Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890eb932ca4c160b30fa7984161d124eb5a7ddb10b54d4ee075bcef3ef9b5fbd
+oid sha256:fb36ca40c1743ba61c897a95b6d56455c33b10ac655b4418a57d0af50941007b
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5780ab7c1c4bbc3e35107067c1eb51537ec052d82a39f26905bb89348fa4a4e
+oid sha256:ddec7b74aef502dd125bab989d40da5e822622e3d40e4b7b50df825027fc71d6
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ceaf1922bf3db1a08d574607be64151b478ec76f9bee9cff4e31dc3ad2dff2
+oid sha256:43fea2fe84a701fbe41f192e97b26f048008b0b195f7713e4d5f9f4bbc7206fc
 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": 0.009965504024530471,
+  "epoch": 0.012776287210936502,
   "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": 0.0939,
       "step": 35
+    },
+    {
+      "epoch": 0.010221029768749201,
+      "grad_norm": 0.2863682508468628,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.138,
+      "step": 40
+    },
+    {
+      "epoch": 0.010221029768749201,
+      "eval_loss": 0.124103844165802,
+      "eval_runtime": 228.0539,
+      "eval_samples_per_second": 7.226,
+      "eval_steps_per_second": 3.613,
+      "step": 40
+    },
+    {
+      "epoch": 0.011498658489842852,
+      "grad_norm": 0.2913203537464142,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1075,
+      "step": 45
+    },
+    {
+      "epoch": 0.012776287210936502,
+      "grad_norm": 0.26606062054634094,
+      "learning_rate": 0.0,
+      "loss": 0.1025,
+      "step": 50
+    },
+    {
+      "epoch": 0.012776287210936502,
+      "eval_loss": 0.1226755753159523,
+      "eval_runtime": 227.985,
+      "eval_samples_per_second": 7.229,
+      "eval_steps_per_second": 3.614,
+      "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": 1725914073268224.0,
+  "total_flos": 2237073293574144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null