Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6167a9f6b238b3dbfbb950bbc3428dffa998034db7242b7ef36b96b8adc12668
+oid sha256:3612fb6c97d25f57095cd8da238025d105f021876634f942e036be79b23efbc5
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd5131717a4e420c7462a1d939ba955b5ebe953944ddda95cd04f64659b6ed26
+oid sha256:57890acb94892b877e4fdf752de51ca28d6d8ba4a8b5ee7ea378f375c626533e
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9611b036ac3f2836113e9fdeb6da59715da9ea7d5e07a531cbd88b2e54f047b0
+oid sha256:671a296d94ac67b9f09b18ab5a94576b53e9c42961d232c595403b7d7a6997ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298586c13efa69da1b703016fc18b029e1de4866603208203d548561e3ce7e74
+oid sha256:7c427886fe1e96c56c52bab98f8a92bec6316c84f4483ba9d42d61192c219792
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7441860465116279,
+  "epoch": 0.7513416815742398,
   "eval_steps": 500,
-  "global_step": 2080,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1671,14 +1671,30 @@
       "loss": 0.3961,
       "num_input_tokens_seen": 1409417,
       "step": 2080
+    },
+    {
+      "epoch": 0.7477638640429338,
+      "grad_norm": 0.3994668424129486,
+      "learning_rate": 5.044722719141324e-05,
+      "loss": 0.417,
+      "num_input_tokens_seen": 1416404,
+      "step": 2090
+    },
+    {
+      "epoch": 0.7513416815742398,
+      "grad_norm": 0.372256338596344,
+      "learning_rate": 4.973166368515206e-05,
+      "loss": 0.3864,
+      "num_input_tokens_seen": 1423004,
+      "step": 2100
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1409417,
+  "num_input_tokens_seen": 1423004,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.1692811126081536e+16,
+  "total_flos": 3.199833477505843e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null