Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e02cdfc7b8fc4880b42b8ff60be321dacd0a8ff78df092d3ed9e52862423e16
+oid sha256:7037ea4e291eac2e48ee4ecd64404586724c771e0bf45eed7de66157f1a01e5d
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb7e9078af9812f92989f4557b21957498f3f10e74175d72f32a1b306258348
+oid sha256:d7fcc4171f8b7424f26a95c8b7da7fbb38ec64258e6575b016641189ed4b0bb6
 size 111412180

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f44f8535e242739088c844171d04d95514925895ac23749b1a2bf84bc76bccfa
+oid sha256:e71508bceee1b229b726e8b5d62504c8aa133c2dd299af3de84e48855dd39576
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d94e3c2c501d5df9361a581f9e3f0d0b765f815dc284faaddce0a0aff0524cd1
+oid sha256:c5acf097404dd7afd5c403595639fcdc6a40ab2ea8c63acaf311360ca1a0f103
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7c6b205e1552be0830a6d7bc56be5230d8f9d9a142f3205ff3e7dff8c8730a
+oid sha256:fd82e2c4dd46a0c4163e78a1bb05a9e321fb40a1c884136f2f4f92fe2449cbde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8775137111517367,
+  "epoch": 1.053016453382084,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,27 @@
       "eval_samples_per_second": 7.097,
       "eval_steps_per_second": 1.774,
       "step": 15
+    },
+    {
+      "epoch": 0.9360146252285192,
+      "grad_norm": 10.739554405212402,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.776,
+      "step": 16
+    },
+    {
+      "epoch": 0.9945155393053017,
+      "grad_norm": 9.82874870300293,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.9549,
+      "step": 17
+    },
+    {
+      "epoch": 1.053016453382084,
+      "grad_norm": 26.742786407470703,
+      "learning_rate": 0.0,
+      "loss": 8.1481,
+      "step": 18
     }
   ],
   "logging_steps": 1,
@@ -158,12 +179,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.0682396231663616e+17,
+  "total_flos": 4.881887547799634e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null