Commit
·
e4b8a42
1
Parent(s):
eb04563
Delete checkpoint-200
Browse files- checkpoint-200/config.json +0 -47
- checkpoint-200/generation_config.json +0 -6
- checkpoint-200/optimizer.pt +0 -3
- checkpoint-200/pytorch_model.bin +0 -3
- checkpoint-200/rng_state.pth +0 -3
- checkpoint-200/scheduler.pt +0 -3
- checkpoint-200/special_tokens_map.json +0 -1
- checkpoint-200/tokenizer.model +0 -3
- checkpoint-200/tokenizer_config.json +0 -14
- checkpoint-200/trainer_state.json +0 -136
- checkpoint-200/training_args.bin +0 -3
checkpoint-200/config.json
DELETED
|
@@ -1,47 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "chatglm2-6b",
|
| 3 |
-
"add_bias_linear": false,
|
| 4 |
-
"add_qkv_bias": true,
|
| 5 |
-
"apply_query_key_layer_scaling": true,
|
| 6 |
-
"apply_residual_connection_post_layernorm": false,
|
| 7 |
-
"architectures": [
|
| 8 |
-
"ChatGLMForConditionalGeneration"
|
| 9 |
-
],
|
| 10 |
-
"attention_dropout": 0.0,
|
| 11 |
-
"attention_softmax_in_fp32": true,
|
| 12 |
-
"auto_map": {
|
| 13 |
-
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
|
| 14 |
-
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
| 15 |
-
"AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
| 16 |
-
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
| 17 |
-
"AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
|
| 18 |
-
},
|
| 19 |
-
"bias_dropout_fusion": true,
|
| 20 |
-
"classifier_dropout": null,
|
| 21 |
-
"eos_token_id": 2,
|
| 22 |
-
"ffn_hidden_size": 13696,
|
| 23 |
-
"fp32_residual_connection": false,
|
| 24 |
-
"hidden_dropout": 0.0,
|
| 25 |
-
"hidden_size": 4096,
|
| 26 |
-
"kv_channels": 128,
|
| 27 |
-
"layernorm_epsilon": 1e-05,
|
| 28 |
-
"model_type": "chatglm",
|
| 29 |
-
"multi_query_attention": true,
|
| 30 |
-
"multi_query_group_num": 2,
|
| 31 |
-
"num_attention_heads": 32,
|
| 32 |
-
"num_layers": 28,
|
| 33 |
-
"original_rope": true,
|
| 34 |
-
"pad_token_id": 0,
|
| 35 |
-
"padded_vocab_size": 65024,
|
| 36 |
-
"post_layer_norm": true,
|
| 37 |
-
"pre_seq_len": 128,
|
| 38 |
-
"prefix_projection": false,
|
| 39 |
-
"quantization_bit": 0,
|
| 40 |
-
"rmsnorm": true,
|
| 41 |
-
"seq_length": 32768,
|
| 42 |
-
"tie_word_embeddings": false,
|
| 43 |
-
"torch_dtype": "float16",
|
| 44 |
-
"transformers_version": "4.30.2",
|
| 45 |
-
"use_cache": true,
|
| 46 |
-
"vocab_size": 65024
|
| 47 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/generation_config.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"eos_token_id": 2,
|
| 4 |
-
"pad_token_id": 0,
|
| 5 |
-
"transformers_version": "4.30.2"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/optimizer.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:933b7b82708ba6a23d949d7b05fcb8644b9ab8b06ecf625f35c30aeba85b3ba2
|
| 3 |
-
size 14681892
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:54e939cf8e3ee1c58646595ea0e7748202c1e1b85f82aeb536a388bbe8d36e86
|
| 3 |
-
size 7341306
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/rng_state.pth
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:51523eedac643c13a3a71297ac9e347331249d1d4cc19f9738a182bae3585fb2
|
| 3 |
-
size 14244
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/scheduler.pt
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3db1c4819d8e7a76f34cf5f8f4aa0bf9497992cd0862dbd9ba3fc68b9886b79e
|
| 3 |
-
size 1064
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/special_tokens_map.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{}
|
|
|
|
|
|
checkpoint-200/tokenizer.model
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
| 3 |
-
size 1018370
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/tokenizer_config.json
DELETED
|
@@ -1,14 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"auto_map": {
|
| 3 |
-
"AutoTokenizer": [
|
| 4 |
-
"tokenization_chatglm.ChatGLMTokenizer",
|
| 5 |
-
null
|
| 6 |
-
]
|
| 7 |
-
},
|
| 8 |
-
"clean_up_tokenization_spaces": false,
|
| 9 |
-
"do_lower_case": false,
|
| 10 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 11 |
-
