Training in progress, step 1920, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ee3bc105445eb2df06fba647a3f2cf55ff36262dc3f3e9c26e50230f699d1f
+oid sha256:5b870a0e7956f1262db1a4c5aef5432c3ec742c8fde13bcd6f2e3c396586cb77
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd564025e00406b04a30419884506257c3e2fcaf586dae04d71f954afe7e32c
+oid sha256:51da4492196b6a9086d0a146412eb40e5ce7a1343c46940127cbd0a9a0bbdcb4
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c73f6534671c1393f49b2a23b2a0228bc4188be53782b23d30d3f093b14235d
+oid sha256:664d1554b6d667624b0962efadcbe8a7a07a7fdf1f68db1a18116bf98d13cfb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647105993ec1d397fca55b8b39ed9e456faa245e3a9bcb86e3e0d264db700da1
+oid sha256:a803c8c681e722b33ed0b628f93a55855af2e03fe7687b8b6a531e8a84502442
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6797853309481217,
+  "epoch": 0.6869409660107334,
   "eval_steps": 500,
-  "global_step": 1900,
+  "global_step": 1920,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1527,14 +1527,30 @@
       "loss": 0.3835,
       "num_input_tokens_seen": 1286733,
       "step": 1900
+    },
+    {
+      "epoch": 0.6833631484794276,
+      "grad_norm": 0.299207478761673,
+      "learning_rate": 6.332737030411449e-05,
+      "loss": 0.3905,
+      "num_input_tokens_seen": 1293454,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6869409660107334,
+      "grad_norm": 0.48610031604766846,
+      "learning_rate": 6.261180679785331e-05,
+      "loss": 0.374,
+      "num_input_tokens_seen": 1299015,
+      "step": 1920
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1286733,
+  "num_input_tokens_seen": 1299015,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.8934081211377664e+16,
+  "total_flos": 2.921026001882112e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null