Training in progress, step 7700, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:161c63173b11d278454f76e096130af0ea2e197a6c275cfa04ebf9e466be9c63
+oid sha256:d7035fed27b87e53ef5459140a353c4757291550688e801bd1a0749612505385
 size 4978139416

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a9ff8292338e7bef2a92a787972e8c312dc811b53b5c8f487afd672c88d3a2
+oid sha256:9308fa164b0a0e31eab5e62c35936cfc1077227e00e83d664edb27c65c44c8c3
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:effe03ee93685e827f87da010b75e451bf179e605eefd74137f038217c39e61d
+oid sha256:e3b9a39df796a8f78147f1c34914a1acc6755648902c94af056852922118959f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:070566d04626f1a1199d33a844fca7649870a2f1dc42c459cb3ffc8f9fae256c
+oid sha256:a122898eab5e64ec9f7a327b27560bc6d150e37aff057ddeb4ae81aad25785fb
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baab263627df2d83ddbd983f1bff3bce2c66dd722c961b1e37caa6a98898e772
+oid sha256:e86686b461d0cb83b0c1cfa82a7f2c4a32e887c3772a7cfc60e249f37abcb8d0
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.157230056830141,
+  "epoch": 3.2414228583456115,
   "eval_steps": 100,
-  "global_step": 7500,
+  "global_step": 7700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1207,6 +1207,38 @@
       "eval_samples_per_second": 25.45,
       "eval_steps_per_second": 3.182,
       "step": 7500
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 2.642812967300415,
+      "learning_rate": 4.4988692579505305e-05,
+      "loss": 3.1774,
+      "step": 7600
+    },
+    {
+      "epoch": 3.2,
+      "eval_cer": 0.5154300770403973,
+      "eval_loss": 2.36077618598938,
+      "eval_runtime": 375.4381,
+      "eval_samples_per_second": 25.245,
+      "eval_steps_per_second": 3.156,
+      "step": 7600
+    },
+    {
+      "epoch": 3.24,
+      "grad_norm": 4.245635509490967,
+      "learning_rate": 4.491802120141343e-05,
+      "loss": 1.7844,
+      "step": 7700
+    },
+    {
+      "epoch": 3.24,
+      "eval_cer": 0.5169381330413358,
+      "eval_loss": 2.6845099925994873,
+      "eval_runtime": 355.3776,
+      "eval_samples_per_second": 26.67,
+      "eval_steps_per_second": 3.334,
+      "step": 7700
     }
   ],
   "logging_steps": 100,
@@ -1214,7 +1246,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 8.232776432614433e+19,
+  "total_flos": 8.450652260775636e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null