Training in progress, step 2200, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4e148dbf45ee0c1b00413faa78a1fe84e8ab9819c7f9e728e4c5e30519ee934
+oid sha256:00172f6dd05a49b1cf2f8ff023f3ca93980f8b4e3060eeb47e74d8f65933ac36
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8787bac1231fb5b7b2b3f2e31b1a1cc032f8441964b82d0bb566039e4f39228b
+oid sha256:0d59fdb186dd6719014f3267c673ca01c879f220542715dcb5862f4204903bc2
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766eb030afa62f812221a4873fc80200f2130440660a4ab8893d5971174019e0
+oid sha256:fbe23e6ec83e38f888ce1b667257f959e02478dbaef89d9e23350f77615b295b
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38091ee0235dae3b62dd1e1fdf55b8c87b4cf4944d0b07d3a101719f8706e81c
-size 14503
+oid sha256:39c98aca05a0d374052b7c1cb664ff3eb713201073b7a44e234eb536fbccee1c
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53944e7556a428dc9e5909eb4fd8f2f65cd084397466c50c8d395df612051b69
+oid sha256:1665cb8324f796c9f90a2705fd01fef5d8ec3fa89b088395f8b2aa4bae6228c2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8419280151547043,
+  "epoch": 0.9261208166701747,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -327,6 +327,38 @@
       "eval_samples_per_second": 27.767,
       "eval_steps_per_second": 3.472,
       "step": 2000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.842353343963623,
+      "learning_rate": 4.8873498233215547e-05,
+      "loss": 2.1649,
+      "step": 2100
+    },
+    {
+      "epoch": 0.88,
+      "eval_cer": 0.544757733369833,
+      "eval_loss": 2.421653985977173,
+      "eval_runtime": 358.7261,
+      "eval_samples_per_second": 26.421,
+      "eval_steps_per_second": 3.303,
+      "step": 2100
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.818225383758545,
+      "learning_rate": 4.880282685512368e-05,
+      "loss": 2.2775,
+      "step": 2200
+    },
+    {
+      "epoch": 0.93,
+      "eval_cer": 0.5533832270931915,
+      "eval_loss": 2.188101291656494,
+      "eval_runtime": 354.4215,
+      "eval_samples_per_second": 26.742,
+      "eval_steps_per_second": 3.343,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -334,7 +366,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.194770023027631e+19,
+  "total_flos": 2.411832086421037e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null