Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68e79387e775d123e0af9a502fc4136512616403076eb4593a9de7a3adf10bd2
+oid sha256:0dfd07fe70ff7f96204e9fe2ed307ecb0e5d977879334cd15f504c35223f6d74
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af443bff2d83c21ec7fa41f61cc5db0bddcfe48879b97812ed88fff49db48761
+oid sha256:39517c5026f77e66658f863fe78cf9e33a1b3f375adb78283908e7ee06d51522
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81b800cd73c6e076181244eeadb7e8e3f37788a94fa12c62485d611962aa6ba
+oid sha256:d119126267194af793d63127d10340d3f3bb4ac76d871af58281d54f59c44a0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007735148514851485,
+  "epoch": 0.01547029702970297,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 4.601,
       "eval_steps_per_second": 4.601,
       "step": 25
+    },
+    {
+      "epoch": 0.009282178217821782,
+      "grad_norm": 21.752103805541992,
+      "learning_rate": 5e-05,
+      "loss": 7.5132,
+      "step": 30
+    },
+    {
+      "epoch": 0.010829207920792078,
+      "grad_norm": 11.453251838684082,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 7.5282,
+      "step": 35
+    },
+    {
+      "epoch": 0.012376237623762377,
+      "grad_norm": 14.995335578918457,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.517,
+      "step": 40
+    },
+    {
+      "epoch": 0.013923267326732673,
+      "grad_norm": 22.817428588867188,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.4861,
+      "step": 45
+    },
+    {
+      "epoch": 0.01547029702970297,
+      "grad_norm": 21.126054763793945,
+      "learning_rate": 0.0,
+      "loss": 9.1762,
+      "step": 50
+    },
+    {
+      "epoch": 0.01547029702970297,
+      "eval_loss": 7.1646647453308105,
+      "eval_runtime": 77.8098,
+      "eval_samples_per_second": 4.627,
+      "eval_steps_per_second": 4.627,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 112649109504000.0,
+  "total_flos": 225298219008000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null