Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c59c9a73081018f9935c7827972a4c96c091e134bec87a67b615ed60a5f241c
+oid sha256:b4663053c60e5f267803a23dfc4bf6b7799e1bea84539190c45eeb0994148fd0
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21103e6050d033638c5a313b15a95db6f7f0ee96b52eaab7515f511c5bdf2c1a
+oid sha256:db2037ccc8f01df1eb9dd3cb62165d668a40294b816104d67ba12a3f0bcb38fa
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da5eddeaa757c6d016160549ec4b158dd730ee5eb61636139ede6dfade684bcc
+oid sha256:f733f68e9af3a413f7f5c8bf128e0ef057938927e43869c070a32516f9bd1d62
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5527715682983398,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 1.384335154826958,
+  "best_metric": 1.5026806592941284,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 1.530054644808743,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,13 +273,41 @@
       "eval_samples_per_second": 11.278,
       "eval_steps_per_second": 1.411,
       "step": 1900
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0002,
+      "loss": 1.5057,
+      "step": 2000
+    },
+    {
+      "epoch": 1.46,
+      "eval_loss": 1.5266777276992798,
+      "eval_runtime": 556.4442,
+      "eval_samples_per_second": 11.275,
+      "eval_steps_per_second": 1.411,
+      "step": 2000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0002,
+      "loss": 1.4851,
+      "step": 2100
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 1.5026806592941284,
+      "eval_runtime": 556.1829,
+      "eval_samples_per_second": 11.28,
+      "eval_steps_per_second": 1.411,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.9544045126846054e+17,
+  "total_flos": 5.47414668374655e+17,
   "trial_name": null,
   "trial_params": null
 }