Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c6dca074a8294ef498829131c5e3ea74e7dd645faf6724a1d2313d67092ba12
+oid sha256:fa9f0fc0d188bcce65b743eb53ac79212eac49bf154aedddb8bc5fbf4c356eeb
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e441730382dfc262833538c00776306a01f73d347776857ae0f8d23fa7b5dbf
+oid sha256:aabc56c4e398423b3568a889626a8b94dce0f1e5cfb4a78ca324ac00d9de7eb8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a34150fa91a698f18d7a20c0315359a3d0f8d3fdc873014559cab737ae6ef67f
+oid sha256:5e9e087880269e21bbba387f740b3260a46483698f0aa961209cd92c1dd50aa7
 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": 0.003118378443209531,
+  "epoch": 0.00399792108103786,
   "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": 0.2985,
       "step": 35
+    },
+    {
+      "epoch": 0.003198336864830288,
+      "grad_norm": 0.4196644127368927,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1386,
+      "step": 40
+    },
+    {
+      "epoch": 0.003198336864830288,
+      "eval_loss": 0.20123553276062012,
+      "eval_runtime": 474.4269,
+      "eval_samples_per_second": 11.1,
+      "eval_steps_per_second": 5.55,
+      "step": 40
+    },
+    {
+      "epoch": 0.0035981289729340744,
+      "grad_norm": 0.3079071342945099,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1249,
+      "step": 45
+    },
+    {
+      "epoch": 0.00399792108103786,
+      "grad_norm": 0.5225589871406555,
+      "learning_rate": 0.0,
+      "loss": 0.1616,
+      "step": 50
+    },
+    {
+      "epoch": 0.00399792108103786,
+      "eval_loss": 0.19879676401615143,
+      "eval_runtime": 473.5767,
+      "eval_samples_per_second": 11.12,
+      "eval_steps_per_second": 5.56,
+      "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": 9941407833784320.0,
+  "total_flos": 1.2669515099799552e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null