Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0695d406714cc12c7b4b5d4910b9e5314a889c62eb76f0303e2511628ac8599c
+oid sha256:2774a796753478dafed475f6ae03274c1ed79d5c1dea054850a91fc6c244def0
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d168e40be03685ddd8996e633d9f43e4e5386cd068968a749c059f9d0d9006b1
+oid sha256:f7267e6d6a40d6f7a56890b005aedc5561255d442204033ec2901437e97ee525
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2235c504a4d94fb2685c50547ca4cc4d6e3c4aeb30bc383c1a9562fe9ba514e0
+oid sha256:4ac727c8d1b09cb5c6714aef1e24be1f747baf4690a1f0b52b6673366565e9cf
 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": 0.0004310785530129904,
+  "epoch": 0.0005526648115551159,
   "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": 0.8146,
       "step": 35
+    },
+    {
+      "epoch": 0.0004421318492440927,
+      "grad_norm": 17.325223922729492,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2595,
+      "step": 40
+    },
+    {
+      "epoch": 0.0004421318492440927,
+      "eval_loss": 0.43640169501304626,
+      "eval_runtime": 2052.9477,
+      "eval_samples_per_second": 18.555,
+      "eval_steps_per_second": 9.278,
+      "step": 40
+    },
+    {
+      "epoch": 0.0004973983303996043,
+      "grad_norm": 4.131010055541992,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2891,
+      "step": 45
+    },
+    {
+      "epoch": 0.0005526648115551159,
+      "grad_norm": 7.422944068908691,
+      "learning_rate": 0.0,
+      "loss": 0.4703,
+      "step": 50
+    },
+    {
+      "epoch": 0.0005526648115551159,
+      "eval_loss": 0.4152521789073944,
+      "eval_runtime": 2055.2428,
+      "eval_samples_per_second": 18.535,
+      "eval_steps_per_second": 9.268,
+      "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": 2973577594798080.0,
+  "total_flos": 3793452898713600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null