Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23bf7dd8ddd45fe3bbe2116526ec2df2efb383b7f8f6bcbd896cc090493588a8
+oid sha256:815ff460bd3d9c306cd519184b10c79d242ab690d72f66d01a4bbf0c530d46c8
 size 16794864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6353c7dc21b4f745012ed15f3f27fdcc60d57d51224aee410b13575a750a4eb
+oid sha256:4774546fd039508e5e3ebfa295b974e130207acb6bd158a2234109724f0d84e3
 size 8671162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2423dd4b3ab702d2b45b13b58ccc749b24e72846b935a78ebc0d869e72c1e889
+oid sha256:4776274a336ad4294e43c53bdf650309df73cbfe2f63e77e2d0f5b790d95f837
 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": 0.0008318669012957927,
+  "epoch": 0.0010664960273022983,
   "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": 4.9699,
       "step": 35
+    },
+    {
+      "epoch": 0.0008531968218418387,
+      "grad_norm": 4.612921714782715,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.5087,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008531968218418387,
+      "eval_loss": 1.3007169961929321,
+      "eval_runtime": 423.1715,
+      "eval_samples_per_second": 46.648,
+      "eval_steps_per_second": 23.324,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009598464245720685,
+      "grad_norm": 3.6289823055267334,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 5.1549,
+      "step": 45
+    },
+    {
+      "epoch": 0.0010664960273022983,
+      "grad_norm": 3.7956082820892334,
+      "learning_rate": 0.0,
+      "loss": 5.3804,
+      "step": 50
+    },
+    {
+      "epoch": 0.0010664960273022983,
+      "eval_loss": 1.296925663948059,
+      "eval_runtime": 423.4498,
+      "eval_samples_per_second": 46.617,
+      "eval_steps_per_second": 23.309,
+      "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": 1665928047624192.0,
+  "total_flos": 2159536358031360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null