Training in progress, step 6000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057f9570a6cc72688abe71630c100e57d8ed5e79a107a7c1dbf260b46e1fd4da
+oid sha256:43d64164218ceb70df3188e5d55bcfa4289cb63f7182305fcc19b63af2b99185
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36620432df2b5bec3be20dd101be03752eb30e228a15f087605a4b1b3817ad40
+oid sha256:f0c5f7365e986a4df25beb4c71b990dd0017fde5984b8e75111d186387f61b95
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d7b821883cd1ae362dfa89c4e8eef945c5104a2fd3f8917f33805e64a31688a
+oid sha256:bc61d44fe8afd95895c257c0e8778313394a3453a26e03b583759623c7260b89
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a3b30c167fde20793f59d220cb75d7e62231451f8337cafebba1ca6c36c689
+oid sha256:f69fe8240e55c5995426573757e5623029e976dcfdb9639d983a89e4307225f9
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f36e4a30c4e4159533881d5d1202edb3c351c6c5b1afb1031c411b06ae9325
+oid sha256:8fe5c154bf4966b68a2d37446afad8d6e4131f9298c56c1acc1015e0b966ad66
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.4415912439486425,
+  "epoch": 2.5257840454641127,
   "eval_steps": 100,
-  "global_step": 5800,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -935,6 +935,38 @@
       "eval_samples_per_second": 26.94,
       "eval_steps_per_second": 3.368,
       "step": 5800
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 2.4776511192321777,
+      "learning_rate": 4.618939929328622e-05,
+      "loss": 2.3876,
+      "step": 5900
+    },
+    {
+      "epoch": 2.48,
+      "eval_cer": 0.5089310156036134,
+      "eval_loss": 3.134875774383545,
+      "eval_runtime": 372.2436,
+      "eval_samples_per_second": 25.462,
+      "eval_steps_per_second": 3.183,
+      "step": 5900
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 9.97956657409668,
+      "learning_rate": 4.611872791519435e-05,
+      "loss": 4.1527,
+      "step": 6000
+    },
+    {
+      "epoch": 2.53,
+      "eval_cer": 0.4981815337687224,
+      "eval_loss": 1.7425427436828613,
+      "eval_runtime": 363.658,
+      "eval_samples_per_second": 26.063,
+      "eval_steps_per_second": 3.259,
+      "step": 6000
     }
   ],
   "logging_steps": 100,
@@ -942,7 +974,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 6.356688358918305e+19,
+  "total_flos": 6.577336385232916e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null