Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ybelkada/flan-t5-xl-sharded-bf16",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v",
+    "q"
+  ],
+  "task_type": "SEQ_2_SEQ_LM"
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39175635a5b25e7b27b99521c9d172f131f109f6a4cd7b6fa699891813ae7b86
+size 37789864

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a720f2411fa54b4aadcfebec190ac32f8034d3c730280698dd4fe693c265a94b
+size 1256

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3206cfea353705871f16d46e55ccf93893b489d46b83fd7ba2c4d45d71b93a7
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbbce1a9a0a14aed15a48869dcc67eb483872b083bc9497eb19d0ae31a00297
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,32 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 328,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 10.608247422680412,
+      "eval_loss": 0.6409556865692139,
+      "eval_rouge1": 34.177,
+      "eval_rouge2": 25.6788,
+      "eval_rougeL": 30.5719,
+      "eval_rougeLsum": 30.9342,
+      "eval_runtime": 147.7579,
+      "eval_samples_per_second": 1.969,
+      "eval_steps_per_second": 0.25,
+      "step": 328
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3936,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "total_flos": 2458142180573184.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:816b4f782df7c74affb1e8b0c9582de2ff643eab772bb2aebc376257308f9bc0
+size 4728