Training in progress, step 1040, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f83a14bad50ef4fa91e680835e699b0c0964a4a774e2df1471356c3eb34e2483
+oid sha256:fafd0f157d14e49e4739550f3f127d870e4c0caf60624531f00c5d7035d51299
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7179eeb1d5838aa0994421930ee7b5ee69dcf694fc54329d4f179111f91064
+oid sha256:68070370254082a9da3aeac4075c069ea60def96eef668a1fc6d9c0196fc0554
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:664088f4b02d6d61794dd3cc474ef676f9f1cadbd823aaac3a55e095bfff17cf
+oid sha256:98d3711de76e8c84da6b52967c082fa25514ac6013e7232a9fdcdac089584cc1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c65fe91d72914e2f842d7acfa2a9853868230249fce07bd2008aa85a142a90
+oid sha256:dde20670de2d0a6327803d0e03f03b8ccee00551dc9309464bb5c115b97010c1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0816,
+  "epoch": 0.0832,
   "eval_steps": 500,
-  "global_step": 1020,
+  "global_step": 1040,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -364,6 +364,13 @@
       "learning_rate": 2.996531923195246e-05,
       "loss": 3.7106,
       "step": 1020
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 37.24673843383789,
+      "learning_rate": 2.996193909122197e-05,
+      "loss": 3.7447,
+      "step": 1040
     }
   ],
   "logging_steps": 20,
@@ -371,7 +378,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2427112636022784.0,
+  "total_flos": 2473139331366912.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null