Training in progress, step 23900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621d5b082bdb2c827da94b16868ec6bb037254d515e80be4d82bfd0d547aa079
+oid sha256:534d2ec58806cf0406b243b3a40b55aced31f1221f35942206aebf1011f8eb45
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b6004c98a5aec94f0540baa0a4686e89ea42f59964c397abe229ba3d26bfac
+oid sha256:b2de9be3becc541ed69b75b47fcb52e55d337b4bb44dd3461d867a50ece8370f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e42c66575a6b4fba312c81c8ca7e4d2122eb77637384577cb7f7d90a458e0a7
+oid sha256:02a3ca665b49a6ee94542cba4571576580ed40077cbe8f242c5e2c4a3a9715e9
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1534bb272b01698f0e69072c937dd3bc74cf940685bb7c98b7450f40e337209e
-size 14503
+oid sha256:a4c012312b5f595ff9a144d4688b864116f1aa4fd2b3b74ba5004f78c1e3dd36
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efdb099c87b1e1f52b6d92cc12e09cc1bf288b64927150f98eff84b969c0b27f
+oid sha256:b8afa21305abd66240d65fd4f9e149e423e42ae4f4d5f37065fa94d5df4b4f66
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.976846979583245,
+  "epoch": 10.061039781098716,
   "eval_steps": 100,
-  "global_step": 23700,
+  "global_step": 23900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3799,6 +3799,38 @@
       "eval_samples_per_second": 26.189,
       "eval_steps_per_second": 3.274,
       "step": 23700
+    },
+    {
+      "epoch": 10.02,
+      "grad_norm": 12.59276294708252,
+      "learning_rate": 3.35434628975265e-05,
+      "loss": 1.2522,
+      "step": 23800
+    },
+    {
+      "epoch": 10.02,
+      "eval_cer": 0.43885651714833207,
+      "eval_loss": 2.233562707901001,
+      "eval_runtime": 381.3188,
+      "eval_samples_per_second": 24.856,
+      "eval_steps_per_second": 3.108,
+      "step": 23800
+    },
+    {
+      "epoch": 10.06,
+      "grad_norm": 6.893917560577393,
+      "learning_rate": 3.347279151943463e-05,
+      "loss": 1.2052,
+      "step": 23900
+    },
+    {
+      "epoch": 10.06,
+      "eval_cer": 0.44252522388643384,
+      "eval_loss": 2.4695940017700195,
+      "eval_runtime": 366.61,
+      "eval_samples_per_second": 25.853,
+      "eval_steps_per_second": 3.232,
+      "step": 23900
     }
   ],
   "logging_steps": 100,
@@ -3806,7 +3838,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.59704435509843e+20,
+  "total_flos": 2.6188595514552674e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null