Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b8553637cdc4c237ca46908167a61c4ba6ab57ec1914c2ca66711e0c59d365e
+oid sha256:5203057d5ec9315f69d6f6154a7ad594de6bd647b87d65f3f2c09e513b6ad482
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e592696f25c8a7f8c388d7ad7bff077ea61d6625f81e89b2f6c34163f367d6f1
+oid sha256:d535a43582b548246d59c8e6bf7cfa1f942223608d026f9b598dcba9124c9e4e
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd02f143f7f3623496ceb4789d51e487857b4fe6db678fd0ec9d179938869bae
+oid sha256:6abf1f5f142077ef268dd05bc1f31451ee03172c05cd015beffd3ed0ada56893
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0099247694015503,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.0071921348571777,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 5.45,
       "eval_steps_per_second": 0.683,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 0.8634,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.0071921348571777,
+      "eval_runtime": 353.8229,
+      "eval_samples_per_second": 5.455,
+      "eval_steps_per_second": 0.684,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.2622081570707046e+17,
+  "total_flos": 2.545011713639301e+17,
   "trial_name": null,
   "trial_params": null
 }