Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c57df137b047e07d3ec9cad5abd8e5836f544647443a904da3d70b8691638a8
+oid sha256:0d76fb8a8bd08701c4eefbd63cbd9e73158597efe820dbc3ede59401a0e62e9e
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fde1b6bc518120df30a0ec1edd08211863f3032a3038cf8c99442be2e549781
+oid sha256:6ff0b0cd430c0d6a49ad6088c2ec0dfb7479a9801b6c3be81759caa791f2611f
 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": 0.010790396547073105,
+  "epoch": 0.016185594820609658,
   "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": 51.117,
       "eval_steps_per_second": 25.591,
       "step": 20
+    },
+    {
+      "epoch": 0.01132991637442676,
+      "grad_norm": 2.7558438777923584,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 7.025,
+      "step": 21
+    },
+    {
+      "epoch": 0.012948475856487725,
+      "grad_norm": 2.9869544506073,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 7.2359,
+      "step": 24
+    },
+    {
+      "epoch": 0.013487995683841382,
+      "eval_loss": 1.760362982749939,
+      "eval_runtime": 15.3059,
+      "eval_samples_per_second": 51.026,
+      "eval_steps_per_second": 25.546,
+      "step": 25
+    },
+    {
+      "epoch": 0.014567035338548692,
+      "grad_norm": 2.3133647441864014,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 6.754,
+      "step": 27
+    },
+    {
+      "epoch": 0.016185594820609658,
+      "grad_norm": 2.724479913711548,
+      "learning_rate": 0.0,
+      "loss": 7.0305,
+      "step": 30
+    },
+    {
+      "epoch": 0.016185594820609658,
+      "eval_loss": 1.7582391500473022,
+      "eval_runtime": 15.255,
+      "eval_samples_per_second": 51.196,
+      "eval_steps_per_second": 25.631,
+      "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": 307163125776384.0,
+  "total_flos": 458848619986944.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null