Training in progress, step 10100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5744380703f87f970b57582712646d1195547ea2deb809f1e728c012a141e65
+oid sha256:0152ae7665e14b7649e1603869eac2627c4b46968a4140b59e840be45c462043
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1dfdf11a2a9cfabe064ab18caf2d667bf041175304c131085bc56d0b7260ec8
+oid sha256:f2ca09b9d6895bf99912a3b620ebf15f2699cd4d85234bae948db7af35d3805b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9b7d365602a80d5be1805125aa374b02c292b64a53e40e7d4a6fc4b2c32c3b5
+oid sha256:64f7c21bc62e1590ba7d33964a61cd28c89e814d09700786d96a59dfd2d2f37a
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe42a9a6d1a2aa6e8b3204aaff4e79e9911c21ae2de7ab694db56cf080fb011
+oid sha256:9ac36883a60e8fdddb046d3d099aec879515eeb495fb66554d35da33f561e776
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e024ad4d2c469d51bc12b39f389559da78567c0b22ee2b58dd4cac9872e0c9b3
+oid sha256:c00379d1a32b555abafe33a1610f228542dd2b56a05a75c6d377908358a81a67
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.167543675015786,
+  "epoch": 4.251736476531256,
   "eval_steps": 100,
-  "global_step": 9900,
+  "global_step": 10100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1591,6 +1591,38 @@
       "eval_samples_per_second": 26.528,
       "eval_steps_per_second": 3.317,
       "step": 9900
+    },
+    {
+      "epoch": 4.21,
+      "grad_norm": 2.77481746673584,
+      "learning_rate": 4.329328621908127e-05,
+      "loss": 1.45,
+      "step": 10000
+    },
+    {
+      "epoch": 4.21,
+      "eval_cer": 0.49421952602557584,
+      "eval_loss": 1.6775341033935547,
+      "eval_runtime": 376.5454,
+      "eval_samples_per_second": 25.171,
+      "eval_steps_per_second": 3.147,
+      "step": 10000
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 7.3151140213012695,
+      "learning_rate": 4.32226148409894e-05,
+      "loss": 1.5163,
+      "step": 10100
+    },
+    {
+      "epoch": 4.25,
+      "eval_cer": 0.49458370810683977,
+      "eval_loss": 2.463066577911377,
+      "eval_runtime": 349.9183,
+      "eval_samples_per_second": 27.086,
+      "eval_steps_per_second": 3.387,
+      "step": 10100
     }
   ],
   "logging_steps": 100,
@@ -1598,7 +1630,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.0845390616473847e+20,
+  "total_flos": 1.1062718286020878e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null