Training in progress, step 6500, checkpoint
Browse files- checkpoint-6500/config.json +195 -0
- checkpoint-6500/generation_config.json +4 -0
- checkpoint-6500/model.safetensors +3 -0
- checkpoint-6500/optimizer.pt +3 -0
- checkpoint-6500/rng_state_0.pth +3 -0
- checkpoint-6500/rng_state_1.pth +3 -0
- checkpoint-6500/rng_state_2.pth +3 -0
- checkpoint-6500/rng_state_3.pth +3 -0
- checkpoint-6500/scheduler.pt +3 -0
- checkpoint-6500/trainer_state.json +0 -0
- checkpoint-6500/training_args.bin +3 -0
checkpoint-6500/config.json
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SrcProberForConditionalGeneration"
|
4 |
+
],
|
5 |
+
"asm_encoder_config": {
|
6 |
+
"_name_or_path": "",
|
7 |
+
"add_cross_attention": false,
|
8 |
+
"architectures": [
|
9 |
+
"LongelmForMaskedLMWithEdgePrediction"
|
10 |
+
],
|
11 |
+
"attention_probs_dropout_prob": 0.1,
|
12 |
+
"bad_words_ids": null,
|
13 |
+
"begin_suppress_tokens": null,
|
14 |
+
"block_size": 8,
|
15 |
+
"bos_token_id": 1,
|
16 |
+
"chunk_size_feed_forward": 0,
|
17 |
+
"classifier_dropout": null,
|
18 |
+
"cross_attention_hidden_size": null,
|
19 |
+
"decoder_start_token_id": null,
|
20 |
+
"diversity_penalty": 0.0,
|
21 |
+
"do_sample": false,
|
22 |
+
"early_stopping": false,
|
23 |
+
"encoder_no_repeat_ngram_size": 0,
|
24 |
+
"eos_token_id": 2,
|
25 |
+
"ep_add_linear_projection": true,
|
26 |
+
"exponential_decay_length_penalty": null,
|
27 |
+
"finetuning_task": null,
|
28 |
+
"forced_bos_token_id": null,
|
29 |
+
"forced_eos_token_id": null,
|
30 |
+
"global_memory_size": 1,
|
31 |
+
"hidden_act": "gelu",
|
32 |
+
"hidden_dropout_prob": 0.1,
|
33 |
+
"hidden_size": 768,
|
34 |
+
"id2label": {
|
35 |
+
"0": "LABEL_0",
|
36 |
+
"1": "LABEL_1"
|
37 |
+
},
|
38 |
+
"initializer_range": 0.02,
|
39 |
+
"intermediate_size": 3072,
|
40 |
+
"is_decoder": false,
|
41 |
+
"is_encoder_decoder": false,
|
42 |
+
"label2id": {
|
43 |
+
"LABEL_0": 0,
|
44 |
+
"LABEL_1": 1
|
45 |
+
},
|
46 |
+
"layer_norm_eps": 1e-12,
|
47 |
+
"length_penalty": 1.0,
|
48 |
+
"max_blocks": 200,
|
49 |
+
"max_length": 20,
|
50 |
+
"max_position_embeddings": 1805,
|
51 |
+
"max_relative_position_embeddings": 8,
|
52 |
+
"min_length": 0,
|
53 |
+
"model_type": "longelm",
|
54 |
+
"no_repeat_ngram_size": 0,
|
55 |
+
"node_size": 1,
|
56 |
+
"num_attention_heads": 12,
|
57 |
+
"num_beam_groups": 1,
|
58 |
+
"num_beams": 1,
|
59 |
+
"num_hidden_layers": 12,
|
60 |
+
"num_return_sequences": 1,
|
61 |
+
"output_attentions": false,
|
62 |
+
"output_hidden_states": false,
|
63 |
+
"output_scores": false,
|
64 |
+
"pad_token_id": 3,
|
65 |
+
"position_embedding_type": "mixed",
|
66 |
+
"prefix": null,
|
67 |
+
"problem_type": null,
|
68 |
+
"pruned_heads": {},
|
69 |
+
"remove_invalid_values": false,
|
70 |
+
"repetition_penalty": 1.0,
