Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e5de2e9452ec91d1bda82ec2b49168c1b40efac772b330f775400b25835f18
+oid sha256:6d951cb6461972e04ed870e0b7c293c6b3cf731ba2029fe63552e42c64dba5b2
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cce5259b3b667acd83a8309eb3c5f1a11e1e196fe8849de4bb9442bea4481d7
+oid sha256:cb8562b93c5422e92aecf213455351d9032f279ee284779cb349d5eafcdf3125
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c92eaf57053cbecdaa0579160167ea852314d5e01fbc4749b533abb666c0771
+oid sha256:a4a906bb698465209c126b422af04612476e6201f2ba8b1d53312d08d82be13b
 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": 0.16595744680851063,
+  "epoch": 0.2127659574468085,
   "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": 3.607,
       "step": 35
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 4.84646463394165,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.2878,
+      "step": 40
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "eval_loss": 3.181182861328125,
+      "eval_runtime": 12.3541,
+      "eval_samples_per_second": 8.014,
+      "eval_steps_per_second": 4.047,
+      "step": 40
+    },
+    {
+      "epoch": 0.19148936170212766,
+      "grad_norm": 5.343417644500732,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.2881,
+      "step": 45
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 6.617802619934082,
+      "learning_rate": 0.0,
+      "loss": 3.1203,
+      "step": 50
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "eval_loss": 3.1708755493164062,
+      "eval_runtime": 12.3253,
+      "eval_samples_per_second": 8.032,
+      "eval_steps_per_second": 4.057,
+      "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": 7213300567769088.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null