Training in progress, step 180, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64380cdeda885e3f553ba7fcb7d6ff8d4418829bf89dcf425b6fd78879cb6fb
+oid sha256:2f2be77f4046d57162a2a1634e71c05173859bf5557783dfa12ea6e9468e051d
 size 723674912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:936bdc7085d91b4f1f2e0ce6a7cca97f7dc1249ed3b5140e8b9cc64a5bf4c88c
+oid sha256:19b0ef4a865592b1c1398462392fee5da43bb5d95cb04ee8282d992c017e215b
 size 735625370

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd022fe9a852268c9938ee7ec723da82135f24b7b81519ddd3fa10bc5532abc3
+oid sha256:5179acd504f9caefc428bad8368a9feed783597605227f04c17ed5843af96dfc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d5b7286e18d17d32a5d7eefb437a53934b7aa905d2edb287b66e963a806d73
+oid sha256:6d57da5f6b8845015897fecc79abf7ca6507809cfcf86ed0e80e8a671f77e231
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a5060e223b8d6548a605200749266caae1209b0c1599f9a178131935fc077fa
+oid sha256:c2f8edafee3984ce0824458e1123790dbcab896cab979f7abfa8851dd911b81b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddfa187dc754906a5ece5a1101d66a597575ede390926eb4c7dae90e1450ce8
+oid sha256:982ef26a1a303041dac26c15f97f86f53c622fcb36d57d2226e4c72f425873e3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef6aff989d644b47d122f2b587320b4b7487648735e57cddc52e97c1261de49
+oid sha256:723432e9081dffbc4dea9b11807f9120cba5ae794b58bf13637161ca198c867f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.0,
+  "epoch": 22.5,
   "eval_steps": 20,
-  "global_step": 160,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,6 +191,28 @@
       "eval_samples_per_second": 305.926,
       "eval_steps_per_second": 3.465,
       "step": 160
+    },
+    {
+      "epoch": 21.25,
+      "grad_norm": 0.12890625,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 2.0101,
+      "step": 170
+    },
+    {
+      "epoch": 22.5,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 2.0169,
+      "step": 180
+    },
+    {
+      "epoch": 22.5,
+      "eval_loss": 2.0683298110961914,
+      "eval_runtime": 4.9925,
+      "eval_samples_per_second": 300.65,
+      "eval_steps_per_second": 3.405,
+      "step": 180
     }
   ],
   "logging_steps": 10,
@@ -210,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.691101391146189e+16,
+  "total_flos": 6.402489065039462e+16,
   "train_batch_size": 23,
   "trial_name": null,
   "trial_params": null