Training in progress, step 6400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a863722ec1d87aec7fd9e98fc57ce968157fd4527814212a9254f9bf4b2eccd
+oid sha256:ac7d16d29dc7622f01e2d28eecb7e0add759d0f9d8043d96d64fde190f2fa5ad
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cb744f0d5f666422c5a7f99a1d8df94750f263c7d24426930046bab63c6d24b
+oid sha256:5af8744b4590c2dc3360130a9d9a624f707d729192543e3c10acf72e8b1c6050
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eeab5a3fec411dde41e1e4da5efdaacfe0816dd24edffca8142d79b058cfe80
+oid sha256:1e2eb66119faf4da4efd1d509bddf53a23b7f025570fd8de5b78afa3bd1309aa
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c02d15367d3e2c48c0709cb18e5d948989b3d743d9405d0ec8c31cf19092d33c
-size 14567
+oid sha256:a13ae0fb662f6207edb63c99af46719be7164af933cafaf35984cf8a7790df00
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:491f92ba9ce65f06837d35b0bf7a55395d7ef01dd1adf1e1cc66473509666736
+oid sha256:edca11951c56aed9e8cdf63fe04accd5c41069d01ff1b594b65f6a3496d35be5
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.609976846979583,
+  "epoch": 2.6941696484950537,
   "eval_steps": 100,
-  "global_step": 6200,
+  "global_step": 6400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -999,6 +999,38 @@
       "eval_samples_per_second": 26.013,
       "eval_steps_per_second": 3.252,
       "step": 6200
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 10.607972145080566,
+      "learning_rate": 4.590742049469965e-05,
+      "loss": 3.6419,
+      "step": 6300
+    },
+    {
+      "epoch": 2.65,
+      "eval_cer": 0.5374105431934614,
+      "eval_loss": 2.2622523307800293,
+      "eval_runtime": 370.8325,
+      "eval_samples_per_second": 25.559,
+      "eval_steps_per_second": 3.196,
+      "step": 6300
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 4.678300857543945,
+      "learning_rate": 4.5836749116607775e-05,
+      "loss": 1.7309,
+      "step": 6400
+    },
+    {
+      "epoch": 2.69,
+      "eval_cer": 0.5418393883696375,
+      "eval_loss": 1.8007577657699585,
+      "eval_runtime": 357.8741,
+      "eval_samples_per_second": 26.484,
+      "eval_steps_per_second": 3.311,
+      "step": 6400
     }
   ],
   "logging_steps": 100,
@@ -1006,7 +1038,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.794282177267883e+19,
+  "total_flos": 7.012483001392289e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null