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:e7c7c0bd6426d5a97049550cd96cd8cd8cc58da8c92a873360a5fefdd5961e24
+oid sha256:c334e7e9330f9abdc6e23babd32721e203952674fe583749d94ff5bb7b81bb3a
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575dbe7adca18cdf6dc933f69e4e95a5479a782fc062a7cf4448639290474adc
+oid sha256:c9c75069f9288c740b4336ac62bea31f20f2ba49037ac8a47e16fe036e859ade
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a55ac0c992411009853207820ca4f6897afa3f8dc742e986d6f2be555193f7
+oid sha256:1dd3509d75db320bd92d53f924abbdeab3ef848a57c7fd322c68ea874c41c4f7
 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": 0.033854166666666664,
+  "epoch": 0.043402777777777776,
   "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": 1.0924,
       "step": 35
+    },
+    {
+      "epoch": 0.034722222222222224,
+      "grad_norm": 2.26999831199646,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0614,
+      "step": 40
+    },
+    {
+      "epoch": 0.034722222222222224,
+      "eval_loss": 0.9549398422241211,
+      "eval_runtime": 16.2023,
+      "eval_samples_per_second": 29.934,
+      "eval_steps_per_second": 14.998,
+      "step": 40
+    },
+    {
+      "epoch": 0.0390625,
+      "grad_norm": 2.241302728652954,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9946,
+      "step": 45
+    },
+    {
+      "epoch": 0.043402777777777776,
+      "grad_norm": 2.1079211235046387,
+      "learning_rate": 0.0,
+      "loss": 0.9447,
+      "step": 50
+    },
+    {
+      "epoch": 0.043402777777777776,
+      "eval_loss": 0.9167178273200989,
+      "eval_runtime": 15.9527,
+      "eval_samples_per_second": 30.402,
+      "eval_steps_per_second": 15.233,
+      "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": 1233910298050560.0,
+  "total_flos": 1581936279552000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null