Training in progress, step 750, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c85ccd2d8f7fed25fa90e9cbc1809dc3678b16093649b77b9d0294a5d7521fc
+oid sha256:77f5c4bb61551feebcac9c0da6b303e325c053a4fd69c4f093ef1a5cdd526908
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12713859786a4771f1f53038cc506f8a2af69a22a568239e40fab40d3c479ed8
+oid sha256:7fb0635ad14c320dca7f97c2d3d371f8ca3e9678b324e2f75556c62bccc96c5c
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2616293446c1c2f2c6b0e270c4bb50dd25782b075145433b30550e3bb3a1845c
+oid sha256:30b57ec052aeaf035e39cd5057ce6977dfdadd2be87b9e8aaa1d9afd55d2f8e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da0b9a1e2fa3da24e9af8b74787d70ff4c95d9bc9b74eeab135df0350a00b462
+oid sha256:e8974fc0327a603be8a90ee235d3ef81c4ee4af2818c873bdeb9bfb38f108e1a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7165840268135071,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 19.565217391304348,
+  "epoch": 32.608695652173914,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -346,6 +346,232 @@
       "eval_samples_per_second": 24.844,
       "eval_steps_per_second": 24.844,
       "step": 450
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.1217708587646484,
+      "learning_rate": 2.9996147467351856e-05,
+      "loss": 0.5145,
+      "step": 460
+    },
+    {
+      "epoch": 20.434782608695652,
+      "grad_norm": 1.275344967842102,
+      "learning_rate": 2.9995930474939773e-05,
+      "loss": 0.4782,
+      "step": 470
+    },
+    {
+      "epoch": 20.869565217391305,
+      "grad_norm": 1.4735126495361328,
+      "learning_rate": 2.9995707538619975e-05,
+      "loss": 0.5707,
+      "step": 480
+    },
+    {
+      "epoch": 21.304347826086957,
+      "grad_norm": 1.32221257686615,
+      "learning_rate": 2.9995478658480822e-05,
+      "loss": 0.5165,
+      "step": 490
+    },
+    {
+      "epoch": 21.73913043478261,
+      "grad_norm": 1.2421287298202515,
+      "learning_rate": 2.9995243834613043e-05,
+      "loss": 0.5205,
+      "step": 500
+    },
+    {
+      "epoch": 22.17391304347826,
+      "grad_norm": 1.7849466800689697,
+      "learning_rate": 2.9995003067109707e-05,
+      "loss": 0.4834,
+      "step": 510
+    },
+    {
+      "epoch": 22.608695652173914,
+      "grad_norm": 1.5369889736175537,
+      "learning_rate": 2.9994756356066246e-05,
+      "loss": 0.5613,
+      "step": 520
+    },
+    {
+      "epoch": 23.043478260869566,
+      "grad_norm": 1.7313120365142822,
+      "learning_rate": 2.999450370158046e-05,
+      "loss": 0.4928,
+      "step": 530
+    },
+    {
+      "epoch": 23.47826086956522,
+      "grad_norm": 1.3083937168121338,
+      "learning_rate": 2.9994245103752478e-05,
+      "loss": 0.4382,
+      "step": 540
+    },
+    {
+      "epoch": 23.91304347826087,
+      "grad_norm": 1.233344554901123,
+      "learning_rate": 2.999398056268481e-05,
+      "loss": 0.5264,
+      "step": 550
+    },
+    {
+      "epoch": 24.347826086956523,
+      "grad_norm": 1.4090428352355957,
+      "learning_rate": 2.9993710078482306e-05,
+      "loss": 0.5206,
+      "step": 560
+    },
+    {
+      "epoch": 24.782608695652176,
+      "grad_norm": 0.9520849585533142,
+      "learning_rate": 2.9993433651252185e-05,
+      "loss": 0.4429,
+      "step": 570
+    },
+    {
+      "epoch": 25.217391304347824,
+      "grad_norm": 1.7179316282272339,
+      "learning_rate": 2.9993151281104006e-05,
+      "loss": 0.5329,
+      "step": 580
+    },
+    {
+      "epoch": 25.652173913043477,
+      "grad_norm": 1.1341142654418945,
