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:f820aad73575acef0239927148bc6853a0dac96310d278b645b1f753fc6bc443
+oid sha256:56de0ca7b5b41a32c1cd6172301ed10c7d538e99558ded3370023b83963c6caf
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471d2f63dc7e5da54371b5961651c18e09781c8f5af6f0f887a3bf988f99d2b1
+oid sha256:6690ae2dab47907a3bd66de33375332c7bfafacd6c3ff814cdbc88bac1432047
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3949030dcda35f66dc328beaae94fc7f8d90fb1cac1d3bce305cde4c8c769d13
+oid sha256:9da52b6a7c3714da24ca8e61ad06823be8cc6f827b5b6b50bf203c06396e612c
 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": 0.04275143875034256,
+  "epoch": 0.05480953685941354,
   "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": 0.2792,
       "step": 35
+    },
+    {
+      "epoch": 0.04384762948753083,
+      "grad_norm": 0.4467286169528961,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3702,
+      "step": 40
+    },
+    {
+      "epoch": 0.04384762948753083,
+      "eval_loss": 0.16739042103290558,
+      "eval_runtime": 34.89,
+      "eval_samples_per_second": 11.035,
+      "eval_steps_per_second": 5.532,
+      "step": 40
+    },
+    {
+      "epoch": 0.04932858317347218,
+      "grad_norm": 0.5335176587104797,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2862,
+      "step": 45
+    },
+    {
+      "epoch": 0.05480953685941354,
+      "grad_norm": 0.4365200698375702,
+      "learning_rate": 0.0,
+      "loss": 0.0772,
+      "step": 50
+    },
+    {
+      "epoch": 0.05480953685941354,
+      "eval_loss": 0.16572637856006622,
+      "eval_runtime": 34.9,
+      "eval_samples_per_second": 11.032,
+      "eval_steps_per_second": 5.53,
+      "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": 1.017260336480256e+16,
+  "total_flos": 1.294694973702144e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null