Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5509df886d57a562315e1e20c8d9b73031c653d38b39ee797c2ae9af0b3f9326
+oid sha256:f418493b09e4ffae3be7007d234b8b8affd7ec3d9f8ccb8891eac0b7308f045d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fddafbc116384bf1fc4c7783a02cfae987390eaad8d4cf07951bb3104daf24a
+oid sha256:3bb7c9afd0ec3938a1f6a765c4a29102c3494cd31abb7445336e45c08e6b7c4c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc18d436d3f28c2199b1b26c44b98b8a68857600b301be9e35e8da71ec804a3b
+oid sha256:29047e2ee2d7b8c8cf4b4f522e4dda58747cc106e3aa6c47295126ce6ca456ca
 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": 0.022553129969640016,
+  "epoch": 0.028914269191846177,
   "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": 0.6166,
       "step": 35
+    },
+    {
+      "epoch": 0.02313141535347694,
+      "grad_norm": 0.6335359215736389,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5805,
+      "step": 40
+    },
+    {
+      "epoch": 0.02313141535347694,
+      "eval_loss": 0.578225314617157,
+      "eval_runtime": 53.8643,
+      "eval_samples_per_second": 13.534,
+      "eval_steps_per_second": 6.776,
+      "step": 40
+    },
+    {
+      "epoch": 0.026022842272661557,
+      "grad_norm": 0.6076445579528809,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.568,
+      "step": 45
+    },
+    {
+      "epoch": 0.028914269191846177,
+      "grad_norm": 0.697899580001831,
+      "learning_rate": 0.0,
+      "loss": 0.5862,
+      "step": 50
+    },
+    {
+      "epoch": 0.028914269191846177,
+      "eval_loss": 0.5754016637802124,
+      "eval_runtime": 53.7864,
+      "eval_samples_per_second": 13.554,
+      "eval_steps_per_second": 6.786,
+      "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": 7536974311194624.0,
+  "total_flos": 9617734090358784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null