Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3d7cdf226bad03dbef63e9b9f6505dcf65ef1b30da355ff5e8f3d8ae9d26bbf
+oid sha256:cd4dadc415aa400ed6b902d2d416b092e92f2559c3e9a5a22b223c5cfeada727
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16204f53b210de3cbf2b4ceaca61d7cd5a00e5aeb96f90dfe60d22d513f86c9c
+oid sha256:7c96fab9e6e3502dccd053971f14a7fd18adc9cc7f98bd8825b6387df7843d01
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7435821fdd367275b38dd7f43b19cc2552d64f5a2461fe7a22bbd1ed764a7350
+oid sha256:932c4e48fee6be9b11c4ae188107e01db76c957663b4a0ce6a3899adf5ee4f11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79af33a7cc5e89926792af60c545e28f6f3569216a6e1a04e51a93b6477fd5cc
+oid sha256:59fb9c579d7f7f4aa986f5f762cd9981f0dcd26b5aa72ad6a0ef96ae89405fbd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019746121297602257,
+  "epoch": 0.025858015984955338,
   "eval_steps": 14,
-  "global_step": 42,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,13 @@
       "eval_samples_per_second": 389.905,
       "eval_steps_per_second": 194.953,
       "step": 42
+    },
+    {
+      "epoch": 0.023507287259050307,
+      "grad_norm": 0.03093448095023632,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 10.3729,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -81,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 617450864640.0,
+  "total_flos": 821112668160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null