Delete checkpoint-400

checkpoint-400/config.json

@@ -1,47 +0,0 @@
-{
-  "_name_or_path": "chatglm2-6b",
-  "add_bias_linear": false,
-  "add_qkv_bias": true,
-  "apply_query_key_layer_scaling": true,
-  "apply_residual_connection_post_layernorm": false,
-  "architectures": [
-    "ChatGLMForConditionalGeneration"
-  ],
-  "attention_dropout": 0.0,
-  "attention_softmax_in_fp32": true,
-  "auto_map": {
-    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
-    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
-  },
-  "bias_dropout_fusion": true,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "ffn_hidden_size": 13696,
-  "fp32_residual_connection": false,
-  "hidden_dropout": 0.0,
-  "hidden_size": 4096,
-  "kv_channels": 128,
-  "layernorm_epsilon": 1e-05,
-  "model_type": "chatglm",
-  "multi_query_attention": true,
-  "multi_query_group_num": 2,
-  "num_attention_heads": 32,
-  "num_layers": 28,
-  "original_rope": true,
-  "pad_token_id": 0,
-  "padded_vocab_size": 65024,
-  "post_layer_norm": true,
-  "pre_seq_len": 128,
-  "prefix_projection": false,
-  "quantization_bit": 0,
-  "rmsnorm": true,
-  "seq_length": 32768,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.30.2",
-  "use_cache": true,
-  "vocab_size": 65024
-}

checkpoint-400/generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "eos_token_id": 2,
-  "pad_token_id": 0,
-  "transformers_version": "4.30.2"
-}

checkpoint-400/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2ddda63cbe968668b459a73f0a54c34fc36c007f9f202063794ded2a8814a37a
-size 14681892

checkpoint-400/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1b954c8f23337c53ad1c86bafb2969338878db3b96c2bc2459aa04e1198a2141
-size 7341306

checkpoint-400/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:11204a688e287bc0c7409fba921f7fd490e9471d91d738932d045851e4742a4e
-size 14244

checkpoint-400/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c32c17fb8a573adc159285286f456bfb53c7e2d80664d0c2cce541b6013ed8d7
-size 1064

checkpoint-400/special_tokens_map.json

@@ -1 +0,0 @@
-{}

checkpoint-400/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
-size 1018370

checkpoint-400/tokenizer_config.json

@@ -1,14 +0,0 @@
-{
-  "auto_map": {
-    "AutoTokenizer": [
-      "tokenization_chatglm.ChatGLMTokenizer",
-      null
-    ]
-  },
-  "clean_up_tokenization_spaces": false,
-  "do_lower_case": false,
-  "model_max_length": 1000000000000000019884624838656,
-  "padding_side": "left",
-  "remove_space": false,
-  "tokenizer_class": "ChatGLMTokenizer"
-}

