Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45de1bc95dd219a865a9a8d3613c0b20f9dfc0476be531f4621cc4a8a11c94f9
+oid sha256:a2411cec1f293a5e1edee124fd06a4e6cb75b40342aa849fb63c59673a16aa8d
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:462ba99a6e59cfc458daba18401f82ce7cb968b379afa8bb8b9dbb1e7a9857ea
+oid sha256:730fc5c749c3417deeaaaa46ffbe482dae65f2760d67d87e6408dc4ac1118a48
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98dc5740d8ab8834be2aa90384982a9fc46db80dac0ebece12ebcc9e0a3150ff
+oid sha256:26f3dd2d0a091a302e7d561fe8532f63a666092f6556b354ddb5bdb93e236096
 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": 0.009798379498775203,
+  "epoch": 0.012562024998429747,
   "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": 1.4925,
       "step": 35
+    },
+    {
+      "epoch": 0.010049619998743797,
+      "grad_norm": 1.5435250997543335,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5101,
+      "step": 40
+    },
+    {
+      "epoch": 0.010049619998743797,
+      "eval_loss": 1.459788203239441,
+      "eval_runtime": 81.209,
+      "eval_samples_per_second": 20.638,
+      "eval_steps_per_second": 10.319,
+      "step": 40
+    },
+    {
+      "epoch": 0.011305822498586773,
+      "grad_norm": 1.7534375190734863,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4827,
+      "step": 45
+    },
+    {
+      "epoch": 0.012562024998429747,
+      "grad_norm": 1.682039737701416,
+      "learning_rate": 0.0,
+      "loss": 1.4508,
+      "step": 50
+    },
+    {
+      "epoch": 0.012562024998429747,
+      "eval_loss": 1.455602765083313,
+      "eval_runtime": 80.9896,
+      "eval_samples_per_second": 20.694,
+      "eval_steps_per_second": 10.347,
+      "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": 2673865880764416.0,
+  "total_flos": 3428033180467200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null