
+      "eval_runtime": 0.3965,
+      "eval_samples_per_second": 25.221,
+      "eval_steps_per_second": 25.221,
       "step": 150
     },
     {
       "epoch": 6.521739130434782,
-      "eval_loss": 0.8609360456466675,
-      "eval_runtime": 0.4444,
-      "eval_samples_per_second": 22.502,
-      "eval_steps_per_second": 22.502,
+      "eval_loss": 0.8606523275375366,
+      "eval_runtime": 0.4092,
+      "eval_samples_per_second": 24.439,
+      "eval_steps_per_second": 24.439,
       "step": 150
     },
     {
       "epoch": 6.521739130434782,
-      "eval_loss": 0.8611894845962524,
-      "eval_runtime": 0.4421,
-      "eval_samples_per_second": 22.618,
-      "eval_steps_per_second": 22.618,
-      "step": 150
-    },
-    {
-      "epoch": 6.956521739130435,
-      "grad_norm": 1.5320531129837036,
-      "learning_rate": 2.9999892980750297e-05,
-      "loss": 0.6585,
-      "step": 160
-    },
-    {
-      "epoch": 7.391304347826087,
-      "grad_norm": 1.346379041671753,
-      "learning_rate": 2.9999854334972675e-05,
-      "loss": 0.7392,
-      "step": 170
-    },
-    {
-      "epoch": 7.826086956521739,
-      "grad_norm": 1.726070761680603,
-      "learning_rate": 2.999980974373204e-05,
-      "loss": 0.7292,
-      "step": 180
-    },
-    {
-      "epoch": 8.26086956521739,
-      "grad_norm": 1.5403681993484497,
-      "learning_rate": 2.9999759207046075e-05,
-      "loss": 0.6246,
-      "step": 190
-    },
-    {
-      "epoch": 8.695652173913043,
-      "grad_norm": 1.7414804697036743,
-      "learning_rate": 2.9999702724934804e-05,
-      "loss": 0.6765,
-      "step": 200
-    },
-    {
-      "epoch": 9.130434782608695,
-      "grad_norm": 1.0415966510772705,
-      "learning_rate": 2.999964029742062e-05,
-      "loss": 0.652,
-      "step": 210
-    },
-    {
-      "epoch": 9.565217391304348,
-      "grad_norm": 1.2198948860168457,
-      "learning_rate": 2.9999571924528263e-05,
-      "loss": 0.5593,
-      "step": 220
-    },
-    {
-      "epoch": 10.0,
-      "grad_norm": 1.529250979423523,
-      "learning_rate": 2.9999497606284837e-05,
-      "loss": 0.756,
-      "step": 230
-    },
-    {
-      "epoch": 10.434782608695652,
-      "grad_norm": 1.4208300113677979,
-      "learning_rate": 2.9999417342719796e-05,
-      "loss": 0.7117,
-      "step": 240
-    },
-    {
-      "epoch": 10.869565217391305,
-      "grad_norm": 0.974891722202301,
-      "learning_rate": 2.9999331133864956e-05,
-      "loss": 0.5896,
-      "step": 250
-    },
-    {
-      "epoch": 11.304347826086957,
-      "grad_norm": 1.1935385465621948,
-      "learning_rate": 2.9999238979754485e-05,
-      "loss": 0.6548,
-      "step": 260
-    },
-    {
-      "epoch": 11.73913043478261,
-      "grad_norm": 1.0492814779281616,
-      "learning_rate": 2.999914088042492e-05,
-      "loss": 0.6473,
-      "step": 270
-    },
-    {
-      "epoch": 12.173913043478262,
-      "grad_norm": 1.3129431009292603,
-      "learning_rate": 2.9999036835915132e-05,
-      "loss": 0.5941,
-      "step": 280
-    },
-    {
-      "epoch": 12.608695652173914,
-      "grad_norm": 1.0831547975540161,
-      "learning_rate": 2.9998926846266365e-05,
-      "loss": 0.6329,
-      "step": 290
-    },
-    {
-      "epoch": 13.043478260869565,
-      "grad_norm": 1.3950847387313843,
-      "learning_rate": 2.9998810911522213e-05,
-      "loss": 0.5809,
-      "step": 300
-    },
-    {
-      "epoch": 13.043478260869565,
-      "eval_loss": 0.7313653230667114,
-      "eval_runtime": 0.4017,
-      "eval_samples_per_second": 24.891,
-      "eval_steps_per_second": 24.891,
-      "step": 300
-    },
-    {
-      "epoch": 13.043478260869565,
-      "eval_loss": 0.8609360456466675,
-      "eval_runtime": 0.4064,
-      "eval_samples_per_second": 24.603,
-      "eval_steps_per_second": 24.603,
-      "step": 300
-    },
-    {
-      "epoch": 13.043478260869565,
-      "eval_loss": 0.7313653230667114,
+      "eval_loss": 0.8619200587272644,
       "eval_runtime": 0.3955,
-      "eval_samples_per_second": 25.286,
-      "eval_steps_per_second": 25.286,
-      "step": 300
-    },
-    {
-      "epoch": 13.043478260869565,
-      "eval_loss": 0.7757944464683533,
-      "eval_runtime": 0.396,
-      "eval_samples_per_second": 25.25,
-      "eval_steps_per_second": 25.25,
-      "step": 300
-    },
-    {
-      "epoch": 13.043478260869565,
-      "eval_loss": 0.8611125946044922,