+      "learning_rate": 2.9992862968149695e-05,
+      "loss": 0.4735,
+      "step": 590
+    },
+    {
+      "epoch": 26.08695652173913,
+      "grad_norm": 1.1748226881027222,
+      "learning_rate": 2.9992568712503533e-05,
+      "loss": 0.4608,
+      "step": 600
+    },
+    {
+      "epoch": 26.08695652173913,
+      "eval_loss": 0.7199766039848328,
+      "eval_runtime": 0.5422,
+      "eval_samples_per_second": 18.442,
+      "eval_steps_per_second": 18.442,
+      "step": 600
+    },
+    {
+      "epoch": 26.52173913043478,
+      "grad_norm": 1.0799683332443237,
+      "learning_rate": 2.9992268514282142e-05,
+      "loss": 0.5121,
+      "step": 610
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 1.3288029432296753,
+      "learning_rate": 2.999196237360452e-05,
+      "loss": 0.4316,
+      "step": 620
+    },
+    {
+      "epoch": 27.391304347826086,
+      "grad_norm": 1.1912176609039307,
+      "learning_rate": 2.9991650290592016e-05,
+      "loss": 0.4763,
+      "step": 630
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 1.3694884777069092,
+      "learning_rate": 2.999133226536832e-05,
+      "loss": 0.5015,
+      "step": 640
+    },
+    {
+      "epoch": 28.26086956521739,
+      "grad_norm": 1.3749481439590454,
+      "learning_rate": 2.9991008298059493e-05,
+      "loss": 0.4116,
+      "step": 650
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 1.5401527881622314,
+      "learning_rate": 2.9990678388793944e-05,
+      "loss": 0.5073,
+      "step": 660
+    },
+    {
+      "epoch": 29.130434782608695,
+      "grad_norm": 1.2782667875289917,
+      "learning_rate": 2.999034253770244e-05,
+      "loss": 0.4355,
+      "step": 670
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 1.0564625263214111,
+      "learning_rate": 2.9990000744918097e-05,
+      "loss": 0.4714,
+      "step": 680
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 2.43731427192688,
+      "learning_rate": 2.9989653010576392e-05,
+      "loss": 0.4153,
+      "step": 690
+    },
+    {
+      "epoch": 30.434782608695652,
+      "grad_norm": 1.2880218029022217,
+      "learning_rate": 2.9989299334815158e-05,
+      "loss": 0.4778,
+      "step": 700
+    },
+    {
+      "epoch": 30.869565217391305,
+      "grad_norm": 1.5784273147583008,
+      "learning_rate": 2.9988939717774578e-05,
+      "loss": 0.4135,
+      "step": 710
+    },
+    {
+      "epoch": 31.304347826086957,
+      "grad_norm": 0.8963285684585571,
+      "learning_rate": 2.9988574159597194e-05,
+      "loss": 0.4262,
+      "step": 720
+    },
+    {
+      "epoch": 31.73913043478261,
+      "grad_norm": 1.6010137796401978,
+      "learning_rate": 2.9988202660427907e-05,
+      "loss": 0.4843,
+      "step": 730
+    },
+    {
+      "epoch": 32.17391304347826,
+      "grad_norm": 1.1745761632919312,
+      "learning_rate": 2.9987825220413958e-05,
+      "loss": 0.4404,
+      "step": 740
+    },
+    {
+      "epoch": 32.608695652173914,
+      "grad_norm": 1.7309991121292114,
+      "learning_rate": 2.998744183970496e-05,
+      "loss": 0.4753,
+      "step": 750
+    },
+    {
+      "epoch": 32.608695652173914,
+      "eval_loss": 0.7314043045043945,
+      "eval_runtime": 0.4014,
+      "eval_samples_per_second": 24.911,
+      "eval_steps_per_second": 24.911,
+      "step": 750
     }
   ],
   "logging_steps": 10,
@@ -365,7 +591,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1591800814075904e+16,
+  "total_flos": 1.9231766387195904e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null