add
Browse files- added_tokens.json +3 -0
- config.json +23 -0
- generation_config.json +7 -0
- pytorch_model-00001-of-00003.bin +3 -0
- pytorch_model-00002-of-00003.bin +3 -0
- pytorch_model-00003-of-00003.bin +3 -0
- pytorch_model.bin.index.json +330 -0
- runs/._Mar22_02-17-27_nv23u9o4yt +0 -0
- runs/._Mar23_16-08-14_nrs4s3eo1s +0 -0
- runs/._Mar23_16-15-05_nrs4s3eo1s +0 -0
- runs/._Mar23_17-20-31_nrs4s3eo1s +0 -0
- runs/._Mar23_17-38-14_nrs4s3eo1s +0 -0
- runs/Mar22_02-17-27_nv23u9o4yt/._1679451514.250914 +0 -0
- runs/Mar22_02-17-27_nv23u9o4yt/._events.out.tfevents.1679451514.nv23u9o4yt.4106.0 +3 -0
- runs/Mar22_02-17-27_nv23u9o4yt/1679451514.250914/._events.out.tfevents.1679451514.nv23u9o4yt.4106.1 +3 -0
- runs/Mar22_02-17-27_nv23u9o4yt/1679451514.250914/events.out.tfevents.1679451514.nv23u9o4yt.4106.1 +3 -0
- runs/Mar22_02-17-27_nv23u9o4yt/events.out.tfevents.1679451514.nv23u9o4yt.4106.0 +3 -0
- runs/Mar23_16-08-14_nrs4s3eo1s/._1679587783.9238882 +0 -0
- runs/Mar23_16-08-14_nrs4s3eo1s/._events.out.tfevents.1679587783.nrs4s3eo1s.396.0 +3 -0
- runs/Mar23_16-08-14_nrs4s3eo1s/1679587783.9238882/._events.out.tfevents.1679587783.nrs4s3eo1s.396.1 +3 -0
- runs/Mar23_16-08-14_nrs4s3eo1s/1679587783.9238882/events.out.tfevents.1679587783.nrs4s3eo1s.396.1 +3 -0
- runs/Mar23_16-08-14_nrs4s3eo1s/events.out.tfevents.1679587783.nrs4s3eo1s.396.0 +3 -0
- runs/Mar23_16-15-05_nrs4s3eo1s/._1679588175.7056534 +0 -0
- runs/Mar23_16-15-05_nrs4s3eo1s/._events.out.tfevents.1679588175.nrs4s3eo1s.577.0 +3 -0
- runs/Mar23_16-15-05_nrs4s3eo1s/1679588175.7056534/._events.out.tfevents.1679588175.nrs4s3eo1s.577.1 +3 -0
- runs/Mar23_16-15-05_nrs4s3eo1s/1679588175.7056534/events.out.tfevents.1679588175.nrs4s3eo1s.577.1 +3 -0
- runs/Mar23_16-15-05_nrs4s3eo1s/events.out.tfevents.1679588175.nrs4s3eo1s.577.0 +3 -0
- runs/Mar23_17-20-31_nrs4s3eo1s/._1679592100.584624 +0 -0
- runs/Mar23_17-20-31_nrs4s3eo1s/._events.out.tfevents.1679592100.nrs4s3eo1s.698.0 +3 -0
- runs/Mar23_17-20-31_nrs4s3eo1s/1679592100.584624/._events.out.tfevents.1679592100.nrs4s3eo1s.698.1 +3 -0
- runs/Mar23_17-20-31_nrs4s3eo1s/1679592100.584624/events.out.tfevents.1679592100.nrs4s3eo1s.698.1 +3 -0
- runs/Mar23_17-20-31_nrs4s3eo1s/events.out.tfevents.1679592100.nrs4s3eo1s.698.0 +3 -0
- runs/Mar23_17-38-14_nrs4s3eo1s/._1679593162.7529712 +0 -0
- runs/Mar23_17-38-14_nrs4s3eo1s/._events.out.tfevents.1679593162.nrs4s3eo1s.1035.0 +3 -0
- runs/Mar23_17-38-14_nrs4s3eo1s/1679593162.7529712/._events.out.tfevents.1679593162.nrs4s3eo1s.1035.1 +3 -0
- runs/Mar23_17-38-14_nrs4s3eo1s/1679593162.7529712/events.out.tfevents.1679593162.nrs4s3eo1s.1035.1 +3 -0
- runs/Mar23_17-38-14_nrs4s3eo1s/events.out.tfevents.1679593162.nrs4s3eo1s.1035.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.model +3 -0
- tokenizer_config.json +9 -0
- trainer_state.json +565 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 32000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./llama-7b",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_sequence_length": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"rms_norm_eps": 1e-06,
|
18 |
+
"tie_word_embeddings": false,
|
19 |
+
"torch_dtype": "float32",
|
20 |
+
"transformers_version": "4.28.0.dev0",
|
21 |
+
"use_cache": true,
|
22 |
+
"vocab_size": 32001
|
23 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.28.0.dev0"
|
7 |
+
}
|
pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd45660a9665b24706948105917b1e85074cd300fe1fad05503fe65d4eadc0a6
|
3 |
+
size 9878005970
|
pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:150c461c7a60ad064d2f7c98f153c515ca2a2ed4b2099323b6d991ad62349536
|
3 |
+
size 9894801014
|
pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6d14ef493c9950f6757b8bbc22f2c59b21b8a1cecb04c74d0e163948353f4e4
|
3 |
+
size 7181007033
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26953703424
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
268 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
269 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
270 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
271 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
272 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
273 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
274 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
275 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
276 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
277 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
278 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
