Training in progress, step 36900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e7d744e605fdeb47c357c118df95f001014156b76f00db93fae8270b36d782
+oid sha256:0646fcf5cf97fb5503e2fbbc9e98c3960fec3e656e2c994965054eac8467df2b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a0e0ccb6fbb91ed7c1319992741aa3473b384fd1962f0a2bdef33fd8f0424a5
+oid sha256:c691890dc2b6f3211ced073de26ccb0d7c08362c3a77fadc55959c2aea6190dd
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2329d5a7fedc8f15c09d69541a87944d288c3f9c2684c5d81d7725abd374732
+oid sha256:65fd8a1c0a883c5d4e5251be70dcd09108e90ba7f22053441648adf6f980589f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792ef05d47d8fddd57baa2e5e4c79c5f1008526305f0fc51b7e4b0ff90c07793
+oid sha256:86d17156c6a1f8e32f040e09547b8bc921e30af508cd3be63ca008523dbabbb3
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28baba878695b471c12cd9b5814de5f1bb170226354cdd018df9f14201aec249
+oid sha256:dc136ee3addae9eeb904fb18be82d28a7b235388655ca82f3c8bea405623e110
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.449379078088823,
+  "epoch": 15.533571879604294,
   "eval_steps": 100,
-  "global_step": 36700,
+  "global_step": 36900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5879,6 +5879,38 @@
       "eval_samples_per_second": 25.396,
       "eval_steps_per_second": 3.175,
       "step": 36700
+    },
+    {
+      "epoch": 15.49,
+      "grad_norm": 1.7568877935409546,
+      "learning_rate": 2.4359010600706712e-05,
+      "loss": 0.8502,
+      "step": 36800
+    },
+    {
+      "epoch": 15.49,
+      "eval_cer": 0.3838430253021,
+      "eval_loss": 2.477693796157837,
+      "eval_runtime": 393.1117,
+      "eval_samples_per_second": 24.11,
+      "eval_steps_per_second": 3.014,
+      "step": 36800
+    },
+    {
+      "epoch": 15.53,
+      "grad_norm": 1.5188319683074951,
+      "learning_rate": 2.4288339222614844e-05,
+      "loss": 1.1122,
+      "step": 36900
+    },
+    {
+      "epoch": 15.53,
+      "eval_cer": 0.3783705173829729,
+      "eval_loss": 2.0704104900360107,
+      "eval_runtime": 376.2486,
+      "eval_samples_per_second": 25.191,
+      "eval_steps_per_second": 3.15,
+      "step": 36900
     }
   ],
   "logging_steps": 100,
@@ -5886,7 +5918,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.022627751818035e+20,
+  "total_flos": 4.044598170257006e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null