Training in progress, step 500

.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

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/mt5-small",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v",
+    "q"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6ac3e830ae50bf86c7cb924e5805992764c0d8a6e2da5f74c47af2c38935d9
+size 1027183888

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2161d79be15aa5b9ca5327f44791ed567cff8661f69863d29eefb5abc14716
+size 16033349

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": [
+    "<2te>",
+    "<2hi>"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_id": 2,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 500,
+  "best_metric": 7.9791436195373535,
+  "best_model_checkpoint": "/kaggle/working/checkpoints/checkpoint-500",
+  "epoch": 0.4477277815088426,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04477277815088426,
+      "grad_norm": 298.04815673828125,
+      "learning_rate": 2.4257425742574257e-05,
+      "loss": 112.46427734375,
+      "step": 50
+    },
+    {
+      "epoch": 0.08954555630176853,
+      "grad_norm": 515.502685546875,
+      "learning_rate": 4.9009900990099014e-05,
+      "loss": 108.94888671875,
+      "step": 100
+    },
+    {
+      "epoch": 0.1343183344526528,
+      "grad_norm": 224.24559020996094,
+      "learning_rate": 4.926153846153847e-05,
+      "loss": 102.64640625,
+      "step": 150
+    },
+    {
+      "epoch": 0.17909111260353705,
+      "grad_norm": 328.56585693359375,
+      "learning_rate": 4.849230769230769e-05,
+      "loss": 93.7025390625,
+      "step": 200
+    },
+    {
+      "epoch": 0.2238638907544213,
+      "grad_norm": 212.02337646484375,
+      "learning_rate": 4.772307692307693e-05,
+      "loss": 86.589169921875,
+      "step": 250
+    },
+    {
+      "epoch": 0.2686366689053056,
+      "grad_norm": 371.2373962402344,
+      "learning_rate": 4.695384615384615e-05,
+      "loss": 78.94826171875,
+      "step": 300
+    },
+    {
+      "epoch": 0.31340944705618984,
+      "grad_norm": 127.3225326538086,
+      "learning_rate": 4.618461538461539e-05,
+      "loss": 72.1776416015625,
+      "step": 350
+    },
+    {
+      "epoch": 0.3581822252070741,
+      "grad_norm": 112.87958526611328,
+      "learning_rate": 4.541538461538462e-05,
+      "loss": 66.216123046875,
+      "step": 400
+    },
+    {
+      "epoch": 0.40295500335795836,
+      "grad_norm": 73.62041473388672,
+      "learning_rate": 4.464615384615385e-05,
+      "loss": 60.0425634765625,
+      "step": 450
+    },
+    {
+      "epoch": 0.4477277815088426,
+      "grad_norm": 61.61714172363281,
+      "learning_rate": 4.3876923076923076e-05,
+      "loss": 54.319912109375,
+      "step": 500
+    },
+    {
+      "epoch": 0.4477277815088426,
+      "eval_loss": 7.9791436195373535,
+      "eval_runtime": 11.3347,
+      "eval_samples_per_second": 63.698,
+      "eval_steps_per_second": 8.028,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3351,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4246783131648000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19156ac353fa48da06b4c41a771842d317d52305f57a718e207b4557d7b05081
+size 5457