Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f797b65a5054689b3875d91f0d6957d5042e22421089998a891d4f437a4281d
+oid sha256:be9bcd15d69a11514441b9a28179ee8268bda6cf39836bd197826e70d3c2e78f
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b039ac1f98a24dbd2c7df7abfb5f0a90d2ce49589f2eb6e90fa079d81c30ccb9
+oid sha256:27797170f27ae4d267d28364b8334de9d90b83d21c688a7b582d73f87f668e49
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670c55e1c37931a635c4dc0ef163d2b6c1b7a374aff2f09fb80d53eeb5e58616
+oid sha256:432b633e5dda27995d4289f9c9b4c7fc095ba96fbfd82e14d7f383c303196238
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
+oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.975382924079895,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 2.4,
+  "best_metric": 0.9727230072021484,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 2.533333333333333,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,6 +259,20 @@
       "eval_samples_per_second": 5.095,
       "eval_steps_per_second": 0.639,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 0.8297,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 0.9727230072021484,
+      "eval_runtime": 366.7965,
+      "eval_samples_per_second": 5.262,
+      "eval_steps_per_second": 0.66,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.0879453793069466e+17,
+  "total_flos": 5.3702940947828736e+17,
   "trial_name": null,
   "trial_params": null
 }