Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46399d41413b5080b552dda616ea35bd3488631be3e1854b9a806cd6105d011f
+oid sha256:af22da22dcb55495498fefcb5dc38bf2adcd79d63e0f4a0329b693212754dec9
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8a9a6596bab23b5a8e6a9b214eda26e35ea8151338789219052f17d217aa76
+oid sha256:f28f46a184d1ffaf9bd2ae5d038805c4df8196e1192359c8f5423d22118b958f
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc669a9ff7b73f5867475f77d3df999096e967d95b32a7949f42d2191cc58e1f
+oid sha256:27917d88cdf4e1cd610266e1bad5287f7c270415c57a7781c0adaab154ebaaf5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0019044596095857801,
+  "epoch": 0.002116066232873089,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 29.031,
       "eval_steps_per_second": 14.516,
       "step": 9
+    },
+    {
+      "epoch": 0.002116066232873089,
+      "grad_norm": 4.896476745605469,
+      "learning_rate": 0.0002,
+      "loss": 9.4719,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1332361122576384.0,
+  "total_flos": 1512409922924544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null