Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79770a4cf85c6b4f990d47ec7f78d07982914cf11bf55d277f415fb0269d7758
+oid sha256:1e746f2a4006542a3daba63c581720d27a8e69e4183ffe3d429829d88129cc38
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:743d83fee4a9aa1b41dcbf4ac2437fa4d56ddd6bd974c3b38683707997228e25
+oid sha256:f479093c73e573c17b17709d7d37117e2fb68b03ff48f5ccb14fe3e9b93d90f7
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be8487cf05ea0074174fea05b5c29e640fe072093941da1693aedc4198f5aaaf
+oid sha256:6748e95ed652e9797300ce034b853849090c26e294deb0f828a3657e7e6347f4
 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": 0.02478157267672756,
+  "epoch": 0.03177124702144559,
   "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": 0.8815,
       "step": 35
+    },
+    {
+      "epoch": 0.025416997617156472,
+      "grad_norm": 0.8634251356124878,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.965,
+      "step": 40
+    },
+    {
+      "epoch": 0.025416997617156472,
+      "eval_loss": 0.9698567986488342,
+      "eval_runtime": 44.2143,
+      "eval_samples_per_second": 14.995,
+      "eval_steps_per_second": 7.509,
+      "step": 40
+    },
+    {
+      "epoch": 0.028594122319301033,
+      "grad_norm": 1.1116752624511719,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.91,
+      "step": 45
+    },
+    {
+      "epoch": 0.03177124702144559,
+      "grad_norm": 1.3982998132705688,
+      "learning_rate": 0.0,
+      "loss": 0.8825,
+      "step": 50
+    },
+    {
+      "epoch": 0.03177124702144559,
+      "eval_loss": 0.9606435298919678,
+      "eval_runtime": 44.1126,
+      "eval_samples_per_second": 15.03,
+      "eval_steps_per_second": 7.526,
+      "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": 3768979009044480.0,
+  "total_flos": 4845830154485760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null