Training in progress, step 9300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bbee931196582b3943799fea6fad9126c367e3f66b33f31350eb68c8e369ac5
+oid sha256:e53d952088e21ee7c18f6fee4b8d7769b753af22ca10b63a69e3f8de2b65b0be
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b5eea1245176ae49a93bbf3af3ce453f09302734a757c1989c08339e3ac6740
+oid sha256:76dd5b4a8826aefc4d28f9aba3108c5d9d8a9bb5ddbd6054bc88418f54521ed3
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a372c874bbe208d173cdf674b526297d0b78e20ec1684ee1fa2fe9c6285b8b8
+oid sha256:5bb833d4bc9327bd0e01ea33487a3bf19e25b2de7bacf92eb09217f6b4297dc2
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29f4043ffeadfb240b8eac65e4ab4f2b6109a3126928822311083ed99f5376bf
-size 14503
+oid sha256:f7b3c74ecbda77c6abb056be85c9b612f31948352a984f5f4ba2d90f864dc773
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da5eeff1d9d5c6004df620e11b35d3b63eb34d8e5fdfa4922d3c6f9e09140f6a
+oid sha256:336d1b7b025618b96c60c17b8c9303a9e5e4f82eb8a6c5c17e6b7e590bbf1488
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.8307724689539047,
+  "epoch": 3.914965270469375,
   "eval_steps": 100,
-  "global_step": 9100,
+  "global_step": 9300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1463,6 +1463,38 @@
       "eval_samples_per_second": 25.953,
       "eval_steps_per_second": 3.245,
       "step": 9100
+    },
+    {
+      "epoch": 3.87,
+      "grad_norm": 1.68573796749115,
+      "learning_rate": 4.3857950530035335e-05,
+      "loss": 2.5474,
+      "step": 9200
+    },
+    {
+      "epoch": 3.87,
+      "eval_cer": 0.5048394665832389,
+      "eval_loss": 2.7017831802368164,
+      "eval_runtime": 374.6095,
+      "eval_samples_per_second": 25.301,
+      "eval_steps_per_second": 3.163,
+      "step": 9200
+    },
+    {
+      "epoch": 3.91,
+      "grad_norm": 4.48902702331543,
+      "learning_rate": 4.378727915194347e-05,
+      "loss": 2.2683,
+      "step": 9300
+    },
+    {
+      "epoch": 3.91,
+      "eval_cer": 0.49138917132689375,
+      "eval_loss": 1.5836848020553589,
+      "eval_runtime": 360.7206,
+      "eval_samples_per_second": 26.275,
+      "eval_steps_per_second": 3.285,
+      "step": 9300
     }
   ],
   "logging_steps": 100,
@@ -1470,7 +1502,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 9.973966921673019e+19,
+  "total_flos": 1.0193037614760552e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null