Training in progress, step 21000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e4814097f95292581f1fa41351bbc66ced1628a34f7e406c1d973bdfa268c2
+oid sha256:0914d34b789b137bde7b5e425800476cd3b8a0c1c2a2f6dca29e198df8bce8d1
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4281b3413ac6bfae58364c1649b3032d24b966004ceed96933c7ba6a5d6273b
+oid sha256:8b055483df48b82f8f43aae9c1bf44543d9d6b475dd015afb266b79d61079e91
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f12f5880c497ab5a7a2b205f32136065c330a41316d4e0177eb04fd5d02d93
+oid sha256:0d1f86a4256547c5562fc9179cc66f200a56f9f53b2448731cd2d83aadb1bd70
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6484a98615c86c255086193fe3b7042881674afdf95988ec90167572328c2cbb
-size 14567
+oid sha256:73aa4ed4dedc1aae7d9f7534e9a473a7d481fd77c26b1dac6a9acd73c2b3a117
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c543c9e610e453a76673ad3939ff1bdf7432f91d895bb0c3b414985ca5e44f7
+oid sha256:73620584f32d0b623d2e9a17c6bb745cf56317c4ff398df3fcc5b050e7d94c8b
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.756051357608925,
+  "epoch": 8.840244159124396,
   "eval_steps": 100,
-  "global_step": 20800,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3335,6 +3335,38 @@
       "eval_samples_per_second": 26.137,
       "eval_steps_per_second": 3.268,
       "step": 20800
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 10.084565162658691,
+      "learning_rate": 3.5592226148409895e-05,
+      "loss": 1.3031,
+      "step": 20900
+    },
+    {
+      "epoch": 8.8,
+      "eval_cer": 0.44013237652027687,
+      "eval_loss": 1.9289778470993042,
+      "eval_runtime": 383.5806,
+      "eval_samples_per_second": 24.709,
+      "eval_steps_per_second": 3.089,
+      "step": 20900
+    },
+    {
+      "epoch": 8.84,
+      "grad_norm": 2.5064008235931396,
+      "learning_rate": 3.552155477031802e-05,
+      "loss": 2.0089,
+      "step": 21000
+    },
+    {
+      "epoch": 8.84,
+      "eval_cer": 0.4491318290250675,
+      "eval_loss": 2.749382734298706,
+      "eval_runtime": 372.5311,
+      "eval_samples_per_second": 25.442,
+      "eval_steps_per_second": 3.181,
+      "step": 21000
     }
   ],
   "logging_steps": 100,
@@ -3342,7 +3374,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.278855149050551e+20,
+  "total_flos": 2.300997184346249e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null