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:d77a12570603948f1640a382e9d11c104960fae7b18085d6b3406f9753d290c4
+oid sha256:f7a182ef327f1ed8fa94421a212d1a2e8d5a2a894fe133d44c8dbe7276fec462
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d44ac5d1976ed5698788376d5ce1a394f8bda3f6ae1c0b530845747510d51f
+oid sha256:151232e9c736ccb6cf2e387294c10babdeca8d337ecdb1a190365f652848db49
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69760d704f2e1f2ae55fb0e41b4294d3fa392d7fec1a79bfd80e4b1c835abbe
+oid sha256:2007300033ffe59536453e93518be5034813ba514af7c276320bfa27ef7efeb0
 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": 0.001180307031149513,
+  "epoch": 0.0015132141424993757,
   "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": 0.6598,
       "step": 35
+    },
+    {
+      "epoch": 0.0012105713139995006,
+      "grad_norm": 4.827195167541504,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5349,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012105713139995006,
+      "eval_loss": 0.7397270202636719,
+      "eval_runtime": 939.4323,
+      "eval_samples_per_second": 14.81,
+      "eval_steps_per_second": 7.406,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013618927282494381,
+      "grad_norm": 4.576770782470703,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7968,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015132141424993757,
+      "grad_norm": 5.5793232917785645,
+      "learning_rate": 0.0,
+      "loss": 0.8362,
+      "step": 50
+    },
+    {
+      "epoch": 0.0015132141424993757,
+      "eval_loss": 0.7375583052635193,
+      "eval_runtime": 939.1711,
+      "eval_samples_per_second": 14.814,
+      "eval_steps_per_second": 7.408,
+      "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