Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1183c50265c0f5242d8f5b944f33671bc47e43a6b7c5f81a40b7265b8d394803
+oid sha256:577a7ef3ad3854e732728c6b339581887a5d0f0d54326260503bcef0836f20a1
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a19bc83c293ee4a7e37d538cb1e2bda59004fbb1b064f57b81a75938bccf694d
+oid sha256:1f5aaf31bef5a0e10ef24f99bfabab81bc976cbbc3d8e7013e472feb66e2ae47
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b0cad0d7e91d023da3e5f53d89c7d15bfd3ff2e6ca23c99c8d224d5325fe57
+oid sha256:321f726baf0a9d0497f306e91cb0488d163a7822c2112d4e168fff7bdce703d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16421052631578947,
+  "epoch": 0.21052631578947367,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.6452,
       "step": 35
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.47658050060272217,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8139,
+      "step": 40
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "eval_loss": 1.9745097160339355,
+      "eval_runtime": 3.9944,
+      "eval_samples_per_second": 25.035,
+      "eval_steps_per_second": 12.517,
+      "step": 40
+    },
+    {
+      "epoch": 0.18947368421052632,
+      "grad_norm": 1.0479307174682617,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7238,
+      "step": 45
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.6328036785125732,
+      "learning_rate": 0.0,
+      "loss": 1.7828,
+      "step": 50
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 1.9637155532836914,
+      "eval_runtime": 3.8584,
+      "eval_samples_per_second": 25.918,
+      "eval_steps_per_second": 12.959,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1353945229295616.0,
+  "total_flos": 1751210595975168.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null