Training in progress, step 110, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4a9506f73921c53994cf5aa43954f949a4111e7aebd908099675167c3e7aee
+oid sha256:797691a5c1bede0a3013242e12ad082cf5b59954a8a0fc0dd7a75224b4282d66
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bde8169b298ed164c0b878c30c6b39f1068dd9204b9f052724c216b38abd4c6
+oid sha256:1c6da235d2be338d88881dc48554c3fe142c62bdbac18c080cd1bbe05a538c5e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d228656fc4662fbb158acab12ab048938d5ec4032384bd70b245c74cf2162ee1
+oid sha256:3a4992a0a541377e74f550ef72fa9af6f8fee0ce175cbdc61ec06b94024e86a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c855c846898181ed358c1ef65b19ad1435172d9025fde7f25f4580bfc48faa
+oid sha256:802e09b6cc63e64e726d0b68ba37b81d6a6fcf54cdf00e4821b3e38426a8a5c4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.051347881899871634,
+  "epoch": 0.05379301913319885,
   "eval_steps": 34,
-  "global_step": 105,
+  "global_step": 110,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -774,6 +774,41 @@
       "learning_rate": 0.00011837495178165706,
       "loss": 0.7804,
       "step": 105
+    },
+    {
+      "epoch": 0.05183690934653708,
+      "grad_norm": 1.6085052490234375,
+      "learning_rate": 0.000116555387618413,
+      "loss": 1.093,
+      "step": 106
+    },
+    {
+      "epoch": 0.05232593679320252,
+      "grad_norm": 1.4606610536575317,
+      "learning_rate": 0.00011473016980546377,
+      "loss": 1.0967,
+      "step": 107
+    },
+    {
+      "epoch": 0.052814964239867965,
+      "grad_norm": 1.591978669166565,
+      "learning_rate": 0.00011289992165302035,
+      "loss": 1.1526,
+      "step": 108
+    },
+    {
+      "epoch": 0.05330399168653341,
+      "grad_norm": 1.4087272882461548,
+      "learning_rate": 0.00011106526818915008,
+      "loss": 1.1814,
+      "step": 109
+    },
+    {
+      "epoch": 0.05379301913319885,
+      "grad_norm": 1.3588765859603882,
+      "learning_rate": 0.00010922683594633021,
+      "loss": 1.11,
+      "step": 110
     }
   ],
   "logging_steps": 1,
@@ -793,7 +828,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.6609019053277184e+17,
+  "total_flos": 4.882849615105229e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null