Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c908b5c2a6784e4dd5d8e347637c8d6454025c634ff21ab67d91f423b285a6d
+oid sha256:7541a3fb0eb03bca39eeef356bd5b4d948412f134bd8bf7f7533508c9af8effe
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83747a3f889e04816fd2a0fa373b0defde4b57a8ca51f91973238cad64f97042
+oid sha256:4ba1d3fcf6582c884a39333c7500391dc6fde291db1f3e0f5507ff294a18e8ab
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c92eaf57053cbecdaa0579160167ea852314d5e01fbc4749b533abb666c0771
+oid sha256:a4a906bb698465209c126b422af04612476e6201f2ba8b1d53312d08d82be13b
 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": 0.036329762459245456,
+  "epoch": 0.04657661853749418,
   "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": 1.9613,
       "step": 35
+    },
+    {
+      "epoch": 0.037261294829995344,
+      "grad_norm": 2.235062599182129,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.933,
+      "step": 40
+    },
+    {
+      "epoch": 0.037261294829995344,
+      "eval_loss": 2.0007143020629883,
+      "eval_runtime": 55.7249,
+      "eval_samples_per_second": 8.129,
+      "eval_steps_per_second": 4.074,
+      "step": 40
+    },
+    {
+      "epoch": 0.04191895668374476,
+      "grad_norm": 1.7607734203338623,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.893,
+      "step": 45
+    },
+    {
+      "epoch": 0.04657661853749418,
+      "grad_norm": 2.078504800796509,
+      "learning_rate": 0.0,
+      "loss": 1.7617,
+      "step": 50
+    },
+    {
+      "epoch": 0.04657661853749418,
+      "eval_loss": 1.9849607944488525,
+      "eval_runtime": 55.6865,
+      "eval_samples_per_second": 8.135,
+      "eval_steps_per_second": 4.076,
+      "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": 7213300567769088.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null