Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ccd2c061e607c88d11dd29d3322c67cd59b61128ea341759f662d6a7c14fa57
+oid sha256:805d66892e257016d144ab0c9cd7419d71765465250d8a29c68c007c13969d93
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82945f89b0fa24312458e78fa4d38fd529fb00ad693e7a2b62a7457f36bc4f8d
+oid sha256:64d86601a00080a735aca1b2b54600e6655cef9b1f712a25bb9ce1eed7ec0454
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78bed406bff23e2d8073b677564ac4a9be2d258ee4ae71d16e43dac5fcfaa3ff
+oid sha256:eabec05acb43472d9286b9f2c0adc12c8e4a4583616dd748382e0b2a571efacb
 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": 0.006220095693779904,
+  "epoch": 0.007974481658692184,
   "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": 1.0603,
       "step": 35
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 0.5486422777175903,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0651,
+      "step": 40
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "eval_loss": 1.0430271625518799,
+      "eval_runtime": 232.8498,
+      "eval_samples_per_second": 11.338,
+      "eval_steps_per_second": 5.669,
+      "step": 40
+    },
+    {
+      "epoch": 0.007177033492822967,
+      "grad_norm": 0.3932763338088989,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0669,
+      "step": 45
+    },
+    {
+      "epoch": 0.007974481658692184,
+      "grad_norm": 0.3477610945701599,
+      "learning_rate": 0.0,
+      "loss": 0.9524,
+      "step": 50
+    },
+    {
+      "epoch": 0.007974481658692184,
+      "eval_loss": 1.0419983863830566,
+      "eval_runtime": 232.7443,
+      "eval_samples_per_second": 11.343,
+      "eval_steps_per_second": 5.671,
+      "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": 7044270812823552.0,
+  "total_flos": 9039468904316928.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null