Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042c7c74a6334f4a2ca1d8e1abd8990e052d9e84c2a38b65b904a3e2803accbf
+oid sha256:c35dd744487d89ee85db3e44d2bf8a76804ee4ed69eff1ea66f965d6c629dbd9
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05490d2521ff990a7026002e62cd578f68c239920b3dc887957fab2fcdac0e96
+oid sha256:be4ec2dc0d920858e7590818632bd5515880049d210edcdc62b17b171b8eb5ab
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29da27f0e10b099660d942695bc8238e14ab065c5b302b5c8f27b2fd3ac9cd3e
+oid sha256:e1bf4e26c86f92f00b9b6932fc49365d3baed4afa0f82d2e16b69b3d7487c6d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54142b6ca6117f62853f2199ae6d8db9e25b699f5eb4a808448e7a6a68156810
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005654376251619743,
+  "epoch": 0.007067970314524679,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,48 @@
       "eval_samples_per_second": 50.192,
       "eval_steps_per_second": 25.096,
       "step": 24
+    },
+    {
+      "epoch": 0.005889975262103899,
+      "grad_norm": 0.06733245402574539,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.1237,
+      "step": 25
+    },
+    {
+      "epoch": 0.006125574272588055,
+      "grad_norm": 0.07129982858896255,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3731,
+      "step": 26
+    },
+    {
+      "epoch": 0.006361173283072211,
+      "grad_norm": 0.05901239812374115,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.0953,
+      "step": 27
+    },
+    {
+      "epoch": 0.0065967722935563675,
+      "grad_norm": 0.062444694340229034,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.2358,
+      "step": 28
+    },
+    {
+      "epoch": 0.006832371304040523,
+      "grad_norm": 0.06221400946378708,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.0688,
+      "step": 29
+    },
+    {
+      "epoch": 0.007067970314524679,
+      "grad_norm": 0.06028907373547554,
+      "learning_rate": 0.0,
+      "loss": 1.0554,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 376280532910080.0,
+  "total_flos": 470350666137600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null