Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:729a6b837d40f18baabe1383515ec0a2bf918b8614ccf4220669f927429f9ba0
+oid sha256:a67faafc4a0473fb5064be36ccd397a9abb63a3e80bc43d16148aaf942e03f62
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:214e16443c92f93976e12472f86e19f2fd716e3a3de5bd1e8357b8b981bc3e86
+oid sha256:e725d57233e3fcd17f529e9d4e667bbadfeed9379c095ce4e00a2a81698cdc8c
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17eed42d09edc486c8d5f78ac42131eead6bdad5f39a0c15fe815f049a01376
+oid sha256:2467e7cf7e0ece47f1d524d2f15d75611bac417c83118c615b07a9883bff3683
 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": 0.0009741962880623486,
+  "epoch": 0.001248969600079934,
   "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": 0.5813,
       "step": 35
+    },
+    {
+      "epoch": 0.0009991756800639471,
+      "grad_norm": 0.29770585894584656,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5773,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009991756800639471,
+      "eval_loss": 0.5903847813606262,
+      "eval_runtime": 1204.1728,
+      "eval_samples_per_second": 13.999,
+      "eval_steps_per_second": 7.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0011240726400719406,
+      "grad_norm": 0.2932800054550171,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5666,
+      "step": 45
+    },
+    {
+      "epoch": 0.001248969600079934,
+      "grad_norm": 0.28756025433540344,
+      "learning_rate": 0.0,
+      "loss": 0.5717,
+      "step": 50
+    },
+    {
+      "epoch": 0.001248969600079934,
+      "eval_loss": 0.5883446335792542,
+      "eval_runtime": 1517.3193,
+      "eval_samples_per_second": 11.11,
+      "eval_steps_per_second": 5.555,
+      "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": 5244890766114816.0,
+  "total_flos": 6718945033715712.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null