Training in progress, step 55100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b42d92e7c51f1a2870be09d4104f085519061349b0e05bf31d84ecb29c91a0
+oid sha256:e8c48bb3d612c40a450aa730d13e87c4b64a6c34e5b31e7b8fe6c269f23b421c
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2060a25884097cc91d28479f3135ddc68617e2ec3619ef4b9a089dcbc3bc7227
+oid sha256:f1069f6193c7916eb469ce04a7fa8c02754c89e947e59faab71008137e15e1b8
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8800fcea3d51fb165ceaefcf56d57ec181e51cad449c080d3d9f463d1c8fc031
+oid sha256:bc3024dcfeaef3e6a6bcda461b928f14a072e6bddfed080d72f79930e36aa00b
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129253610a862a0de2bc5a45173af6ab111f2fcf06d9605e1bf74b6ddc0b72a4
+oid sha256:a74bc8c11a5b138c20c6a3a72f1fc0760ad94bd8169c2089dd7b02f38fcd2093
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe11f129e8f022248014946b3a4b6751b41bfbc796ab56504330e3f243c7496d
+oid sha256:0b611b98dbecb53ef90f98b1e408d8bea073963dab97c75432c6a94c95519856
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.110924015996634,
+  "epoch": 23.1951168175121,
   "eval_steps": 100,
-  "global_step": 54900,
+  "global_step": 55100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8791,6 +8791,38 @@
       "eval_samples_per_second": 23.669,
       "eval_steps_per_second": 2.959,
       "step": 54900
+    },
+    {
+      "epoch": 23.15,
+      "grad_norm": 2.888965606689453,
+      "learning_rate": 1.1501060070671379e-05,
+      "loss": 0.2584,
+      "step": 55000
+    },
+    {
+      "epoch": 23.15,
+      "eval_cer": 0.3347419928825623,
+      "eval_loss": 2.6486945152282715,
+      "eval_runtime": 425.0006,
+      "eval_samples_per_second": 22.301,
+      "eval_steps_per_second": 2.788,
+      "step": 55000
+    },
+    {
+      "epoch": 23.2,
+      "grad_norm": 1.428572654724121,
+      "learning_rate": 1.1430388692579507e-05,
+      "loss": 0.2592,
+      "step": 55100
+    },
+    {
+      "epoch": 23.2,
+      "eval_cer": 0.33205340033631847,
+      "eval_loss": 2.5768284797668457,
+      "eval_runtime": 410.5876,
+      "eval_samples_per_second": 23.084,
+      "eval_steps_per_second": 2.886,
+      "step": 55100
     }
   ],
   "logging_steps": 100,
@@ -8798,7 +8830,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.016263856010292e+20,
+  "total_flos": 6.038294629213688e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null