Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37184411fa01962b5584221d26074bdbf2b5678f102eebcb9fa085dc516b3674
+oid sha256:094107617da532e22519fe4608ca4056af6c59a146e4a45bc22999b23602cc46
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3391ca1d7764e3f41bc90049a7517305a4c92ccba94cb3280bde0c5a073d555
+oid sha256:4cfa4a9ca109470ddd20ec8902f9af9f6b51d5513b3a6da9829b572fff788b25
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e534ee577cadd47101335cf1dc7ec5ae8925403b57ec908dcb719cf321ad6fa
+oid sha256:a337492fad45951266c5e5a5dbf843ade9e5a664f8b6b5528acef9d967d34304
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca5a6988b5cff43e20e9bfaf125955c76edea5f09d12086d239e8c25fc37435
+oid sha256:90f5277e82cda3e7666fd66172ee30fc29ff7229307a369870bf39d52fb81a1b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.493765586034913,
+  "epoch": 2.9093931837073983,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "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
     },
     {
@@ -65,6 +65,13 @@
       "learning_rate": 3.374896093100582e-06,
       "loss": 0.3423,
       "step": 3000
+    },
+    {
+      "epoch": 2.9093931837073983,
+      "grad_norm": 24834.95703125,
+      "learning_rate": 6.040454419506789e-07,
+      "loss": 0.3347,
+      "step": 3500
     }
   ],
   "logging_steps": 500,
@@ -84,7 +91,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.461377145765888e+16,
+  "total_flos": 1.704960301989888e+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