初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/cds_sh1_fr_30
Source: Original Platform

checkpoint-870/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

checkpoint-870/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-870/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fff665240fc8f1f6fc9c6b3ec92056aa2d0d33a1dde940830e177cfd97c4d79
+size 392536704

checkpoint-870/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc91d20b8a51d2c405295b67271820fe2385d482e4a53b633f2a80ccf1d2da8
+size 785167627

checkpoint-870/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88359add1cf79f0f6fba642f7b02c6eafdf05bd456c00b8897e3f00d40be16b8
+size 14709

checkpoint-870/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad194d0830fd2f0531ad618973d2d00736c7f792d7c1efb129737cb25f18061
+size 1383

checkpoint-870/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04378f703797440546a988635c1743590cb89a3ad7236ecc531c580f56f2677e
+size 1465

checkpoint-870/special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

checkpoint-870/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-870/trainer_state.json

@@ -0,0 +1,131 @@
+{
+  "best_global_step": 870,
+  "best_metric": 3.4479944705963135,
+  "best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/cds_sh1_fr_30/checkpoint-870",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 870,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006896551724137931,
+      "grad_norm": 34.13589859008789,
+      "learning_rate": 0.0,
+      "loss": 9.8164,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4214282035827637,
+      "learning_rate": 2.88e-05,
+      "loss": 6.0017,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.516501426696777,
+      "eval_runtime": 4.3416,
+      "eval_samples_per_second": 810.983,
+      "eval_steps_per_second": 3.225,
+      "step": 145
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7844622135162354,
+      "learning_rate": 5.7799999999999995e-05,
+      "loss": 4.1747,
+      "step": 290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.028092384338379,
+      "eval_runtime": 4.4671,
+      "eval_samples_per_second": 788.2,
+      "eval_steps_per_second": 3.134,
+      "step": 290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2072691917419434,
+      "learning_rate": 8.680000000000001e-05,
+      "loss": 3.8777,
+      "step": 435
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.7704145908355713,
+      "eval_runtime": 4.3729,
+      "eval_samples_per_second": 805.181,
+      "eval_steps_per_second": 3.202,
+      "step": 435
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.2117047309875488,
+      "learning_rate": 9.668067226890756e-05,
+      "loss": 3.6723,
+      "step": 580
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.6042661666870117,
+      "eval_runtime": 4.4715,
+      "eval_samples_per_second": 787.434,
+      "eval_steps_per_second": 3.131,
+      "step": 580
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2041577100753784,
+      "learning_rate": 9.058823529411765e-05,
+      "loss": 3.5366,
+      "step": 725
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.5113701820373535,
+      "eval_runtime": 4.511,
+      "eval_samples_per_second": 780.542,
+      "eval_steps_per_second": 3.104,
+      "step": 725
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.1716428995132446,
+      "learning_rate": 8.449579831932774e-05,
+      "loss": 3.4452,
+      "step": 870
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.4479944705963135,
+      "eval_runtime": 4.4139,
+      "eval_samples_per_second": 797.713,
+      "eval_steps_per_second": 3.172,
+      "step": 870
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4474664050688e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-870/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae6cc6c783e227db1116f8c005f43aa568ec75be9eed4765d2de3e98ad03a41
+size 5905