Training in progress, epoch 14, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8755cbe7e2398d1959416d6feb911384858a351204adb4f45a8e698f8710fd55
+oid sha256:7415a33eadc4a72f7ee8a58c72bed36a025bbcc1ca1e89dfa2d2ce164b000c5c
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f66a5ce1a780e3e1ff27f566dc0f0ffc09cedbb81984f67263cfbe2c21bb457c
+oid sha256:32fbae7221f081ebb469450f3a8f3fa245312ed697db0b4357b8f97b88f52fb4
 size 60252034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235ab0e10f5c7cdfbbd49cc3926a6ca3af658975caba14cd01311559832e2b6e
+oid sha256:e51e3e2f1bea9b7e703a1b7ac2c1ee4d3b75a36bbde79aa557a24cb0493a46b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bbd78e2bc5c115f006119ec58fcb69b8d548f43ab2f01e37b0763759baab3bc
+oid sha256:02613a6afb86ae474ea068b51099dfd9dc4abfb57724ef7ae1f766d5528370f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.0,
+  "epoch": 14.989939637826962,
   "eval_steps": 500,
-  "global_step": 3474,
+  "global_step": 3720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,27 @@
       "learning_rate": 0.0002,
       "loss": 0.1555,
       "step": 3400
+    },
+    {
+      "epoch": 14.104627766599597,
+      "grad_norm": 0.3850514888763428,
+      "learning_rate": 0.0002,
+      "loss": 0.1537,
+      "step": 3500
+    },
+    {
+      "epoch": 14.507042253521126,
+      "grad_norm": 0.3872847855091095,
+      "learning_rate": 0.0002,
+      "loss": 0.1427,
+      "step": 3600
+    },
+    {
+      "epoch": 14.909456740442655,
+      "grad_norm": 0.3384864032268524,
+      "learning_rate": 0.0002,
+      "loss": 0.1471,
+      "step": 3700
     }
   ],
   "logging_steps": 100,
@@ -259,12 +280,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.235863557546967e+17,
+  "total_flos": 5.606624189428531e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null