Training in progress, step 3800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f67821ac1225d4d6ddda4314d6a5229d5d7e025037b4629626781330dcd8ba7
+oid sha256:dad49df5b2df7646aa362b89959fb3a68f02e445d91649201aa7875d14451182
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c6cf5fc78cecc2d7df7b5890bb7f1585faa029834b2a8424b07945ae424657
+oid sha256:267a2036f4138e7cda6f843ad4f4096f8ff700ae0fe86cbe32da71d427faaf00
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9291966c403e7bde3e2744cb48c547f09f71e192a421d27ace1f464288c63654
+oid sha256:872e352590e3a4a2cb815be063d894442037481619a588e6b703cf8f8edc317a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5ef771961ae1ef92dd7080688347888d76bf3cdf936856cea7f523a48bc1bee
+oid sha256:3a02c00cee72ba53cc6916bd67dc0363d3b2574076a95ff3d48c5db212f6a902
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002677187020104931,
+  "epoch": 0.0028259196323329825,
   "eval_steps": 2000,
-  "global_step": 3600,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,13 @@
       "learning_rate": 1.9999985922889644e-05,
       "loss": 1.5725,
       "step": 3600
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.9052414894104004,
+      "learning_rate": 1.9999984311180655e-05,
+      "loss": 1.5804,
+      "step": 3800
     }
   ],
   "logging_steps": 200,
@@ -140,7 +147,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 4.69863606565847e+16,
+  "total_flos": 4.986484165808947e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null