Training in progress, epoch 1, checkpoint

checkpoint-4/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 4.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.5.0

checkpoint-4/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "flaubert/flaubert_large_cased",
+  "bias": "all",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": [
+    "classifier.bias",
+    "classifier.weight"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_lin",
+    "k_lin",
+    "v_lin",
+    "out_lin"
+  ],
+  "task_type": "TOKEN_CLS"
+}

checkpoint-4/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d01cdfa8b30ff745d5e612123a815e0dbf4ddb3e1700172d7314d8d02e5d09
+size 30440349

checkpoint-4/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7815b4c9010c60064ea3325b4eee9b32c34b150449f33c6c62e8951c223fbe3d
+size 60898982

checkpoint-4/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5336281f41cb1f2a85ef1320992a24517ea5d9b76a7aacbdce850019a0f51d6
+size 14575

checkpoint-4/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3094f0027b432eee076116a5efe082c1c77789c9c2288da023fc9e05266808
+size 627

checkpoint-4/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "</s>",
+  "mask_token": "<special1>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-4/tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<special0>",
+    "<special1>",
+    "<special2>",
+    "<special3>",
+    "<special4>",
+    "<special5>",
+    "<special6>",
+    "<special7>",
+    "<special8>",
+    "<special9>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "</s>",
+  "do_lower_case": false,
+  "id2lang": null,
+  "lang2id": null,
+  "mask_token": "<special1>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "FlaubertTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-4/trainer_state.json

@@ -0,0 +1,27 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": NaN,
+      "eval_runtime": 11.7568,
+      "eval_samples_per_second": 430.984,
+      "eval_steps_per_second": 13.524,
+      "step": 4
+    }
+  ],
+  "logging_steps": 2000,
+  "max_steps": 400,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 7161154002048.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238151b110e2e4dfc6ebf1dd217dc2b2ee63a49132a41b9b3baa63652e9edd25
+size 4219