Training in progress, step 42400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f693484def2b2a6313d116c6f4c54dafa51df3b9cbbafe6194f4aebf6a1037f4
+oid sha256:8eb5e8a8c3913874632acd49200dba6774b649b80d691bac2de8698703d173f2
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111113eeb7f0cfb250b86c2d9112db0d080532efaab2b65ce354d94770c0163a
+oid sha256:b2a365b2b1eda3b4d40d294bf3d1d2528140be1086ee7281be0cb77eac082dd5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761caed2751672ced9080aac4251531b7fdea3daeaed6abed0a76b368594d8e0
+oid sha256:85b4fbf04fb8e2638c63948e77b404a82ac1a1199d47aa7e8daef622cf570a3c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cad0da5e21b95095501337deb354a217aa91e17d351f9de3d09b404d08ce3095
-size 14503
+oid sha256:bed2ef934924df36237d6b92f88d8afdb2ae9179694a6e1795a8c6982411bfbd
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0634da82e984807c433cb6f91a27dc4d3830ec402aae54effd98d0a8ab70cc0
+oid sha256:381e5d2327dff853aa604f48fadfd328924933b3ceb5ad7ae600c987d864cb21
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.76468111976426,
+  "epoch": 17.84887392127973,
   "eval_steps": 100,
-  "global_step": 42200,
+  "global_step": 42400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6759,6 +6759,38 @@
       "eval_samples_per_second": 25.028,
       "eval_steps_per_second": 3.129,
       "step": 42200
+    },
+    {
+      "epoch": 17.81,
+      "grad_norm": 2.2286911010742188,
+      "learning_rate": 2.0473498233215547e-05,
+      "loss": 0.6528,
+      "step": 42300
+    },
+    {
+      "epoch": 17.81,
+      "eval_cer": 0.3575412576747096,
+      "eval_loss": 1.9768012762069702,
+      "eval_runtime": 400.1546,
+      "eval_samples_per_second": 23.686,
+      "eval_steps_per_second": 2.961,
+      "step": 42300
+    },
+    {
+      "epoch": 17.85,
+      "grad_norm": 1.9678279161453247,
+      "learning_rate": 2.0402826855123676e-05,
+      "loss": 0.641,
+      "step": 42400
+    },
+    {
+      "epoch": 17.85,
+      "eval_cer": 0.3585751437174925,
+      "eval_loss": 2.0739636421203613,
+      "eval_runtime": 379.1375,
+      "eval_samples_per_second": 24.999,
+      "eval_steps_per_second": 3.126,
+      "step": 42400
     }
   ],
   "logging_steps": 100,
@@ -6766,7 +6798,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.624647649840507e+20,
+  "total_flos": 4.646327481092861e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null