Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77da02d4e2a0eb80068bf6f67a1dcde4360a9ad8867b5362309a9610c75594bd
+oid sha256:716fdd743aa4f57100081e9af84aa24b91d76791a19b5888f60f930b0b066e54
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c53c397419c932c0b7174813fc81d37647d40f7f16abd0056e340f42a0dbe2
+oid sha256:be5e05db0617036104ce51760726e995101bfe47365a617198033d1ca0bd9dd2
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e651d14e7ee52a338fd24cd91e6b6490d38a4418546e878a83bea1f77d0d566
+oid sha256:7bc62039e23d827e5793fcd3c6e8c411b81ac50eccbcd443fbf45ad08d2dcf56
 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": 0.0009012444105514923,
+  "epoch": 0.0011554415519890926,
   "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": 2.8928,
       "step": 35
+    },
+    {
+      "epoch": 0.0009243532415912742,
+      "grad_norm": 0.36021822690963745,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6814,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009243532415912742,
+      "eval_loss": 2.7485904693603516,
+      "eval_runtime": 341.8594,
+      "eval_samples_per_second": 53.3,
+      "eval_steps_per_second": 26.651,
+      "step": 40
+    },
+    {
+      "epoch": 0.0010398973967901833,
+      "grad_norm": 0.2863467335700989,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.7984,
+      "step": 45
+    },
+    {
+      "epoch": 0.0011554415519890926,
+      "grad_norm": 0.2972218096256256,
+      "learning_rate": 0.0,
+      "loss": 2.6367,
+      "step": 50
+    },
+    {
+      "epoch": 0.0011554415519890926,
+      "eval_loss": 2.748222589492798,
+      "eval_runtime": 341.7227,
+      "eval_samples_per_second": 53.321,
+      "eval_steps_per_second": 26.662,
+      "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": 205755902853120.0,
+  "total_flos": 265768041185280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null