Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675a09efa5a487718c6251c24c902159f8b28c5385c39fe87ca76b26ae288869
+oid sha256:0bbc1bdb0ad133afc42f49514ad8b7c12ae01617cd5b64345f0ea871a160f663
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410f6ab443a1887eadb3512a1da1f4a0ebfe1d674ec55b6993ffa888b5785b8d
+oid sha256:9ab9788b1e3587a485f07a964b31bee0abdd33a9b5d5fc458a8cc797e61db3d5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b2b655181cbd20071e25a8c2ca5953708370f3dc36111fe4dce52cd2f9b572
+oid sha256:b7042bdbd5d7c9a3eb673dc175e638e7b8ab24fef9447fe35d89ab1bc819bafe
 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": 0.08249603384452671,
+  "epoch": 0.10576414595452142,
   "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": 0.7223,
       "step": 35
+    },
+    {
+      "epoch": 0.08461131676361713,
+      "grad_norm": 1.2346258163452148,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5583,
+      "step": 40
+    },
+    {
+      "epoch": 0.08461131676361713,
+      "eval_loss": 0.21320515871047974,
+      "eval_runtime": 17.6578,
+      "eval_samples_per_second": 11.27,
+      "eval_steps_per_second": 5.663,
+      "step": 40
+    },
+    {
+      "epoch": 0.09518773135906927,
+      "grad_norm": 4.054224967956543,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.612,
+      "step": 45
+    },
+    {
+      "epoch": 0.10576414595452142,
+      "grad_norm": 1.2979183197021484,
+      "learning_rate": 0.0,
+      "loss": 0.6284,
+      "step": 50
+    },
+    {
+      "epoch": 0.10576414595452142,
+      "eval_loss": 0.2118646502494812,
+      "eval_runtime": 17.8839,
+      "eval_samples_per_second": 11.127,
+      "eval_steps_per_second": 5.592,
+      "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": 7189115808251904.0,
+  "total_flos": 9161739048321024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null