Training in progress, step 42800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd083cd2c2adf295b4416b5a6cbd62c8ae4ec825f7d712b8b23db3c311e6447
+oid sha256:5f3fe48a7f9a7950c3f5192c1381760445d2536c203f774c213fe6030cc54d5b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a90a16894239d60d395cbbb59c27fe238ba58a4b4698a2124c23c282724e5d8
+oid sha256:65c21f7ea185f2d6edfb6473b152b0747c194d41917ab9329acd84bfb6c5dc2f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074cb3e9f93346af354cfcf651447bb7e30eb63cfb4d4755f7940c1910946f52
+oid sha256:49f39beebeb407f963a212e24893da40a81bd4c1f5931713d30e89b46ab86f3b
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc15f6e11474bda0aeb4de725889e5fe80ddfdc6c26f74bc09de3156f76d497d
+oid sha256:8c5dd5b6adbd79cf2ac7181561cc774617ae917a7182e146aab5041d5014f6fe
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee091f7285a2fae77250085cbf6825e16ec2cbc3b1e9f9b28f5ea3798afa697
+oid sha256:db730777aa403ea449f67eca81518cbd04846ed2f8416611ee9829c6c93f3138
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.9330667227952,
+  "epoch": 18.01725952431067,
   "eval_steps": 100,
-  "global_step": 42600,
+  "global_step": 42800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6823,6 +6823,38 @@
       "eval_samples_per_second": 24.847,
       "eval_steps_per_second": 3.106,
       "step": 42600
+    },
+    {
+      "epoch": 17.98,
+      "grad_norm": 4.013895034790039,
+      "learning_rate": 2.0190812720848056e-05,
+      "loss": 0.6373,
+      "step": 42700
+    },
+    {
+      "epoch": 17.98,
+      "eval_cer": 0.3598925540651519,
+      "eval_loss": 3.0558464527130127,
+      "eval_runtime": 405.1328,
+      "eval_samples_per_second": 23.395,
+      "eval_steps_per_second": 2.925,
+      "step": 42700
+    },
+    {
+      "epoch": 18.02,
+      "grad_norm": 5.639492988586426,
+      "learning_rate": 2.0120141342756185e-05,
+      "loss": 0.6082,
+      "step": 42800
+    },
+    {
+      "epoch": 18.02,
+      "eval_cer": 0.3542000703922412,
+      "eval_loss": 2.6185314655303955,
+      "eval_runtime": 382.1723,
+      "eval_samples_per_second": 24.8,
+      "eval_steps_per_second": 3.101,
+      "step": 42800
     }
   ],
   "logging_steps": 100,
@@ -6830,7 +6862,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.6682581684747534e+20,
+  "total_flos": 4.690252137745783e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null