Training in progress, step 9100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3d3cd63d6d2b7817fcaeb0e700ec073e895b1392f5b11376dc400ab356ad89
+oid sha256:9bbee931196582b3943799fea6fad9126c367e3f66b33f31350eb68c8e369ac5
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19af523b850e718dee98ab66147dcd21a5c1fd9aaa4d714d77ca732c79c11797
+oid sha256:2b5eea1245176ae49a93bbf3af3ce453f09302734a757c1989c08339e3ac6740
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b3a0ca77765fef36444952fa33403a178b84113717e1a5400a06d438d3d2241
+oid sha256:1a372c874bbe208d173cdf674b526297d0b78e20ec1684ee1fa2fe9c6285b8b8
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf0eecf02c50d92c6abe3654ed45f596e15ae45458fb25a4d3411d8513d6ee7d
+oid sha256:29f4043ffeadfb240b8eac65e4ab4f2b6109a3126928822311083ed99f5376bf
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ddf596f4dea4d14b5183a987af8ee8a1b47eeae5be8f03bff40eab4d3ed32c
+oid sha256:da5eeff1d9d5c6004df620e11b35d3b63eb34d8e5fdfa4922d3c6f9e09140f6a
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.746579667438434,
+  "epoch": 3.8307724689539047,
   "eval_steps": 100,
-  "global_step": 8900,
+  "global_step": 9100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1431,6 +1431,38 @@
       "eval_samples_per_second": 26.374,
       "eval_steps_per_second": 3.297,
       "step": 8900
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 4.16035270690918,
+      "learning_rate": 4.3999293286219085e-05,
+      "loss": 2.312,
+      "step": 9000
+    },
+    {
+      "epoch": 3.79,
+      "eval_cer": 0.503619823237261,
+      "eval_loss": 1.6672168970108032,
+      "eval_runtime": 375.3507,
+      "eval_samples_per_second": 25.251,
+      "eval_steps_per_second": 3.157,
+      "step": 9000
+    },
+    {
+      "epoch": 3.83,
+      "grad_norm": 1.9299957752227783,
+      "learning_rate": 4.392862190812721e-05,
+      "loss": 2.0043,
+      "step": 9100
+    },
+    {
+      "epoch": 3.83,
+      "eval_cer": 0.4974531696061945,
+      "eval_loss": 3.044623613357544,
+      "eval_runtime": 365.1986,
+      "eval_samples_per_second": 25.953,
+      "eval_steps_per_second": 3.245,
+      "step": 9100
     }
   ],
   "logging_steps": 100,
@@ -1438,7 +1470,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 9.754876784382558e+19,
+  "total_flos": 9.973966921673019e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null