Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e241dba4b97071f4d4c03728e546f14a90b467c0589bf9d0c8f37a9a1dfa99ab
+oid sha256:4f59c9e592599775568e90592fc92a6966af9741bb8979967ee2e514e53f001a
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a26ffea765714fe791eb0ad797905729ef5de535a52914b0e1a50dbab623cdbb
+oid sha256:ca2d1c81d06904658757389d737e94281c8fff797c1d53231a7ee80d93184e67
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25279979d254cdec51c016acdd348679fc5c3680e3245236eada67c793e9019
+oid sha256:e2234e82ca1570847a5bcb17690e940ac550265a88280c567f452baa9416cd04
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004553189129552824,
+  "epoch": 0.0005837421960965159,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 44.2187,
       "step": 35
+    },
+    {
+      "epoch": 0.0004669937568772127,
+      "grad_norm": 1.132824420928955,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 44.2731,
+      "step": 40
+    },
+    {
+      "epoch": 0.0004669937568772127,
+      "eval_loss": 11.06089973449707,
+      "eval_runtime": 241.2691,
+      "eval_samples_per_second": 149.48,
+      "eval_steps_per_second": 74.742,
+      "step": 40
+    },
+    {
+      "epoch": 0.0005253679764868643,
+      "grad_norm": 1.2608704566955566,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 44.2339,
+      "step": 45
+    },
+    {
+      "epoch": 0.0005837421960965159,
+      "grad_norm": 1.1074978113174438,
+      "learning_rate": 0.0,
+      "loss": 44.2599,
+      "step": 50
+    },
+    {
+      "epoch": 0.0005837421960965159,
+      "eval_loss": 11.059405326843262,
+      "eval_runtime": 249.6947,
+      "eval_samples_per_second": 144.436,
+      "eval_steps_per_second": 72.22,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 612444930048.0,
+  "total_flos": 793284968448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null