Commit
•
390c787
1
Parent(s):
97813ba
Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- all_results.json +8 -0
- checkpoint-100/config.json +47 -0
- checkpoint-100/generation_config.json +6 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/pytorch_model.bin +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +1 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +14 -0
- checkpoint-100/trainer_state.json +76 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-200/config.json +47 -0
- checkpoint-200/generation_config.json +6 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/pytorch_model.bin +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +1 -0
- checkpoint-200/tokenizer.model +3 -0
- checkpoint-200/tokenizer_config.json +14 -0
- checkpoint-200/trainer_state.json +136 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/config.json +47 -0
- checkpoint-300/generation_config.json +6 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/pytorch_model.bin +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +1 -0
- checkpoint-300/tokenizer.model +3 -0
- checkpoint-300/tokenizer_config.json +14 -0
- checkpoint-300/trainer_state.json +196 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-400/config.json +47 -0
- checkpoint-400/generation_config.json +6 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/pytorch_model.bin +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/special_tokens_map.json +1 -0
- checkpoint-400/tokenizer.model +3 -0
- checkpoint-400/tokenizer_config.json +14 -0
- checkpoint-400/trainer_state.json +256 -0
- checkpoint-400/training_args.bin +3 -0
- checkpoint-500/config.json +47 -0
- checkpoint-500/generation_config.json +6 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/rng_state.pth +3 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 97.96,
|
3 |
+
"train_loss": 0.302445507645607,
|
4 |
+
"train_runtime": 8265.7464,
|
5 |
+
"train_samples": 98,
|
6 |
+
"train_samples_per_second": 1.161,
|
7 |
+
"train_steps_per_second": 0.073
|
8 |
+
}
|
checkpoint-100/config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-100/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.30.2"
|
6 |
+
}
|
checkpoint-100/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5b9322b7c791be0283cae33d01cb2e6c40786a9c9fab7fc421715ba39faa314
|
3 |
+
size 14681892
|
checkpoint-100/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:119f3aee6155af1456cc129b0eab064a91fd3a95f864e8b1a4985d7e10381988
|
3 |
+
size 7341306
|
checkpoint-100/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:723f496b9d8d8e776f11531f4652ca1ce47b825b86325d6f5aba8841ca36f1a0
|
3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e97f84b2e9cf03e34106548e8fd72d9181e088fcbe9b5747b6e8466de9610724
|
3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
checkpoint-100/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
checkpoint-100/tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-100/trainer_state.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 16.3265306122449,
|
5 |
+
"global_step": 100,
|
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 |
+
"max_steps": 600,
|
72 |
+
"num_train_epochs": 100,
|
73 |
+
"total_flos": 1.1757481562734592e+17,
|
74 |
+
"trial_name": null,
|
75 |
+
"trial_params": null
|
76 |
+
}
|
checkpoint-100/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df0a343e1f2ccb38a19082ba999546089030c0e15418471a24d346cbb68fa7af
|
3 |
+
size 4472
|
checkpoint-200/config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:933b7b82708ba6a23d949d7b05fcb8644b9ab8b06ecf625f35c30aeba85b3ba2
|
3 |
+
size 14681892
|
checkpoint-200/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54e939cf8e3ee1c58646595ea0e7748202c1e1b85f82aeb536a388bbe8d36e86
|
3 |
+
size 7341306
|
checkpoint-200/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51523eedac643c13a3a71297ac9e347331249d1d4cc19f9738a182bae3585fb2
|
3 |
+
size 14244
|
checkpoint-200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3db1c4819d8e7a76f34cf5f8f4aa0bf9497992cd0862dbd9ba3fc68b9886b79e
|
3 |
+
size 1064
|
checkpoint-200/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
checkpoint-200/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
checkpoint-200/tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df0a343e1f2ccb38a19082ba999546089030c0e15418471a24d346cbb68fa7af
|
3 |
+
size 4472
|
checkpoint-300/config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-300/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.30.2"
|
6 |
+
}
|
checkpoint-300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb80ab0b61a192373221d205400431f1f9db5591d3be1fcdb9051924f1b410d2
|
3 |
+
size 14681892
|
checkpoint-300/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:187b159480029f605a8ec08a6da076afe43110d3c1ae18d10931f2ac9e5793ec
|
3 |
+
size 7341306
|
checkpoint-300/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5035452976c183913e118a486015c4dbd9cf61159f30c79ac9dd02dbf2cd81c
|
3 |
+
size 14244
|
checkpoint-300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b5ff897392aa57ce97759b435acfdb4ee39aef21d4a4a68095c3294c513f6c0
|
3 |
+
size 1064
|
checkpoint-300/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
checkpoint-300/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
checkpoint-300/tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-300/trainer_state.json
ADDED
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 48.97959183673469,
|
5 |
+
"global_step": 300,
|
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 |
+
"epoch": 34.29,
|
132 |
+
"learning_rate": 0.006500000000000001,
|
133 |
+
"loss": 0.0492,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 35.92,
|
138 |
+
"learning_rate": 0.006333333333333333,
|
139 |
+
"loss": 0.0458,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 37.55,
|
144 |
+
"learning_rate": 0.0061666666666666675,
|
145 |
+
"loss": 0.0434,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 39.18,
|
150 |
+
"learning_rate": 0.006,
|
151 |
+
"loss": 0.0387,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 40.82,
|
156 |
+
