Training in progress, step 55300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c48bb3d612c40a450aa730d13e87c4b64a6c34e5b31e7b8fe6c269f23b421c
+oid sha256:2f38a0345160eafc7a2bff16ecb3b832e4bed866ef2900dd0baf0b2f9d5d0eb0
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1069f6193c7916eb469ce04a7fa8c02754c89e947e59faab71008137e15e1b8
+oid sha256:c019cff8f9be930c3fc0d37425de55b6c57a313e24c2bb3dc34b7f2486efdfbe
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc3024dcfeaef3e6a6bcda461b928f14a072e6bddfed080d72f79930e36aa00b
+oid sha256:e7e4a457495ababe0eb08547a34b3470fd36b5930b98f33eb20ef364970e0c83
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a74bc8c11a5b138c20c6a3a72f1fc0760ad94bd8169c2089dd7b02f38fcd2093
+oid sha256:2f106411af63d8226ffb8f49ed683b71c1bcf027a8df03274802b22a6f8fda8f
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b611b98dbecb53ef90f98b1e408d8bea073963dab97c75432c6a94c95519856
+oid sha256:f5aa0f94c39f4406774a86e68d3997d19d329feb34dcd618fc1dc95189d45b9f
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.1951168175121,
+  "epoch": 23.279309619027572,
   "eval_steps": 100,
-  "global_step": 55100,
+  "global_step": 55300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8823,6 +8823,38 @@
       "eval_samples_per_second": 23.084,
       "eval_steps_per_second": 2.886,
       "step": 55100
+    },
+    {
+      "epoch": 23.24,
+      "grad_norm": 1.8620479106903076,
+      "learning_rate": 1.1359717314487633e-05,
+      "loss": 0.2719,
+      "step": 55200
+    },
+    {
+      "epoch": 23.24,
+      "eval_cer": 0.3328697548003598,
+      "eval_loss": 3.229948043823242,
+      "eval_runtime": 423.4357,
+      "eval_samples_per_second": 22.384,
+      "eval_steps_per_second": 2.799,
+      "step": 55200
+    },
+    {
+      "epoch": 23.28,
+      "grad_norm": 1.727643609046936,
+      "learning_rate": 1.128904593639576e-05,
+      "loss": 0.2628,
+      "step": 55300
+    },
+    {
+      "epoch": 23.28,
+      "eval_cer": 0.33284286887489734,
+      "eval_loss": 2.7340400218963623,
+      "eval_runtime": 394.6323,
+      "eval_samples_per_second": 24.017,
+      "eval_steps_per_second": 3.003,
+      "step": 55300
     }
   ],
   "logging_steps": 100,
@@ -8830,7 +8862,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.038294629213688e+20,
+  "total_flos": 6.060174194718131e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null