Training in progress, step 33500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47bc7f7088c31739e0ace84393ace249d63ff0dd0e8a1b98132d7b7dc588abef
+oid sha256:20ce46d2a2c82e633563d7d6bea7e0e03fc9c69522a60a684e11b7f317bcab34
 size 497774208

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b990330a857e00a5ce2f41d4a9ca84ef42d6a864ef37f94dd9c5e8eb78e17be
+oid sha256:ab89966ee8db1907e13da1e6629a7fd5aaa31aa7d82a3778a7807a3ca7bcdba0
 size 995642298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a241274c2d956a7ab88f9479cb5a472ed3ed1ad8a6c865470569a83abed4ca
+oid sha256:cf03505c0b77875f4136a7186b108fab66ea11065326ebf8ddcbd18923367278
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc874f14ee9621b207a47560264a39873b8014c0caefdc0ea9a68bdcf1f837c6
+oid sha256:03d6bdda27653a3a7898d264569b7ec48737b8064569d40262a6265e2c91562b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.971090670170828,
+  "epoch": 2.0009556803249313,
   "eval_steps": 500,
-  "global_step": 33000,
+  "global_step": 33500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,21 @@
       "eval_samples_per_second": 210.485,
       "eval_steps_per_second": 6.578,
       "step": 16742
+    },
+    {
+      "epoch": 1.9998805399593835,
+      "grad_norm": 1.373618721961975,
+      "learning_rate": 6.673037868832876e-06,
+      "loss": 3.8963,
+      "step": 33482
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.7781829833984375,
+      "eval_runtime": 281.2653,
+      "eval_samples_per_second": 210.701,
+      "eval_steps_per_second": 6.585,
+      "step": 33484
     }
   ],
   "logging_steps": 16741,
@@ -41,7 +56,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.8980312571904e+16,
+  "total_flos": 7.0024696823808e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null