Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283756972a8cf19e99338d195f1500b250a6b5b064ddcbb75bd8cb66def22fe9
+oid sha256:fbbd0a6b214093ed109e3e6546bc7492288cc4086bca98ca1c0987ade228da5e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590f33165a134af295d03b0dd766a3df10650432248129b850bede444e423128
+oid sha256:d21085f9696039b356e9de73838658275b688657b7da69b20581220857449ae7
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5f0eac312b1545ecb7cec2dfaf09849808e8a59aee995ff3546a578309a234
+oid sha256:2f3dfab2f15c077a3bfe1d57e8f4dfb9954e3c582cff3d86c56d618335c8d869
 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": 0.0018630202424314802,
+  "epoch": 0.0023884874902967697,
   "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": 7.0869,
       "step": 35
+    },
+    {
+      "epoch": 0.0019107899922374157,
+      "grad_norm": 3.8861474990844727,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.0943,
+      "step": 40
+    },
+    {
+      "epoch": 0.0019107899922374157,
+      "eval_loss": 1.7261768579483032,
+      "eval_runtime": 1056.955,
+      "eval_samples_per_second": 8.34,
+      "eval_steps_per_second": 4.17,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021496387412670926,
+      "grad_norm": 4.873538970947266,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.6387,
+      "step": 45
+    },
+    {
+      "epoch": 0.0023884874902967697,
+      "grad_norm": 4.656768798828125,
+      "learning_rate": 0.0,
+      "loss": 6.9,
+      "step": 50
+    },
+    {
+      "epoch": 0.0023884874902967697,
+      "eval_loss": 1.7244895696640015,
+      "eval_runtime": 1056.3801,
+      "eval_samples_per_second": 8.345,
+      "eval_steps_per_second": 4.173,
+      "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": 1.3670824330395648e+16,
+  "total_flos": 1.75266978594816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null