Training in progress, step 160, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e740ffbbdfadc8bf234148d76ac0ed60381ced5dfbd658d49b9b798316874f7
+oid sha256:e64380cdeda885e3f553ba7fcb7d6ff8d4418829bf89dcf425b6fd78879cb6fb
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a2f1ddbd3db8cdaf06e7423793917493328e0a8cb44ed0e8d28035287cca420
+oid sha256:936bdc7085d91b4f1f2e0ce6a7cca97f7dc1249ed3b5140e8b9cc64a5bf4c88c
 size 735625370

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fc92af0f7629ac7a872f96d896483407615467dfa6d229c0bce0291923d54d2
+oid sha256:dd022fe9a852268c9938ee7ec723da82135f24b7b81519ddd3fa10bc5532abc3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c01fd1d8f82dc5b8d4b0f55c2ab8164cf309fea692e13308378886e8a4c284e0
+oid sha256:09d5b7286e18d17d32a5d7eefb437a53934b7aa905d2edb287b66e963a806d73
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce04f332c8a6301f4e0e3529f0f24d4ecc77280aa968eb8788a8dbde321f8780
+oid sha256:1a5060e223b8d6548a605200749266caae1209b0c1599f9a178131935fc077fa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cdd0d6703b8a4673eb5f0f1700b967c31563a5843fa11ee1bc8ac7bd3c25784
+oid sha256:bddfa187dc754906a5ece5a1101d66a597575ede390926eb4c7dae90e1450ce8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ad7d13c349dc6d2db1696e8cfa744a9b690a7740ecbd387461ee1d69ba8e9e
+oid sha256:2ef6aff989d644b47d122f2b587320b4b7487648735e57cddc52e97c1261de49
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.5,
+  "epoch": 20.0,
   "eval_steps": 20,
-  "global_step": 140,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,28 @@
       "eval_samples_per_second": 281.135,
       "eval_steps_per_second": 3.184,
       "step": 140
+    },
+    {
+      "epoch": 18.75,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 2.009,
+      "step": 150
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 2.0108,
+      "step": 160
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 2.0700676441192627,
+      "eval_runtime": 4.9064,
+      "eval_samples_per_second": 305.926,
+      "eval_steps_per_second": 3.465,
+      "step": 160
     }
   ],
   "logging_steps": 10,
@@ -188,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.979713717252915e+16,
+  "total_flos": 5.691101391146189e+16,
   "train_batch_size": 23,
   "trial_name": null,
   "trial_params": null