Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58eadfa6617e3e1d0ff3394dcf553eabd47aba1de02ab15fdac8eaab8c08cf66
+oid sha256:50e6fac66e65d026e3861ea4727109898e8e9fee4ce4f6241def908f3d21dadd
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07eeb9ee2ce78c05124fba829a27d09a26082535809e93a9d89c7a7c42331fb5
+oid sha256:8a4182b4326aa07f29f890596704719d308cf9eeb8387f0a9b85f6f9f330dc67
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0215b9b0c756446a0a4927e0fe6fa21e780ad4150be2177b0182afb17c78ac6a
+oid sha256:5c0c0ade96e49f1197c7e40ecd2fd9e91be217c89901880a014eccf43aa01f57
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.994540810585022,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 0.9898069500923157,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.7333333333333334,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 5.458,
       "eval_steps_per_second": 0.684,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 0.8524,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 0.9898069500923157,
+      "eval_runtime": 353.7953,
+      "eval_samples_per_second": 5.455,
+      "eval_steps_per_second": 0.684,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.392066003002245e+17,
+  "total_flos": 3.6755826480358195e+17,
   "trial_name": null,
   "trial_params": null
 }