Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf000e9e8c39da1dc0a0bcf06f238b37c4e0f0876cd29099f16087ea89286c2
+oid sha256:37184411fa01962b5584221d26074bdbf2b5678f102eebcb9fa085dc516b3674
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55606d8da721a91e0821501004b025d6ea9c30206ee13d7e2e597dd64a37c536
+oid sha256:d3391ca1d7764e3f41bc90049a7517305a4c92ccba94cb3280bde0c5a073d555
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eae0fa9442d73f2cd98224b9c1fc91ed082aafa5f1d19bbfa57bc0db06de5093
+oid sha256:3e534ee577cadd47101335cf1dc7ec5ae8925403b57ec908dcb719cf321ad6fa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90d85d749cc7fe25c024c6278fe3a3756946cc0a4f59d66bc07b1689fdb74e7b
+oid sha256:dca5a6988b5cff43e20e9bfaf125955c76edea5f09d12086d239e8c25fc37435
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0781379883624274,
+  "epoch": 2.493765586034913,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25,9 +25,9 @@
     {
       "epoch": 1.0,
       "eval_loss": 0.31241247057914734,
-      "eval_runtime": 36.3382,
-      "eval_samples_per_second": 13.595,
-      "eval_steps_per_second": 1.706,
+      "eval_runtime": 34.4517,
+      "eval_samples_per_second": 14.339,
+      "eval_steps_per_second": 1.8,
       "step": 1203
     },
     {
@@ -47,9 +47,9 @@
     {
       "epoch": 2.0,
       "eval_loss": 0.29697325825691223,
-      "eval_runtime": 36.2867,
-      "eval_samples_per_second": 13.614,
-      "eval_steps_per_second": 1.709,
+      "eval_runtime": 34.4842,
+      "eval_samples_per_second": 14.325,
+      "eval_steps_per_second": 1.798,
       "step": 2406
     },
     {
@@ -58,6 +58,13 @@
       "learning_rate": 6.145746744250486e-06,
       "loss": 0.3445,
       "step": 2500
+    },
+    {
+      "epoch": 2.493765586034913,
+      "grad_norm": 39468.3359375,
+      "learning_rate": 3.374896093100582e-06,
+      "loss": 0.3423,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -77,7 +84,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.217793989541888e+16,
+  "total_flos": 1.461377145765888e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c6902ddb0f6942cea8435dc8faed1ce85b2ddfb716f52e329197e58e67bcbec
+oid sha256:2a0eee04499ccdf8d802fc08cc9a27a978fedc8125cdd17ba42f942e0fa36ff2
 size 5368