Training in progress, step 21700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd295564c886cab31b38fdc522144c8184d26012f8017f463f8b19068b69ce54
+oid sha256:4c8f7133601f6241adb6bd6bf01a75d224f71ba6cb54aeb09296f655d47f3a1c
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10129ed8317e1eb717c2b209ed001fa2e165c880f232b8ab7fc6026685e36a65
+oid sha256:173421e8ecf6978117ae5b199e2a50f45c7c092152472c947077b42e03c89cca
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5ca3cb0ab23b9c64be740c79b07d64816cd7d9490aeeae08ccc4a3f3b37ddc
+oid sha256:241e1f0ab55a70d32c9f789ad9ea31e0da83a3e1004167f836a2db341c5607c0
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a20e1a39d049694d044e652201b8a810f3562871d67cc396aaad5e0bbc2f803
+oid sha256:2e1d0bd8c568f0c227459d6e419ca5b7a73769c308ffd09703cd18e64758377c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48225e4ec8a66fcccd258aec5acd97fada08046f07bbc5a0c629141f0b9c9d7d
+oid sha256:be01cce06a3b36303f6edddcac607adba712c87a93866bac4ad77aaf758f37b2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.008629762155335,
+  "epoch": 9.134918964428541,
   "eval_steps": 100,
-  "global_step": 21400,
+  "global_step": 21700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3431,6 +3431,54 @@
       "eval_samples_per_second": 26.074,
       "eval_steps_per_second": 3.26,
       "step": 21400
+    },
+    {
+      "epoch": 9.05,
+      "grad_norm": 2.522552251815796,
+      "learning_rate": 3.5168197879858664e-05,
+      "loss": 1.2512,
+      "step": 21500
+    },
+    {
+      "epoch": 9.05,
+      "eval_cer": 0.44793418325446793,
+      "eval_loss": 2.5103232860565186,
+      "eval_runtime": 384.7009,
+      "eval_samples_per_second": 24.637,
+      "eval_steps_per_second": 3.08,
+      "step": 21500
+    },
+    {
+      "epoch": 9.09,
+      "grad_norm": 17.708566665649414,
+      "learning_rate": 3.5097526501766785e-05,
+      "loss": 1.2248,
+      "step": 21600
+    },
+    {
+      "epoch": 9.09,
+      "eval_cer": 0.4432878064995503,
+      "eval_loss": 2.5621256828308105,
+      "eval_runtime": 370.664,
+      "eval_samples_per_second": 25.57,
+      "eval_steps_per_second": 3.197,
+      "step": 21600
+    },
+    {
+      "epoch": 9.13,
+      "grad_norm": 2.740123987197876,
+      "learning_rate": 3.502685512367491e-05,
+      "loss": 1.3298,
+      "step": 21700
+    },
+    {
+      "epoch": 9.13,
+      "eval_cer": 0.441982617027101,
+      "eval_loss": 2.49664568901062,
+      "eval_runtime": 372.6231,
+      "eval_samples_per_second": 25.436,
+      "eval_steps_per_second": 3.18,
+      "step": 21700
     }
   ],
   "logging_steps": 100,
@@ -3438,7 +3486,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.3455923104904626e+20,
+  "total_flos": 2.3783863994215714e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null