Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:190c7a6593fd8455b16867a1f19329a4f665b21d39aada11e8d6a487328ebf58
+oid sha256:9a3cbf86108d4f823b34aa6a37b43a6ab09a4af79226e06bbb8be668e9886e90
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6724ef3d3855b0f55c4a0611e70d0d35cd23663c3a3848cb295522ba31cf0f6b
+oid sha256:6e3adc1a52e6bf340a803ae835482ffbcb47fba6be3b471592b6858932420d60
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b626c13d49d84d2de1b88ddb2d6b4b95b03930a7805888e3dde5b34dc87399a
+oid sha256:74ba3669bacc4ea4f79c359d621616f8d9b16119502f2941eafaf4e25d9bb973
 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": 0.021041273266792556,
+  "epoch": 0.026975991367682764,
   "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": 7.7337,
       "step": 35
+    },
+    {
+      "epoch": 0.02158079309414621,
+      "grad_norm": 7.108482837677002,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.3231,
+      "step": 40
+    },
+    {
+      "epoch": 0.02158079309414621,
+      "eval_loss": 2.0455877780914307,
+      "eval_runtime": 48.528,
+      "eval_samples_per_second": 16.094,
+      "eval_steps_per_second": 8.057,
+      "step": 40
+    },
+    {
+      "epoch": 0.024278392230914485,
+      "grad_norm": 7.392975330352783,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.3295,
+      "step": 45
+    },
+    {
+      "epoch": 0.026975991367682764,
+      "grad_norm": 6.484737873077393,
+      "learning_rate": 0.0,
+      "loss": 7.8415,
+      "step": 50
+    },
+    {
+      "epoch": 0.026975991367682764,
+      "eval_loss": 2.045379638671875,
+      "eval_runtime": 48.5278,
+      "eval_samples_per_second": 16.094,
+      "eval_steps_per_second": 8.057,
+      "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": 6879228909846528.0,
+  "total_flos": 8850982419038208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null