Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1421fe13e497491d66a2520bce89a66ff5a552a2e9f03313349eef8143554aee
+oid sha256:86959a7f92d9510c6d9a3489a74a32dfb9a4d804b75f69fa68ee4f356287e232
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3167ca23a2a197612ad72dc3600b0b9d6973f8f4b16ec12349963a693f8b595
+oid sha256:a4246996e8aa0749b606dca319c25d727e58585b7096d894d747209929c4290c
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c0a3892426d471eda45de06c5d910a0dff8451e4b7f6aae0491711afd0a32a1
+oid sha256:6674d6633b78d582f608f5a0b1fd423afd92a63951f30082aaecb644a4c06fd1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.031189083820662766,
+  "epoch": 0.04678362573099415,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 10.239,
       "eval_steps_per_second": 5.138,
       "step": 20
+    },
+    {
+      "epoch": 0.03274853801169591,
+      "grad_norm": 0.25635430216789246,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.3608,
+      "step": 21
+    },
+    {
+      "epoch": 0.03742690058479532,
+      "grad_norm": 0.25514256954193115,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.3215,
+      "step": 24
+    },
+    {
+      "epoch": 0.03898635477582846,
+      "eval_loss": 1.3476552963256836,
+      "eval_runtime": 26.484,
+      "eval_samples_per_second": 10.233,
+      "eval_steps_per_second": 5.135,
+      "step": 25
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.20033127069473267,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.4183,
+      "step": 27
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": 0.21877515316009521,
+      "learning_rate": 0.0,
+      "loss": 1.2605,
+      "step": 30
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "eval_loss": 1.345063328742981,
+      "eval_runtime": 26.458,
+      "eval_samples_per_second": 10.243,
+      "eval_steps_per_second": 5.14,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1680565359017984e+16,
+  "total_flos": 1.7888418277097472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null