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:a70a13bdaf216ea23acdc7c3c6bac13583f0fc88df4f06ef72cd7795946203ab
+oid sha256:92bb1216267849bbda2fadfca822890ef69a755bc752607051aafb05cea2fc18
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebeee78893fab2aeb75aa57658207d425f5cee63bdcdf4f2e68766771acf16b0
+oid sha256:9da9e351bb454392c3c404ceba21c42ea7fc8c69f110c366bc7dcb705eb0f2f4
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ef024fdb50d2b5245e358e85c40ce33acc74b982ce82b2769eebe5c2cafd32
+oid sha256:9721883eeb5dfd58d4927218422ce48028e14bf282115382a00d7498ac3281ed
 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": 1.2422055006027222,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.4,
+  "best_metric": 1.2401798963546753,
+  "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": 15.266,
       "eval_steps_per_second": 1.914,
       "step": 1800
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0002,
+      "loss": 1.0601,
+      "step": 1900
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 1.2401798963546753,
+      "eval_runtime": 126.5967,
+      "eval_samples_per_second": 15.245,
+      "eval_steps_per_second": 1.912,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
@@ -266,7 +280,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.382682082163507e+16,
+  "total_flos": 6.736067175819264e+16,
   "trial_name": null,
   "trial_params": null
 }