Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d1bc86e67764afa65feb8abf3fa71c18524a0d272c83a2431212fdf9b4d8993
+oid sha256:9457c2ecf3bf90646e072a41e733df7345802bcfe3dd1277141297e9b8e398de
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7459fada6cde56f4741f5a4fca49407d69dc4ede5bb19252daf89ccbf9d7175a
+oid sha256:5024bd1b775e21ae3c12b1f01a6cd967af0703f6b898c1835fefc8a857066111
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.0016834653486715733,
+  "epoch": 0.002158288908553299,
   "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": 41.499,
       "step": 35
+    },
+    {
+      "epoch": 0.0017266311268426392,
+      "grad_norm": 0.35912802815437317,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 41.5075,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017266311268426392,
+      "eval_loss": 10.374703407287598,
+      "eval_runtime": 43.9409,
+      "eval_samples_per_second": 222.003,
+      "eval_steps_per_second": 111.013,
+      "step": 40
+    },
+    {
+      "epoch": 0.001942460017697969,
+      "grad_norm": 0.37208297848701477,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 41.5038,
+      "step": 45
+    },
+    {
+      "epoch": 0.002158288908553299,
+      "grad_norm": 0.3831227421760559,
+      "learning_rate": 0.0,
+      "loss": 41.4827,
+      "step": 50
+    },
+    {
+      "epoch": 0.002158288908553299,
+      "eval_loss": 10.374635696411133,
+      "eval_runtime": 43.8109,
+      "eval_samples_per_second": 222.662,
+      "eval_steps_per_second": 111.342,
+      "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": 1000927789056.0,
+  "total_flos": 1283240755200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null