Training in progress, step 42600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb5e8a8c3913874632acd49200dba6774b649b80d691bac2de8698703d173f2
+oid sha256:bfd083cd2c2adf295b4416b5a6cbd62c8ae4ec825f7d712b8b23db3c311e6447
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2a365b2b1eda3b4d40d294bf3d1d2528140be1086ee7281be0cb77eac082dd5
+oid sha256:9a90a16894239d60d395cbbb59c27fe238ba58a4b4698a2124c23c282724e5d8
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b4fbf04fb8e2638c63948e77b404a82ac1a1199d47aa7e8daef622cf570a3c
+oid sha256:074cb3e9f93346af354cfcf651447bb7e30eb63cfb4d4755f7940c1910946f52
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed2ef934924df36237d6b92f88d8afdb2ae9179694a6e1795a8c6982411bfbd
+oid sha256:fc15f6e11474bda0aeb4de725889e5fe80ddfdc6c26f74bc09de3156f76d497d
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381e5d2327dff853aa604f48fadfd328924933b3ceb5ad7ae600c987d864cb21
+oid sha256:aee091f7285a2fae77250085cbf6825e16ec2cbc3b1e9f9b28f5ea3798afa697
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.84887392127973,
+  "epoch": 17.9330667227952,
   "eval_steps": 100,
-  "global_step": 42400,
+  "global_step": 42600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6791,6 +6791,38 @@
       "eval_samples_per_second": 24.999,
       "eval_steps_per_second": 3.126,
       "step": 42400
+    },
+    {
+      "epoch": 17.89,
+      "grad_norm": 4.927220344543457,
+      "learning_rate": 2.0332155477031804e-05,
+      "loss": 0.6499,
+      "step": 42500
+    },
+    {
+      "epoch": 17.89,
+      "eval_cer": 0.3600440929177584,
+      "eval_loss": 2.656733512878418,
+      "eval_runtime": 405.5316,
+      "eval_samples_per_second": 23.372,
+      "eval_steps_per_second": 2.922,
+      "step": 42500
+    },
+    {
+      "epoch": 17.93,
+      "grad_norm": 1.9719730615615845,
+      "learning_rate": 2.0261484098939932e-05,
+      "loss": 0.6453,
+      "step": 42600
+    },
+    {
+      "epoch": 17.93,
+      "eval_cer": 0.3558694419459544,
+      "eval_loss": 3.2607502937316895,
+      "eval_runtime": 381.4619,
+      "eval_samples_per_second": 24.847,
+      "eval_steps_per_second": 3.106,
+      "step": 42600
     }
   ],
   "logging_steps": 100,
@@ -6798,7 +6830,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.646327481092861e+20,
+  "total_flos": 4.6682581684747534e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null