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:cc8a717d7936bc5b8f311f71f62874984905d4d47f58fdda4f6aa5e4898edf85
+oid sha256:3f142acaede1be2422aede5788f05bee242598d8861a6bb82f7d3b6f612a4e22
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f70ce29e1e782a7f4b7ff70d7274a0e5fbf58bb7c6997e990772cf3df7ad27
+oid sha256:020d7152f7ba96de02be62f9c8c4e036a12fd0b1c60077143c25b33cd2ab527a
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c92b486b14f7a50cc9e7e571422ae87d331c417b0c0a958af23c536241b187d
+oid sha256:a3261a0429b7b1953b82adcaaa9f9e26f9a23ece6dcda65cdd3932732766f2d1
 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": 1.9744948148727417,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.1363636363636362,
+  "best_metric": 1.9583721160888672,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2784090909090908,
   "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": 27.827,
       "eval_steps_per_second": 3.488,
       "step": 800
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0002,
+      "loss": 2.0852,
+      "step": 900
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 1.9583721160888672,
+      "eval_runtime": 53.7484,
+      "eval_samples_per_second": 27.759,
+      "eval_steps_per_second": 3.479,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.424565849208832e+16,
+  "total_flos": 2.726008577316864e+16,
   "trial_name": null,
   "trial_params": null
 }