Training in progress, step 14900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8576ccb82b21bcc2b8addf4916f2f16bf5fac1bf334cb43ac6adf88efbcf106
+oid sha256:754b1828cc167e6cab0ffbfc255be209fdb52e699fa01a76ef98fb551e01e46f
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650672fda6e5ee3003c98bce94c3d3b2333fe3a6cbc8b34be4d9defa333723aa
+oid sha256:a389819ab49bc7ca78cb2be2fa01aa4870f6a6faba478c25fd1690a6389bc966
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23908ca485378ebcbd5221e3f9a4dfc2825be11cae4030a2167b67baabd7bf90
+oid sha256:414a7a1b420818e98a3d84f5bcf74aa2f7777a0ef52dcbde83df3ffb6cdca039
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e3479363f6845648909d8b217e2aa3767b3ef51cc2decc24f7fd96a7818af1
-size 14567
+oid sha256:c9c0687a4091703f6184c454999271ab1b078907b3d7227b3900790c9d656ca3
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73db81e910b9ea3c99b0a41dadeb749a85548b72d68b5ef751adf848d3f6ccc4
+oid sha256:2c25ac89a1303cae92d19e5e1836924b87fa1d1a947021780db194d57b5ef2f4
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.188170911387076,
+  "epoch": 6.272363712902547,
   "eval_steps": 100,
-  "global_step": 14700,
+  "global_step": 14900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2359,6 +2359,38 @@
       "eval_samples_per_second": 25.994,
       "eval_steps_per_second": 3.25,
       "step": 14700
+    },
+    {
+      "epoch": 6.23,
+      "grad_norm": 2.604834794998169,
+      "learning_rate": 3.99017667844523e-05,
+      "loss": 1.4781,
+      "step": 14800
+    },
+    {
+      "epoch": 6.23,
+      "eval_cer": 0.4741137421297564,
+      "eval_loss": 2.4959936141967773,
+      "eval_runtime": 380.3259,
+      "eval_samples_per_second": 24.921,
+      "eval_steps_per_second": 3.116,
+      "step": 14800
+    },
+    {
+      "epoch": 6.27,
+      "grad_norm": 5.067722797393799,
+      "learning_rate": 3.983109540636042e-05,
+      "loss": 1.6941,
+      "step": 14900
+    },
+    {
+      "epoch": 6.27,
+      "eval_cer": 0.4551322787532752,
+      "eval_loss": 2.24949049949646,
+      "eval_runtime": 359.186,
+      "eval_samples_per_second": 26.387,
+      "eval_steps_per_second": 3.299,
+      "step": 14900
     }
   ],
   "logging_steps": 100,
@@ -2366,7 +2398,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.6107102446089286e+20,
+  "total_flos": 1.63280482609936e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null