Training in progress, epoch 5, checkpoint

checkpoint-1060/README.md

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

checkpoint-1060/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": 128,
+  "revision": null,
+  "target_modules": [
+    "query",
+    "key",
+    "value",
+    "dense"
+  ],
+  "task_type": "TOKEN_CLS"
+}

checkpoint-1060/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcd04b0679144aa4828d0df260eaadf4073fb0b3491e7cd576562ec87c3179b
+size 230550429

checkpoint-1060/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3954334f99081185ac3f0146aaa3bf5b2c2874a90cffefc4d0e4047e2aa5f1c
+size 461144966

checkpoint-1060/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce766356fe38c31114f62a6c30fc3b84d1bbf4c4465c11dca5d0676244b2279b
+size 14575

checkpoint-1060/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac8c06a0e85b0caec7620183687dcb47291efc48a5c8db53f654a60b112de0db
+size 627

checkpoint-1060/sentencepiece.bpe.model

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

checkpoint-1060/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-1060/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-1060/trainer_state.json

@@ -0,0 +1,89 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1060,
+  "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": 6.3737,
+      "step": 212
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 5.842774868011475,
+      "eval_runtime": 3.9529,
+      "eval_samples_per_second": 171.015,
+      "eval_steps_per_second": 21.503,
+      "step": 212
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 9.900000000000001e-05,
+      "loss": 5.5296,
+      "step": 424
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.859792232513428,
+      "eval_runtime": 4.2848,
+      "eval_samples_per_second": 157.766,
+      "eval_steps_per_second": 19.837,
+      "step": 424
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.850000000000001e-05,
+      "loss": 4.6838,
+      "step": 636
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 4.013933181762695,
+      "eval_runtime": 4.1662,
+      "eval_samples_per_second": 162.258,
+      "eval_steps_per_second": 20.402,
+      "step": 636
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.8e-05,
+      "loss": 3.9438,
+      "step": 848
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.277362585067749,
+      "eval_runtime": 4.2258,
+      "eval_samples_per_second": 159.97,
+      "eval_steps_per_second": 20.115,
+      "step": 848
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 9.75e-05,
+      "loss": 3.2751,
+      "step": 1060
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.62673282623291,
+      "eval_runtime": 4.5502,
+      "eval_samples_per_second": 148.565,
+      "eval_steps_per_second": 18.68,
+      "step": 1060
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 42400,
+  "num_train_epochs": 200,
+  "save_steps": 500,
+  "total_flos": 1546564063916460.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1060/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45ac36706a0f96e1fbfd751ddcc73ed3d4e95773bdb931420d6f73f3adff937
+size 4155