Training in progress, step 4000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8397db461e41b61712c457016b351f7f6dc554101c570e4a6daff1bf4160f00
+oid sha256:10e34560d7ceb961c8ed1daafdbc8d29639fec0a982153daab41f97d4037611d
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3874c420fe9a2f73893b67a2dea07956637705f44be263169a4a4590aba7ffa
+oid sha256:ae19cfcaee886abb8174d3662413d49264385fe5c93861421f1cfa8344a7ffd8
 size 3497859804

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4df07c96cd5b34fe2c47040206f73bf07f974f4e6c2b7b7219d670c2d00c146
+oid sha256:cb1d32a5240cd2bec4435f56208363b0d59e8bf8c99164c7cbee490171e7de00
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529b103d77a0239f5cc9fdc12d2f27ed56abb5aedd679ea0594afff05c3a18f5
+oid sha256:c645775385b221b832715f20158171035bab79b5b82f53d47dfdb772e39b0bc8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9321004692243997,
+  "epoch": 2.2081148219707423,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -252,6 +252,41 @@
       "learning_rate": 7.701361106073043e-05,
       "loss": 0.247,
       "step": 3500
+    },
+    {
+      "epoch": 1.9873033397736681,
+      "grad_norm": 1.1327725648880005,
+      "learning_rate": 7.537188922633076e-05,
+      "loss": 0.2376,
+      "step": 3600
+    },
+    {
+      "epoch": 2.0425062103229368,
+      "grad_norm": 0.8765416741371155,
+      "learning_rate": 7.369246315753623e-05,
+      "loss": 0.1724,
+      "step": 3700
+    },
+    {
+      "epoch": 2.0977090808722054,
+      "grad_norm": 0.8936216831207275,
+      "learning_rate": 7.19778285878565e-05,
+      "loss": 0.1515,
+      "step": 3800
+    },
+    {
+      "epoch": 2.152911951421474,
+      "grad_norm": 0.7982431650161743,
+      "learning_rate": 7.023053357286366e-05,
+      "loss": 0.1542,
+      "step": 3900
+    },
+    {
+      "epoch": 2.2081148219707423,
+      "grad_norm": 0.7692477107048035,
+      "learning_rate": 6.845317470362014e-05,
+      "loss": 0.154,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -271,7 +306,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8555493591209738e+18,
+  "total_flos": 2.1211958631160873e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null