checkpoint-400/trainer_state.json

@@ -1,256 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 65.3061224489796,
-  "global_step": 400,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.63,
-      "learning_rate": 0.009833333333333333,
-      "loss": 2.53,
-      "step": 10
-    },
-    {
-      "epoch": 3.27,
-      "learning_rate": 0.009666666666666667,
-      "loss": 2.0016,
-      "step": 20
-    },
-    {
-      "epoch": 4.9,
-      "learning_rate": 0.0095,
-      "loss": 1.7775,
-      "step": 30
-    },
-    {
-      "epoch": 6.53,
-      "learning_rate": 0.009333333333333334,
-      "loss": 1.6576,
-      "step": 40
-    },
-    {
-      "epoch": 8.16,
-      "learning_rate": 0.009166666666666667,
-      "loss": 1.5048,
-      "step": 50
-    },
-    {
-      "epoch": 9.8,
-      "learning_rate": 0.009000000000000001,
-      "loss": 1.3572,
-      "step": 60
-    },
-    {
-      "epoch": 11.43,
-      "learning_rate": 0.008833333333333334,
-      "loss": 1.2067,
-      "step": 70
-    },
-    {
-      "epoch": 13.06,
-      "learning_rate": 0.008666666666666668,
-      "loss": 1.0777,
-      "step": 80
-    },
-    {
-      "epoch": 14.69,
-      "learning_rate": 0.0085,
-      "loss": 0.9188,
-      "step": 90
-    },
-    {
-      "epoch": 16.33,
-      "learning_rate": 0.008333333333333333,
-      "loss": 0.7241,
-      "step": 100
-    },
-    {
-      "epoch": 17.96,
-      "learning_rate": 0.008166666666666666,
-      "loss": 0.5775,
-      "step": 110
-    },
-    {
-      "epoch": 19.59,
-      "learning_rate": 0.008,
-      "loss": 0.4235,
-      "step": 120
-    },
-    {
-      "epoch": 21.22,
-      "learning_rate": 0.007833333333333333,
-      "loss": 0.3182,
-      "step": 130
-    },
-    {
-      "epoch": 22.86,
-      "learning_rate": 0.007666666666666667,
-      "loss": 0.2155,
-      "step": 140
-    },
-    {
-      "epoch": 24.49,
-      "learning_rate": 0.0075,
-      "loss": 0.1633,
-      "step": 150
-    },
-    {
-      "epoch": 26.12,
-      "learning_rate": 0.007333333333333333,
-      "loss": 0.1234,
-      "step": 160
-    },
-    {
-      "epoch": 27.76,
-      "learning_rate": 0.007166666666666667,
-      "loss": 0.0911,
-      "step": 170
-    },
-    {
-      "epoch": 29.39,
-      "learning_rate": 0.006999999999999999,
-      "loss": 0.0738,
-      "step": 180
-    },
-    {
-      "epoch": 31.02,
-      "learning_rate": 0.006833333333333334,
-      "loss": 0.0673,
-      "step": 190
-    },
-    {
-      "epoch": 32.65,
-      "learning_rate": 0.006666666666666666,
-      "loss": 0.0544,
-      "step": 200
-    },
-    {
-      "epoch": 34.29,
-      "learning_rate": 0.006500000000000001,
-      "loss": 0.0492,
-      "step": 210
-    },
-    {
-      "epoch": 35.92,
-      "learning_rate": 0.006333333333333333,
-      "loss": 0.0458,
-      "step": 220
-    },
-    {
-      "epoch": 37.55,
-      "learning_rate": 0.0061666666666666675,
-      "loss": 0.0434,
-      "step": 230
-    },
-    {
-      "epoch": 39.18,
-      "learning_rate": 0.006,
-      "loss": 0.0387,
-      "step": 240
-    },
-    {
-      "epoch": 40.82,
-      "learning_rate": 0.005833333333333334,
-      "loss": 0.0375,
-      "step": 250
-    },
-    {
-      "epoch": 42.45,
-      "learning_rate": 0.005666666666666666,
-      "loss": 0.0363,
-      "step": 260
-    },
-    {
-      "epoch": 44.08,
-      "learning_rate": 0.0055000000000000005,
-      "loss": 0.0347,
-      "step": 270
-    },
-    {
-      "epoch": 45.71,
-      "learning_rate": 0.005333333333333333,
-      "loss": 0.0341,
-      "step": 280
-    },
-    {
-      "epoch": 47.35,
-      "learning_rate": 0.0051666666666666675,
-      "loss": 0.0327,
-      "step": 290
-    },
-    {
-      "epoch": 48.98,
-      "learning_rate": 0.005,
-      "loss": 0.0307,
-      "step": 300
-    },
-    {
-      "epoch": 50.61,
-      "learning_rate": 0.004833333333333334,
-      "loss": 0.031,
-      "step": 310
-    },
-    {
-      "epoch": 52.24,
-      "learning_rate": 0.004666666666666667,
-      "loss": 0.0312,
-      "step": 320
-    },
-    {
-      "epoch": 53.88,
-      "learning_rate": 0.0045000000000000005,
-      "loss": 0.033,
-      "step": 330
-    },
-    {
-      "epoch": 55.51,
-      "learning_rate": 0.004333333333333334,
-      "loss": 0.0294,
-      "step": 340
-    },
-    {
-      "epoch": 57.14,
-      "learning_rate": 0.004166666666666667,
-      "loss": 0.0308,
-      "step": 350
-    },
-    {
-      "epoch": 58.78,
-      "learning_rate": 0.004,
-      "loss": 0.0301,
-      "step": 360
-    },
-    {
-      "epoch": 60.41,
-      "learning_rate": 0.0038333333333333336,
-      "loss": 0.0292,
-      "step": 370
-    },
-    {
-      "epoch": 62.04,
-      "learning_rate": 0.0036666666666666666,
-      "loss": 0.0316,
-      "step": 380
-    },
-    {
-      "epoch": 63.67,
-      "learning_rate": 0.0034999999999999996,
-      "loss": 0.0302,
-      "step": 390
-    },
-    {
-      "epoch": 65.31,
-      "learning_rate": 0.003333333333333333,
-      "loss": 0.0295,
-      "step": 400
-    }
-  ],
-  "max_steps": 600,
-  "num_train_epochs": 100,
-  "total_flos": 4.702992625093837e+17,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-400/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:df0a343e1f2ccb38a19082ba999546089030c0e15418471a24d346cbb68fa7af
-size 4472