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:e575516f38afcfc99392c6c96cf43e2da88e10bb6a86086027f603c5704f1fdc
+oid sha256:5ebc87bbab8164691873103edd6eb447a0898460c68609d39102c85cc0e36bf6
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7fafbad1fdf1b94c77a27336dec9584e09f8fa3ef0928eea9ad391535aa022
+oid sha256:ca790762270c996bc16d508f4d1e77382bbf74d4a5098056dc243b941962cbe5
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
+oid sha256:fdedc6314c9f75a198e58bac1038c3adc8fc2a5f73e82a6a71a371fdac27e199
 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": 0.0025356370788160525,
+  "epoch": 0.0032508167677128877,
   "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": 6.5863,
       "step": 35
+    },
+    {
+      "epoch": 0.00260065341417031,
+      "grad_norm": 2.789621591567993,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.3783,
+      "step": 40
+    },
+    {
+      "epoch": 0.00260065341417031,
+      "eval_loss": 6.456869125366211,
+      "eval_runtime": 86.6189,
+      "eval_samples_per_second": 74.776,
+      "eval_steps_per_second": 37.394,
+      "step": 40
+    },
+    {
+      "epoch": 0.002925735090941599,
+      "grad_norm": 3.052328109741211,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.1808,
+      "step": 45
+    },
+    {
+      "epoch": 0.0032508167677128877,
+      "grad_norm": 3.4268128871917725,
+      "learning_rate": 0.0,
+      "loss": 6.6516,
+      "step": 50
+    },
+    {
+      "epoch": 0.0032508167677128877,
+      "eval_loss": 6.452789783477783,
+      "eval_runtime": 86.0149,
+      "eval_samples_per_second": 75.301,
+      "eval_steps_per_second": 37.656,
+      "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": 5031618281472.0,
+  "total_flos": 6441126985728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null