Training in progress, step 2260, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0632b909fd1c9aca69067d0bed149621d32fc888cd885edfe8a9c9167000cd0
+oid sha256:5077a398af295249ce2f4d98872ffaaf66d62ab91667ded3732057696cb98d05
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12617d04abf8d5849ea18ccd1caeaec1b356dd520401e75c5bd06ee3fc8e8aa6
+oid sha256:5f37afe2c737cc2e3e0daf8579556cc1d76cf5d3b7d751612fad5ffa14825dfc
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b4460282b72eb6f8903bafdf89fcbbe259019be8c29ef42adde2e2a7ce8a185
+oid sha256:200623e06ecf672802d7eae0c71722793b083804f6358d7108007423c07e494e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f05e22fba1c2918a10ec5938a0705454f8a1b28f2198ed555d6f8a3e293559a
+oid sha256:8f24aa350ef290461846581cc1e60d9a5fe6b837e2dd0a4ee4c53e1368aeb953
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8014311270125224,
+  "epoch": 0.8085867620751341,
   "eval_steps": 500,
-  "global_step": 2240,
+  "global_step": 2260,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1799,14 +1799,30 @@
       "loss": 0.3883,
       "num_input_tokens_seen": 1515223,
       "step": 2240
+    },
+    {
+      "epoch": 0.8050089445438283,
+      "grad_norm": 0.30987629294395447,
+      "learning_rate": 3.899821109123435e-05,
+      "loss": 0.3868,
+      "num_input_tokens_seen": 1523801,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8085867620751341,
+      "grad_norm": 0.2742662727832794,
+      "learning_rate": 3.828264758497317e-05,
+      "loss": 0.369,
+      "num_input_tokens_seen": 1530483,
+      "step": 2260
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1515223,
+  "num_input_tokens_seen": 1530483,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.4072014423619584e+16,
+  "total_flos": 3.4415157934577664e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null