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:c63a867c8db87715acaf143fffb8868554ea82d0db868e929642eac10c512bf9
+oid sha256:44c87f6f29aa8d93fe243b717949d5b409d99c20e087556547d901209c4e627a
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672ecbb20cce52778115a57abe024848f8e2958b1ff86dd11c715efa234a545a
+oid sha256:3dd853c92a15ba23b7398fd90430f378a3e46ca2af8bd5e500a325ccf5955af0
 size 21318842

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6007453ef3302b28392872965c1119107f0eed10e3e9c97a557e7a8e54feb6f
+oid sha256:0b3473cbb838e3eccf1948f591b8f538c9da34959cffe3fade8914cc5e270ddc
 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": 0.03508771929824561,
+  "epoch": 0.05263157894736842,
   "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": 11.2499,
       "step": 18
+    },
+    {
+      "epoch": 0.03684210526315789,
+      "grad_norm": 4.116658687591553,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.8468,
+      "step": 21
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 3.66119122505188,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 12.7503,
+      "step": 24
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "eval_loss": 2.961115598678589,
+      "eval_runtime": 3.3481,
+      "eval_samples_per_second": 71.682,
+      "eval_steps_per_second": 35.841,
+      "step": 24
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "grad_norm": 3.368849992752075,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 12.2036,
+      "step": 27
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 3.71175217628479,
+      "learning_rate": 0.0,
+      "loss": 11.5137,
+      "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": 93767124123648.0,
+  "total_flos": 139034011631616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null