279 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
280 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
281 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
282 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
283 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
284 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
285 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
286 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
287 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
288 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
289 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
290 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
291 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
292 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
293 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
294 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
295 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
296 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
297 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
298 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
299 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
300 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
301 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
302 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
303 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
304 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
305 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
306 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
307 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
308 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
309 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
310 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
311 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
312 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
313 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
314 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
315 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
316 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
317 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
318 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
319 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
320 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
321 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
322 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
323 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
324 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
325 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
326 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
327 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
328 |
+
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
|
329 |
+
}
|
330 |
+
}
|
runs/._Mar22_02-17-27_nv23u9o4yt
ADDED
Binary file (4.1 kB). View file
|
|
runs/._Mar23_16-08-14_nrs4s3eo1s
ADDED
Binary file (4.1 kB). View file
|
|
runs/._Mar23_16-15-05_nrs4s3eo1s
ADDED
Binary file (4.1 kB). View file
|
|
runs/._Mar23_17-20-31_nrs4s3eo1s
ADDED
Binary file (4.1 kB). View file
|
|
runs/._Mar23_17-38-14_nrs4s3eo1s
ADDED
Binary file (4.1 kB). View file
|
|
runs/Mar22_02-17-27_nv23u9o4yt/._1679451514.250914
ADDED
Binary file (4.1 kB). View file
|
|
runs/Mar22_02-17-27_nv23u9o4yt/._events.out.tfevents.1679451514.nv23u9o4yt.4106.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar22_02-17-27_nv23u9o4yt/1679451514.250914/._events.out.tfevents.1679451514.nv23u9o4yt.4106.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar22_02-17-27_nv23u9o4yt/1679451514.250914/events.out.tfevents.1679451514.nv23u9o4yt.4106.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bad93f8069ea680c5fee1551ebc7a12772b84b07150300eb441a013c5b4bccec
|
3 |
+
size 5980
|
runs/Mar22_02-17-27_nv23u9o4yt/events.out.tfevents.1679451514.nv23u9o4yt.4106.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fddd411558161a24b403ad3d2c02d470ee43f6c8ad94ac6b18be1bcf8186da0
|
3 |
+
size 3996
|
runs/Mar23_16-08-14_nrs4s3eo1s/._1679587783.9238882
ADDED
Binary file (4.1 kB). View file
|
|
runs/Mar23_16-08-14_nrs4s3eo1s/._events.out.tfevents.1679587783.nrs4s3eo1s.396.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar23_16-08-14_nrs4s3eo1s/1679587783.9238882/._events.out.tfevents.1679587783.nrs4s3eo1s.396.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar23_16-08-14_nrs4s3eo1s/1679587783.9238882/events.out.tfevents.1679587783.nrs4s3eo1s.396.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bc9829e74b0b5dd4a5d65023b471c26a90d08f0d32ff989d1203c5f720e6f33
