Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd4b3dc21a5d658ff730997146fb747aa0f30ede231f6a313892b6f1a4a72af
+oid sha256:c503eedd03ffe89a50c051273996c553e42472e8c01658413c75be373c13e786
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9354400c3c6ab792f0c4c04cca3d95cc700aa081a0ec27e4dc7626e82d770cbe
+oid sha256:41b32fca024d5a88ba1bf117cc42863887cf5794db033d502be1d13c96167a82
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2984c51083c54f2a93eb7c7b2418dea66d8f3c5351ed7e42b1e0477edc7c96a3
+oid sha256:87ac1a33f136aa1f47e5b25f5555000c65160f91613dd9094dd725f4ba48f816
 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": 0.006169031462060457,
+  "epoch": 0.009253547193090685,
   "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": 22.393,
       "eval_steps_per_second": 11.205,
       "step": 20
+    },
+    {
+      "epoch": 0.006477483035163479,
+      "grad_norm": 0.32985055446624756,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.5103,
+      "step": 21
+    },
+    {
+      "epoch": 0.007402837754472548,
+      "grad_norm": 0.2573980987071991,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.5534,
+      "step": 24
+    },
+    {
+      "epoch": 0.0077112893275755705,
+      "eval_loss": 0.5697392821311951,
+      "eval_runtime": 61.3179,
+      "eval_samples_per_second": 22.261,
+      "eval_steps_per_second": 11.139,
+      "step": 25
+    },
+    {
+      "epoch": 0.008328192473781616,
+      "grad_norm": 0.2890177071094513,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.5204,
+      "step": 27
+    },
+    {
+      "epoch": 0.009253547193090685,
+      "grad_norm": 0.26763761043548584,
+      "learning_rate": 0.0,
+      "loss": 0.5363,
+      "step": 30
+    },
+    {
+      "epoch": 0.009253547193090685,
+      "eval_loss": 0.5661888718605042,
+      "eval_runtime": 61.2334,
+      "eval_samples_per_second": 22.292,
+      "eval_steps_per_second": 11.154,
+      "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": 1305053327523840.0,
+  "total_flos": 1957579991285760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null