Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50bf695388fb6418a1b51216d11ebaec4b701f3f8815f33914e3eec5ce19f4b0
+oid sha256:c4b978a9cf4d8ebaf9038a0abb3f5e1e7ad0f3eb8d6136c4d30ef92566da1e5f
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e53afffbec57a4260433dea5c8d5f31ee99a48a99fb1d96f5acd9b13f3f6559
+oid sha256:a2fab5bef055179d256e643bb9347fc6ba0078dcfb8ec483d0de333f1b9613dc
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b764ffc4614cec5f111c8369b8ceeec43213ce61615549f2a5e6385c87d399f3
+oid sha256:50b8a75d34b06d6c431f52afedcaf57fbfdcdab14fc1661fccca02d5bad756f8
 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": 0.022209567198177675,
+  "epoch": 0.02847380410022779,
   "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": 42.9937,
       "step": 35
+    },
+    {
+      "epoch": 0.022779043280182234,
+      "grad_norm": 11.99741268157959,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 42.8419,
+      "step": 40
+    },
+    {
+      "epoch": 0.022779043280182234,
+      "eval_loss": 10.675810813903809,
+      "eval_runtime": 3.5628,
+      "eval_samples_per_second": 207.702,
+      "eval_steps_per_second": 103.851,
+      "step": 40
+    },
+    {
+      "epoch": 0.02562642369020501,
+      "grad_norm": 11.16051959991455,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 42.8,
+      "step": 45
+    },
+    {
+      "epoch": 0.02847380410022779,
+      "grad_norm": 8.583091735839844,
+      "learning_rate": 0.0,
+      "loss": 42.69,
+      "step": 50
+    },
+    {
+      "epoch": 0.02847380410022779,
+      "eval_loss": 10.664730072021484,
+      "eval_runtime": 3.4854,
+      "eval_samples_per_second": 212.316,
+      "eval_steps_per_second": 106.158,
+      "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": 629323333632.0,
+  "total_flos": 812574572544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null