Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90808d8b4d606843903dfd1c210f2d0487ac041293aa80da1599ddced1793441
+oid sha256:08bb6e8c08d61a0ba22a243f113a61b440e9817db46529b446cd8d25b5f07fa3
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96434455a69b750321213344a638f6847020d852a3fecc483908760b1cc79e3
+oid sha256:00b8fd4c6d4cb01678a7cf68ee671f2b78b50acb1d5a12ed489aa24cb081b121
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61141caaeced524e90af469f8106bd16c8272535a3eec7b36e1b27ae19b4be44
+oid sha256:10f4204b2bbcc7cf89fe1739fc0e2095ff84ed0f658a01fa3c11e35b9313101e
 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": 0.001623663859948584,
+  "epoch": 0.0020816203332674156,
   "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": 0.6446,
       "step": 35
+    },
+    {
+      "epoch": 0.0016652962666139322,
+      "grad_norm": 1.3737820386886597,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.576,
+      "step": 40
+    },
+    {
+      "epoch": 0.0016652962666139322,
+      "eval_loss": 0.5835541486740112,
+      "eval_runtime": 1207.1343,
+      "eval_samples_per_second": 8.379,
+      "eval_steps_per_second": 4.189,
+      "step": 40
+    },
+    {
+      "epoch": 0.0018734582999406738,
+      "grad_norm": 0.8879534602165222,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7198,
+      "step": 45
+    },
+    {
+      "epoch": 0.0020816203332674156,
+      "grad_norm": 1.4516291618347168,
+      "learning_rate": 0.0,
+      "loss": 0.8384,
+      "step": 50
+    },
+    {
+      "epoch": 0.0020816203332674156,
+      "eval_loss": 0.5801019668579102,
+      "eval_runtime": 1207.2168,
+      "eval_samples_per_second": 8.378,
+      "eval_steps_per_second": 4.189,
+      "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": 1.4241644710723584e+16,
+  "total_flos": 1.826444695044096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null