Training in progress, epoch 8, checkpoint

checkpoint-1696/README.md

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

checkpoint-1696/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-1696/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d333cdd5ad47dc84a239d6208d801bfd887007706461754c16bac9aca9df49d9
+size 117304221

checkpoint-1696/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6460d63c6b1bd21d1893954de100d3aaceab92d53e7977472ef45bb63b6a4b4
+size 234652550

checkpoint-1696/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0928388809799d0d7cc5f1f719a0aa30d3ef2e66d625a08bca4cb357e85303a
+size 14575

checkpoint-1696/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1972b2b253cd1ec722414e8aa12ff468785763ce31077387b553bd6aa9ce6b44
+size 627

checkpoint-1696/sentencepiece.bpe.model

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

checkpoint-1696/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-1696/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-1696/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1696,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42400,
+  "num_train_epochs": 200,
+  "save_steps": 500,
+  "total_flos": 2278145890746792.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1696/training_args.bin

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