Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91583bf9ad332fd8bd1cfe0bb3fc697efde43d83a573ffe396813ea729791984
+oid sha256:327a3de6277111500df098c132446c9fdf86e50591131938419903c8248728f4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420961f9e766105cfb5079b03bd8ff23b272de1271a93cba9ae82202c5375d5d
+oid sha256:cf7c3a0037e5c7b4f26cb280958247c0518a498cd8080500501375cb2a322a11
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
+oid sha256:8dd60e9ba809120cc78feb8bd27109edcdf93018d99882fdeecb2257ff3c3de7
 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": 0.0004278967271249084,
+  "epoch": 0.0006418450906873626,
   "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": 6.545084971874738e-05,
       "loss": 2.286,
       "step": 18
+    },
+    {
+      "epoch": 0.0004492915634811538,
+      "grad_norm": 2.8848774433135986,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.1907,
+      "step": 21
+    },
+    {
+      "epoch": 0.00051347607254989,
+      "grad_norm": 2.1118345260620117,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.0544,
+      "step": 24
+    },
+    {
+      "epoch": 0.00051347607254989,
+      "eval_loss": 2.096832275390625,
+      "eval_runtime": 2546.8778,
+      "eval_samples_per_second": 7.728,
+      "eval_steps_per_second": 3.864,
+      "step": 24
+    },
+    {
+      "epoch": 0.0005776605816186263,
+      "grad_norm": 2.1737489700317383,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.0826,
+      "step": 27
+    },
+    {
+      "epoch": 0.0006418450906873626,
+      "grad_norm": 2.259516954421997,
+      "learning_rate": 0.0,
+      "loss": 1.9007,
+      "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": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null