|
71 |
+
"return_dict": true,
|
72 |
+
"return_dict_in_generate": false,
|
73 |
+
"sep_token_id": null,
|
74 |
+
"suppress_tokens": null,
|
75 |
+
"task_specific_params": null,
|
76 |
+
"temperature": 1.0,
|
77 |
+
"tf_legacy_loss": false,
|
78 |
+
"tie_encoder_decoder": false,
|
79 |
+
"tie_word_embeddings": true,
|
80 |
+
"tokenizer_class": null,
|
81 |
+
"top_k": 50,
|
82 |
+
"top_p": 1.0,
|
83 |
+
"torch_dtype": "float32",
|
84 |
+
"torchscript": false,
|
85 |
+
"type_vocab_size": 2,
|
86 |
+
"typical_p": 1.0,
|
87 |
+
"use_bfloat16": false,
|
88 |
+
"use_cache": true,
|
89 |
+
"vocab_size": 50265
|
90 |
+
},
|
91 |
+
"asm_feature_select_strategy": "nodes",
|
92 |
+
"asm_token_index": 32016,
|
93 |
+
"ignore_index": -100,
|
94 |
+
"model_type": "rad-prober",
|
95 |
+
"pad_token_id": 2,
|
96 |
+
"projector_hidden_act": "gelu",
|
97 |
+
"src_lm_config": {
|
98 |
+
"_name_or_path": "codellama/CodeLlama-7b-hf",
|
99 |
+
"add_cross_attention": false,
|
100 |
+
"architectures": [
|
101 |
+
"LlamaForCausalLM"
|
102 |
+
],
|
103 |
+
"attention_bias": false,
|
104 |
+
"attention_dropout": 0.0,
|
105 |
+
"bad_words_ids": null,
|
106 |
+
"begin_suppress_tokens": null,
|
107 |
+
"bos_token_id": 1,
|
108 |
+
"chunk_size_feed_forward": 0,
|
109 |
+
"cross_attention_hidden_size": null,
|
110 |
+
"decoder_start_token_id": null,
|
111 |
+
"diversity_penalty": 0.0,
|
112 |
+
"do_sample": false,
|
113 |
+
"early_stopping": false,
|
114 |
+
"encoder_no_repeat_ngram_size": 0,
|
115 |
+
"eos_token_id": 2,
|
116 |
+
"exponential_decay_length_penalty": null,
|
117 |
+
"finetuning_task": null,
|
118 |
+
"forced_bos_token_id": null,
|
119 |
+
"forced_eos_token_id": null,
|
120 |
+
"hidden_act": "silu",
|
121 |
+
"hidden_size": 4096,
|
122 |
+
"id2label": {
|
123 |
+
"0": "LABEL_0",
|
124 |
+
"1": "LABEL_1"
|
125 |
+
},
|
126 |
+
"initializer_range": 0.02,
|
127 |
+
"intermediate_size": 11008,
|
128 |
+
"is_decoder": false,
|
129 |
+
"is_encoder_decoder": false,
|
130 |
+
"label2id": {
|
131 |
+
"LABEL_0": 0,
|
132 |
+
"LABEL_1": 1
|
133 |
+
},
|
134 |
+
"length_penalty": 1.0,
|
135 |
+
"max_length": 20,
|
136 |
+
"max_position_embeddings": 16384,
|
137 |
+
"min_length": 0,
|
138 |
+
"model_type": "llama",
|
139 |
+
"no_repeat_ngram_size": 0,
|
140 |
+
"num_attention_heads": 32,
|
141 |
+
"num_beam_groups": 1,
|
142 |
+
"num_beams": 1,
|
143 |
+
"num_hidden_layers": 32,
|
144 |
+
"num_key_value_heads": 32,
|
145 |
+
"num_return_sequences": 1,
|
146 |
+
"output_attentions": false,
|
147 |
+
"output_hidden_states": false,
|
148 |
+
"output_scores": false,
|
149 |
+
"pad_token_id": null,
|
150 |
+
"prefix": null,
|
151 |
+
"pretraining_tp": 1,
|
152 |
+
"problem_type": null,
|
153 |
+
"pruned_heads": {},
|
154 |
+
"quantization_config": {
|
155 |
+
"_load_in_4bit": false,
