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:d236718147972e52885d1ed418b5ec712af84dd8207eb4ec790d6d09d2237960
+oid sha256:ef599a8bdf051535480e08c570d34c9437f0c8e7a63e5bca59704d9f2678ff6a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9da540c6069a1dde069efd0f33414218fe251e996da2bcd219f487857d92a513
+oid sha256:4661339ea46f064628ea6bd671db336c7289ee10c658f2ef8f2f9b8a235b41fa
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66de9fc177bdcbf3172e9f4d8c7b78bbdd6693131941887d9822655df6687616
+oid sha256:e8229894919a0a9c2636a72a16fd8c07b701bf68839284ea80e4963f829b2390
 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": 0.0013010842368640534,
+  "epoch": 0.0016680567139282735,
   "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": 0.8172,
       "step": 35
+    },
+    {
+      "epoch": 0.0013344453711426189,
+      "grad_norm": 1.0777671337127686,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7301,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013344453711426189,
+      "eval_loss": 0.7576377391815186,
+      "eval_runtime": 1747.0451,
+      "eval_samples_per_second": 7.225,
+      "eval_steps_per_second": 3.612,
+      "step": 40
+    },
+    {
+      "epoch": 0.0015012510425354462,
+      "grad_norm": 1.1099690198898315,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7626,
+      "step": 45
+    },
+    {
+      "epoch": 0.0016680567139282735,
+      "grad_norm": 1.361476182937622,
+      "learning_rate": 0.0,
+      "loss": 0.7898,
+      "step": 50
+    },
+    {
+      "epoch": 0.0016680567139282735,
+      "eval_loss": 0.7537627816200256,
+      "eval_runtime": 1745.7828,
+      "eval_samples_per_second": 7.23,
+      "eval_steps_per_second": 3.615,
+      "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": 1.0958668170264576e+16,
+  "total_flos": 1.433412292313088e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null