Training in progress, step 50100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c030a05cedfb701f1f900ac5f26cde012f010403c760db37339a226c2da019b
+oid sha256:5c467a55474359ea150af7f199402cf84590658e0255a9165922970cef84e170
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011ba2a8625abf53042a63306d8a7372e4ce9afaa38b9b2ed242865f4641eb35
+oid sha256:489d7ba688753abe3e33833a76b4ae882115ed3d90c66c7a1a12d1ffa7f82528
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ee240f317d6efe3bef85d93c11c29152c2835f327f23980767091f56826096
+oid sha256:f413dee5c854704d5963137b5956e9d25624be5f512c8185c3af5befb0aca4f7
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f06d58a45fbcf190e6121835ad9ae3823578f428a1fa2340da936ad10e470b66
-size 14503
+oid sha256:7672fe3061dcd7690545b653f58f4ee116feae4c3b67a28c5239aa57cd8e646c
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88466590320f3a52b9bb148645555d7df1e6a76ed6ca782ad8cb3e3e4334e3f9
+oid sha256:08ae60acffa23a34f3e2f8fcc14339c1e29295c511dc2b5dad5d07178f8a8bf5
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.00610397810987,
+  "epoch": 21.09029677962534,
   "eval_steps": 100,
-  "global_step": 49900,
+  "global_step": 50100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7991,6 +7991,38 @@
       "eval_samples_per_second": 24.261,
       "eval_steps_per_second": 3.033,
       "step": 49900
+    },
+    {
+      "epoch": 21.05,
+      "grad_norm": 4.511066913604736,
+      "learning_rate": 1.50339222614841e-05,
+      "loss": 0.3451,
+      "step": 50000
+    },
+    {
+      "epoch": 21.05,
+      "eval_cer": 0.34278332877087325,
+      "eval_loss": 2.672588348388672,
+      "eval_runtime": 415.0883,
+      "eval_samples_per_second": 22.834,
+      "eval_steps_per_second": 2.855,
+      "step": 50000
+    },
+    {
+      "epoch": 21.09,
+      "grad_norm": 3.952530860900879,
+      "learning_rate": 1.4963250883392227e-05,
+      "loss": 0.3449,
+      "step": 50100
+    },
+    {
+      "epoch": 21.09,
+      "eval_cer": 0.3425169136912909,
+      "eval_loss": 2.945607900619507,
+      "eval_runtime": 386.6565,
+      "eval_samples_per_second": 24.513,
+      "eval_steps_per_second": 3.065,
+      "step": 50100
     }
   ],
   "logging_steps": 100,
@@ -7998,7 +8030,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.468477204725173e+20,
+  "total_flos": 5.490253620598738e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null