Model save

all_results.json

@@ -0,0 +1,8 @@
+{
+ "epoch": 4.0,
+ "total_flos": 9299872197181440.0,
+ "train_loss": 2.19787335395813,
+ "train_runtime": 9.6458,
+ "train_samples_per_second": 12.441,
+ "train_steps_per_second": 1.659
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a110e8eea8034693e2f9b34ef810e41d42ce5a7e707f54a013b839c3f1b5b767
+oid sha256:91a5a93286280abbc7080b1d52c268a5f4aa7d839be30fbfe11d56c82f4addbf
 size 343254736

runs/Mar21_23-39-14_X5C922065N/events.out.tfevents.1711060766.X5C922065N.86888.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdb8f14f571fce39e5deb3ae03537cb13c053c9abc37157cf823400535d3225a
+size 6018

train_results.json

@@ -0,0 +1,8 @@
+{
+ "epoch": 4.0,
+ "total_flos": 9299872197181440.0,
+ "train_loss": 2.19787335395813,
+ "train_runtime": 9.6458,
+ "train_samples_per_second": 12.441,
+ "train_steps_per_second": 1.659
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 4.0,
+ "eval_steps": 1000,
+ "global_step": 16,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 2.5,
+ "grad_norm": 2.5156421661376953,
+ "learning_rate": 1.8750000000000002e-05,
+ "loss": 2.3138,
+ "step": 10
+ },
+ {
+ "epoch": 4.0,
+ "step": 16,
+ "total_flos": 9299872197181440.0,
+ "train_loss": 2.19787335395813,
+ "train_runtime": 9.6458,
+ "train_samples_per_second": 12.441,
+ "train_steps_per_second": 1.659
+ }
+ ],
+ "logging_steps": 10,
+ "max_steps": 16,
+ "num_input_tokens_seen": 0,
+ "num_train_epochs": 4,
+ "save_steps": 1000,
+ "total_flos": 9299872197181440.0,
+ "train_batch_size": 8,
+ "trial_name": null,
+ "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f970bf7af869319589b3115f65a6aa2bea54f1eddd1a82511e828454f9d99fe
+oid sha256:b53471da88ac891f6cf1d8d672d15ebb919a7297ac9d87622e592033071fef61
 size 4920