Training in progress, step 23700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf49c6b82f7665a604e40742defaf43941c7586bf80b494ee902b2c620087cc4
+oid sha256:621d5b082bdb2c827da94b16868ec6bb037254d515e80be4d82bfd0d547aa079
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f98af73c68edabc39c71995cd33d7c87eed9ee1a1350930152351ece5229c762
+oid sha256:f1b6004c98a5aec94f0540baa0a4686e89ea42f59964c397abe229ba3d26bfac
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95a4e83c0629f0505bbb8d535207996a723259667e4045da0c20dd5dcda6985
+oid sha256:9e42c66575a6b4fba312c81c8ca7e4d2122eb77637384577cb7f7d90a458e0a7
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5113b92b4d7def74e8c7a35c67502e1a4c59c5544bae2c22551f00c5f5b8acd6
+oid sha256:1534bb272b01698f0e69072c937dd3bc74cf940685bb7c98b7450f40e337209e
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:549665abf4f20a24c12813b0847df3413b770048a1d4544619085eecf6a394ea
+oid sha256:efdb099c87b1e1f52b6d92cc12e09cc1bf288b64927150f98eff84b969c0b27f
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.892654178067776,
+  "epoch": 9.976846979583245,
   "eval_steps": 100,
-  "global_step": 23500,
+  "global_step": 23700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3767,6 +3767,38 @@
       "eval_samples_per_second": 26.104,
       "eval_steps_per_second": 3.264,
       "step": 23500
+    },
+    {
+      "epoch": 9.93,
+      "grad_norm": 9.951347351074219,
+      "learning_rate": 3.368480565371025e-05,
+      "loss": 1.5735,
+      "step": 23600
+    },
+    {
+      "epoch": 9.93,
+      "eval_cer": 0.4422074811309687,
+      "eval_loss": 1.6464565992355347,
+      "eval_runtime": 386.065,
+      "eval_samples_per_second": 24.55,
+      "eval_steps_per_second": 3.069,
+      "step": 23600
+    },
+    {
+      "epoch": 9.98,
+      "grad_norm": 4.360719203948975,
+      "learning_rate": 3.3614134275618375e-05,
+      "loss": 1.6236,
+      "step": 23700
+    },
+    {
+      "epoch": 9.98,
+      "eval_cer": 0.44366909780610847,
+      "eval_loss": 1.770129919052124,
+      "eval_runtime": 361.9008,
+      "eval_samples_per_second": 26.189,
+      "eval_steps_per_second": 3.274,
+      "step": 23700
     }
   ],
   "logging_steps": 100,
@@ -3774,7 +3806,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.575180974094451e+20,
+  "total_flos": 2.59704435509843e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null