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:fcb83edb4db37ae8fcf1897a79583502d24a84fb9170dd01a3da0dcc0a0eaf5e
+oid sha256:1f648cc1bddf971904295b4f59d1691fccc8bc6a5cef4a56656b5e5a963c864b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ab52ec8eb1e1109ab9a9615408a7c91e3104306e6926209e3332f6b7f27d3d0
+oid sha256:96cd187f588d3014e476fa529656b6c261b7cbd510b700c399589cc669e95155
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4983d71e319f9e21c9711f39e1b30bc6171dbcb39df362b58f72f84be87098fd
+oid sha256:05b699e8b938ae6281aae7f7604df0c93b97befab973ba12f8b50994b199a116
 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": 0.0010685882989581264,
+  "epoch": 0.0013699849986642647,
   "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": 0.6821,
       "step": 35
+    },
+    {
+      "epoch": 0.0010959879989314116,
+      "grad_norm": 1.1443864107131958,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5364,
+      "step": 40
+    },
+    {
+      "epoch": 0.0010959879989314116,
+      "eval_loss": 0.531443178653717,
+      "eval_runtime": 1040.094,
+      "eval_samples_per_second": 14.776,
+      "eval_steps_per_second": 7.388,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012329864987978383,
+      "grad_norm": 1.2471452951431274,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4965,
+      "step": 45
+    },
+    {
+      "epoch": 0.0013699849986642647,
+      "grad_norm": 0.9611670970916748,
+      "learning_rate": 0.0,
+      "loss": 0.4534,
+      "step": 50
+    },
+    {
+      "epoch": 0.0013699849986642647,
+      "eval_loss": 0.5210013389587402,
+      "eval_runtime": 1041.6703,
+      "eval_samples_per_second": 14.753,
+      "eval_steps_per_second": 7.377,
+      "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": 7352017886380032.0,
+  "total_flos": 9432777665544192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null