Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0b256324c77b74ce7cf35a934a1dea4cf2f1c4e901640287d88f57a3f16226
+oid sha256:d6182a1bf66b3e9471386ce49f5b81916a920ee2586faf2b33d43c13d5947f5c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54788bd57376a0ecc9872c34fed24cc6327e9699d90ddaa7ba48b2e34adcbf9a
+oid sha256:d786bfb07515005a60cacddfa1a37bcf2424ba648fb856f7801dddeddf8e7fc7
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:501917edc59cb38fa8ba673663fd0069ec90987aba1d4647ea54c9fb6fe18e47
+oid sha256:1e2701e6433cbd351cde5d73f1b3cbd9cefb4bc8bfbd165ddcbca91b8495404c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61487aeef4449a4dec50f3ae9ec76bca52908878863009a40746a21c237f51ad
+oid sha256:78248a64468e8e03af894427063f3f9a858b670b67d13949fb12f06211d294f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.026896509566599426,
+  "epoch": 0.029341646799926645,
   "eval_steps": 34,
-  "global_step": 55,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -408,6 +408,41 @@
       "learning_rate": 0.00018951632913550626,
       "loss": 0.9054,
       "step": 55
+    },
+    {
+      "epoch": 0.02738553701326487,
+      "grad_norm": 0.3576945662498474,
+      "learning_rate": 0.0001886773685920062,
+      "loss": 1.0002,
+      "step": 56
+    },
+    {
+      "epoch": 0.027874564459930314,
+      "grad_norm": 0.2915222942829132,
+      "learning_rate": 0.0001878081248083698,
+      "loss": 0.9491,
+      "step": 57
+    },
+    {
+      "epoch": 0.028363591906595757,
+      "grad_norm": 0.296265572309494,
+      "learning_rate": 0.00018690889463055283,
+      "loss": 1.0483,
+      "step": 58
+    },
+    {
+      "epoch": 0.0288526193532612,
+      "grad_norm": 0.3489420413970947,
+      "learning_rate": 0.00018597998514483725,
+      "loss": 0.9064,
+      "step": 59
+    },
+    {
+      "epoch": 0.029341646799926645,
+      "grad_norm": 0.37772810459136963,
+      "learning_rate": 0.00018502171357296144,
+      "loss": 0.9779,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -427,7 +462,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4414248075526144e+17,
+  "total_flos": 2.6633725173301248e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null