Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f5d7b7c33ee6f990b99d2369cecf44560f2299c45d0cc4e6243426213d7ca5e
+oid sha256:8621b618b301f865cadc91959441872f5434678c1ac6424423e50c3e9e10cf52
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786fe5cf7031fc54610c6ff1e3d066ffdeac9fedc533d1d2955573ddbe5c0477
+oid sha256:56c287583a4d39a4a8f3665ea1201526cd6abc65cda2be60f1f30c4992b325d2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c1ee15529a526a9fe4c19508572c414c6ef23f4c5c37a9bdfac25ac8b91945
+oid sha256:826e666b3f1881e003df1e799293232a6d3ede1a55e213829eb507201e9190b8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc75fc1c14b28d29d31fa9d4252536c919fc25a390fac3a1e8c09d6575b4029
+oid sha256:8d9707e13ab424365dde92daf30c033711d2caa0fada77309f65d41532581807
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.039122195733235526,
+  "epoch": 0.041567332966562745,
   "eval_steps": 34,
-  "global_step": 80,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -591,6 +591,41 @@
       "learning_rate": 0.00016026346363792567,
       "loss": 1.042,
       "step": 80
+    },
+    {
+      "epoch": 0.03961122317990097,
+      "grad_norm": 1.3361854553222656,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 1.1104,
+      "step": 81
+    },
+    {
+      "epoch": 0.040100250626566414,
+      "grad_norm": 1.0672283172607422,
+      "learning_rate": 0.00015727351400805052,
+      "loss": 0.7879,
+      "step": 82
+    },
+    {
+      "epoch": 0.04058927807323186,
+      "grad_norm": 1.6033365726470947,
+      "learning_rate": 0.00015574894393428855,
+      "loss": 1.0356,
+      "step": 83
+    },
+    {
+      "epoch": 0.0410783055198973,
+      "grad_norm": 1.579293131828308,
+      "learning_rate": 0.00015420533564724495,
+      "loss": 1.3671,
+      "step": 84
+    },
+    {
+      "epoch": 0.041567332966562745,
+      "grad_norm": 3.389050006866455,
+      "learning_rate": 0.0001526432162877356,
+      "loss": 1.0248,
+      "step": 85
     }
   ],
   "logging_steps": 1,
@@ -610,7 +645,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.5511633564401664e+17,
+  "total_flos": 3.773111066217677e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null