Training in progress, step 20600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424006b63705ff8d128ce03cf112d0f0202b9b53563618c80069b74aadf6b121
+oid sha256:3d497e2e9992b95123edca43ea44a4f202dad1f6f849d37d3412aa944ee8b758
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486219a9cbd763fd42552ee2a1a2647b831dc1b08e3f181c8b5b51fe133f0228
+oid sha256:ebbfddaab2cb6b8976eb7300b0190223785e3130315d50c050c962fc69fe2a84
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0908165977f8c3d9489a849f85d9268f712bef0a616c664c5b76ba43a71c7f3d
+oid sha256:50d1b4164fc962c7aec4eee9c6701be1ec088b6f308360e6a9ee1734436272b1
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae9aa79a869a104ab7e27c688f3cfabb1a5b016e6c0d9194e567985352b95f11
+oid sha256:4c4ec211a6cd6bd5b7539fcf647a5b942b4dfee369f2618d5c30e0877818725f
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006c5e8305ef9dc1fe3403e1173068b8cb7f990d0fc5d4b955050dc8157ec06d
+oid sha256:05bf1a7e422f9aff57863d8882bd203339bb8d9f359aa0d93a3570a059702d97
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.587665754577984,
+  "epoch": 8.671858556093454,
   "eval_steps": 100,
-  "global_step": 20400,
+  "global_step": 20600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3271,6 +3271,38 @@
       "eval_samples_per_second": 26.076,
       "eval_steps_per_second": 3.26,
       "step": 20400
+    },
+    {
+      "epoch": 8.63,
+      "grad_norm": 3.379791498184204,
+      "learning_rate": 3.587491166077739e-05,
+      "loss": 1.4381,
+      "step": 20500
+    },
+    {
+      "epoch": 8.63,
+      "eval_cer": 0.4450402800046928,
+      "eval_loss": 2.9096951484680176,
+      "eval_runtime": 384.973,
+      "eval_samples_per_second": 24.62,
+      "eval_steps_per_second": 3.078,
+      "step": 20500
+    },
+    {
+      "epoch": 8.67,
+      "grad_norm": 2.5090067386627197,
+      "learning_rate": 3.580424028268551e-05,
+      "loss": 1.6658,
+      "step": 20600
+    },
+    {
+      "epoch": 8.67,
+      "eval_cer": 0.4514855695905518,
+      "eval_loss": 2.3211405277252197,
+      "eval_runtime": 367.2057,
+      "eval_samples_per_second": 25.811,
+      "eval_steps_per_second": 3.227,
+      "step": 20600
     }
   ],
   "logging_steps": 100,
@@ -3278,7 +3310,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.2352658822253032e+20,
+  "total_flos": 2.2571911239866106e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null