Training in progress, step 6600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6787e0eaa9a56e0fa6384e31cadb399d551788e841dc96c421a54c989efc069
+oid sha256:23ecbd17698411abba08f800223d4f97c20ce6694fc5497eae762462f06c3ee3
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93664eaaa2494807cb13b7289c551278a5569b899724bfce116b35cb065a15b1
+oid sha256:8e240a4ccbdf1ba5b7269029cb4c7fbd098170a36530fb8a7924ca7a51629862
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06ae7e7d534fe7c098495e70ee979302efce6ee6dcf9f99dc5c535716646d42a
+oid sha256:1fcac68827b9f46f3ac71f10fc39a641a04d0ffa77754feb125895a9297c3035
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61184dac90fcc9cbb0e85bbabd16a1b7709c95fe49eceb7bec3bd299bccf398e
+oid sha256:6a5a6b913ef84b8f56bbbc750706d31053f1c2d4afa8b1e983e030aad31a2507
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004759443591297655,
+  "epoch": 0.004908176203525707,
   "eval_steps": 2000,
-  "global_step": 6400,
+  "global_step": 6600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,13 @@
       "learning_rate": 1.999995543968414e-05,
       "loss": 1.6274,
       "step": 6400
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.9622883796691895,
+      "learning_rate": 1.9999952606205736e-05,
+      "loss": 1.6222,
+      "step": 6600
     }
   ],
   "logging_steps": 200,
@@ -238,7 +245,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 8.403014572720128e+16,
+  "total_flos": 8.670264252137472e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null