Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fac2a188ca757124ed37df4c4e3cd760af896f06cb1852013bed461e07edd15
+oid sha256:eb8f9c20ff848f97c9be76e903f682cab9928a9e7a4234368fffbc3ae82ae492
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d7315c5918a3d91c3ff30c4f7cbbc0252e41f75551ad8b77f74d0ebc7a4e14
+oid sha256:d6b87fbb9d48467f85b9ed2b65af9f2b02a235337a09f6a5324590cf757d7513
 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": 1.2247,
       "step": 80
+    },
+    {
+      "epoch": 0.03961122317990097,
+      "grad_norm": 0.32489892840385437,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.9108,
+      "step": 81
+    },
+    {
+      "epoch": 0.040100250626566414,
+      "grad_norm": 0.3395017981529236,
+      "learning_rate": 0.00015727351400805052,
+      "loss": 0.9968,
+      "step": 82
+    },
+    {
+      "epoch": 0.04058927807323186,
+      "grad_norm": 0.34815898537635803,
+      "learning_rate": 0.00015574894393428855,
+      "loss": 0.967,
+      "step": 83
+    },
+    {
+      "epoch": 0.0410783055198973,
+      "grad_norm": 0.4931004047393799,
+      "learning_rate": 0.00015420533564724495,
+      "loss": 1.0232,
+      "step": 84
+    },
+    {
+      "epoch": 0.041567332966562745,
+      "grad_norm": 0.45658788084983826,
+      "learning_rate": 0.0001526432162877356,
+      "loss": 1.0845,
+      "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