Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006584a63bebf4892d3f5d9520b78ddc712d903c2b73f4501d67a268dea3c521
+oid sha256:d430ce268f48fbc6f10035333b7ceddea01bb4d8b6a26f5e7df49d0e48f1afa2
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa1571fc1023d22f47d8e7849973316678c943aa681619fc1e09cb542f59254
+oid sha256:9803d4e6d52495720c335101f38337ad32a828f5bea4e80cc3194a2f4ca7994c
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85d652eda0ebe1a70ad73278519ff3500afe66328ab23abca0e62f25a966ae5
+oid sha256:7e4f6c87152ba0490e78276bd7f401c62e9412d5f9f272f0e45b8cc6a4b8874e
 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": 0.0015690273991409574,
+  "epoch": 0.0023535410987114364,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 13.479,
       "eval_steps_per_second": 6.739,
       "step": 20
+    },
+    {
+      "epoch": 0.0016474787690980053,
+      "grad_norm": 0.8007903099060059,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.7372,
+      "step": 21
+    },
+    {
+      "epoch": 0.001882832878969149,
+      "grad_norm": 1.1209689378738403,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.6574,
+      "step": 24
+    },
+    {
+      "epoch": 0.0019612842489261967,
+      "eval_loss": 1.6789103746414185,
+      "eval_runtime": 398.2796,
+      "eval_samples_per_second": 13.478,
+      "eval_steps_per_second": 6.739,
+      "step": 25
+    },
+    {
+      "epoch": 0.002118186988840293,
+      "grad_norm": 0.8475488424301147,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.6364,
+      "step": 27
+    },
+    {
+      "epoch": 0.0023535410987114364,
+      "grad_norm": 0.7514108419418335,
+      "learning_rate": 0.0,
+      "loss": 1.6479,
+      "step": 30
+    },
+    {
+      "epoch": 0.0023535410987114364,
+      "eval_loss": 1.6707888841629028,
+      "eval_runtime": 398.2873,
+      "eval_samples_per_second": 13.478,
+      "eval_steps_per_second": 6.739,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8581442955116544.0,
+  "total_flos": 1.2819192562581504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null