Training in progress, step 17500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9915848c279a32e634c469b0cd49c641ab6e19d1f12ab63586b15141e71e2ff
+oid sha256:abbcad510f5d6d17da77ac25180b09d3437fab9772e7c44ff2b3717ab2555827
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f68a28b7e883abd00c6a38b16ebfd97e5dbc91456ae2135fbf6f28e8d925b88f
+oid sha256:a68f90a5153d4c6d993bcbe7dfb647ef73f657679f4aaf49e0141450a805cabb
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7df9b4087f5ce2cea1f800e25a7466947cb6d1214cdffaffc25123e1bb0bb13
+oid sha256:bd60b24f7ae9d45a90489d4bf13a52080f5bef0765dbfd70e0655cc95cf2a575
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19a2b3d5b09e84e1a35bc5f845262cba53dc3c05a02dcd9cba7de0d91a8a4f5
-size 14567
+oid sha256:1c66fd25519e26fd88891aa401ed778beca63619aeba161031fca5e7539ce650
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9ba2f276f83843e2fa9769f7226e4efaa28337fe59f7a213254e795359656f2
+oid sha256:8d0b60ffa460bee76500f761630a9787c479b8332d14ac3a0ab84782353df19d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.282677331088192,
+  "epoch": 7.366870132603663,
   "eval_steps": 100,
-  "global_step": 17300,
+  "global_step": 17500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2775,6 +2775,38 @@
       "eval_samples_per_second": 26.189,
       "eval_steps_per_second": 3.274,
       "step": 17300
+    },
+    {
+      "epoch": 7.32,
+      "grad_norm": 3.9697859287261963,
+      "learning_rate": 3.8065017667844525e-05,
+      "loss": 1.3348,
+      "step": 17400
+    },
+    {
+      "epoch": 7.32,
+      "eval_cer": 0.460401920143913,
+      "eval_loss": 2.626167058944702,
+      "eval_runtime": 377.1422,
+      "eval_samples_per_second": 25.131,
+      "eval_steps_per_second": 3.142,
+      "step": 17400
+    },
+    {
+      "epoch": 7.37,
+      "grad_norm": 2.342355251312256,
+      "learning_rate": 3.7994346289752653e-05,
+      "loss": 2.0519,
+      "step": 17500
+    },
+    {
+      "epoch": 7.37,
+      "eval_cer": 0.4643712604121857,
+      "eval_loss": 1.923600196838379,
+      "eval_runtime": 360.7805,
+      "eval_samples_per_second": 26.271,
+      "eval_steps_per_second": 3.285,
+      "step": 17500
     }
   ],
   "logging_steps": 100,
@@ -2782,7 +2814,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.896270263543528e+20,
+  "total_flos": 1.9185164331179065e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null