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:d9a1732159479b1b28fd2ed327a9c1667531b80f10ffcc32305406b6c6cf8ee8
+oid sha256:43844f2ec6c00d715cdc0480421ac877365a31de1baf7985eddb3d45679c89e4
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dedab212f478a5135071d9adf9666e028f4239f404fe086f5482bdbc67fbf58
+oid sha256:7fda62695a2ac517a954a1957a3fd2776cbf2c18b696848f3c3772d4c6b9dfc6
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087abc3a4df12662fc626ac5e265ecf304ec53b044c94ecf55c64e219c224944
+oid sha256:711b94e042de3347c38639a147f3405c44b1c514053f9813bf288b332eb6e5fe
 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": 0.016679140382764888,
+  "epoch": 0.021383513311237036,
   "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": 2.937,
       "step": 35
+    },
+    {
+      "epoch": 0.01710681064898963,
+      "grad_norm": 0.9677534103393555,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.1459,
+      "step": 40
+    },
+    {
+      "epoch": 0.01710681064898963,
+      "eval_loss": 3.132866621017456,
+      "eval_runtime": 15.3849,
+      "eval_samples_per_second": 64.024,
+      "eval_steps_per_second": 32.044,
+      "step": 40
+    },
+    {
+      "epoch": 0.01924516198011333,
+      "grad_norm": 1.0127432346343994,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.2155,
+      "step": 45
+    },
+    {
+      "epoch": 0.021383513311237036,
+      "grad_norm": 0.9054535031318665,
+      "learning_rate": 0.0,
+      "loss": 3.195,
+      "step": 50
+    },
+    {
+      "epoch": 0.021383513311237036,
+      "eval_loss": 3.121145009994507,
+      "eval_runtime": 15.0793,
+      "eval_samples_per_second": 65.321,
+      "eval_steps_per_second": 32.694,
+      "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": 133741336854528.0,
+  "total_flos": 171463252377600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null