Training in progress, step 17900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b1498b08a6639bedf117caea6b35ac96fa9b8ee131f6ffaccbc2e8e9177c796
+oid sha256:5ac85ec2c9aba65ba5a73c821698bedfac0ab44056cd9185b3e753286a39e09c
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:384bd802bf21cb1a27b836850e4820fe91126c62756261b9a247d59b2fa7efa8
+oid sha256:0f61593c5f78f153cc487d9b55550c24e4357647243b54c97f2007711e16bc6a
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:619651e240468638db04ed81e283eda35fc105eb098b17746a777d41118f1405
+oid sha256:91da2be2eef1794b5936410e53d53a35f682508081fa6cc959e3b5be890cfca3
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f5a1b4d910cdecfc94d665d7ca48c0140621b4304151906605cb242fb93fef
+oid sha256:97ab373cd59fc6f59c96aa1f7842448ef3e4e7e697c811c91fd0af922706a46c
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3b87bb384b796d63345d139b5280a7bcb6e545e4f041e3f5f37032761b459b4
+oid sha256:b095bc8b48379c3c360d6339687aca8dc7b9bc6703181a7b751f54a1030c1459
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.451062934119133,
+  "epoch": 7.535255735634603,
   "eval_steps": 100,
-  "global_step": 17700,
+  "global_step": 17900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2839,6 +2839,38 @@
       "eval_samples_per_second": 25.637,
       "eval_steps_per_second": 3.205,
       "step": 17700
+    },
+    {
+      "epoch": 7.49,
+      "grad_norm": 3.0026488304138184,
+      "learning_rate": 3.778233215547704e-05,
+      "loss": 1.3286,
+      "step": 17800
+    },
+    {
+      "epoch": 7.49,
+      "eval_cer": 0.44898517852254505,
+      "eval_loss": 1.3857167959213257,
+      "eval_runtime": 387.1419,
+      "eval_samples_per_second": 24.482,
+      "eval_steps_per_second": 3.061,
+      "step": 17800
+    },
+    {
+      "epoch": 7.54,
+      "grad_norm": 4.501519203186035,
+      "learning_rate": 3.771166077738516e-05,
+      "loss": 1.3409,
+      "step": 17900
+    },
+    {
+      "epoch": 7.54,
+      "eval_cer": 0.4575813421453991,
+      "eval_loss": 2.416992664337158,
+      "eval_runtime": 359.7708,
+      "eval_samples_per_second": 26.345,
+      "eval_steps_per_second": 3.294,
+      "step": 17900
     }
   ],
   "logging_steps": 100,
@@ -2846,7 +2878,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.9400692292566293e+20,
+  "total_flos": 1.9617546605638022e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null