Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecfdcd722cf0bfeed1fdb741b1ce2a4d3dc9e42ff5949cd0d287aedb893ed30a
+oid sha256:55e67e4ee1e3d3c65d41826d1c8d1c001d18729359b342d22c773085711b2969
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea20630ec4c87a0c9bc73dd1c600ea9fae73d09c49caab3b0f94f8fafad23f25
+oid sha256:9fff8d76ef952782911a91bf22cb5620f31ade00758cfd8f9ea8852d1256e7e8
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0cd7e6f6c31c2c6445a437b119b4c74596a2530adcf9cfe83af331668aeb064
+oid sha256:43a586f21cedf9022a5cba7d8a05d997c2747c0dfc57abc02015a95bb29a9d1e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43427779b8e6e83ef9780afcdea7472d2419de40e6f85cfedb90b60f89a2ff0f
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02020365718607352,
+  "epoch": 0.02160818950382195,
   "eval_steps": 17,
-  "global_step": 187,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -537,6 +537,34 @@
       "eval_samples_per_second": 94.789,
       "eval_steps_per_second": 11.851,
       "step": 187
+    },
+    {
+      "epoch": 0.02041973908111174,
+      "grad_norm": 0.050048764795064926,
+      "learning_rate": 8.247462563808817e-07,
+      "loss": 11.921,
+      "step": 189
+    },
+    {
+      "epoch": 0.02074386192366907,
+      "grad_norm": 0.06726805865764618,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 11.9195,
+      "step": 192
+    },
+    {
+      "epoch": 0.0210679847662264,
+      "grad_norm": 0.07607147097587585,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 11.9209,
+      "step": 195
+    },
+    {
+      "epoch": 0.02139210760878373,
+      "grad_norm": 0.0720086470246315,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 11.9206,
+      "step": 198
     }
   ],
   "logging_steps": 3,
@@ -551,12 +579,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 550860226560.0,
+  "total_flos": 589457915904.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null