Training in progress, step 35100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b206f2369d31cae35a08aab2df578e781b6943ef77ce53d8ba5787f71a665d5
+oid sha256:4d51827e7f72b6ac13c7717909863137b26f796acdc33d0c423939d31b26e877
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae2198c7d773d1f56253a07cd8ae7a4c209a916ae2f8d8eda3a288ec2b9d3a1
+oid sha256:ba371bbb66479ca88edc50cd8c19bfba12e60e4cf0ec3ad5a6c9f0889746173e
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9be35650088eb24a02be1e6a194809f0cc95f8e622d969c1b31c9e1e0a7e851
+oid sha256:2c302482ccc44393e57785ca619efb81e7753d4f5ae50c608e086133a7e9658c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab3843d78d7e496fe9b5af38e4b4d8927ff90626a6cfdc3d3f661a4b13faa85
+oid sha256:63135dd8fba75904a387c365b3db0392d738b290969b3cffabe4604b1916dbc0
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9054242e692acef1ddb101099ef9d20fe1d70541a460911930073f47b77157
+oid sha256:879222c4151189909f68ebdb26981095b855d468d9fc1fdcd4a5718b314345ac
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.69164386444959,
+  "epoch": 14.775836665965059,
   "eval_steps": 100,
-  "global_step": 34900,
+  "global_step": 35100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5591,6 +5591,38 @@
       "eval_samples_per_second": 25.85,
       "eval_steps_per_second": 3.232,
       "step": 34900
+    },
+    {
+      "epoch": 14.73,
+      "grad_norm": 2.4123330116271973,
+      "learning_rate": 2.5631095406360423e-05,
+      "loss": 1.0998,
+      "step": 35000
+    },
+    {
+      "epoch": 14.73,
+      "eval_cer": 0.3869789018810371,
+      "eval_loss": 1.8494433164596558,
+      "eval_runtime": 395.7827,
+      "eval_samples_per_second": 23.947,
+      "eval_steps_per_second": 2.994,
+      "step": 35000
+    },
+    {
+      "epoch": 14.78,
+      "grad_norm": 2.7764666080474854,
+      "learning_rate": 2.5560424028268555e-05,
+      "loss": 0.9243,
+      "step": 35100
+    },
+    {
+      "epoch": 14.78,
+      "eval_cer": 0.38634097219506475,
+      "eval_loss": 1.8553264141082764,
+      "eval_runtime": 368.5207,
+      "eval_samples_per_second": 25.719,
+      "eval_steps_per_second": 3.216,
+      "step": 35100
     }
   ],
   "logging_steps": 100,
@@ -5598,7 +5630,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.824337597929555e+20,
+  "total_flos": 3.8462099464838395e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null