Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382b240f9d1673407b68b093fbad91a0baff5d06d465f933ca68136c1ff0fe18
+oid sha256:6cd6a8c8c1468699da8d51d26a846134b85a031bce54bbb660e7a2f78079e9a7
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d4f81ff79ebfb2f522b13eb064a7487bf55b02343f8b37eccc1cce33f7ba689
+oid sha256:15da2900754f221e84c4ce33e4200d975d78a7126c64d5cf3fabfd15b01be288
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5af4843563639e31994cfd1ddd0f7cdf98dd7ca1ff3693b235dde4ed21ecd00
+oid sha256:0ed35cbf543f36a580a139da6bcc1e610cc110a46122a95130e54e6b31626588
 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": 1.2204071283340454,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.2131980657577515,
+  "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": 4.062,
       "eval_steps_per_second": 0.509,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 0.9923,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.2131980657577515,
+      "eval_runtime": 472.507,
+      "eval_samples_per_second": 4.085,
+      "eval_steps_per_second": 0.512,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.993638976897024e+16,
+  "total_flos": 4.32763510039511e+16,
   "trial_name": null,
   "trial_params": null
 }