Training in progress, step 2000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9504097674ab65e0b578a537215795127828dc3848d2e4873d658311c1534e62
+oid sha256:b4e148dbf45ee0c1b00413faa78a1fe84e8ab9819c7f9e728e4c5e30519ee934
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7951a74954187d35b833d6d8691c87dcbdef74a3c5d520bbb89ddf73c4c64a1c
+oid sha256:8787bac1231fb5b7b2b3f2e31b1a1cc032f8441964b82d0bb566039e4f39228b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f18849e5ff0941d6d82b638d7c00894ec5fd481eaf6afd0143fabdea22866d0
+oid sha256:766eb030afa62f812221a4873fc80200f2130440660a4ab8893d5971174019e0
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbd1a54c5b324d97726a1024b86dcbf61d66728c010a8906fe7f5578ce6b350f
+oid sha256:38091ee0235dae3b62dd1e1fdf55b8c87b4cf4944d0b07d3a101719f8706e81c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a476ee52ee296b1d46ee34fc092913aff5958cef2900b5569da3f9890dd90c4
+oid sha256:53944e7556a428dc9e5909eb4fd8f2f65cd084397466c50c8d395df612051b69
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7577352136392338,
+  "epoch": 0.8419280151547043,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -295,6 +295,38 @@
       "eval_samples_per_second": 27.565,
       "eval_steps_per_second": 3.446,
       "step": 1800
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.9933278560638428,
+      "learning_rate": 4.90148409893993e-05,
+      "loss": 3.2046,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8,
+      "eval_cer": 0.5539844941535333,
+      "eval_loss": 1.928993821144104,
+      "eval_runtime": 357.2509,
+      "eval_samples_per_second": 26.53,
+      "eval_steps_per_second": 3.317,
+      "step": 1900
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.917328357696533,
+      "learning_rate": 4.8944169611307425e-05,
+      "loss": 3.1904,
+      "step": 2000
+    },
+    {
+      "epoch": 0.84,
+      "eval_cer": 0.5568001838019632,
+      "eval_loss": 2.729193925857544,
+      "eval_runtime": 341.3463,
+      "eval_samples_per_second": 27.767,
+      "eval_steps_per_second": 3.472,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -302,7 +334,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.9750080760883966e+19,
+  "total_flos": 2.194770023027631e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null