Training in progress, step 16700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffcfe122bd2d59d01967428904ec5ea9fa859cb879f1770bb1d1e760b1b7688c
+oid sha256:3132aba995deb3e9a62f8586490ea152a8c2191d407f35d7797370ed0f468775
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f82abcf3aa79e7aebdfb7e800e2da4ec60cfd150519c69f6e42fff57f12e5649
+oid sha256:38bfe3bf3a40f1e030bac1d38293804c951b5e71979c1aa88a546da71cd72ede
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4863c0159897cbd8e6cad80102a7234e43e4dd9ec61c50a16d612844e381c121
+oid sha256:c761581dae884ee2dc52193ff57723855ada2efff7b89719e658ab91db8d56e1
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:958c40c9a12bc1ec4000782ee24253ec47677cd329681042cb696da20d4daa37
-size 14567
+oid sha256:39ce27b6fe5c4a6a8ed11673dc9593b6a866d17de3e334d7e9d50d3687ae64fa
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:815a23a9cc5b941ec9802a205234677f07d3ff4d13a1a86a9f1b1c15fe345d83
+oid sha256:0bb9f1f915324f76cd3b7d66524b9d86b094231ff2bf22c1a230837b1a765ae4
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.94590612502631,
+  "epoch": 7.030098926541781,
   "eval_steps": 100,
-  "global_step": 16500,
+  "global_step": 16700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2647,6 +2647,38 @@
       "eval_samples_per_second": 26.36,
       "eval_steps_per_second": 3.296,
       "step": 16500
+    },
+    {
+      "epoch": 6.99,
+      "grad_norm": 1.8204373121261597,
+      "learning_rate": 3.862968197879859e-05,
+      "loss": 1.3562,
+      "step": 16600
+    },
+    {
+      "epoch": 6.99,
+      "eval_cer": 0.46081498572601776,
+      "eval_loss": 2.0778937339782715,
+      "eval_runtime": 381.9051,
+      "eval_samples_per_second": 24.818,
+      "eval_steps_per_second": 3.103,
+      "step": 16600
+    },
+    {
+      "epoch": 7.03,
+      "grad_norm": 2.9875051975250244,
+      "learning_rate": 3.8559010600706715e-05,
+      "loss": 1.5916,
+      "step": 16700
+    },
+    {
+      "epoch": 7.03,
+      "eval_cer": 0.4623352626021665,
+      "eval_loss": 1.5354750156402588,
+      "eval_runtime": 364.3123,
+      "eval_samples_per_second": 26.016,
+      "eval_steps_per_second": 3.253,
+      "step": 16700
     }
   ],
   "logging_steps": 100,
@@ -2654,7 +2686,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.807384038236432e+20,
+  "total_flos": 1.8305404207742734e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null