Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a4115b9c8be12d47d473dda16e0f38890e54cf251362c88c4c98cec087d4308
+oid sha256:1f0b67b3f14032ad95d66fe91860e03a89847538fcaf262167369335b0965460
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6dedff1cecf76773f8e3c26adc19594e9f77d6866ac07a2ae1c96d6969c04e
+oid sha256:a19ab322560896220785403fcba888af80a0d4a4d0363389bc5f7a8d313b5e1b
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
+oid sha256:a080d3277fb6ccb5ed989cb90ca2c5dbb10923ca8748d5a82c16ca3dd1e9dbd3
 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": 0.0009079269002444419,
+  "epoch": 0.0011640088464672331,
   "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": 52.4185,
       "step": 35
+    },
+    {
+      "epoch": 0.0009312070771737865,
+      "grad_norm": 1.4340275526046753,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 102.6157,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009312070771737865,
+      "eval_loss": NaN,
+      "eval_runtime": 79.0865,
+      "eval_samples_per_second": 228.699,
+      "eval_steps_per_second": 114.356,
+      "step": 40
+    },
+    {
+      "epoch": 0.0010476079618205098,
+      "grad_norm": 2.0773160457611084,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 107.0737,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011640088464672331,
+      "grad_norm": 2.476154327392578,
+      "learning_rate": 0.0,
+      "loss": 61.5862,
+      "step": 50
+    },
+    {
+      "epoch": 0.0011640088464672331,
+      "eval_loss": NaN,
+      "eval_runtime": 78.8102,
+      "eval_samples_per_second": 229.501,
+      "eval_steps_per_second": 114.757,
+      "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": 30257971200.0,
+  "total_flos": 38662963200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null