Training in progress, step 37100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0646fcf5cf97fb5503e2fbbc9e98c3960fec3e656e2c994965054eac8467df2b
+oid sha256:381f57f24d93696513b5b64ff4e2b26e4aa55b4c5527b3fea9b18b1fc4cf72bc
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c691890dc2b6f3211ced073de26ccb0d7c08362c3a77fadc55959c2aea6190dd
+oid sha256:fb33ab1b771a570de1383d0627b9c859532e9fc93dbf7d6c5f3ea94a017d8931
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65fd8a1c0a883c5d4e5251be70dcd09108e90ba7f22053441648adf6f980589f
+oid sha256:dede614aaa93a8236b1aaee0b270dbb1e0e0ee731df570c565b17414017d0f04
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d17156c6a1f8e32f040e09547b8bc921e30af508cd3be63ca008523dbabbb3
+oid sha256:953d28bb26d9f06c74ed4ce0f50682b88b7c1a740875d4c88a1a0b092ef89394
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc136ee3addae9eeb904fb18be82d28a7b235388655ca82f3c8bea405623e110
+oid sha256:5bbb7a0763de581151b4ca9c96854f5bc48332bf11f33793e4cc2d52e736e678
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.533571879604294,
+  "epoch": 15.617764681119764,
   "eval_steps": 100,
-  "global_step": 36900,
+  "global_step": 37100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5911,6 +5911,38 @@
       "eval_samples_per_second": 25.191,
       "eval_steps_per_second": 3.15,
       "step": 36900
+    },
+    {
+      "epoch": 15.58,
+      "grad_norm": 5.990358352661133,
+      "learning_rate": 2.4217667844522972e-05,
+      "loss": 0.8376,
+      "step": 37000
+    },
+    {
+      "epoch": 15.58,
+      "eval_cer": 0.38022809041492317,
+      "eval_loss": 1.795945405960083,
+      "eval_runtime": 393.6062,
+      "eval_samples_per_second": 24.08,
+      "eval_steps_per_second": 3.011,
+      "step": 37000
+    },
+    {
+      "epoch": 15.62,
+      "grad_norm": 37.267982482910156,
+      "learning_rate": 2.4146996466431096e-05,
+      "loss": 0.8422,
+      "step": 37100
+    },
+    {
+      "epoch": 15.62,
+      "eval_cer": 0.38063137929685975,
+      "eval_loss": 2.6164886951446533,
+      "eval_runtime": 378.7126,
+      "eval_samples_per_second": 25.027,
+      "eval_steps_per_second": 3.129,
+      "step": 37100
     }
   ],
   "logging_steps": 100,
@@ -5918,7 +5950,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.044598170257006e+20,
+  "total_flos": 4.066405780809435e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null