Training in progress, step 2240, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe4cb03d3561140a6dc960340bfc20239d79b812171f8665033b7d5950060c16
+oid sha256:f0632b909fd1c9aca69067d0bed149621d32fc888cd885edfe8a9c9167000cd0
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02194e64ab0e46b57c09b90a41edf3c57c35eb6a761d021610ca25fe7722be96
+oid sha256:12617d04abf8d5849ea18ccd1caeaec1b356dd520401e75c5bd06ee3fc8e8aa6
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2417621c0c251f9779f9e28a0066e04b9dea3b724de678a9d2863d36bd10fb07
+oid sha256:4b4460282b72eb6f8903bafdf89fcbbe259019be8c29ef42adde2e2a7ce8a185
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcda9d1b5e596e9a16f8101054c6161f73e1500ea7e6c07e8c2aa6c3a698c4fe
+oid sha256:1f05e22fba1c2918a10ec5938a0705454f8a1b28f2198ed555d6f8a3e293559a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7942754919499105,
+  "epoch": 0.8014311270125224,
   "eval_steps": 500,
-  "global_step": 2220,
+  "global_step": 2240,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1783,14 +1783,30 @@
       "loss": 0.3809,
       "num_input_tokens_seen": 1503138,
       "step": 2220
+    },
+    {
+      "epoch": 0.7978533094812165,
+      "grad_norm": 0.39187124371528625,
+      "learning_rate": 4.042933810375671e-05,
+      "loss": 0.3779,
+      "num_input_tokens_seen": 1509279,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8014311270125224,
+      "grad_norm": 0.3644355833530426,
+      "learning_rate": 3.971377459749553e-05,
+      "loss": 0.3883,
+      "num_input_tokens_seen": 1515223,
+      "step": 2240
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1503138,
+  "num_input_tokens_seen": 1515223,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.3800265450491904e+16,
+  "total_flos": 3.4072014423619584e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null