Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:530235c1b14f102a1b80ff9f4829ebf5b6e0498dc3cced5e7fd427d74d898e84
+oid sha256:2c487ac378b416f578476c06b2f78d5fa0fdee9b1631935244f6c995be422156
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac9de7f3ce9ae397c87250b2b4a4515cb000a5ff096471f068aba0cf15125384
+oid sha256:d6b7111c179159fc7127d2a893f803c34acf6dc055f8f898f2b1fd273ac86d1f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ecfaea88d4cd9a6281e406a175e4c0d0cb520dcd7993696cea1e4d1fcf86814
+oid sha256:f418f8a06b79dc4b6b0a46d187cd9d6759a7d773a125a1edaf65ee3e53b4732a
 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": 0.10803324099722991,
+  "epoch": 0.13850415512465375,
   "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": 0.658,
       "step": 35
+    },
+    {
+      "epoch": 0.11080332409972299,
+      "grad_norm": 0.5392118096351624,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6982,
+      "step": 40
+    },
+    {
+      "epoch": 0.11080332409972299,
+      "eval_loss": 0.7300357222557068,
+      "eval_runtime": 11.8185,
+      "eval_samples_per_second": 12.946,
+      "eval_steps_per_second": 6.515,
+      "step": 40
+    },
+    {
+      "epoch": 0.12465373961218837,
+      "grad_norm": 0.6359060406684875,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7617,
+      "step": 45
+    },
+    {
+      "epoch": 0.13850415512465375,
+      "grad_norm": 0.504328727722168,
+      "learning_rate": 0.0,
+      "loss": 0.6836,
+      "step": 50
+    },
+    {
+      "epoch": 0.13850415512465375,
+      "eval_loss": 0.7285895347595215,
+      "eval_runtime": 11.7706,
+      "eval_samples_per_second": 12.998,
+      "eval_steps_per_second": 6.542,
+      "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": 8600473753878528.0,
+  "total_flos": 1.109738548887552e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null