Training in progress, step 6200, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d64164218ceb70df3188e5d55bcfa4289cb63f7182305fcc19b63af2b99185
+oid sha256:4a863722ec1d87aec7fd9e98fc57ce968157fd4527814212a9254f9bf4b2eccd
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c5f7365e986a4df25beb4c71b990dd0017fde5984b8e75111d186387f61b95
+oid sha256:5cb744f0d5f666422c5a7f99a1d8df94750f263c7d24426930046bab63c6d24b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc61d44fe8afd95895c257c0e8778313394a3453a26e03b583759623c7260b89
+oid sha256:7eeab5a3fec411dde41e1e4da5efdaacfe0816dd24edffca8142d79b058cfe80
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69fe8240e55c5995426573757e5623029e976dcfdb9639d983a89e4307225f9
+oid sha256:c02d15367d3e2c48c0709cb18e5d948989b3d743d9405d0ec8c31cf19092d33c
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe5c154bf4966b68a2d37446afad8d6e4131f9298c56c1acc1015e0b966ad66
+oid sha256:491f92ba9ce65f06837d35b0bf7a55395d7ef01dd1adf1e1cc66473509666736
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5257840454641127,
+  "epoch": 2.609976846979583,
   "eval_steps": 100,
-  "global_step": 6000,
+  "global_step": 6200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -967,6 +967,38 @@
       "eval_samples_per_second": 26.063,
       "eval_steps_per_second": 3.259,
       "step": 6000
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 3.353976249694824,
+      "learning_rate": 4.604805653710248e-05,
+      "loss": 1.7398,
+      "step": 6100
+    },
+    {
+      "epoch": 2.57,
+      "eval_cer": 0.5255465175394001,
+      "eval_loss": 2.6437551975250244,
+      "eval_runtime": 380.4559,
+      "eval_samples_per_second": 24.912,
+      "eval_steps_per_second": 3.115,
+      "step": 6100
+    },
+    {
+      "epoch": 2.61,
+      "grad_norm": 2.671917676925659,
+      "learning_rate": 4.5978091872791526e-05,
+      "loss": 2.2359,
+      "step": 6200
+    },
+    {
+      "epoch": 2.61,
+      "eval_cer": 0.537452094169176,
+      "eval_loss": 3.4509007930755615,
+      "eval_runtime": 364.3511,
+      "eval_samples_per_second": 26.013,
+      "eval_steps_per_second": 3.252,
+      "step": 6200
     }
   ],
   "logging_steps": 100,
@@ -974,7 +1006,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.577336385232916e+19,
+  "total_flos": 6.794282177267883e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null