Training in progress, epoch 9, checkpoint

checkpoint-1908/README.md

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

checkpoint-1908/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": 16,
+  "revision": null,
+  "target_modules": [
+    "query",
+    "key",
+    "value",
+    "dense"
+  ],
+  "task_type": "TOKEN_CLS"
+}

checkpoint-1908/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68024815d1ea4c204bbc08947303f452e164f6cb95b84cb23764737ec51c1bda
+size 32369117

checkpoint-1908/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc721034e8f8d7d58f429c4890280625995b9427364fccac3fd3683198cd5fc
+size 64782278

checkpoint-1908/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09dc264af7f407d231aec865f06b726a55bbd0d0118ee7c6052f8de350cbe631
+size 14575

checkpoint-1908/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:643c232092163254ce86613fb97c17e3e2bd3932ce3c4c2ce7e3c96298d350cc
+size 627

checkpoint-1908/sentencepiece.bpe.model

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

checkpoint-1908/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-1908/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-1908/trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 1908,
+  "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": 6.3597,
+      "step": 212
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.853069305419922,
+      "eval_runtime": 3.5937,
+      "eval_samples_per_second": 188.106,
+      "eval_steps_per_second": 23.652,
+      "step": 212
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 5.5629,
+      "step": 424
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.915834903717041,
+      "eval_runtime": 3.704,
+      "eval_samples_per_second": 182.506,
+      "eval_steps_per_second": 22.948,
+      "step": 424
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.850000000000001e-05,
+      "loss": 4.8228,
+      "step": 636
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.177055835723877,
+      "eval_runtime": 3.7104,
+      "eval_samples_per_second": 182.193,
+      "eval_steps_per_second": 22.909,
+      "step": 636
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.8e-05,
+      "loss": 4.1035,
+      "step": 848
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.462527275085449,
+      "eval_runtime": 3.1205,
+      "eval_samples_per_second": 216.633,
+      "eval_steps_per_second": 27.239,
+      "step": 848
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 9.75e-05,
+      "loss": 3.467,
+      "step": 1060
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.8398332595825195,
+      "eval_runtime": 3.3235,
+      "eval_samples_per_second": 203.402,
+      "eval_steps_per_second": 25.576,
+      "step": 1060
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 9.7e-05,
+      "loss": 2.8887,
+      "step": 1272
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.3201420307159424,
+      "eval_runtime": 3.4255,
+      "eval_samples_per_second": 197.342,
+      "eval_steps_per_second": 24.814,
+      "step": 1272
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 9.65e-05,
+      "loss": 2.4003,
+      "step": 1484
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.8698177337646484,
+      "eval_runtime": 3.5218,
+      "eval_samples_per_second": 191.945,
+      "eval_steps_per_second": 24.135,
+      "step": 1484
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 9.6e-05,
+      "loss": 1.9919,
+      "step": 1696
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.532776951789856,
+      "eval_runtime": 3.5514,
+      "eval_samples_per_second": 190.345,
+      "eval_steps_per_second": 23.934,
+      "step": 1696
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 9.55e-05,
+      "loss": 1.6656,
+      "step": 1908
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 1.2841078042984009,
+      "eval_runtime": 3.622,
+      "eval_samples_per_second": 186.637,
+      "eval_steps_per_second": 23.468,
+      "step": 1908
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42400,
+  "num_train_epochs": 200,
+  "save_steps": 500,
+  "total_flos": 2399636558645124.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1908/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bbad506d5d7c9f6e6c369455b23a5312c048f6fdad38f9f3772905289326b4f
+size 4155