Training in progress, step 2500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ebef077dc2a1548b4bd8ff3afaf334f691d35d8c1ef2e4977fb2cc7f293113
+oid sha256:bdf000e9e8c39da1dc0a0bcf06f238b37c4e0f0876cd29099f16087ea89286c2
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863f89d341fbd901e8100eaec6ef85a33a2909b18973183f0a03f7287ec27744
+oid sha256:55606d8da721a91e0821501004b025d6ea9c30206ee13d7e2e597dd64a37c536
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f9cb9d6e1ba87b5eeb02e889a5436d8e663c21608f949834bc4c838fca998f
+oid sha256:eae0fa9442d73f2cd98224b9c1fc91ed082aafa5f1d19bbfa57bc0db06de5093
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:492277267f87cbfa8c3f646f1bbcb1be0a18bb655f8e2e8d4b304f797cb4be4a
+oid sha256:90d85d749cc7fe25c024c6278fe3a3756946cc0a4f59d66bc07b1689fdb74e7b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6625103906899419,
+  "epoch": 2.0781379883624274,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "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
     },
     {
@@ -43,6 +43,21 @@
       "learning_rate": 8.916597395400388e-06,
       "loss": 0.3557,
       "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.29697325825691223,
+      "eval_runtime": 34.4842,
+      "eval_samples_per_second": 14.325,
+      "eval_steps_per_second": 1.798,
+      "step": 2406
+    },
+    {
+      "epoch": 2.0781379883624274,
+      "grad_norm": 28119.84375,
+      "learning_rate": 6.145746744250486e-06,
+      "loss": 0.3445,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
@@ -62,7 +77,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9742717291069440.0,
+  "total_flos": 1.217793989541888e+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