Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52efa5693197c6bddb7732fca8a6fab9b915bb3cb5f98a86059492498037a65c
+oid sha256:b9143fca904af8327fba16c5957b4b3d966491ec74cedef39ba28eafed812f1c
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dce1791a001dea4fbaddd5262eb11d319910e00bad6a4c157e4090d4b0b3d09
+oid sha256:14620b9280b174a28f255531d734af0a69d18b44666845d14623d42352c1fe95
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad126059eda90deccd7392c4c88acf9f2b706ce7fbf93830d8a6d7c95e06c329
+oid sha256:f1433e271c5a4a0e8d91fb41c44aea67a603bc5c77f4ce7cfe334d0e0d4c0f92
 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": 0.04292790313703908,
+  "epoch": 0.0550357732526142,
   "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": 0.0187,
       "step": 35
+    },
+    {
+      "epoch": 0.04402861860209136,
+      "grad_norm": 0.13033170998096466,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0135,
+      "step": 40
+    },
+    {
+      "epoch": 0.04402861860209136,
+      "eval_loss": 0.015340453945100307,
+      "eval_runtime": 12.4106,
+      "eval_samples_per_second": 30.861,
+      "eval_steps_per_second": 15.471,
+      "step": 40
+    },
+    {
+      "epoch": 0.04953219592735278,
+      "grad_norm": 0.18985408544540405,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0102,
+      "step": 45
+    },
+    {
+      "epoch": 0.0550357732526142,
+      "grad_norm": 0.1414397656917572,
+      "learning_rate": 0.0,
+      "loss": 0.0143,
+      "step": 50
+    },
+    {
+      "epoch": 0.0550357732526142,
+      "eval_loss": 0.013763569295406342,
+      "eval_runtime": 12.2973,
+      "eval_samples_per_second": 31.145,
+      "eval_steps_per_second": 15.613,
+      "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": 1138274303213568.0,
+  "total_flos": 1470803874938880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null