Training in progress, step 11100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925ca6a7a657be372a1ede2493cfd96a2f133c25e9867ec4da48475676fa164f
+oid sha256:38845a6d475e55c7af4738fbf1bef5e6aa4428194cc36187595ff717d29e376d
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f27c0cb6141c94d0dacfc876e294ea98c7799ee63d706b3da7170f154c3148ea
+oid sha256:c448e3473a9bd6e3fca35633f4e7f2cc43de8978501fbe48005531b52a96c915
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e99b8e65f7bf166bd10fd6d514d5c480e8db3676f1ced31fa5161b09b6df98
+oid sha256:213bf4cf344741084305edd2d79cb275a078f419b2ad9b4078e43ce7d3755617
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327dc357355df114a69c34bffd061d4e755c0d795f133172f85021369d644224
+oid sha256:1ae07eed3236de31c3edf8dbd34e2911ff4cc229408ebfe09f2600715ceec861
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5da37cafd44a01d142bb7be841997aa67fccdece5e8c01b177bc8c267b367398
+oid sha256:a72c943223bc50a40d5a42f6ea92f61ddf405e907f0a3013f6482c87c32b94b0
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.588507682593138,
+  "epoch": 4.672700484108609,
   "eval_steps": 100,
-  "global_step": 10900,
+  "global_step": 11100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1751,6 +1751,38 @@
       "eval_samples_per_second": 26.189,
       "eval_steps_per_second": 3.274,
       "step": 10900
+    },
+    {
+      "epoch": 4.63,
+      "grad_norm": 1.7070709466934204,
+      "learning_rate": 4.258657243816255e-05,
+      "loss": 1.8732,
+      "step": 11000
+    },
+    {
+      "epoch": 4.63,
+      "eval_cer": 0.4698926518321536,
+      "eval_loss": 2.4386019706726074,
+      "eval_runtime": 373.6335,
+      "eval_samples_per_second": 25.367,
+      "eval_steps_per_second": 3.172,
+      "step": 11000
+    },
+    {
+      "epoch": 4.67,
+      "grad_norm": 11.575754165649414,
+      "learning_rate": 4.2515901060070675e-05,
+      "loss": 1.9211,
+      "step": 11100
+    },
+    {
+      "epoch": 4.67,
+      "eval_cer": 0.5030527746275077,
+      "eval_loss": 2.1613056659698486,
+      "eval_runtime": 353.1639,
+      "eval_samples_per_second": 26.837,
+      "eval_steps_per_second": 3.355,
+      "step": 11100
     }
   ],
   "logging_steps": 100,
@@ -1758,7 +1790,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.1931430816580592e+20,
+  "total_flos": 1.2150748438607638e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null