Training in progress, step 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79634597e850a2e3b6846f980bc6c2f927fe2c5ffd8440d3ce72d62f0d944c3d
+oid sha256:66ed8e33be3f30165ded875de0d3d8a94e75e3302ebc28c7960784f6abce0475
 size 433386912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7136f86380644bcaf803c434b35e022827a7bd58553f3a1102ac9d507efb5637
+oid sha256:2718ff8526278b7841fa6f6f93b7478030381c430ffb91ae1df75b12527d1395
 size 866895354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e558ca7120159000602cfc6a4540193b091c74c311b23428363b684a95e1f661
+oid sha256:797ae513ea2c3b4b8a096003d70d7015814d17c41ef73abc3424bd7235872747
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb48b29d34f57a219b094c388ccda1651e585a71cc7928e87baa7ff08a1983cf
+oid sha256:82c67f4c0c84490d9ab91ce25949988532c8a1049298729caa9fba405b74ea36
 size 1064

last-checkpoint/trainer_state.json

@@ -1,20 +1,20 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.5,
+  "epoch": 0.8333333333333334,
   "eval_steps": 500,
-  "global_step": 15,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [],
   "logging_steps": 500,
-  "max_steps": 40,
+  "max_steps": 30,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 20,
+  "num_train_epochs": 5,
   "save_steps": 5,
-  "total_flos": 147536007528.0,
-  "train_batch_size": 5,
+  "total_flos": 10795317624.0,
+  "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:519e9126e22323fab677b4c6b9879a0c66eb6be095a989c4a5abd7e2bbefbd64
+oid sha256:4bac87304580ebcd3ff7eccc9e1e2ae4269ef04b98d2fcecf5ba897031aa4f88
 size 4984