Training in progress, epoch 4, checkpoint

checkpoint-848/README.md

@@ -0,0 +1,9 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+
+- PEFT 0.5.0

checkpoint-848/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "camembert/camembert-large",
+  "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": 64,
+  "revision": null,
+  "target_modules": [
+    "query",
+    "key",
+    "value",
+    "dense"
+  ],
+  "task_type": "TOKEN_CLS"
+}

checkpoint-848/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d614dca6268594c86196e110b317396f2a0ad74a0fec7a01731324b34efca08
+size 117304221

checkpoint-848/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3131bdad7b92f5b960454412c32bec8e34bb3ea8fd2d8270635ce0ac105417f
+size 234652550

checkpoint-848/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d07361c03fa2a06405e4cc8a520c264d950bd1841409699cbc9c74ae871a1e
+size 14575

checkpoint-848/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ebf5afaa4fe964310eb3e13f18aa5d6d841ea6c96b5e2cb8ec0fcfa518d44a7
+size 627

checkpoint-848/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
+size 808767

checkpoint-848/special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

checkpoint-848/tokenizer_config.json

@@ -0,0 +1,24 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-848/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 848,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.950235849056605e-06,
+      "loss": 6.539,
+      "step": 212
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 6.494007587432861,
+      "eval_runtime": 2.5292,
+      "eval_samples_per_second": 267.281,
+      "eval_steps_per_second": 33.608,
+      "step": 212
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.900235849056603e-06,
+      "loss": 6.4697,
+      "step": 424
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.410468101501465,
+      "eval_runtime": 2.6306,
+      "eval_samples_per_second": 256.98,
+      "eval_steps_per_second": 32.313,
+      "step": 424
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.850235849056604e-06,
+      "loss": 6.3924,
+      "step": 636
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 6.319283962249756,
+      "eval_runtime": 2.6112,
+      "eval_samples_per_second": 258.881,
+      "eval_steps_per_second": 32.552,
+      "step": 636
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.800235849056604e-06,
+      "loss": 6.3093,
+      "step": 848
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 6.226834297180176,
+      "eval_runtime": 2.5547,
+      "eval_samples_per_second": 264.612,
+      "eval_steps_per_second": 33.272,
+      "step": 848
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42400,
+  "num_train_epochs": 200,
+  "save_steps": 500,
+  "total_flos": 1137839826710832.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-848/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932083cda874171956e29a9559decb3e85350d37f61015836b2c832b21575f2e
+size 4155