Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8034066eab84385c925f8d5cb7dfaac1a9310cd520ef42543c10ecb68356f02b
+oid sha256:2ecc01b71a76705132d298e0c075641c65a3983b4b1ba5ac999e915f6e02f52c
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50c1dd1e7f5c32e67e8beda7ac94af84589283a31635d51cbb5771bc4ec16f98
+oid sha256:11f81d8b72df57282207286293b2e614c3794396914cece9a35c025731e7070f
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f497f2a858c936111630bbf34f23fec2b0221ce321dcb916b0ed6dfb1c17ee4
+oid sha256:cebf5eef07fb28063a75d0fe9d065e793debfc8330a59ed9c6dc7cfb9949d888
 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": 0.006594800253646164,
+  "epoch": 0.008454872120059184,
   "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": 0.2584,
       "step": 35
+    },
+    {
+      "epoch": 0.006763897696047347,
+      "grad_norm": 0.11750715970993042,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2531,
+      "step": 40
+    },
+    {
+      "epoch": 0.006763897696047347,
+      "eval_loss": 0.2599148452281952,
+      "eval_runtime": 303.6003,
+      "eval_samples_per_second": 8.202,
+      "eval_steps_per_second": 4.101,
+      "step": 40
+    },
+    {
+      "epoch": 0.007609384908053266,
+      "grad_norm": 0.11680182069540024,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2381,
+      "step": 45
+    },
+    {
+      "epoch": 0.008454872120059184,
+      "grad_norm": 0.1036166399717331,
+      "learning_rate": 0.0,
+      "loss": 0.2547,
+      "step": 50
+    },
+    {
+      "epoch": 0.008454872120059184,
+      "eval_loss": 0.2593758702278137,
+      "eval_runtime": 304.1021,
+      "eval_samples_per_second": 8.188,
+      "eval_steps_per_second": 4.094,
+      "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": 1.3461863456047104e+16,
+  "total_flos": 1.7295662757445632e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null