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:acb016e448f85e89cc782b2d9c7df113e491d5e2eb04350ed12e986f99996f43
+oid sha256:812b3e363cb0c2c82f4a0951db14454732ab61b09a85bd6fa02544d31bd2e2f1
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d3332b5bac0ae51032f79bf4b898d0f7cb87aa2ed5491f4533cd1a2d0b14b2
+oid sha256:8419538e8bb0f4e206630152b045f0ec137638be9e6e9e7ea1652dde2c1aec32
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9dbdd915e523edf9fbadf618141dbc0ab0a7ef9e84774dcab8a9237c5a21f51
+oid sha256:e3bc68ed2edac47b7ad5543f96be38b55d18efd2ed351d107e1a33fa8224f3bc
 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": 0.024671832990668986,
+  "epoch": 0.03163055511624229,
   "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": 0.5741,
       "step": 35
+    },
+    {
+      "epoch": 0.025304444092993834,
+      "grad_norm": 0.34637877345085144,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5633,
+      "step": 40
+    },
+    {
+      "epoch": 0.025304444092993834,
+      "eval_loss": 0.56394362449646,
+      "eval_runtime": 82.3016,
+      "eval_samples_per_second": 8.092,
+      "eval_steps_per_second": 4.046,
+      "step": 40
+    },
+    {
+      "epoch": 0.02846749960461806,
+      "grad_norm": 0.37049219012260437,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5798,
+      "step": 45
+    },
+    {
+      "epoch": 0.03163055511624229,
+      "grad_norm": 0.3430643081665039,
+      "learning_rate": 0.0,
+      "loss": 0.5545,
+      "step": 50
+    },
+    {
+      "epoch": 0.03163055511624229,
+      "eval_loss": 0.5589888095855713,
+      "eval_runtime": 82.3564,
+      "eval_samples_per_second": 8.087,
+      "eval_steps_per_second": 4.043,
+      "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": 1.3592561159503872e+16,
+  "total_flos": 1.74263604609024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null