Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ddf1e9f0fb238a137f958cf30901e693809cfa3b30cf06c53fd915c3e75aac
+oid sha256:fde5b17e55217edcc02ffe0df5485c54d7d4637a1296bb3e3dceb17df4dc2a82
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c012d13bb8060984790c3570e79e2499e1c03430dac0bb1cc9f443e47d877284
+oid sha256:bfe81e67181475bc7e8bfbe52781b6a8141c14abc34aef56479ab69b93ce819c
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6262ab7a2c890a47ec0fa3c4e272fd834b906cfbebf7abfe585a8f4ba8efeb6e
+oid sha256:558a15d6c78806ac0c100c0db9159ffa92e82b5ce97abfa18ca818111c735b5b
 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": 0.0028834423866030833,
+  "epoch": 0.003696721008465491,
   "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": 0.1384,
       "step": 35
+    },
+    {
+      "epoch": 0.002957376806772393,
+      "grad_norm": 0.3911191523075104,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1775,
+      "step": 40
+    },
+    {
+      "epoch": 0.002957376806772393,
+      "eval_loss": 0.1539893001317978,
+      "eval_runtime": 469.0958,
+      "eval_samples_per_second": 12.14,
+      "eval_steps_per_second": 6.071,
+      "step": 40
+    },
+    {
+      "epoch": 0.003327048907618942,
+      "grad_norm": 0.39024609327316284,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1339,
+      "step": 45
+    },
+    {
+      "epoch": 0.003696721008465491,
+      "grad_norm": 0.4059450924396515,
+      "learning_rate": 0.0,
+      "loss": 0.1446,
+      "step": 50
+    },
+    {
+      "epoch": 0.003696721008465491,
+      "eval_loss": 0.15335358679294586,
+      "eval_runtime": 465.599,
+      "eval_samples_per_second": 12.232,
+      "eval_steps_per_second": 6.117,
+      "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": 2422915077242880.0,
+  "total_flos": 3059236208640000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null