Training in progress, step 105, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3aae5e22c885800d90b299eaaf44aee69e3a90e7d46275d0085e4ac6a673db3
+oid sha256:6f211ae62887dce0fa42817d05e0aabed7b171367db2fd132779e56a4899860e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:358866885ea048cd89ba52e27e6ed69c858994b3c209c6e2637fb566d18d918b
+oid sha256:82b28abe9afb6f0a471ca1628e1779cb9272b993bee79979db7696d79f8a646d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58fe55f37e15eaaf48a322b8fab1abce8bcd6c4961dc9be21f59761cc27ae094
+oid sha256:d228656fc4662fbb158acab12ab048938d5ec4032384bd70b245c74cf2162ee1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b8a5b9aaab52c529e8225a8efdb5ee4b1c103decfe1101828eac45305d759c
+oid sha256:e8c855c846898181ed358c1ef65b19ad1435172d9025fde7f25f4580bfc48faa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04890274466654441,
+  "epoch": 0.051347881899871634,
   "eval_steps": 34,
-  "global_step": 100,
+  "global_step": 105,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -731,6 +731,49 @@
       "learning_rate": 0.0001273662990072083,
       "loss": 1.011,
       "step": 100
+    },
+    {
+      "epoch": 0.04939177211320985,
+      "grad_norm": 0.3369726240634918,
+      "learning_rate": 0.00012558427775944357,
+      "loss": 0.9987,
+      "step": 101
+    },
+    {
+      "epoch": 0.049880799559875295,
+      "grad_norm": 0.33174750208854675,
+      "learning_rate": 0.00012379351950426187,
+      "loss": 0.9603,
+      "step": 102
+    },
+    {
+      "epoch": 0.049880799559875295,
+      "eval_loss": 0.9992830753326416,
+      "eval_runtime": 1359.1213,
+      "eval_samples_per_second": 1.9,
+      "eval_steps_per_second": 0.633,
+      "step": 102
+    },
+    {
+      "epoch": 0.05036982700654074,
+      "grad_norm": 0.4101943373680115,
+      "learning_rate": 0.00012199463578396688,
+      "loss": 0.931,
+      "step": 103
+    },
+    {
+      "epoch": 0.05085885445320618,
+      "grad_norm": 0.39311182498931885,
+      "learning_rate": 0.00012018824091570103,
+      "loss": 1.1224,
+      "step": 104
+    },
+    {
+      "epoch": 0.051347881899871634,
+      "grad_norm": 0.3011833429336548,
+      "learning_rate": 0.00011837495178165706,
+      "loss": 1.0653,
+      "step": 105
     }
   ],
   "logging_steps": 1,
@@ -750,7 +793,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.438954195550208e+17,
+  "total_flos": 4.6609019053277184e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null