Training in progress, step 15300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd61a41f4cf03f5858195ca5fe96d3c3669fe49f638ea09912e26a01aa52e086
+oid sha256:31e3b409ae9269874d0dd07332eaabd922261fe01cec899b7c68b52edc3ad9fd
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0916989ad40b3bfe12c6ac9e11f6329dbeaad0ddceacffcd280cb2def46715a8
+oid sha256:c1863c52a91cc2b8af17921581add7d3bdb0649beb55c88accdc1808b8887921
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a98ae89a09009e626d84ebaa74d059e720c000f959a2a59e925259dd1b538d
+oid sha256:e7b49ad51dac0d37607816c8facfc0a5fc8fab9c0432f13fc416fe9a10708dbf
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c18a3a2fcaa038440f8b838aa2256d7e37374c67a3328231524132648f3eb179
+oid sha256:fa352733c862d27845c9026dc711e2ed499a1cad4d9c2f6e899513e4bf06feaf
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29cec3c1ed3d0958d8f6b240320ad40e3ee07494f39436857c7553488102e86
+oid sha256:d3eed1d7dd9c8188a0bfa480abfdd7fb182d631c9cffcad33cd5ac2b85611af8
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.356556514418017,
+  "epoch": 6.440749315933488,
   "eval_steps": 100,
-  "global_step": 15100,
+  "global_step": 15300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2423,6 +2423,38 @@
       "eval_samples_per_second": 25.728,
       "eval_steps_per_second": 3.217,
       "step": 15100
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 22.448034286499023,
+      "learning_rate": 3.961908127208481e-05,
+      "loss": 1.3858,
+      "step": 15200
+    },
+    {
+      "epoch": 6.4,
+      "eval_cer": 0.45766688827187046,
+      "eval_loss": 1.999880313873291,
+      "eval_runtime": 380.7492,
+      "eval_samples_per_second": 24.893,
+      "eval_steps_per_second": 3.112,
+      "step": 15200
+    },
+    {
+      "epoch": 6.44,
+      "grad_norm": 10.558205604553223,
+      "learning_rate": 3.9548409893992935e-05,
+      "loss": 1.3921,
+      "step": 15300
+    },
+    {
+      "epoch": 6.44,
+      "eval_cer": 0.47037904266551955,
+      "eval_loss": 2.6411163806915283,
+      "eval_runtime": 363.6122,
+      "eval_samples_per_second": 26.066,
+      "eval_steps_per_second": 3.259,
+      "step": 15300
     }
   ],
   "logging_steps": 100,
@@ -2430,7 +2462,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.6546343911883774e+20,
+  "total_flos": 1.6764322951864136e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null