Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f7f00c76fa335fcb409d713899c410dd4e99a3c31d84f2239cdadeb4d294a0
+oid sha256:6d489923d85ac7a8008491f5c2fbc7776da70ee7a758e5fb3d2545ec8499ccb1
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773a2e8cf022733eb421882caff264a3c9ba78db0ecfac728ee78421af86f7ac
+oid sha256:1a4007afc6cc95013d7aece448148009df5b7820839ba14886a7abe321f0848d
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2236a932f5fe9d9505f2039eabbf1dbc44f1c805989c3860d7c3726de7b75a7
+oid sha256:89cfca901e337dc814f6cc4f4a77f8983cb6b74b9a0982e953d582cba4f38568
 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": 0.013282247765006385,
+  "epoch": 0.017028522775649212,
   "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": 0.98,
       "step": 35
+    },
+    {
+      "epoch": 0.01362281822051937,
+      "grad_norm": 0.5246570110321045,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8977,
+      "step": 40
+    },
+    {
+      "epoch": 0.01362281822051937,
+      "eval_loss": 1.2319979667663574,
+      "eval_runtime": 100.1281,
+      "eval_samples_per_second": 12.354,
+      "eval_steps_per_second": 6.182,
+      "step": 40
+    },
+    {
+      "epoch": 0.01532567049808429,
+      "grad_norm": 0.6063374876976013,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9623,
+      "step": 45
+    },
+    {
+      "epoch": 0.017028522775649212,
+      "grad_norm": 0.4231788218021393,
+      "learning_rate": 0.0,
+      "loss": 0.8506,
+      "step": 50
+    },
+    {
+      "epoch": 0.017028522775649212,
+      "eval_loss": 1.2166956663131714,
+      "eval_runtime": 99.9676,
+      "eval_samples_per_second": 12.374,
+      "eval_steps_per_second": 6.192,
+      "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": 9433786236272640.0,
+  "total_flos": 1.202910734057472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null