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:fc4e93a380252e0e09cd06911f45857f80a114e8097eb8ba8fe298e9bea5a976
+oid sha256:187b4ada49867ca449f76c3201efad24818b7eab5cba18863e2c572d28f700ea
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b09e0a517be3f2ab1a20ab17bbf4862d038fd933ca3721c17500cdc65f6cf4d
+oid sha256:764a70f15f023bf76803c3ae2da501052e66217f332cf599f75a430d56f6d78b
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d47816a1b73ecd2c9a80831c828ddc87522a100a6bc1d431d3f6e1a9e1a2e444
+oid sha256:23e1d883c2c38af0fa0defbf64ff1ab38d25cd454411105215f59bcc6f2d008d
 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": 0.0007389302563519582,
+  "epoch": 0.0009473464825025104,
   "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": 0.0138,
       "step": 35
+    },
+    {
+      "epoch": 0.0007578771860020084,
+      "grad_norm": 0.12831038236618042,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0191,
+      "step": 40
+    },
+    {
+      "epoch": 0.0007578771860020084,
+      "eval_loss": 0.013603359460830688,
+      "eval_runtime": 1583.8231,
+      "eval_samples_per_second": 14.031,
+      "eval_steps_per_second": 7.016,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008526118342522594,
+      "grad_norm": 0.21416833996772766,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0125,
+      "step": 45
+    },
+    {
+      "epoch": 0.0009473464825025104,
+      "grad_norm": 0.0766138806939125,
+      "learning_rate": 0.0,
+      "loss": 0.0102,
+      "step": 50
+    },
+    {
+      "epoch": 0.0009473464825025104,
+      "eval_loss": 0.012373189441859722,
+      "eval_runtime": 1581.8505,
+      "eval_samples_per_second": 14.049,
+      "eval_steps_per_second": 7.025,
+      "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": 3363154549014528.0,
+  "total_flos": 4275832177557504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null