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:d7345c7582c88f62cc9cffebc470693ac89d5c237d4a0ed77d2126983ba9ff1e
+oid sha256:726996319bec7e53b1964e3ece8993652b031a9194ddb251a6ac58e8101d6c72
 size 114106856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdeed46d0193a2e3e0040a82ca59c80c67f01196ddfe5bdbea98742711ec5444
+oid sha256:1429a3b2fcde1d57878a2089f16f861c2aa6da375364d2b4617f14b6edb8fbbf
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2556a93e19ae846c23294d8d1538c98306480c21d3cb7a74daeea73db340a640
+oid sha256:666eb058ba2fef45ad8e5a43df5734ee939f73967fffe4f4679099694b63c6af
 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": 0.002374356944994064,
+  "epoch": 0.0030440473653770054,
   "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": 0.3941,
       "step": 35
+    },
+    {
+      "epoch": 0.0024352378923016044,
+      "grad_norm": 3.092489719390869,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2197,
+      "step": 40
+    },
+    {
+      "epoch": 0.0024352378923016044,
+      "eval_loss": 0.09255023300647736,
+      "eval_runtime": 652.4356,
+      "eval_samples_per_second": 10.6,
+      "eval_steps_per_second": 5.3,
+      "step": 40
+    },
+    {
+      "epoch": 0.002739642628839305,
+      "grad_norm": 1.480410099029541,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2702,
+      "step": 45
+    },
+    {
+      "epoch": 0.0030440473653770054,
+      "grad_norm": 12.40324592590332,
+      "learning_rate": 0.0,
+      "loss": 0.3534,
+      "step": 50
+    },
+    {
+      "epoch": 0.0030440473653770054,
+      "eval_loss": 0.08161197602748871,
+      "eval_runtime": 650.1445,
+      "eval_samples_per_second": 10.638,
+      "eval_steps_per_second": 5.319,
+      "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": 1.112316825305088e+16,
+  "total_flos": 1.4260472119296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null