Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b7fadf0d5568593a13ac920086541c720ec2b126f47749c744a779bbd3a6aeb
+oid sha256:3cfafb11524d0cad476ea68028b3a9212b0ba013e0ef4634168ccc7368ee1797
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95a7c1852460800add3b726c90c8c8ea4ba20b8a4e7b5a9e985af37859ebece
+oid sha256:7f19650f30f38352478ace1787b60c74fc185d1076b2a5a5a0761dcc2e977e54
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da57a3a869ac100e03e854428cb96b9fe176c6ed5065d0878032c78bdd0f415e
+oid sha256:0f70044af2bf806d36eee202f06cd6fe1ee465e8a1d9f7ce321d93c2a261931e
 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": 0.05418548106981591,
+  "epoch": 0.06946856547412296,
   "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": 0.7125,
       "step": 35
+    },
+    {
+      "epoch": 0.055574852379298365,
+      "grad_norm": 1.2340679168701172,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.729,
+      "step": 40
+    },
+    {
+      "epoch": 0.055574852379298365,
+      "eval_loss": 0.6776606440544128,
+      "eval_runtime": 11.7869,
+      "eval_samples_per_second": 25.706,
+      "eval_steps_per_second": 12.896,
+      "step": 40
+    },
+    {
+      "epoch": 0.06252170892671066,
+      "grad_norm": 1.6182198524475098,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6616,
+      "step": 45
+    },
+    {
+      "epoch": 0.06946856547412296,
+      "grad_norm": 0.9537201523780823,
+      "learning_rate": 0.0,
+      "loss": 0.6614,
+      "step": 50
+    },
+    {
+      "epoch": 0.06946856547412296,
+      "eval_loss": 0.6699821949005127,
+      "eval_runtime": 11.548,
+      "eval_samples_per_second": 26.238,
+      "eval_steps_per_second": 13.162,
+      "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": 3198189793443840.0,
+  "total_flos": 4100243324928000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null