Training in progress, step 840, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8266c5ce2daff311c6b7f99a82121a7d104c99faa78c3777323bc8fb69e449a
+oid sha256:2bd269f9603e3fe38017dedc2c25f29d5956ffac0a0680ff4be53723cc230308
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba87eaf9f2c58fb6d0b0a1c2263a7833cdee74039a7d283d9e26e781413fe8ff
+oid sha256:169e61d06045c7d645f7845cd193774033d2c62e8074bc7f3bcd8b429da9c1ff
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7526970e790becb006619bd780f0a177e541ca6e1e03e8171224f11d2b3cdea
+oid sha256:cebdc5bb99a062fec3bff67f2ffff14c060d2d591a43384bf4d1c5af4cf78ddb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38f6fcd2abad4866e3102113773264731c828e1e13009602886e42cd304ea258
+oid sha256:d27f27dc8317758e5054e3267c676ecc55b2a293cbb2708d11be857eb327f7ee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29338103756708406,
+  "epoch": 0.3005366726296959,
   "eval_steps": 500,
-  "global_step": 820,
+  "global_step": 840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -663,14 +663,30 @@
       "loss": 0.4142,
       "num_input_tokens_seen": 548183,
       "step": 820
+    },
+    {
+      "epoch": 0.29695885509839,
+      "grad_norm": 0.4515162408351898,
+      "learning_rate": 0.00014060822898032203,
+      "loss": 0.404,
+      "num_input_tokens_seen": 553861,
+      "step": 830
+    },
+    {
+      "epoch": 0.3005366726296959,
+      "grad_norm": 0.3883764147758484,
+      "learning_rate": 0.00013989266547406083,
+      "loss": 0.4159,
+      "num_input_tokens_seen": 559943,
+      "step": 840
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 548183,
+  "num_input_tokens_seen": 559943,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1.2326699820939264e+16,
+  "total_flos": 1.2591140691769344e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null