Training in progress, step 53100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38856c5de97012a6bbddb265016f45f787498a984601f0d5f3432a3dd21d3b08
+oid sha256:633d033e0feaf0bf4322349a4c2c21f2d9cac42e95486f6edc465534c3e94d22
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f7daf3b2a573c62d3f1e255b201aea1d79bd60a6b957765f25b4a1f67c0e2c
+oid sha256:f396277c9eced74d208c1a0a4c9b4fc9e72369b2bd0928d8da6ef34b6dce864c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2396e720c3c604a71d73a5cfdd04c82f1b06481005dcbfbc4e609d17cd8dc459
+oid sha256:ba3188b916823703b8f1761ccc19c30690dec44a4be3f89bd70b12f8dabc77e8
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f4b3f4fdec252a3fb47435e761c164da7b4d341aa24a2cc22079721594d2e4
-size 14503
+oid sha256:db752bd188273ee158b3e145391265b4293483bb7f634f864afe75f2821bf9a1
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07280b3905388184ad6f524c0c254f08ba9be422c3d6452b00f45b36031ca6fa
+oid sha256:ed67a7cf08915cbe3b030bce4e92226fc3b82cf21f5936d3ab71491cd41ba3f4
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.268996000841927,
+  "epoch": 22.353188802357398,
   "eval_steps": 100,
-  "global_step": 52900,
+  "global_step": 53100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8471,6 +8471,38 @@
       "eval_samples_per_second": 24.376,
       "eval_steps_per_second": 3.048,
       "step": 52900
+    },
+    {
+      "epoch": 22.31,
+      "grad_norm": 2.294267177581787,
+      "learning_rate": 1.2914487632508834e-05,
+      "loss": 0.3038,
+      "step": 53000
+    },
+    {
+      "epoch": 22.31,
+      "eval_cer": 0.3415172460990966,
+      "eval_loss": 2.524266004562378,
+      "eval_runtime": 399.4446,
+      "eval_samples_per_second": 23.728,
+      "eval_steps_per_second": 2.967,
+      "step": 53000
+    },
+    {
+      "epoch": 22.35,
+      "grad_norm": 2.0384035110473633,
+      "learning_rate": 1.2843816254416963e-05,
+      "loss": 0.2994,
+      "step": 53100
+    },
+    {
+      "epoch": 22.35,
+      "eval_cer": 0.3371079543232568,
+      "eval_loss": 2.487698554992676,
+      "eval_runtime": 374.207,
+      "eval_samples_per_second": 25.328,
+      "eval_steps_per_second": 3.167,
+      "step": 53100
     }
   ],
   "logging_steps": 100,
@@ -8478,7 +8510,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.796971564047972e+20,
+  "total_flos": 5.818817544770568e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null