Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a07086b2bd52deaa5c04f90b79b6d4693f3e2f3c3f5d095af9459b6d5a1d4d
+oid sha256:b6bf061e66e89c78dc8dddfe9757b215a0ca48cdf2bd385a9fcc3fbf7002d5d4
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b043b1bd3990e35dd4e8aec12dc4ef25738895e5afad11991408fd39ff50001e
+oid sha256:adc6d178c355ccbca03670c6dcd972abeacbd11059cae869e6cf37079edfc75e
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4403875ec607cf3108caac6354185aadd4588ae4b29cc7dad762431733537e30
+oid sha256:89ffcad5a84b06fde95717df10413749838a6b711ecc83f3ebee00a93d200145
 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": 0.0028176136979373625,
+  "epoch": 0.003612325253765849,
   "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": 11.9344,
       "step": 35
+    },
+    {
+      "epoch": 0.0028898602030126793,
+      "grad_norm": 0.11014612764120102,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9326,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028898602030126793,
+      "eval_loss": 11.933674812316895,
+      "eval_runtime": 162.6736,
+      "eval_samples_per_second": 35.832,
+      "eval_steps_per_second": 17.919,
+      "step": 40
+    },
+    {
+      "epoch": 0.003251092728389264,
+      "grad_norm": 0.08841203153133392,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9347,
+      "step": 45
+    },
+    {
+      "epoch": 0.003612325253765849,
+      "grad_norm": 0.11199869960546494,
+      "learning_rate": 0.0,
+      "loss": 11.9338,
+      "step": 50
+    },
+    {
+      "epoch": 0.003612325253765849,
+      "eval_loss": 11.933558464050293,
+      "eval_runtime": 163.0871,
+      "eval_samples_per_second": 35.742,
+      "eval_steps_per_second": 17.874,
+      "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": 8166424707072.0,
+  "total_flos": 10450520506368.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null