Training in progress, step 7900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7035fed27b87e53ef5459140a353c4757291550688e801bd1a0749612505385
+oid sha256:fcf23930d595ea17c01a47edb3798852592d31dfd889457b2d9d1c679c37f37c
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9308fa164b0a0e31eab5e62c35936cfc1077227e00e83d664edb27c65c44c8c3
+oid sha256:072b89b705b64c5ce2d1ed54311d307c5b17debef3a5bed90eb6ae9ae9aeeb3c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3b9a39df796a8f78147f1c34914a1acc6755648902c94af056852922118959f
+oid sha256:cc97c919648478a76fc77d365b16ccd77e7685605a6c32a7a953ccbca70c1486
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a122898eab5e64ec9f7a327b27560bc6d150e37aff057ddeb4ae81aad25785fb
-size 14567
+oid sha256:bd14d107eddb60c68c35f7471eb98fd20b6fccbc6c5557a787e6bfda0de7513c
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86686b461d0cb83b0c1cfa82a7f2c4a32e887c3772a7cfc60e249f37abcb8d0
+oid sha256:e743b0e6a41e962bc63d9c92583e4d59314ce7fec2d27ef3526e9f1e5a66f4c2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.2414228583456115,
+  "epoch": 3.3256156598610818,
   "eval_steps": 100,
-  "global_step": 7700,
+  "global_step": 7900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1239,6 +1239,38 @@
       "eval_samples_per_second": 26.67,
       "eval_steps_per_second": 3.334,
       "step": 7700
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 2.799055576324463,
+      "learning_rate": 4.4847349823321555e-05,
+      "loss": 3.4812,
+      "step": 7800
+    },
+    {
+      "epoch": 3.28,
+      "eval_cer": 0.49670036369324627,
+      "eval_loss": 3.4256324768066406,
+      "eval_runtime": 374.5672,
+      "eval_samples_per_second": 25.304,
+      "eval_steps_per_second": 3.164,
+      "step": 7800
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 2.1845884323120117,
+      "learning_rate": 4.477667844522968e-05,
+      "loss": 3.0965,
+      "step": 7900
+    },
+    {
+      "epoch": 3.33,
+      "eval_cer": 0.5227894880919792,
+      "eval_loss": 1.759318232536316,
+      "eval_runtime": 366.7135,
+      "eval_samples_per_second": 25.846,
+      "eval_steps_per_second": 3.231,
+      "step": 7900
     }
   ],
   "logging_steps": 100,
@@ -1246,7 +1278,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 8.450652260775636e+19,
+  "total_flos": 8.66663762734376e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null