Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ff9c79f21e46e34c5f9fda9c1988c3aee9549bb6c9a8c6e4cd902aeed70245
+oid sha256:45b22c43a12860cbaaaf6c0f49a3b256200fed699242c102fe5e646931a6c7ac
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:285e631b04193c0ed63fd5ae42d1c92a78c1f7bc2492813cb38622e61199a109
+oid sha256:c3af9e20f49e7b72db66026d8b4b1ad86e80a51974aa793e16ef826415f1e5f0
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e561009e2ff39b4c9e252526ed009d5bad3c1086f161f5444dce1d8a1097b44c
+oid sha256:498daf035f25dc2316712fb33f68913f82de17ff2e939ecaf09af433b7f94f55
 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": 0.00069119217357785,
+  "epoch": 0.0008861438122792948,
   "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": 0.6266,
       "step": 35
+    },
+    {
+      "epoch": 0.0007089150498234358,
+      "grad_norm": 0.6566690802574158,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5257,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007089150498234358,
+      "eval_loss": 0.5642721056938171,
+      "eval_runtime": 2008.0741,
+      "eval_samples_per_second": 11.831,
+      "eval_steps_per_second": 5.916,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007975294310513653,
+      "grad_norm": 0.8434397578239441,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.586,
+      "step": 45
+    },
+    {
+      "epoch": 0.0008861438122792948,
+      "grad_norm": 1.120571255683899,
+      "learning_rate": 0.0,
+      "loss": 0.5317,
+      "step": 50
+    },
+    {
+      "epoch": 0.0008861438122792948,
+      "eval_loss": 0.5591886043548584,
+      "eval_runtime": 2006.7277,
+      "eval_samples_per_second": 11.839,
+      "eval_steps_per_second": 5.92,
+      "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": 6920856278138880.0,
+  "total_flos": 8980634932346880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null