Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ce9e0bb76b82aed5076df1efe737525d7d1bd47930719c246a8e233f5cbcb20
+oid sha256:f500b1e1778d9ab430caa53991ef306d699101f892bea32e63fbee7f24551918
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d120c4e3741df739bd5703ee0541475293b73317f4743cca40740aabbf4f65c6
+oid sha256:4cc8c14aa0ecafb87acef4d97dc2dcc81629b289dea0fc10b66b45ae5ba32f66
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0afe795030fa7402c0c7d8bf543446a4e0c36611010ca4250fa1b7707b0fa1a3
+oid sha256:3fbbf0ce949c23dfc6caeea4bd21253f0ff1691efaf9433bb3ed819ada9e974e
 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": 0.01374086144631375,
+  "epoch": 0.017616489033735576,
   "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": 0.2083,
       "step": 35
+    },
+    {
+      "epoch": 0.01409319122698846,
+      "grad_norm": 17.68518829345703,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0759,
+      "step": 40
+    },
+    {
+      "epoch": 0.01409319122698846,
+      "eval_loss": 0.1258983165025711,
+      "eval_runtime": 359.288,
+      "eval_samples_per_second": 3.326,
+      "eval_steps_per_second": 1.664,
+      "step": 40
+    },
+    {
+      "epoch": 0.01585484013036202,
+      "grad_norm": 1.8895014524459839,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1442,
+      "step": 45
+    },
+    {
+      "epoch": 0.017616489033735576,
+      "grad_norm": 0.18879897892475128,
+      "learning_rate": 0.0,
+      "loss": 0.1418,
+      "step": 50
+    },
+    {
+      "epoch": 0.017616489033735576,
+      "eval_loss": 0.13739807903766632,
+      "eval_runtime": 420.9639,
+      "eval_samples_per_second": 2.839,
+      "eval_steps_per_second": 1.421,
+      "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": 7978806662922240.0,
+  "total_flos": 1.031989364785152e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null