Training in progress, step 49900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1cbd3e55b0179026181d720a477011010ff856f7a126f268ef27f3561d2d134
+oid sha256:9c030a05cedfb701f1f900ac5f26cde012f010403c760db37339a226c2da019b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3666578dccf6f10399ae741f901f6bff10f04f1d3e32956185152c183581c5
+oid sha256:011ba2a8625abf53042a63306d8a7372e4ce9afaa38b9b2ed242865f4641eb35
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22dc109d90b5af6d6ac2a29d4413cf79d645981920f0b93701c9be3341fda743
+oid sha256:37ee240f317d6efe3bef85d93c11c29152c2835f327f23980767091f56826096
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02990edbfb0b0fa25d6956ac586de6c5fa7a3f14caf505d91e0c9bba2fc45bab
-size 14567
+oid sha256:f06d58a45fbcf190e6121835ad9ae3823578f428a1fa2340da936ad10e470b66
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4bde301d33ddb7b9f708b0f2b4df433fe10f623f71b5b1ed245e09a9c0210de
+oid sha256:88466590320f3a52b9bb148645555d7df1e6a76ed6ca782ad8cb3e3e4334e3f9
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.921911176594403,
+  "epoch": 21.00610397810987,
   "eval_steps": 100,
-  "global_step": 49700,
+  "global_step": 49900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7959,6 +7959,38 @@
       "eval_samples_per_second": 24.299,
       "eval_steps_per_second": 3.038,
       "step": 49700
+    },
+    {
+      "epoch": 20.96,
+      "grad_norm": 2.362006902694702,
+      "learning_rate": 1.5175265017667845e-05,
+      "loss": 0.4054,
+      "step": 49800
+    },
+    {
+      "epoch": 20.96,
+      "eval_cer": 0.34167611747682924,
+      "eval_loss": 2.4431283473968506,
+      "eval_runtime": 408.3684,
+      "eval_samples_per_second": 23.209,
+      "eval_steps_per_second": 2.902,
+      "step": 49800
+    },
+    {
+      "epoch": 21.01,
+      "grad_norm": 1.828452706336975,
+      "learning_rate": 1.5104593639575973e-05,
+      "loss": 0.389,
+      "step": 49900
+    },
+    {
+      "epoch": 21.01,
+      "eval_cer": 0.3424289233897775,
+      "eval_loss": 2.5479896068573,
+      "eval_runtime": 390.6666,
+      "eval_samples_per_second": 24.261,
+      "eval_steps_per_second": 3.033,
+      "step": 49900
     }
   ],
   "logging_steps": 100,
@@ -7966,7 +7998,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.4456441634239906e+20,
+  "total_flos": 5.468477204725173e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null