Training in progress, step 1020, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0961550945a8d91071222b2c49d5b067fac82fe51aa5c15f13f6ac243ab1e46
+oid sha256:afbb78bc5d4f338b3de45927e37c2c7143ab5ee643dfe631e069fa92eb728523
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d536def5a91956b6f6395dc4ff0073ec90ebd6241ccba242033f5a70609842a
+oid sha256:6b6ec8ffdaba9ec2f7d78f345f8b8578b67c63fd524f95af3e96334c16310690
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7200da93a21271134bbc5641ee5b773345641f923b94e0dc1ae8e130692a7cb1
+oid sha256:e250fcc7dfce6fdffa6b0f011754c66243ad148deca4a5febf83c46786e5deaf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d625dd68db868ef82004e5094537a164636a62f93a44b8505c1878b2bd94708
+oid sha256:1475ca4fa302f43b126c66f92deac3cab985ff0c7cf6532a7fd07ee716671370
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.35778175313059035,
+  "epoch": 0.36493738819320215,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1020,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -807,14 +807,30 @@
       "loss": 0.417,
       "num_input_tokens_seen": 666184,
       "step": 1000
+    },
+    {
+      "epoch": 0.3613595706618962,
+      "grad_norm": 0.3744185268878937,
+      "learning_rate": 0.00012772808586762076,
+      "loss": 0.3988,
+      "num_input_tokens_seen": 673125,
+      "step": 1010
+    },
+    {
+      "epoch": 0.36493738819320215,
+      "grad_norm": 0.4000609219074249,
+      "learning_rate": 0.0001270125223613596,
+      "loss": 0.4301,
+      "num_input_tokens_seen": 680863,
+      "step": 1020
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 666184,
+  "num_input_tokens_seen": 680863,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.4980125603151872e+16,
+  "total_flos": 1.5310204475848704e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null