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:ac57e1708ae96d8a754b239e7a24dcbc95bfc8819c0cb304a4d5463df3d9f1e9
+oid sha256:0df78e692defadb84568edca305adffd7b9529abb8c9b3b91b1f9ea47d1a21f5
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0891e5d321b6e79898a6903d5e687dcf1984e09c5c630de43f20284ed62709e4
+oid sha256:de73ad5b03551d4d5684644b29f657d82e4cbc9d8443f9f124c546c260bed71f
 size 1054135994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3db7d037567f9907c679104cc622f6046bdf2f33143ca3a29365b2fa4072ce8
+oid sha256:4ca9142fcbd976a2b9880762578e5776f18d9cad34016a627060f41ab78ec47d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6a671e7a99b2031fac9c2aa2961bdd45065beec21991b71e40498a79f90a5d
+oid sha256:a615c97559beeeb761a113ec8f76cd5a30f01f1e374145e869eb8521acc6eaa9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7168284058570862,
   "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 26.08695652173913,
+  "epoch": 32.608695652173914,
   "eval_steps": 150,
-  "global_step": 600,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -587,6 +587,151 @@
       "eval_samples_per_second": 25.02,
       "eval_steps_per_second": 25.02,
       "step": 600
+    },
+    {
+      "epoch": 26.52173913043478,
+      "grad_norm": 1.0763235092163086,
+      "learning_rate": 2.180702116052084e-06,
+      "loss": 0.5123,
+      "step": 610
+    },
+    {
+      "epoch": 26.956521739130434,
+      "grad_norm": 1.3133342266082764,
+      "learning_rate": 4.361404232104168e-06,
+      "loss": 0.4305,
+      "step": 620
+    },
+    {
+      "epoch": 27.391304347826086,
+      "grad_norm": 1.196905493736267,
+      "learning_rate": 6.5421063481562515e-06,
+      "loss": 0.483,
+      "step": 630
+    },
+    {
+      "epoch": 27.82608695652174,
+      "grad_norm": 1.3611772060394287,
+      "learning_rate": 8.722808464208335e-06,
+      "loss": 0.5073,
+      "step": 640
+    },
+    {
+      "epoch": 28.26086956521739,
+      "grad_norm": 1.3929076194763184,
+      "learning_rate": 1.0903510580260419e-05,
+      "loss": 0.4196,
+      "step": 650
+    },
+    {
+      "epoch": 28.695652173913043,
+      "grad_norm": 1.5381708145141602,
+      "learning_rate": 1.3084212696312503e-05,
+      "loss": 0.5196,
+      "step": 660
+    },
+    {
+      "epoch": 29.130434782608695,
+      "grad_norm": 1.2946442365646362,
+      "learning_rate": 1.5264914812364585e-05,
+      "loss": 0.4475,
+      "step": 670
+    },
+    {
+      "epoch": 29.565217391304348,
+      "grad_norm": 1.0526130199432373,
+      "learning_rate": 1.744561692841667e-05,
+      "loss": 0.4891,
+      "step": 680
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 2.4151837825775146,
+      "learning_rate": 1.9626319044468756e-05,
+      "loss": 0.4298,
+      "step": 690
+    },
+    {
+      "epoch": 30.434782608695652,
+      "grad_norm": 1.2968952655792236,
+      "learning_rate": 2.1807021160520838e-05,
+      "loss": 0.4978,
+      "step": 700
+    },
+    {
+      "epoch": 30.869565217391305,
+      "grad_norm": 1.5897126197814941,
+      "learning_rate": 2.1807018999619227e-05,
+      "loss": 0.4322,
+      "step": 710
+    },
+    {
+      "epoch": 31.304347826086957,
+      "grad_norm": 0.903261661529541,
+      "learning_rate": 2.180701251691525e-05,
+      "loss": 0.4453,
+      "step": 720
+    },
+    {
+      "epoch": 31.73913043478261,
+      "grad_norm": 1.5805950164794922,
+      "learning_rate": 2.180700171241147e-05,
+      "loss": 0.5081,
+      "step": 730
+    },
+    {
+      "epoch": 32.17391304347826,
+      "grad_norm": 1.1670500040054321,
+      "learning_rate": 2.1806986586112178e-05,
+      "loss": 0.4616,
+      "step": 740
+    },
+    {
+      "epoch": 32.608695652173914,
+      "grad_norm": 1.7125110626220703,
+      "learning_rate": 2.1806967138023368e-05,
+      "loss": 0.5002,
+      "step": 750
+    },
+    {
+      "epoch": 32.608695652173914,
+      "eval_loss": 0.7243400812149048,
+      "eval_runtime": 0.5459,
+      "eval_samples_per_second": 18.32,
+      "eval_steps_per_second": 18.32,
+      "step": 750
+    },
+    {
+      "epoch": 32.608695652173914,
+      "eval_loss": 0.8616224527359009,
+      "eval_runtime": 0.4034,
+      "eval_samples_per_second": 24.789,
+      "eval_steps_per_second": 24.789,
+      "step": 750
+    },
+    {
+      "epoch": 32.608695652173914,
+      "eval_loss": 0.7243400812149048,
+      "eval_runtime": 0.4067,
+      "eval_samples_per_second": 24.59,
+      "eval_steps_per_second": 24.59,
+      "step": 750
+    },
+    {
+      "epoch": 32.608695652173914,
+      "eval_loss": 0.7293505668640137,
+      "eval_runtime": 0.4035,
+      "eval_samples_per_second": 24.782,
+      "eval_steps_per_second": 24.782,
+      "step": 750
+    },
+    {
+      "epoch": 32.608695652173914,
+      "eval_loss": 0.8606684803962708,
+      "eval_runtime": 0.4152,
+      "eval_samples_per_second": 24.083,
+      "eval_steps_per_second": 24.083,
+      "step": 750
     }
   ],
   "logging_steps": 10,
@@ -606,7 +751,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5363065839583232e+16,
+  "total_flos": 1.9231766387195904e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null