|
156 |
+
"_load_in_8bit": true,
|
157 |
+
"bnb_4bit_compute_dtype": "float32",
|
158 |
+
"bnb_4bit_quant_storage": "uint8",
|
159 |
+
"bnb_4bit_quant_type": "fp4",
|
160 |
+
"bnb_4bit_use_double_quant": false,
|
161 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
162 |
+
"llm_int8_has_fp16_weight": false,
|
163 |
+
"llm_int8_skip_modules": null,
|
164 |
+
"llm_int8_threshold": 6.0,
|
165 |
+
"load_in_4bit": false,
|
166 |
+
"load_in_8bit": true,
|
167 |
+
"quant_method": "bitsandbytes"
|
168 |
+
},
|
169 |
+
"remove_invalid_values": false,
|
170 |
+
"repetition_penalty": 1.0,
|
171 |
+
"return_dict": true,
|
172 |
+
"return_dict_in_generate": false,
|
173 |
+
"rms_norm_eps": 1e-05,
|
174 |
+
"rope_scaling": null,
|
175 |
+
"rope_theta": 1000000,
|
176 |
+
"sep_token_id": null,
|
177 |
+
"suppress_tokens": null,
|
178 |
+
"task_specific_params": null,
|
179 |
+
"temperature": 1.0,
|
180 |
+
"tf_legacy_loss": false,
|
181 |
+
"tie_encoder_decoder": false,
|
182 |
+
"tie_word_embeddings": false,
|
183 |
+
"tokenizer_class": null,
|
184 |
+
"top_k": 50,
|
185 |
+
"top_p": 1.0,
|
186 |
+
"torch_dtype": "bfloat16",
|
187 |
+
"torchscript": false,
|
188 |
+
"typical_p": 1.0,
|
189 |
+
"use_bfloat16": false,
|
190 |
+
"use_cache": true,
|
191 |
+
"vocab_size": 32017
|
192 |
+
},
|
193 |
+
"torch_dtype": "float32",
|
194 |
+
"transformers_version": "4.39.3"
|
195 |
+
}
|
checkpoint-6500/generation_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.39.3"
|
4 |
+
}
|
checkpoint-6500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cf75b24fa2139e0d31a2d1fc8db4d8ab530e944d1af8eba25a7b097f7ab7acb
|
3 |
+
size 579945600
|
checkpoint-6500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fe27c14ee3ffc95ddeb3a8ea41d05636ac0685d7703361bf37d8d1491b6d390
|
3 |
+
size 216170911
|
checkpoint-6500/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12f4eb0bd3e42f0833fdae942a699fc09b95a0b17d3da8cfad809d7470bc7d31
|
3 |
+
size 14960
|
checkpoint-6500/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c29896824925f3f8eef00c100029978583d33cbd0fba4a8e6368781782a6bf27
|
3 |
+
size 14960
|
checkpoint-6500/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b580d3e5154ebe1907e106df369f4101b3804b7b8f49cf47e3b817e0375be41
|
3 |
+
size 14960
|
checkpoint-6500/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a80acd09680ed36375420d500386b78f70a1e3df0cedd9338ebed76e4f8093
|
3 |
+
size 14960
|
checkpoint-6500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:984cac2c440e6020f2a0a99ec7549953a806f555f26165d673ba39a72bcc5c4f
|
3 |
+
size 1064
|
checkpoint-6500/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-6500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3814e1058daec6f70a62fab0452b08b4d1c663bae76d77a07b33001875b2afcd
|
3 |
+
size 5048
|