Training in progress, step 22100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f528d8b47297dcd25f0ac457540cb950397ab08f61bd370ae0a0f0b358fcf217
+oid sha256:b2effce087c71e7b4f5411ac336511daf6bbbe1e3ecbac9348a8792a025918d9
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6027792961a4f096acc160c9d7140e3a397456675e6172019e0257ab004c55b1
+oid sha256:7a22c61a8979b9f44e4c8c22f66fbed3c19bc88f463a4f974eac0e1c4d0de281
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f2845621466e928fb57dc117cf81e1ef42f0d8d81b0e11e00af6d149a1466a
+oid sha256:112820ec059ab52f61273d81ee9a8ae1d15140adca820a8935a7074524ca4d69
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c985d2a2c043a50fddf4712f00639a3630bd1174d543d92b3ca489c07fa3bb
-size 14567
+oid sha256:699594f94310cf08af521c6d50d89fc54dec73b61991d34be34e9fc33928c3be
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b891928e38cf41772d02e62b28af04076db5001b27d6077652872482d64ab94
+oid sha256:8e6b1f4714aff0d0b0d7f3c9208419cd1fd98d5d42618c80a7c7b656aa11290a
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.219111765944012,
+  "epoch": 9.303304567459483,
   "eval_steps": 100,
-  "global_step": 21900,
+  "global_step": 22100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3511,6 +3511,38 @@
       "eval_samples_per_second": 25.649,
       "eval_steps_per_second": 3.207,
       "step": 21900
+    },
+    {
+      "epoch": 9.26,
+      "grad_norm": 2.3700144290924072,
+      "learning_rate": 3.481554770318021e-05,
+      "loss": 1.3379,
+      "step": 22000
+    },
+    {
+      "epoch": 9.26,
+      "eval_cer": 0.4379032888819366,
+      "eval_loss": 1.7394232749938965,
+      "eval_runtime": 383.407,
+      "eval_samples_per_second": 24.72,
+      "eval_steps_per_second": 3.091,
+      "step": 22000
+    },
+    {
+      "epoch": 9.3,
+      "grad_norm": 2.381225824356079,
+      "learning_rate": 3.4744876325088346e-05,
+      "loss": 2.2422,
+      "step": 22100
+    },
+    {
+      "epoch": 9.3,
+      "eval_cer": 0.43050965937976615,
+      "eval_loss": 1.691564917564392,
+      "eval_runtime": 362.7906,
+      "eval_samples_per_second": 26.125,
+      "eval_steps_per_second": 3.266,
+      "step": 22100
     }
   ],
   "logging_steps": 100,
@@ -3518,7 +3550,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.3997519912106135e+20,
+  "total_flos": 2.4217119796381745e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null