Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0caa4ce0798f8a1e0ed9158407d65dd191ad291cba00c9975d35151fff186d
+oid sha256:f6ea0c800558437c587d9a5d8a94a6813d55bd20af9721d87594c89c37414677
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91c8d969f34f11c89e1b1f8be8e9d4cd4871925cc521f1da2eaeba0ca647aea5
+oid sha256:411069b6af9d8ec44a27876738d42aaeb838f10b870e91a5da7dcc4d0e9e1a65
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e58b9d1afa51d36de3d7ca6e57e2e9e6692f3cd84afbc1b02efc61c4136b7704
+oid sha256:5379ed0202ee64c10f38d7bb6ae7cfabd92065a1065eb0556f925299afb66dec
 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": 0.008506113769271665,
+  "epoch": 0.012759170653907496,
   "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": 73.114,
       "eval_steps_per_second": 36.557,
       "step": 20
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": 23.369600296020508,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 6.3961,
+      "step": 21
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": 22.581483840942383,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 6.1837,
+      "step": 24
+    },
+    {
+      "epoch": 0.01063264221158958,
+      "eval_loss": 1.554789662361145,
+      "eval_runtime": 13.7952,
+      "eval_samples_per_second": 71.764,
+      "eval_steps_per_second": 35.882,
+      "step": 25
+    },
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": 30.673725128173828,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 6.2545,
+      "step": 27
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": 30.781036376953125,
+      "learning_rate": 0.0,
+      "loss": 6.1231,
+      "step": 30
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "eval_loss": 1.5538281202316284,
+      "eval_runtime": 13.5903,
+      "eval_samples_per_second": 72.846,
+      "eval_steps_per_second": 36.423,
+      "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": 358431722569728.0,
+  "total_flos": 535435042357248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null