Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694d3b89e4c309172448addf3540f420802291b943fa3af99974950f2f010e45
+oid sha256:4d74e5cfa3824a9b5dac6b68b1b7f2e8a610976a6ac0b5f2f74ecc96d9cdf7a7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b58244a4bbba332b9d83f9c17cd4b9bd0d988e807759c7eb63965796cf1c704c
+oid sha256:c69f6e7e5a8a336ca3341b29c3fac65325a35ff29208102c1dc7fca62dbf470f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c1a9efc636b7b869b56b9a3c249a5137faaba5ff8c17f65984f4c6ae31ad9e
+oid sha256:89b38edf16e00970afb593efd87e2a583d3afe78398f0ae48ffeddd0350e5bc3
 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": 0.0005856691269775718,
+  "epoch": 0.0007508578550994512,
   "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": 1.488,
       "step": 35
+    },
+    {
+      "epoch": 0.0006006862840795609,
+      "grad_norm": 0.8817258477210999,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8346,
+      "step": 40
+    },
+    {
+      "epoch": 0.0006006862840795609,
+      "eval_loss": 1.9873542785644531,
+      "eval_runtime": 2549.9044,
+      "eval_samples_per_second": 10.996,
+      "eval_steps_per_second": 5.498,
+      "step": 40
+    },
+    {
+      "epoch": 0.000675772069589506,
+      "grad_norm": 0.8855513334274292,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4613,
+      "step": 45
+    },
+    {
+      "epoch": 0.0007508578550994512,
+      "grad_norm": 1.5922638177871704,
+      "learning_rate": 0.0,
+      "loss": 1.768,
+      "step": 50
+    },
+    {
+      "epoch": 0.0007508578550994512,
+      "eval_loss": 1.984639286994934,
+      "eval_runtime": 2555.1253,
+      "eval_samples_per_second": 10.974,
+      "eval_steps_per_second": 5.487,
+      "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": 7814408948416512.0,
+  "total_flos": 9895168727580672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null