Training in progress, step 16900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3132aba995deb3e9a62f8586490ea152a8c2191d407f35d7797370ed0f468775
+oid sha256:87bc7c877cdfbe54847b102871e2d4073e1e3b3e77f4628403c62609d4215ee0
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38bfe3bf3a40f1e030bac1d38293804c951b5e71979c1aa88a546da71cd72ede
+oid sha256:3fa0adf8ce583fad0205dd992aeb22f4bb05366efc58cf6b0feae933acf7733a
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c761581dae884ee2dc52193ff57723855ada2efff7b89719e658ab91db8d56e1
+oid sha256:1057f87e50786d1aca543245abd8aa5218ae3920b5ed10328f1cc6e8d05b8fb8
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ce27b6fe5c4a6a8ed11673dc9593b6a866d17de3e334d7e9d50d3687ae64fa
-size 14503
+oid sha256:70bc272cae15954849873b08592843a4166415a3756dbd7282f8116aed448377
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bb9f1f915324f76cd3b7d66524b9d86b094231ff2bf22c1a230837b1a765ae4
+oid sha256:e5e32e74e7ac82af1d3f98e8ce057551c88fd1fff091ef003d7c5821593146b8
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.030098926541781,
+  "epoch": 7.1142917280572515,
   "eval_steps": 100,
-  "global_step": 16700,
+  "global_step": 16900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2679,6 +2679,38 @@
       "eval_samples_per_second": 26.016,
       "eval_steps_per_second": 3.253,
       "step": 16700
+    },
+    {
+      "epoch": 7.07,
+      "grad_norm": 4.643332004547119,
+      "learning_rate": 3.848833922261484e-05,
+      "loss": 1.3365,
+      "step": 16800
+    },
+    {
+      "epoch": 7.07,
+      "eval_cer": 0.46146024793711626,
+      "eval_loss": 1.8595181703567505,
+      "eval_runtime": 374.6805,
+      "eval_samples_per_second": 25.296,
+      "eval_steps_per_second": 3.163,
+      "step": 16800
+    },
+    {
+      "epoch": 7.11,
+      "grad_norm": 2.433307409286499,
+      "learning_rate": 3.841766784452297e-05,
+      "loss": 1.6175,
+      "step": 16900
+    },
+    {
+      "epoch": 7.11,
+      "eval_cer": 0.468870986664581,
+      "eval_loss": 1.7079046964645386,
+      "eval_runtime": 364.7345,
+      "eval_samples_per_second": 25.986,
+      "eval_steps_per_second": 3.249,
+      "step": 16900
     }
   ],
   "logging_steps": 100,
@@ -2686,7 +2718,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.8305404207742734e+20,
+  "total_flos": 1.8525968673735387e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null