Training in progress, step 52900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe1c93b8017d74a09b637d5419b72f561139b3c1af762e8562b3cb8786654a7
+oid sha256:38856c5de97012a6bbddb265016f45f787498a984601f0d5f3432a3dd21d3b08
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32f313c4502ab1516bf134a75993c4c561fdee3ec545f99a82ba52cad86980eb
+oid sha256:27f7daf3b2a573c62d3f1e255b201aea1d79bd60a6b957765f25b4a1f67c0e2c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a976a4a597b8b9341405e32ca9ff17df9bc058b930b3fb15473565039dee635
+oid sha256:2396e720c3c604a71d73a5cfdd04c82f1b06481005dcbfbc4e609d17cd8dc459
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39d694511c38cf842adf62f634f5a20eb55c12c93d605d719c21b8dcbbcf72b0
-size 14567
+oid sha256:d7f4b3f4fdec252a3fb47435e761c164da7b4d341aa24a2cc22079721594d2e4
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:726de08061b13aa65db2732d53ac93e0334fa97527eefc3b67e0a6227d537660
+oid sha256:07280b3905388184ad6f524c0c254f08ba9be422c3d6452b00f45b36031ca6fa
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.184803199326456,
+  "epoch": 22.268996000841927,
   "eval_steps": 100,
-  "global_step": 52700,
+  "global_step": 52900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8439,6 +8439,38 @@
       "eval_samples_per_second": 24.005,
       "eval_steps_per_second": 3.001,
       "step": 52700
+    },
+    {
+      "epoch": 22.23,
+      "grad_norm": 1.9212164878845215,
+      "learning_rate": 1.305583038869258e-05,
+      "loss": 0.3058,
+      "step": 52800
+    },
+    {
+      "epoch": 22.23,
+      "eval_cer": 0.3395081342145399,
+      "eval_loss": 2.419398546218872,
+      "eval_runtime": 417.7544,
+      "eval_samples_per_second": 22.688,
+      "eval_steps_per_second": 2.837,
+      "step": 52800
+    },
+    {
+      "epoch": 22.27,
+      "grad_norm": 4.1538004875183105,
+      "learning_rate": 1.2985159010600709e-05,
+      "loss": 0.2954,
+      "step": 52900
+    },
+    {
+      "epoch": 22.27,
+      "eval_cer": 0.33905107348167846,
+      "eval_loss": 2.4820761680603027,
+      "eval_runtime": 388.8242,
+      "eval_samples_per_second": 24.376,
+      "eval_steps_per_second": 3.048,
+      "step": 52900
     }
   ],
   "logging_steps": 100,
@@ -8446,7 +8478,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.7751950642202254e+20,
+  "total_flos": 5.796971564047972e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null