Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cd6a8c8c1468699da8d51d26a846134b85a031bce54bbb660e7a2f78079e9a7
+oid sha256:d2b72d1a16aee9666c04ea2581eecea69b8542eae5c07c5479fe4b26ff10874a
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15da2900754f221e84c4ce33e4200d975d78a7126c64d5cf3fabfd15b01be288
+oid sha256:498af9d3c04e734133cbd95e7feb6bbb20240cdcca9f72fdbb9ec6d558f78180
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ed35cbf543f36a580a139da6bcc1e610cc110a46122a95130e54e6b31626588
+oid sha256:afbf266a9b148760edf134e1852525c920aea14cf4004e12741c4e84517464ba
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2131980657577515,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 1.7333333333333334,
+  "best_metric": 1.2085801362991333,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.8666666666666667,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,20 @@
       "eval_samples_per_second": 4.085,
       "eval_steps_per_second": 0.512,
       "step": 1300
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.0002,
+      "loss": 0.9934,
+      "step": 1400
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 1.2085801362991333,
+      "eval_runtime": 469.7498,
+      "eval_samples_per_second": 4.109,
+      "eval_steps_per_second": 0.515,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
@@ -196,7 +210,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.32763510039511e+16,
+  "total_flos": 4.660632774947635e+16,
   "trial_name": null,
   "trial_params": null
 }