Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2afddf3ec7ee4eb13b2ada4bf4720336a66bcb17f46f329977812b67bd67d4e2
+oid sha256:30ee3bc105445eb2df06fba647a3f2cf55ff36262dc3f3e9c26e50230f699d1f
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c254584d7510ca4eeaff0cca975c08ed55d713bbf9e668172f8cbf97495e77e2
+oid sha256:7dd564025e00406b04a30419884506257c3e2fcaf586dae04d71f954afe7e32c
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4550c76533f857f7cf55740ed3623cc9b4550e64e43f48fe63acb894cf87d3
+oid sha256:4c73f6534671c1393f49b2a23b2a0228bc4188be53782b23d30d3f093b14235d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcbe60adc58daefe5828383acc365415f8f2c12797679d185c0ae4e7a1e01d05
+oid sha256:647105993ec1d397fca55b8b39ed9e456faa245e3a9bcb86e3e0d264db700da1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6726296958855098,
+  "epoch": 0.6797853309481217,
   "eval_steps": 500,
-  "global_step": 1880,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1511,14 +1511,30 @@
       "loss": 0.3948,
       "num_input_tokens_seen": 1273256,
       "step": 1880
+    },
+    {
+      "epoch": 0.6762075134168157,
+      "grad_norm": 0.3770650327205658,
+      "learning_rate": 6.475849731663685e-05,
+      "loss": 0.3991,
+      "num_input_tokens_seen": 1280311,
+      "step": 1890
+    },
+    {
+      "epoch": 0.6797853309481217,
+      "grad_norm": 0.3090347945690155,
+      "learning_rate": 6.404293381037567e-05,
+      "loss": 0.3835,
+      "num_input_tokens_seen": 1286733,
+      "step": 1900
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1273256,
+  "num_input_tokens_seen": 1286733,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 2.863103107394765e+16,
+  "total_flos": 2.8934081211377664e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null