Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ac97e83b1ff548309589aabfdab6d2e1d4687dfe98f37c20e887408a1980e3
+oid sha256:a0961550945a8d91071222b2c49d5b067fac82fe51aa5c15f13f6ac243ab1e46
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff578aab41031ebce89be46228ea8e5cc738b9955991c2357aa125882c47fbc
+oid sha256:4d536def5a91956b6f6395dc4ff0073ec90ebd6241ccba242033f5a70609842a
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9fa9b80e86e6f00faed171296591e6c820ce1205bc98d1e1dac11ed9c33eb11
+oid sha256:7200da93a21271134bbc5641ee5b773345641f923b94e0dc1ae8e130692a7cb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:439d59a79ea6f98b7e31cb3d3d054d5d78bf9c23ea4b4c438d0a10fd0910fe22
+oid sha256:2d625dd68db868ef82004e5094537a164636a62f93a44b8505c1878b2bd94708
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.35062611806797855,
+  "epoch": 0.35778175313059035,
   "eval_steps": 500,
-  "global_step": 980,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -791,14 +791,30 @@
       "loss": 0.4146,
       "num_input_tokens_seen": 651211,
       "step": 980
+    },
+    {
+      "epoch": 0.3542039355992844,
+      "grad_norm": 0.2930082082748413,
+      "learning_rate": 0.00012915921288014312,
+      "loss": 0.4248,
+      "num_input_tokens_seen": 658984,
+      "step": 990
+    },
+    {
+      "epoch": 0.35778175313059035,
+      "grad_norm": 0.3553549647331238,
+      "learning_rate": 0.00012844364937388193,
+      "loss": 0.417,
+      "num_input_tokens_seen": 666184,
+      "step": 1000
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 651211,
+  "num_input_tokens_seen": 666184,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.4643435708684288e+16,
+  "total_flos": 1.4980125603151872e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null