Training in progress, step 52100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17ce21e8ae5702d27ee13ccfe698b9519f9191b1c9caff5644e90a5bb5c25d9
+oid sha256:1a160b4e175184a931e59f6e0e078e62570ed360295c0fe949679c0e727f5eea
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a17a30230270a34456dc1ba21c1ead1f7aa39a64e33c3faa6efbf4b18d99cb5f
+oid sha256:362756a97ee496019c94541204764d63f92ffafe15a248f8434077d701710266
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dde4f5875f81547bdef6920d87fd6a84a4cb8fc9273b6febfeb843f0442e8a66
+oid sha256:1af97be2351717a648f3ed627e3a5da1be85bd899722f95b48558a241429b0c7
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4a50bec4064f680866f4e14ae49d80472966a4af2720d1f7bf3be3feeaef2f0
-size 14503
+oid sha256:d5d06a7cdc46e4a528aeb9bb66bf58e9c1dcb3edea8772b30cb812147232c3dd
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5317f1b977bf0c5dd9e58209a5a3433f99d034b727592196ceb70ddd3bde3377
+oid sha256:ff5d1aa72f6daaa98e8456979d83438a50fc20467c64d414fc9148e60e30d500
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.848031993264577,
+  "epoch": 21.932224794780048,
   "eval_steps": 100,
-  "global_step": 51900,
+  "global_step": 52100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8311,6 +8311,38 @@
       "eval_samples_per_second": 24.209,
       "eval_steps_per_second": 3.027,
       "step": 51900
+    },
+    {
+      "epoch": 21.89,
+      "grad_norm": 1.794063687324524,
+      "learning_rate": 1.3621201413427561e-05,
+      "loss": 0.3608,
+      "step": 52000
+    },
+    {
+      "epoch": 21.89,
+      "eval_cer": 0.3389410856047867,
+      "eval_loss": 2.29063081741333,
+      "eval_runtime": 429.6088,
+      "eval_samples_per_second": 22.062,
+      "eval_steps_per_second": 2.758,
+      "step": 52000
+    },
+    {
+      "epoch": 21.93,
+      "grad_norm": 5.02766227722168,
+      "learning_rate": 1.3550530035335691e-05,
+      "loss": 0.3614,
+      "step": 52100
+    },
+    {
+      "epoch": 21.93,
+      "eval_cer": 0.33830315591881427,
+      "eval_loss": 2.339839458465576,
+      "eval_runtime": 388.2936,
+      "eval_samples_per_second": 24.409,
+      "eval_steps_per_second": 3.052,
+      "step": 52100
     }
   ],
   "logging_steps": 100,
@@ -8318,7 +8350,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.6872995302509294e+20,
+  "total_flos": 5.7089616015663346e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null