Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d73c8c1b2b6ee99249d2c3267b856ec91922cbd5cf0636b705365c677fd181
+oid sha256:8f057a2197471b7f639c5d813d1ef9d5a5b63c52d0d36065e3250d176d14265b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016e27af09c31c6428d53846b1abfb5c6a87aba0f5312adb051ceee516accf46
+oid sha256:21a2ea44a05c9c444d9672d07afc049e2e779193cf3dfa0afded237eea3043f2
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0d1b378492ec4e150da1c9feeca26eae7c30c21199e70dec7f166a03613c3d
+oid sha256:0704dd557dce4febe99f56d14200e6282ff3f71d203ef70d72c678236f04eb88
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
+oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4286835193634033,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.3333333333333333,
+  "best_metric": 1.4184046983718872,
+  "best_model_checkpoint": "./outputs/checkpoint-1100",
+  "epoch": 1.4666666666666668,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 15.552,
       "eval_steps_per_second": 1.951,
       "step": 1000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0002,
+      "loss": 1.1844,
+      "step": 1100
+    },
+    {
+      "epoch": 1.47,
+      "eval_loss": 1.4184046983718872,
+      "eval_runtime": 93.2489,
+      "eval_samples_per_second": 15.56,
+      "eval_steps_per_second": 1.952,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.844782394372096e+16,
+  "total_flos": 6.43012944795648e+16,
   "trial_name": null,
   "trial_params": null
 }