Training in progress, epoch 13, checkpoint

checkpoint-2756/README.md

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

checkpoint-2756/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-2756/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a040af46465d9f9826dcaaf587c3e890f9ffd775ae91912e24aa92043804240
+size 117304221

checkpoint-2756/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25274894be7475a14c709487d7eab6f727d198b0285856877bdfcc8c86bd663
+size 234652550

checkpoint-2756/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60933fb688cde84167ff6620e14f6124ccb62aa173f5c56ee382f39ee3c718e
+size 14575

checkpoint-2756/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b50c69157118f984fd17a66b6634ca197ec0c5968d3df000ad14452e5dfc09
+size 627

checkpoint-2756/sentencepiece.bpe.model

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

checkpoint-2756/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-2756/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-2756/trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 13.0,
+  "eval_steps": 500,
+  "global_step": 2756,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.95e-05,
+      "loss": 6.3714,
+      "step": 212
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.850927352905273,
+      "eval_runtime": 3.8282,
+      "eval_samples_per_second": 176.584,
+      "eval_steps_per_second": 22.204,
+      "step": 212
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 5.5438,
+      "step": 424
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.862037658691406,
+      "eval_runtime": 3.7425,
+      "eval_samples_per_second": 180.626,
+      "eval_steps_per_second": 22.712,
+      "step": 424
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.850000000000001e-05,
+      "loss": 4.6993,
+      "step": 636
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.018372058868408,
+      "eval_runtime": 4.0424,
+      "eval_samples_per_second": 167.229,
+      "eval_steps_per_second": 21.027,
+      "step": 636
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.8e-05,
+      "loss": 3.967,
+      "step": 848
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.290557384490967,
+      "eval_runtime": 4.3933,
+      "eval_samples_per_second": 153.872,
+      "eval_steps_per_second": 19.348,
+      "step": 848
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 9.75e-05,
+      "loss": 3.305,
+      "step": 1060
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.6497254371643066,
+      "eval_runtime": 4.3562,
+      "eval_samples_per_second": 155.182,
+      "eval_steps_per_second": 19.513,
+      "step": 1060
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 9.7e-05,
+      "loss": 2.7185,
+      "step": 1272
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.1158342361450195,
+      "eval_runtime": 4.5634,
+      "eval_samples_per_second": 148.135,
+      "eval_steps_per_second": 18.626,
+      "step": 1272
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 9.65e-05,
+      "loss": 2.2181,
+      "step": 1484
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.6882902383804321,
+      "eval_runtime": 4.3232,
+      "eval_samples_per_second": 156.367,
+      "eval_steps_per_second": 19.662,
+      "step": 1484
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 9.6e-05,
+      "loss": 1.8106,
+      "step": 1696
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.3730388879776,
+      "eval_runtime": 4.3486,
+      "eval_samples_per_second": 155.451,
+      "eval_steps_per_second": 19.546,
+      "step": 1696
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 9.55e-05,
+      "loss": 1.497,
+      "step": 1908
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.142008900642395,
+      "eval_runtime": 4.2743,
+      "eval_samples_per_second": 158.154,
+      "eval_steps_per_second": 19.886,
+      "step": 1908
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 9.5e-05,
+      "loss": 1.2526,
+      "step": 2120
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.9753935933113098,
+      "eval_runtime": 4.2134,
+      "eval_samples_per_second": 160.44,
+      "eval_steps_per_second": 20.174,
+      "step": 2120
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 9.449999999999999e-05,
+      "loss": 1.0576,
+      "step": 2332
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.8463678956031799,
+      "eval_runtime": 4.432,
+      "eval_samples_per_second": 152.527,
+      "eval_steps_per_second": 19.179,
+      "step": 2332
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 9.4e-05,
+      "loss": 0.8965,
+      "step": 2544
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.7349700927734375,
+      "eval_runtime": 4.5659,
+      "eval_samples_per_second": 148.054,
+      "eval_steps_per_second": 18.616,
+      "step": 2544
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 9.350000000000001e-05,
+      "loss": 0.7613,
+      "step": 2756
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.6494072675704956,
+      "eval_runtime": 4.499,
+      "eval_samples_per_second": 150.254,
+      "eval_steps_per_second": 18.893,
+      "step": 2756
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42400,
+  "num_train_epochs": 200,
+  "save_steps": 500,
+  "total_flos": 3701919838610772.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2756/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e7d47d9ef4da320ee46463f8716d365eb34b4bc5488090164af1bcf3ad60b35
+size 4155