Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6454113023046638b3e2ebd0108d6cd1f0692dd0812f7d779a642df85bdd353a
+oid sha256:a70641c6f60a07588cab12f05917f2a781d995ec64863344731432ea4d7ada52
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0223eb0199d8482f23fec34621ab38a98663bf22ab0dcce3aaed6d32bec35ac0
+oid sha256:1c9078f54b51d17b33804e85fc3e62abd7344f9ead5defde047e15a2023e6167
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b65f1a0fab783030b9678af169570889794fb3146a39ba3945282029a965db4
+oid sha256:58e75d5b5bd8a26ecc4289dc9b66c0c9515d5460c007200c55b9f512a8b5ac03
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013549217532687486,
+  "epoch": 0.0020323826299031233,
   "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": 0.00013090169943749476,
       "loss": 2.099,
       "step": 18
+    },
+    {
+      "epoch": 0.0014226678409321862,
+      "grad_norm": 0.7007055878639221,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.0154,
+      "step": 21
+    },
+    {
+      "epoch": 0.0016259061039224985,
+      "grad_norm": 1.2184398174285889,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.0561,
+      "step": 24
+    },
+    {
+      "epoch": 0.0016259061039224985,
+      "eval_loss": 1.97639000415802,
+      "eval_runtime": 534.0595,
+      "eval_samples_per_second": 11.639,
+      "eval_steps_per_second": 5.82,
+      "step": 24
+    },
+    {
+      "epoch": 0.001829144366912811,
+      "grad_norm": 0.6282042264938354,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.8654,
+      "step": 27
+    },
+    {
+      "epoch": 0.0020323826299031233,
+      "grad_norm": 2.0086252689361572,
+      "learning_rate": 0.0,
+      "loss": 1.9786,
+      "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": 7604344656494592.0,
+  "total_flos": 1.1313781074296832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null