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:a672d74a821445991b6e12d6f44297237925adaf93a9ecfe04705a28c0e7f1ff
+oid sha256:fc7abf1ab7d9236e56abf92b36eb88e088cb2fb44318b0a3bdd3ee5e0882d319
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf90ca718c193634bcc6e27617fff14caa739cc7bf7710bc4778942a0602baa
+oid sha256:c8c298c2e974aa3849e1b216700e0c402c702c859d005b42f2d5224bef5f9d81
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67564b29c7d5b3904f2bf5afd085152b12ee9b685430ca4dc46ab796ad9112b2
+oid sha256:0e5a040ff609adacbe1fe4c809bf7b3a4743d55ed735f12cf31c9016a2038adb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.425531914893617,
+  "epoch": 0.6382978723404256,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 1.7386,
       "step": 18
+    },
+    {
+      "epoch": 0.44680851063829785,
+      "grad_norm": 3.365093231201172,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.8971,
+      "step": 21
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 2.163831949234009,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.5753,
+      "step": 24
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "eval_loss": 1.422104835510254,
+      "eval_runtime": 2.3784,
+      "eval_samples_per_second": 8.409,
+      "eval_steps_per_second": 4.204,
+      "step": 24
+    },
+    {
+      "epoch": 0.574468085106383,
+      "grad_norm": 4.278740882873535,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.1696,
+      "step": 27
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 2.4858059883117676,
+      "learning_rate": 0.0,
+      "loss": 2.2444,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3333850658242560.0,
+  "total_flos": 4980196662312960.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null