Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534e2adc6008edc04f637f0941b329ed47e9461008c59ca923829be1c42d55c0
+oid sha256:b83478cfc1cdd0ad3bd85c77e70be79cb1cdb348484eccb833079a2d91337407
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b95b67931e469b0617ee5ce686a34f7af6e3a0280e42e8d70bcec6bd91a91b0
+oid sha256:e9d9b6a640798211e4a4ec376affef2a12eaf4af9b58ecd8ee10a1b650feefa1
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db7c63649bbfbc654c9320d13fb127a9fc70ebb76dcfd99ba788425a385a575e
+oid sha256:1e7080bcf59da0b32506b7a5a2d8d25e1abeb09c4e8d9d3f76e7b7d3df2f68de
 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": 0.028901734104046242,
+  "epoch": 0.04335260115606936,
   "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": 13.69,
       "eval_steps_per_second": 6.845,
       "step": 20
+    },
+    {
+      "epoch": 0.030346820809248554,
+      "grad_norm": 2.7139039039611816,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.6674,
+      "step": 21
+    },
+    {
+      "epoch": 0.03468208092485549,
+      "grad_norm": 3.0769095420837402,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.8922,
+      "step": 24
+    },
+    {
+      "epoch": 0.036127167630057806,
+      "eval_loss": 1.7379896640777588,
+      "eval_runtime": 21.3263,
+      "eval_samples_per_second": 13.692,
+      "eval_steps_per_second": 6.846,
+      "step": 25
+    },
+    {
+      "epoch": 0.03901734104046243,
+      "grad_norm": 2.7288920879364014,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.9318,
+      "step": 27
+    },
+    {
+      "epoch": 0.04335260115606936,
+      "grad_norm": 2.5930235385894775,
+      "learning_rate": 0.0,
+      "loss": 6.9707,
+      "step": 30
+    },
+    {
+      "epoch": 0.04335260115606936,
+      "eval_loss": 1.7303022146224976,
+      "eval_runtime": 21.3296,
+      "eval_samples_per_second": 13.69,
+      "eval_steps_per_second": 6.845,
+      "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": 3684183016734720.0,
+  "total_flos": 5526274525102080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null