"learning_rate": 0.005833333333333334,
|
157 |
+
"loss": 0.0375,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 42.45,
|
162 |
+
"learning_rate": 0.005666666666666666,
|
163 |
+
"loss": 0.0363,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 44.08,
|
168 |
+
"learning_rate": 0.0055000000000000005,
|
169 |
+
"loss": 0.0347,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 45.71,
|
174 |
+
"learning_rate": 0.005333333333333333,
|
175 |
+
"loss": 0.0341,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 47.35,
|
180 |
+
"learning_rate": 0.0051666666666666675,
|
181 |
+
"loss": 0.0327,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 48.98,
|
186 |
+
"learning_rate": 0.005,
|
187 |
+
"loss": 0.0307,
|
188 |
+
"step": 300
|
189 |
+
}
|
190 |
+
],
|
191 |
+
"max_steps": 600,
|
192 |
+
"num_train_epochs": 100,
|
193 |
+
"total_flos": 3.5272444688203776e+17,
|
194 |
+
"trial_name": null,
|
195 |
+
"trial_params": null
|
196 |
+
}
|
checkpoint-300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df0a343e1f2ccb38a19082ba999546089030c0e15418471a24d346cbb68fa7af
|
3 |
+
size 4472
|
checkpoint-400/config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-400/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.30.2"
|
6 |
+
}
|
checkpoint-400/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ddda63cbe968668b459a73f0a54c34fc36c007f9f202063794ded2a8814a37a
|
3 |
+
size 14681892
|
checkpoint-400/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b954c8f23337c53ad1c86bafb2969338878db3b96c2bc2459aa04e1198a2141
|
3 |
+
size 7341306
|
checkpoint-400/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11204a688e287bc0c7409fba921f7fd490e9471d91d738932d045851e4742a4e
|
3 |
+
size 14244
|
checkpoint-400/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c32c17fb8a573adc159285286f456bfb53c7e2d80664d0c2cce541b6013ed8d7
|
3 |
+
size 1064
|
checkpoint-400/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
checkpoint-400/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
checkpoint-400/tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-400/trainer_state.json
ADDED
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 65.3061224489796,
|
5 |
+
"global_step": 400,
|
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 |
+
"epoch": 34.29,
|
132 |
+
"learning_rate": 0.006500000000000001,
|
133 |
+
"loss": 0.0492,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 35.92,
|
138 |
+
"learning_rate": 0.006333333333333333,
|
139 |
+
"loss": 0.0458,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 37.55,
|
144 |
+
"learning_rate": 0.0061666666666666675,
|
145 |
+
"loss": 0.0434,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 39.18,
|
150 |
+
"learning_rate": 0.006,
|
151 |
+
"loss": 0.0387,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 40.82,
|
156 |
+
"learning_rate": 0.005833333333333334,
|
157 |
+
"loss": 0.0375,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 42.45,
|
162 |
+
"learning_rate": 0.005666666666666666,
|
163 |
+
"loss": 0.0363,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 44.08,
|
168 |
+
"learning_rate": 0.0055000000000000005,
|
169 |
+
"loss": 0.0347,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 45.71,
|
174 |
+
"learning_rate": 0.005333333333333333,
|
175 |
+
"loss": 0.0341,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 47.35,
|
180 |
+
"learning_rate": 0.0051666666666666675,
|
181 |
+
"loss": 0.0327,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 48.98,
|
186 |
+
"learning_rate": 0.005,
|
187 |
+
"loss": 0.0307,
|
188 |
+
"step": 300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 50.61,
|
192 |
+
"learning_rate": 0.004833333333333334,
|
193 |
+
"loss": 0.031,
|
194 |
+
"step": 310
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 52.24,
|
198 |
+
"learning_rate": 0.004666666666666667,
|
199 |
+
"loss": 0.0312,
|
200 |
+
"step": 320
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 53.88,
|
204 |
+
"learning_rate": 0.0045000000000000005,
|
205 |
+
"loss": 0.033,
|
206 |
+
"step": 330
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 55.51,
|
210 |
+
"learning_rate": 0.004333333333333334,
|
211 |
+
"loss": 0.0294,
|
212 |
+
"step": 340
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 57.14,
|
216 |
+
"learning_rate": 0.004166666666666667,
|
217 |
+
"loss": 0.0308,
|
218 |
+
"step": 350
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 58.78,
|
222 |
+
"learning_rate": 0.004,
|
223 |
+
"loss": 0.0301,
|
224 |
+
"step": 360
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 60.41,
|
228 |
+
"learning_rate": 0.0038333333333333336,
|
229 |
+
"loss": 0.0292,
|
230 |
+
"step": 370
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 62.04,
|
234 |
+
"learning_rate": 0.0036666666666666666,
|
235 |
+
"loss": 0.0316,
|
236 |
+
"step": 380
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 63.67,
|
240 |
+
"learning_rate": 0.0034999999999999996,
|
241 |
+
"loss": 0.0302,
|
242 |
+
"step": 390
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 65.31,
|
246 |
+
"learning_rate": 0.003333333333333333,
|
247 |
+
"loss": 0.0295,
|
248 |
+
"step": 400
|
249 |
+
}
|
250 |
+
],
|
251 |
+
"max_steps": 600,
|
252 |
+
"num_train_epochs": 100,
|
253 |
+
"total_flos": 4.702992625093837e+17,
|
254 |
+
"trial_name": null,
|
255 |
+
"trial_params": null
|
256 |
+
}
|
checkpoint-400/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df0a343e1f2ccb38a19082ba999546089030c0e15418471a24d346cbb68fa7af
|
3 |
+
size 4472
|
checkpoint-500/config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-500/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.30.2"
|
6 |
+
}
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9df4c877e409ae83e7bc7c0f1205d623699a931f44d97cbd852d2946c9fa1c96
|
3 |
+
size 14681892
|
checkpoint-500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a87e680f1db9957f77578eb4f8c6df8112d5951619472ae6cfe33f88f3f54e
|
3 |
+
size 7341306
|
checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e88ac4017435c2ca3872f675a493a2f3116de05fe3fa16f5cc26289716e59698
|
3 |
+
size 14244
|