-      "eval_runtime": 0.4025,
-      "eval_samples_per_second": 24.847,
-      "eval_steps_per_second": 24.847,
-      "step": 300
-    },
-    {
-      "epoch": 13.478260869565217,
-      "grad_norm": 1.7789413928985596,
-      "learning_rate": 2.9998689031728636e-05,
-      "loss": 0.5145,
-      "step": 310
-    },
-    {
-      "epoch": 13.91304347826087,
-      "grad_norm": 1.532348394393921,
-      "learning_rate": 2.9998561206933938e-05,
-      "loss": 0.6494,
-      "step": 320
-    },
-    {
-      "epoch": 14.347826086956522,
-      "grad_norm": 1.4854978322982788,
-      "learning_rate": 2.9998427437188786e-05,
-      "loss": 0.5741,
-      "step": 330
-    },
-    {
-      "epoch": 14.782608695652174,
-      "grad_norm": 1.3134292364120483,
-      "learning_rate": 2.99982877225462e-05,
-      "loss": 0.6014,
-      "step": 340
-    },
-    {
-      "epoch": 15.217391304347826,
-      "grad_norm": 0.9749585390090942,
-      "learning_rate": 2.9998142063061564e-05,
-      "loss": 0.4988,
-      "step": 350
-    },
-    {
-      "epoch": 15.652173913043478,
-      "grad_norm": 1.6409484148025513,
-      "learning_rate": 2.9997990458792603e-05,
-      "loss": 0.5625,
-      "step": 360
-    },
-    {
-      "epoch": 16.08695652173913,
-      "grad_norm": 1.6361374855041504,
-      "learning_rate": 2.9997832909799417e-05,
-      "loss": 0.6672,
-      "step": 370
-    },
-    {
-      "epoch": 16.52173913043478,
-      "grad_norm": 0.9572365880012512,
-      "learning_rate": 2.9997669416144452e-05,
-      "loss": 0.5129,
-      "step": 380
-    },
-    {
-      "epoch": 16.956521739130434,
-      "grad_norm": 0.9357342720031738,
-      "learning_rate": 2.999749997789251e-05,
-      "loss": 0.5798,
-      "step": 390
-    },
-    {
-      "epoch": 17.391304347826086,
-      "grad_norm": 1.1117758750915527,
-      "learning_rate": 2.9997324595110743e-05,
-      "loss": 0.5179,
-      "step": 400
-    },
-    {
-      "epoch": 17.82608695652174,
-      "grad_norm": 1.2845892906188965,
-      "learning_rate": 2.9997143267868683e-05,
-      "loss": 0.5874,
-      "step": 410
-    },
-    {
-      "epoch": 18.26086956521739,
-      "grad_norm": 1.1638511419296265,
-      "learning_rate": 2.9996955996238192e-05,
-      "loss": 0.506,
-      "step": 420
-    },
-    {
-      "epoch": 18.695652173913043,
-      "grad_norm": 1.2020405530929565,
-      "learning_rate": 2.9996762780293503e-05,
-      "loss": 0.5316,
-      "step": 430
-    },
-    {
-      "epoch": 19.130434782608695,
-      "grad_norm": 1.2133735418319702,
-      "learning_rate": 2.9996563620111197e-05,
-      "loss": 0.5338,
-      "step": 440
-    },
-    {
-      "epoch": 19.565217391304348,
-      "grad_norm": 1.4260774850845337,
-      "learning_rate": 2.9996358515770218e-05,
-      "loss": 0.5681,
-      "step": 450
-    },
-    {
-      "epoch": 19.565217391304348,
-      "eval_loss": 0.7164942026138306,
-      "eval_runtime": 0.4121,
-      "eval_samples_per_second": 24.267,
-      "eval_steps_per_second": 24.267,
-      "step": 450
-    },
-    {
-      "epoch": 19.565217391304348,
-      "eval_loss": 0.8609360456466675,
-      "eval_runtime": 0.4438,
-      "eval_samples_per_second": 22.531,
-      "eval_steps_per_second": 22.531,
-      "step": 450
-    },
-    {
-      "epoch": 19.565217391304348,
-      "eval_loss": 0.7164942026138306,
-      "eval_runtime": 0.4426,
-      "eval_samples_per_second": 22.593,
-      "eval_steps_per_second": 22.593,
-      "step": 450
-    },
-    {
-      "epoch": 19.565217391304348,
-      "eval_loss": 0.7564777731895447,
-      "eval_runtime": 0.4418,
-      "eval_samples_per_second": 22.634,
-      "eval_steps_per_second": 22.634,
-      "step": 450
-    },
-    {
-      "epoch": 19.565217391304348,
-      "eval_loss": 0.8607853055000305,
-      "eval_runtime": 0.4381,
-      "eval_samples_per_second": 22.828,
-      "eval_steps_per_second": 22.828,
-      "step": 450
+      "eval_samples_per_second": 25.287,
+      "eval_steps_per_second": 25.287,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -461,7 +171,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1591800814075904e+16,
+  "total_flos": 3894839614291968.0,
   "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 sha256:27988642fde0f0de5ac4a25df3c5174e8198d475d8ed38cade0bee7093fe39e8
+oid sha256:003a11451b42f43906137235259ca60836693a9072ec318195749b927967a9e1
 size 5368