Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31935fc3567e2ab7baf5617ced2fb461a50dd9261a0ac174c1bf4c00012d959f
+oid sha256:ebd9c1701d2f1232006671adaa5cf58233e86fbbf64f3ed66ab111ba0c10c11f
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:528c1699f463afc16f26e58b59a83d71b3a714414afc37f9ce5d9cd81fc2e7c3
+oid sha256:14ef96c1bde5abf32f218683806d79b4801a75f3583617f36822e73e06862d7f
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dadb035fe332ab05f61d640438272f8870c7d52406d5819c6c17bc5754bc7c6
+oid sha256:2dc6520f62449f5945af309ee383bcde13b7ff27997eab6660b261955deb085c
 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": 0.0022946238140766346,
+  "epoch": 0.002941825402662352,
   "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": 0.7698,
       "step": 35
+    },
+    {
+      "epoch": 0.0023534603221298817,
+      "grad_norm": 0.13510183990001678,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8342,
+      "step": 40
+    },
+    {
+      "epoch": 0.0023534603221298817,
+      "eval_loss": 0.8220171928405762,
+      "eval_runtime": 241.7936,
+      "eval_samples_per_second": 29.6,
+      "eval_steps_per_second": 14.802,
+      "step": 40
+    },
+    {
+      "epoch": 0.0026476428623961167,
+      "grad_norm": 0.13403601944446564,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7944,
+      "step": 45
+    },
+    {
+      "epoch": 0.002941825402662352,
+      "grad_norm": 0.1455070823431015,
+      "learning_rate": 0.0,
+      "loss": 0.797,
+      "step": 50
+    },
+    {
+      "epoch": 0.002941825402662352,
+      "eval_loss": 0.8211929798126221,
+      "eval_runtime": 243.7692,
+      "eval_samples_per_second": 29.36,
+      "eval_steps_per_second": 14.682,
+      "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": 1630673861345280.0,
+  "total_flos": 2084704622739456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null