Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a46ed5298399c37f30ba81f0f4192a6fd1237b2d6b520794d4b9627f52953c
+oid sha256:4152d64162b334226bc341030c851027d7d82bafd83cdbd5151f79bb71028e25
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645f7ef00c370ce6f27ac7ff5e94850a7051879f0de94bbc380600badab51489
+oid sha256:0bd34ed9a77b1401735482f57c615bf7e297ecc0eb9402d86b6af39ee7e8a514
 size 501028338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c949c6e825e9b6cc6e61770439637c62f618ab7c470350a60558b82879992b12
+oid sha256:bbd4470c02a817ff3c64b32f3284b0d1d203f6bfe1063498727a8d3bae3c4c1d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.049782202862476664,
+  "epoch": 0.07467330429371499,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 2.53,
       "step": 18
+    },
+    {
+      "epoch": 0.0522713130056005,
+      "grad_norm": 0.9095845818519592,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.4448,
+      "step": 21
+    },
+    {
+      "epoch": 0.059738643434972,
+      "grad_norm": 1.150801181793213,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.5214,
+      "step": 24
+    },
+    {
+      "epoch": 0.059738643434972,
+      "eval_loss": 0.6139063239097595,
+      "eval_runtime": 34.0796,
+      "eval_samples_per_second": 4.988,
+      "eval_steps_per_second": 2.494,
+      "step": 24
+    },
+    {
+      "epoch": 0.0672059738643435,
+      "grad_norm": 0.8832470774650574,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.5143,
+      "step": 27
+    },
+    {
+      "epoch": 0.07467330429371499,
+      "grad_norm": 0.9340922236442566,
+      "learning_rate": 0.0,
+      "loss": 2.408,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.30129688788992e+16,
+  "total_flos": 1.93607585759232e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null