Training in progress, step 1780, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e48abae2f95ba4e9bedb869c8329abdb510faed9a580042f44d70a7f83dfedb
+oid sha256:4dbb1b9bf8cecc82c992b1f0dd17c659790fe9b529483d08774f61e623e89591
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a06145c0e4a87e3902e14e18d5fe445b63ed952afc1411bcb27aeb5ea7f93d1c
+oid sha256:832bb0c6b1189792a3803205e28282733c69357c7a98db906a5b6648c86412ed
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4d63e8a027423d577ea7af105cf9dfa0eceb5cbaa55c3d1be9537ed2066e33
+oid sha256:b16d7438102d976fb534815d7fb6c3fbd3eb0ad6701c9593c3dd315e6b65b9be
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4891f7777b5838c1e2791421eb76185eb3d423f14cc978012d40df3e76c8ad
+oid sha256:2e7b2fb94aba803f2a2d188b149647000a6898e962a195b1f1cc848db18fce06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.629695885509839,
+  "epoch": 0.6368515205724508,
   "eval_steps": 500,
-  "global_step": 1760,
+  "global_step": 1780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1415,14 +1415,30 @@
       "loss": 0.3975,
       "num_input_tokens_seen": 1189185,
       "step": 1760
+    },
+    {
+      "epoch": 0.6332737030411449,
+      "grad_norm": 0.262329638004303,
+      "learning_rate": 7.334525939177103e-05,
+      "loss": 0.3841,
+      "num_input_tokens_seen": 1196883,
+      "step": 1770
+    },
+    {
+      "epoch": 0.6368515205724508,
+      "grad_norm": 0.35897818207740784,
+      "learning_rate": 7.262969588550985e-05,
+      "loss": 0.4004,
+      "num_input_tokens_seen": 1205284,
+      "step": 1780
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1189185,
+  "num_input_tokens_seen": 1205284,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.674057117160448e+16,
+  "total_flos": 2.710258082972467e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null