Training in progress, step 19000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb4a32dca6535b97ec9d409e1a20428735a6caf1a07d9a581e33bfebdd98da98
+oid sha256:9b96997d86855d69f2ad5126d93fcaa54d3bb37195a13dc04ebef709b51c988a
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deeb9007a2105b9fb534ca944aa12eb54abb9e830e8010cc6a86bc5057ba3f51
+oid sha256:2dcc8a135a59102ea5c9d0c77b48315f089af1d4a5eded0462368e4cf5d7d152
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b60272ee229edfde841bdf64339526be164c159e635b4cca6a36b012e8b8f8
+oid sha256:3771dca6c0b151af7b4eb4d18b275f53f8d0c4b7179fb5a0fd76724d6b7cf4c1
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76df4b30fe1f8da5a7cc93cde7f754197127ebb58da2a061a690a113c1c8f092
+oid sha256:0328bf636a13aba797b6ceefa1ee4d2a305b1300590ae78b037aaff65884a506
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f6690eee3cc7efd55068f6778b0cdb2acd34211dc189d0a8d254cc2fc4d966
+oid sha256:1c89953ed9353ba4a200c5e4beeaf9f9e987021f05c25ac9cfcda9cf4c598560
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.91412334245422,
+  "epoch": 7.99831614396969,
   "eval_steps": 100,
-  "global_step": 18800,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3015,6 +3015,38 @@
       "eval_samples_per_second": 26.274,
       "eval_steps_per_second": 3.285,
       "step": 18800
+    },
+    {
+      "epoch": 7.96,
+      "grad_norm": 9.81248950958252,
+      "learning_rate": 3.700494699646643e-05,
+      "loss": 1.327,
+      "step": 18900
+    },
+    {
+      "epoch": 7.96,
+      "eval_cer": 0.45252678815846076,
+      "eval_loss": 2.999907970428467,
+      "eval_runtime": 382.5678,
+      "eval_samples_per_second": 24.775,
+      "eval_steps_per_second": 3.097,
+      "step": 18900
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.9528186321258545,
+      "learning_rate": 3.693427561837456e-05,
+      "loss": 1.3228,
+      "step": 19000
+    },
+    {
+      "epoch": 8.0,
+      "eval_cer": 0.4471960423917719,
+      "eval_loss": 1.6979167461395264,
+      "eval_runtime": 363.6541,
+      "eval_samples_per_second": 26.063,
+      "eval_steps_per_second": 3.259,
+      "step": 19000
     }
   ],
   "logging_steps": 100,
@@ -3022,7 +3054,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.0599593093311608e+20,
+  "total_flos": 2.0812889749495287e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null