Training in progress, step 31700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b873a74cd85a7444c0192282714f2d098858bb6f1a3a0918b2e959c631252ae
+oid sha256:f1945bb6ddf30b2e4e4d92dc6ee4fc7d055d8084fe3ccfb116c609ff34fb39a9
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9847471a8fd7c6857174d23c423cd8a42f9fdb4816150a44f8df1411bd9e1c
+oid sha256:968c0b29c790917699e87f69bf4aa6ac1b07a8edffd5fe57d7f83fe35c794971
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b25a848c08828cafb3a66f0504b00fb96895d1acc816cd999813ceecd40249ca
+oid sha256:5480abc34a2c091a74e506fa88c8f91b9508337e6b6f219e4137a8ec9418527a
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23ac0726bb090165d240f34770fc857f9071db19378988c8da075c49c106078
+oid sha256:43d752b29aed24741788ac40b8b42ea9e26aed84562cc2ec34fd9be16f1fa0b9
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d8f86a3c26a655dfe015c220ca87fec81bde322514d5aa3c29e06276681b938
+oid sha256:acfed987dc1065bc7e53e8a29458596da758156c2105dbe2e31f48b243130117
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.260366238686592,
+  "epoch": 13.344559040202062,
   "eval_steps": 100,
-  "global_step": 31500,
+  "global_step": 31700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5047,6 +5047,38 @@
       "eval_samples_per_second": 25.115,
       "eval_steps_per_second": 3.14,
       "step": 31500
+    },
+    {
+      "epoch": 13.3,
+      "grad_norm": 2.9201929569244385,
+      "learning_rate": 2.8033215547703178e-05,
+      "loss": 0.9921,
+      "step": 31600
+    },
+    {
+      "epoch": 13.3,
+      "eval_cer": 0.40619256188651204,
+      "eval_loss": 1.6753425598144531,
+      "eval_runtime": 390.1339,
+      "eval_samples_per_second": 24.294,
+      "eval_steps_per_second": 3.037,
+      "step": 31600
+    },
+    {
+      "epoch": 13.34,
+      "grad_norm": 3.985402822494507,
+      "learning_rate": 2.796254416961131e-05,
+      "loss": 0.9951,
+      "step": 31700
+    },
+    {
+      "epoch": 13.34,
+      "eval_cer": 0.4047969379375073,
+      "eval_loss": 1.8533233404159546,
+      "eval_runtime": 373.1578,
+      "eval_samples_per_second": 25.399,
+      "eval_steps_per_second": 3.176,
+      "step": 31700
     }
   ],
   "logging_steps": 100,
@@ -5054,7 +5086,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.451975086227115e+20,
+  "total_flos": 3.473760721513529e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null