Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b772cf411bbc0e0f64295d57c9eacf51bdf9e23754af9744c7b817edc9157ac
+oid sha256:7108e55f4c11cfffdd2f98f867939ff4ddf102de1688d3e352a800f0cd23cc9b
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172eac1d480583f90e4eae6492ab071cf922c0a265a3200b8589c33d6e02c367
+oid sha256:94701b277833a11f5b969796cf0a7489e23786ad6f559f54904621c586e9f06a
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f97671355cdef55822c9fc4d2397fd667b2b8d08b3aa4dee220f90d0c78e279
+oid sha256:35a17607c98c1af441214c93d6746d080c77a25c4d6c95347aed638f3a3c61ef
 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": 0.009508136770890473,
+  "epoch": 0.012189918937039069,
   "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": 31.81,
       "step": 35
+    },
+    {
+      "epoch": 0.009751935149631255,
+      "grad_norm": 6907.08984375,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 32.4159,
+      "step": 40
+    },
+    {
+      "epoch": 0.009751935149631255,
+      "eval_loss": 8.049545288085938,
+      "eval_runtime": 12.401,
+      "eval_samples_per_second": 139.263,
+      "eval_steps_per_second": 69.672,
+      "step": 40
+    },
+    {
+      "epoch": 0.010970927043335162,
+      "grad_norm": 5738.95263671875,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 31.8839,
+      "step": 45
+    },
+    {
+      "epoch": 0.012189918937039069,
+      "grad_norm": 7662.15673828125,
+      "learning_rate": 0.0,
+      "loss": 32.7971,
+      "step": 50
+    },
+    {
+      "epoch": 0.012189918937039069,
+      "eval_loss": 8.031700134277344,
+      "eval_runtime": 12.3056,
+      "eval_samples_per_second": 140.342,
+      "eval_steps_per_second": 70.212,
+      "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": 7501101662208.0,
+  "total_flos": 9637491376128.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null