Upload 16 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

trainer_log.jsonl

@@ -0,0 +1,5 @@
+{"current_steps": 10, "total_steps": 48, "loss": 8.6936, "lr": 4.894001499771015e-05, "epoch": 0.6349206349206349, "percentage": 20.83, "elapsed_time": "0:00:20", "remaining_time": "0:01:17"}
+{"current_steps": 20, "total_steps": 48, "loss": 0.4693, "lr": 3.8023508512198256e-05, "epoch": 1.253968253968254, "percentage": 41.67, "elapsed_time": "0:00:42", "remaining_time": "0:00:59"}
+{"current_steps": 30, "total_steps": 48, "loss": 0.1413, "lr": 2.0459078725514092e-05, "epoch": 1.8888888888888888, "percentage": 62.5, "elapsed_time": "0:01:03", "remaining_time": "0:00:37"}
+{"current_steps": 40, "total_steps": 48, "loss": 0.0773, "lr": 5.2125877892686496e-06, "epoch": 2.507936507936508, "percentage": 83.33, "elapsed_time": "0:01:36", "remaining_time": "0:00:19"}
+{"current_steps": 48, "total_steps": 48, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:01:52", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 48,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 25.672040939331055,
+      "learning_rate": 4.894001499771015e-05,
+      "loss": 8.6936,
+      "step": 10
+    },
+    {
+      "epoch": 1.253968253968254,
+      "grad_norm": 5.61480712890625,
+      "learning_rate": 3.8023508512198256e-05,
+      "loss": 0.4693,
+      "step": 20
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 3.9594666957855225,
+      "learning_rate": 2.0459078725514092e-05,
+      "loss": 0.1413,
+      "step": 30
+    },
+    {
+      "epoch": 2.507936507936508,
+      "grad_norm": 0.6755509376525879,
+      "learning_rate": 5.2125877892686496e-06,
+      "loss": 0.0773,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "step": 48,
+      "total_flos": 1.1974639068643328e+16,
+      "train_loss": 1.9668061497310798,
+      "train_runtime": 112.3578,
+      "train_samples_per_second": 53.401,
+      "train_steps_per_second": 0.427
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 48,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1974639068643328e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725e5aab64b5e9292abc54a2edca991520a936aee683c943d9113e8d8699ed4a
+size 6161