Training in progress, step 2080, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aacd2486ad0dffb879950bbd0e228566072cada12669efb472827ad02827bee1
+oid sha256:6167a9f6b238b3dbfbb950bbc3428dffa998034db7242b7ef36b96b8adc12668
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5211b09fe504a464e43c55dfc38d2344163312b5195fd5daf7f89e63f7ced18
+oid sha256:dd5131717a4e420c7462a1d939ba955b5ebe953944ddda95cd04f64659b6ed26
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134cb87f21fc79818d41b8f638e21e286fa4116529d636e02de189068c5b06fb
+oid sha256:9611b036ac3f2836113e9fdeb6da59715da9ea7d5e07a531cbd88b2e54f047b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5b38b213077a686f76d4c3ad3d757ef1baf287b742f46835bdf0d82ea6cc979
+oid sha256:298586c13efa69da1b703016fc18b029e1de4866603208203d548561e3ce7e74
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7370304114490162,
+  "epoch": 0.7441860465116279,
   "eval_steps": 500,
-  "global_step": 2060,
+  "global_step": 2080,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1655,14 +1655,30 @@
       "loss": 0.3869,
       "num_input_tokens_seen": 1395702,
       "step": 2060
+    },
+    {
+      "epoch": 0.740608228980322,
+      "grad_norm": 0.2900319993495941,
+      "learning_rate": 5.18783542039356e-05,
+      "loss": 0.3963,
+      "num_input_tokens_seen": 1402155,
+      "step": 2070
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 0.27532869577407837,
+      "learning_rate": 5.1162790697674425e-05,
+      "loss": 0.3961,
+      "num_input_tokens_seen": 1409417,
+      "step": 2080
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1395702,
+  "num_input_tokens_seen": 1409417,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.1384409209122816e+16,
+  "total_flos": 3.1692811126081536e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null