Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809f1a1aeaef919d82f3f22c05e487fbc5fc7e139d3d58b4d52c8e126c7986e7
+oid sha256:3be4767b437fbc4c7c39707c48fa92943e3ad141030625b52bf0098f03bf586c
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9556b210fcb352112c2a38a6d47a9d83bba4ecf5c0cd6e72b31cd7982e53cb6a
+oid sha256:3818ce85ef6d6e0e908a42d47e066e971c6db7a774a6799318dece03583582f7
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a8f0c85caf6dd2f34d726a24b370bad056914b0890ab902dc89abc74fd551d9
+oid sha256:eb25411738bca161ae6c2a26729b40a97bf70b0a9dd21a74fbe66345edda273f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e04a982a3fa698ff22d0e2f7f2de0d9d80aaf95f3178aef44eaed617903f5e
+oid sha256:4002ec401b29865a446966ea49bed4e5a8d21c249b3ecaee3b7efb93937ff037
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8703241895261846,
+  "epoch": 2.0781379883624274,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -78,6 +78,21 @@
       "learning_rate": 1.2522028262676643e-05,
       "loss": 0.3677,
       "step": 4500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3049054443836212,
+      "eval_runtime": 26.7561,
+      "eval_samples_per_second": 18.463,
+      "eval_steps_per_second": 4.634,
+      "step": 4812
+    },
+    {
+      "epoch": 2.0781379883624274,
+      "grad_norm": 0.5839773416519165,
+      "learning_rate": 1.1690773067331672e-05,
+      "loss": 0.3488,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -97,7 +112,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.096063307218944e+16,
+  "total_flos": 1.217793989541888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null