"padding_side": "left",
|
| 12 |
-
"remove_space": false,
|
| 13 |
-
"tokenizer_class": "ChatGLMTokenizer"
|
| 14 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/trainer_state.json
DELETED
|
@@ -1,136 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 32.6530612244898,
|
| 5 |
-
"global_step": 200,
|
| 6 |
-
"is_hyper_param_search": false,
|
| 7 |
-
"is_local_process_zero": true,
|
| 8 |
-
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
{
|
| 11 |
-
"epoch": 1.63,
|
| 12 |
-
"learning_rate": 0.009833333333333333,
|
| 13 |
-
"loss": 2.53,
|
| 14 |
-
"step": 10
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 3.27,
|
| 18 |
-
"learning_rate": 0.009666666666666667,
|
| 19 |
-
"loss": 2.0016,
|
| 20 |
-
"step": 20
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 4.9,
|
| 24 |
-
"learning_rate": 0.0095,
|
| 25 |
-
"loss": 1.7775,
|
| 26 |
-
"step": 30
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 6.53,
|
| 30 |
-
"learning_rate": 0.009333333333333334,
|
| 31 |
-
"loss": 1.6576,
|
| 32 |
-
"step": 40
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 8.16,
|
| 36 |
-
"learning_rate": 0.009166666666666667,
|
| 37 |
-
"loss": 1.5048,
|
| 38 |
-
"step": 50
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 9.8,
|
| 42 |
-
"learning_rate": 0.009000000000000001,
|
| 43 |
-
"loss": 1.3572,
|
| 44 |
-
"step": 60
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 11.43,
|
| 48 |
-
"learning_rate": 0.008833333333333334,
|
| 49 |
-
"loss": 1.2067,
|
| 50 |
-
"step": 70
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 13.06,
|
| 54 |
-
"learning_rate": 0.008666666666666668,
|
| 55 |
-
"loss": 1.0777,
|
| 56 |
-
"step": 80
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 14.69,
|
| 60 |
-
"learning_rate": 0.0085,
|
| 61 |
-
"loss": 0.9188,
|
| 62 |
-
"step": 90
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 16.33,
|
| 66 |
-
"learning_rate": 0.008333333333333333,
|
| 67 |
-
"loss": 0.7241,
|
| 68 |
-
"step": 100
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 17.96,
|
| 72 |
-
"learning_rate": 0.008166666666666666,
|
| 73 |
-
"loss": 0.5775,
|
| 74 |
-
"step": 110
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 19.59,
|
| 78 |
-
"learning_rate": 0.008,
|
| 79 |
-
"loss": 0.4235,
|
| 80 |
-
"step": 120
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 21.22,
|
| 84 |
-
"learning_rate": 0.007833333333333333,
|
| 85 |
-
"loss": 0.3182,
|
| 86 |
-
"step": 130
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 22.86,
|
| 90 |
-
"learning_rate": 0.007666666666666667,
|
| 91 |
-
"loss": 0.2155,
|
| 92 |
-
"step": 140
|
| 93 |
-
},
|
| 94 |
-
{
|
| 95 |
-
"epoch": 24.49,
|
| 96 |
-
"learning_rate": 0.0075,
|
| 97 |
-
"loss": 0.1633,
|
| 98 |
-
"step": 150
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 26.12,
|
| 102 |
-
"learning_rate": 0.007333333333333333,
|
| 103 |
-
"loss": 0.1234,
|
| 104 |
-
"step": 160
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 27.76,
|
| 108 |
-
"learning_rate": 0.007166666666666667,
|
| 109 |
-
"loss": 0.0911,
|
| 110 |
-
"step": 170
|
| 111 |
-
},
|
| 112 |
-
{
|
| 113 |
-
"epoch": 29.39,
|
| 114 |
-
"learning_rate": 0.006999999999999999,
|
| 115 |
-
"loss": 0.0738,
|
| 116 |
-
"step": 180
|
| 117 |
-
},
|
| 118 |
-
{
|
| 119 |
-
"epoch": 31.02,
|
| 120 |
-
"learning_rate": 0.006833333333333334,
|
| 121 |
-
"loss": 0.0673,
|
| 122 |
-
"step": 190
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 32.65,
|
| 126 |
-
"learning_rate": 0.006666666666666666,
|
| 127 |
-
"loss": 0.0544,
|
| 128 |
-
"step": 200
|
| 129 |
-
}
|
| 130 |
-
],
|
| 131 |
-
"max_steps": 600,
|
| 132 |
-
"num_train_epochs": 100,
|
| 133 |
-
"total_flos": 2.3514963125469184e+17,
|
| 134 |
-
"trial_name": null,
|
| 135 |
-
"trial_params": null
|
| 136 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-200/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:df0a343e1f2ccb38a19082ba999546089030c0e15418471a24d346cbb68fa7af
|
| 3 |
-
size 4472
|
|
|
|
|
|
|
|
|
|
|
|