Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbb1b9bf8cecc82c992b1f0dd17c659790fe9b529483d08774f61e623e89591
+oid sha256:66e3856c23d2e195eb9ae7df24f61ed2a0f7d8ece6b19c7bd72766eca908cb01
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832bb0c6b1189792a3803205e28282733c69357c7a98db906a5b6648c86412ed
+oid sha256:68513830fbf72ea70a1b5ed7fcd232e3c6856576863986c98edcb8f6ea26573a
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b16d7438102d976fb534815d7fb6c3fbd3eb0ad6701c9593c3dd315e6b65b9be
+oid sha256:2c205b5697621377980e186326089bd957e1153b34f60a9fe258d7a714fbda01
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e7b2fb94aba803f2a2d188b149647000a6898e962a195b1f1cc848db18fce06
+oid sha256:44e43231b8b3ce29488aa83c0d16aa2f601068365267d1bd1f2fa894d989bc15
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6368515205724508,
+  "epoch": 0.6440071556350626,
   "eval_steps": 500,
-  "global_step": 1780,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1431,14 +1431,30 @@
       "loss": 0.4004,
       "num_input_tokens_seen": 1205284,
       "step": 1780
+    },
+    {
+      "epoch": 0.6404293381037567,
+      "grad_norm": 0.3555593192577362,
+      "learning_rate": 7.191413237924867e-05,
+      "loss": 0.386,
+      "num_input_tokens_seen": 1210701,
+      "step": 1790
+    },
+    {
+      "epoch": 0.6440071556350626,
+      "grad_norm": 0.3081437349319458,
+      "learning_rate": 7.119856887298749e-05,
+      "loss": 0.3885,
+      "num_input_tokens_seen": 1217841,
+      "step": 1800
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1205284,
+  "num_input_tokens_seen": 1217841,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.710258082972467e+16,
+  "total_flos": 2.738494341603533e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null