Training in progress, step 21900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c8f7133601f6241adb6bd6bf01a75d224f71ba6cb54aeb09296f655d47f3a1c
+oid sha256:f528d8b47297dcd25f0ac457540cb950397ab08f61bd370ae0a0f0b358fcf217
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173421e8ecf6978117ae5b199e2a50f45c7c092152472c947077b42e03c89cca
+oid sha256:6027792961a4f096acc160c9d7140e3a397456675e6172019e0257ab004c55b1
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241e1f0ab55a70d32c9f789ad9ea31e0da83a3e1004167f836a2db341c5607c0
+oid sha256:04f2845621466e928fb57dc117cf81e1ef42f0d8d81b0e11e00af6d149a1466a
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e1d0bd8c568f0c227459d6e419ca5b7a73769c308ffd09703cd18e64758377c
-size 14503
+oid sha256:38c985d2a2c043a50fddf4712f00639a3630bd1174d543d92b3ca489c07fa3bb
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be01cce06a3b36303f6edddcac607adba712c87a93866bac4ad77aaf758f37b2
+oid sha256:9b891928e38cf41772d02e62b28af04076db5001b27d6077652872482d64ab94
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.134918964428541,
+  "epoch": 9.219111765944012,
   "eval_steps": 100,
-  "global_step": 21700,
+  "global_step": 21900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3479,6 +3479,38 @@
       "eval_samples_per_second": 25.436,
       "eval_steps_per_second": 3.18,
       "step": 21700
+    },
+    {
+      "epoch": 9.18,
+      "grad_norm": 7.561341762542725,
+      "learning_rate": 3.495689045936396e-05,
+      "loss": 1.2998,
+      "step": 21800
+    },
+    {
+      "epoch": 9.18,
+      "eval_cer": 0.43526113566149155,
+      "eval_loss": 3.151437282562256,
+      "eval_runtime": 381.1035,
+      "eval_samples_per_second": 24.87,
+      "eval_steps_per_second": 3.109,
+      "step": 21800
+    },
+    {
+      "epoch": 9.22,
+      "grad_norm": 2.588192939758301,
+      "learning_rate": 3.488621908127209e-05,
+      "loss": 1.2493,
+      "step": 21900
+    },
+    {
+      "epoch": 9.22,
+      "eval_cer": 0.46399241328066954,
+      "eval_loss": 1.8955408334732056,
+      "eval_runtime": 369.5234,
+      "eval_samples_per_second": 25.649,
+      "eval_steps_per_second": 3.207,
+      "step": 21900
     }
   ],
   "logging_steps": 100,
@@ -3486,7 +3518,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.3783863994215714e+20,
+  "total_flos": 2.3997519912106135e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null