Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d3b6bacd198c2d78d6ec4df8fe08fce01829fa46a934ea4bb7e8a2e8db8902
+oid sha256:d3718f031d2d9a50bfb0f41459388697bc35f9fd4b49c13709605817fe8ac3a7
 size 95402480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73714c8030a56679c1d165eea466f4c53a8bcb514e9f33e106b6b3e528a33191
+oid sha256:e4b3b6a05e48d9404a7134069c0f9645f18acc804eae1cdb26cd9c7d3e9edccb
 size 191012170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cbde92c40f44796fa92ccdce1b42a550c278b3c9c47995b873b107e5adf740a
+oid sha256:214a8d973d8b75e7d364cb99ea070a294f7e1063ab73329eb42fd1baef6db302
 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": 0.004106143817687214,
+  "epoch": 0.006159215726530822,
   "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": 31.47,
       "eval_steps_per_second": 15.743,
       "step": 20
+    },
+    {
+      "epoch": 0.004311451008571575,
+      "grad_norm": 13.035810470581055,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 7.1339,
+      "step": 21
+    },
+    {
+      "epoch": 0.004927372581224657,
+      "grad_norm": 9.902789115905762,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 5.4977,
+      "step": 24
+    },
+    {
+      "epoch": 0.0051326797721090184,
+      "eval_loss": 0.7941518425941467,
+      "eval_runtime": 65.2408,
+      "eval_samples_per_second": 31.437,
+      "eval_steps_per_second": 15.726,
+      "step": 25
+    },
+    {
+      "epoch": 0.005543294153877739,
+      "grad_norm": 8.039051055908203,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 6.109,
+      "step": 27
+    },
+    {
+      "epoch": 0.006159215726530822,
+      "grad_norm": 13.466979026794434,
+      "learning_rate": 0.0,
+      "loss": 6.987,
+      "step": 30
+    },
+    {
+      "epoch": 0.006159215726530822,
+      "eval_loss": 0.7893955707550049,
+      "eval_runtime": 65.2128,
+      "eval_samples_per_second": 31.451,
+      "eval_steps_per_second": 15.733,
+      "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": 2925325990232064.0,
+  "total_flos": 4387988985348096.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null