Training in progress, step 20800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d497e2e9992b95123edca43ea44a4f202dad1f6f849d37d3412aa944ee8b758
+oid sha256:95e4814097f95292581f1fa41351bbc66ced1628a34f7e406c1d973bdfa268c2
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbfddaab2cb6b8976eb7300b0190223785e3130315d50c050c962fc69fe2a84
+oid sha256:f4281b3413ac6bfae58364c1649b3032d24b966004ceed96933c7ba6a5d6273b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d1b4164fc962c7aec4eee9c6701be1ec088b6f308360e6a9ee1734436272b1
+oid sha256:45f12f5880c497ab5a7a2b205f32136065c330a41316d4e0177eb04fd5d02d93
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c4ec211a6cd6bd5b7539fcf647a5b942b4dfee369f2618d5c30e0877818725f
+oid sha256:6484a98615c86c255086193fe3b7042881674afdf95988ec90167572328c2cbb
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05bf1a7e422f9aff57863d8882bd203339bb8d9f359aa0d93a3570a059702d97
+oid sha256:7c543c9e610e453a76673ad3939ff1bdf7432f91d895bb0c3b414985ca5e44f7
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.671858556093454,
+  "epoch": 8.756051357608925,
   "eval_steps": 100,
-  "global_step": 20600,
+  "global_step": 20800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3303,6 +3303,38 @@
       "eval_samples_per_second": 25.811,
       "eval_steps_per_second": 3.227,
       "step": 20600
+    },
+    {
+      "epoch": 8.71,
+      "grad_norm": 2.2183985710144043,
+      "learning_rate": 3.573356890459364e-05,
+      "loss": 2.1266,
+      "step": 20700
+    },
+    {
+      "epoch": 8.71,
+      "eval_cer": 0.45651323765202767,
+      "eval_loss": 1.70187246799469,
+      "eval_runtime": 382.2617,
+      "eval_samples_per_second": 24.795,
+      "eval_steps_per_second": 3.1,
+      "step": 20700
+    },
+    {
+      "epoch": 8.76,
+      "grad_norm": 1.713640570640564,
+      "learning_rate": 3.5662897526501774e-05,
+      "loss": 1.3038,
+      "step": 20800
+    },
+    {
+      "epoch": 8.76,
+      "eval_cer": 0.44218548355559034,
+      "eval_loss": 1.8959708213806152,
+      "eval_runtime": 362.6249,
+      "eval_samples_per_second": 26.137,
+      "eval_steps_per_second": 3.268,
+      "step": 20800
     }
   ],
   "logging_steps": 100,
@@ -3310,7 +3342,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.2571911239866106e+20,
+  "total_flos": 2.278855149050551e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null