Training in progress, step 5400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:526f37a1fd8614e33d688ca0c95a0b4bdb2270b3c6287907514481f46e211e72
+oid sha256:49a9af9605c3906a1b6201f31fe2e2fefb03a67c40a338ba51cff95ed8f7b20e
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ce64a952a4cce525f3a0cb0ed6d5e65ba07369000da2ff59f3ff55e450ce479
+oid sha256:f2774d795ce38b6d916deba57ca044f1e6fc174438a05dde9c1651a651c9e878
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c379ec78bc415dd3c67bb2c638a8e23762a3c06fee68b3ab33b1391af723912b
+oid sha256:63825d3eaa200eddbf762aeb8547833820295db590b26732e0e85a911b0d5d91
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:268b899628f3fbd3f8e86b05216b622b8e7edbffdb48136b8a16736e8c90ff48
+oid sha256:2e3f4a2dab0aeb0cd0b06645f79437bf62a24263c82bcbe99dbb49bfb3319ca7
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784d3c121c9f359553146d9fe14f9140da42065b084f4fa423f15dfc626b4e3b
+oid sha256:5dfb0d0b3b5a880ecd881c57b956364f90897bc6653e089f1f8e6e7eff0c817d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1890128394022312,
+  "epoch": 2.2732056409177015,
   "eval_steps": 100,
-  "global_step": 5200,
+  "global_step": 5400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -839,6 +839,38 @@
       "eval_samples_per_second": 26.241,
       "eval_steps_per_second": 3.281,
       "step": 5200
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 2.109961986541748,
+      "learning_rate": 4.661342756183746e-05,
+      "loss": 2.4585,
+      "step": 5300
+    },
+    {
+      "epoch": 2.23,
+      "eval_cer": 0.5222273278323101,
+      "eval_loss": 1.6703613996505737,
+      "eval_runtime": 374.7053,
+      "eval_samples_per_second": 25.295,
+      "eval_steps_per_second": 3.162,
+      "step": 5300
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 3.7831201553344727,
+      "learning_rate": 4.654275618374558e-05,
+      "loss": 1.6107,
+      "step": 5400
+    },
+    {
+      "epoch": 2.27,
+      "eval_cer": 0.5470601462594346,
+      "eval_loss": 2.0870959758758545,
+      "eval_runtime": 367.5169,
+      "eval_samples_per_second": 25.789,
+      "eval_steps_per_second": 3.224,
+      "step": 5400
     }
   ],
   "logging_steps": 100,
@@ -846,7 +878,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.703634893009586e+19,
+  "total_flos": 5.92170964075638e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null