Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9cdc025278c7bf8f5fd92e05c7fd81ba593644a076b25ebacc8ec24d1d40a0
+oid sha256:44860e8b73a98ec679f4883adff95164a234ab82fd76f1add769d24b88093827
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1402bdb32544eb9efbb42b819dcee9ac1a90f72f4247b16bb494ed9614814b5b
+oid sha256:e45139284073b3ff67f40527885f82e59cbc6f720e57d03f6c5404cceff5fe79
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28bb8cd36f407a81ad8a852c0cafc09272cd757fc0bb883a948f9d458d361cbc
+oid sha256:d378fa09b23e2e59c0e79aaeae12fa612d44258b487e5ee7c59dba1c6ef48774
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09803921568627451,
+  "epoch": 0.14705882352941177,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 8.113,
       "eval_steps_per_second": 2.075,
       "step": 20
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "grad_norm": 2.0282931327819824,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.8578,
+      "step": 21
+    },
+    {
+      "epoch": 0.10784313725490197,
+      "grad_norm": 0.8347979784011841,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.775,
+      "step": 22
+    },
+    {
+      "epoch": 0.11274509803921569,
+      "grad_norm": 1.1945385932922363,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 0.6854,
+      "step": 23
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 1.330310583114624,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 0.8785,
+      "step": 24
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "eval_loss": 0.8344882726669312,
+      "eval_runtime": 10.6019,
+      "eval_samples_per_second": 8.112,
+      "eval_steps_per_second": 2.075,
+      "step": 24
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "grad_norm": 1.4803705215454102,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.6359,
+      "step": 25
+    },
+    {
+      "epoch": 0.12745098039215685,
+      "grad_norm": 1.536838173866272,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.6286,
+      "step": 26
+    },
+    {
+      "epoch": 0.1323529411764706,
+      "grad_norm": 1.0436162948608398,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.7679,
+      "step": 27
+    },
+    {
+      "epoch": 0.13725490196078433,
+      "grad_norm": 2.5319721698760986,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 1.1476,
+      "step": 28
+    },
+    {
+      "epoch": 0.13725490196078433,
+      "eval_loss": 0.8303804397583008,
+      "eval_runtime": 10.618,
+      "eval_samples_per_second": 8.099,
+      "eval_steps_per_second": 2.072,
+      "step": 28
+    },
+    {
+      "epoch": 0.14215686274509803,
+      "grad_norm": 1.8032675981521606,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 0.8761,
+      "step": 29
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 2.128256320953369,
+      "learning_rate": 0.0,
+      "loss": 1.0381,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7106761756508160.0,
+  "total_flos": 1.041223234093056e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null