|
3 |
+
size 5989
|
runs/Mar23_16-08-14_nrs4s3eo1s/events.out.tfevents.1679587783.nrs4s3eo1s.396.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3f6b4cb86efbc7cc6311e98ec99d15ec7fce740b9a675567a3ddc766e6249ec
|
3 |
+
size 4009
|
runs/Mar23_16-15-05_nrs4s3eo1s/._1679588175.7056534
ADDED
Binary file (4.1 kB). View file
|
|
runs/Mar23_16-15-05_nrs4s3eo1s/._events.out.tfevents.1679588175.nrs4s3eo1s.577.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar23_16-15-05_nrs4s3eo1s/1679588175.7056534/._events.out.tfevents.1679588175.nrs4s3eo1s.577.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar23_16-15-05_nrs4s3eo1s/1679588175.7056534/events.out.tfevents.1679588175.nrs4s3eo1s.577.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b1bac4cefdb7f3d371b638b4970751af65f4b18d247442f5e596eccc86936f6
|
3 |
+
size 5980
|
runs/Mar23_16-15-05_nrs4s3eo1s/events.out.tfevents.1679588175.nrs4s3eo1s.577.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3229d1863c6b696a2ccee96b4739039f0840e8cd9ec97b8d9094c3d588aa978
|
3 |
+
size 5730
|
runs/Mar23_17-20-31_nrs4s3eo1s/._1679592100.584624
ADDED
Binary file (4.1 kB). View file
|
|
runs/Mar23_17-20-31_nrs4s3eo1s/._events.out.tfevents.1679592100.nrs4s3eo1s.698.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar23_17-20-31_nrs4s3eo1s/1679592100.584624/._events.out.tfevents.1679592100.nrs4s3eo1s.698.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar23_17-20-31_nrs4s3eo1s/1679592100.584624/events.out.tfevents.1679592100.nrs4s3eo1s.698.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b8af7fd691dd8fcd8c2ff42e8e9b2aff50dd1118812912398fe13f3a887085b
|
3 |
+
size 5980
|
runs/Mar23_17-20-31_nrs4s3eo1s/events.out.tfevents.1679592100.nrs4s3eo1s.698.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1857bf6b90257dd22186a160a9cfe769a18fbfa30c5d4dea78d75eadbaa4ee00
|
3 |
+
size 3997
|
runs/Mar23_17-38-14_nrs4s3eo1s/._1679593162.7529712
ADDED
Binary file (4.1 kB). View file
|
|
runs/Mar23_17-38-14_nrs4s3eo1s/._events.out.tfevents.1679593162.nrs4s3eo1s.1035.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar23_17-38-14_nrs4s3eo1s/1679593162.7529712/._events.out.tfevents.1679593162.nrs4s3eo1s.1035.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4960ba34fc8876aa52d1c648d53a68eac8f3117f5424ced728fed2470e075ece
|
3 |
+
size 4096
|
runs/Mar23_17-38-14_nrs4s3eo1s/1679593162.7529712/events.out.tfevents.1679593162.nrs4s3eo1s.1035.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01215bc2654f2d58587dab2ccb7a33efdd7b3535f1f5ec668d764096d37bbeda
|
3 |
+
size 5980
|
runs/Mar23_17-38-14_nrs4s3eo1s/events.out.tfevents.1679593162.nrs4s3eo1s.1035.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f19124613eed5c0019d9908c391791e028b8819c01b2531f2df4e86230fc1918
|
3 |
+
size 18205
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "</s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"unk_token": "</s>"
|
6 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "",
|
3 |
+
"eos_token": "",
|
4 |
+
"model_max_length": 512,
|
5 |
+
"padding_side": "right",
|
6 |
+
"special_tokens_map_file": "./llama-7b/special_tokens_map.json",
|
7 |
+
"tokenizer_class": "LlamaTokenizer",
|
8 |
+
"unk_token": ""
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,565 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 27.692307692307693,
|
5 |
+
"global_step": 90,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.31,
|
12 |
+
"learning_rate": 6.666666666666667e-06,
|
13 |
+
"loss": 3.768,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.62,
|
18 |
+
"learning_rate": 1.3333333333333333e-05,
|
19 |
+
"loss": 12.368,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.92,
|
24 |
+
"learning_rate": 2e-05,
|
25 |
+
"loss": 11.537,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 1.23,
|
30 |
+
"learning_rate": 1.999348095389677e-05,
|
31 |
+
"loss": 7.8117,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.54,
|
36 |
+
"learning_rate": 1.9973932315179502e-05,
|
37 |
+
"loss": 5.6659,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.85,
|
42 |
+
"learning_rate": 1.9941379571543597e-05,
|
43 |
+
"loss": 4.2924,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 2.15,
|
48 |
+
"learning_rate": 1.9895865165556375e-05,
|
49 |
+
"loss": 2.1566,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 2.46,
|
54 |
+
"learning_rate": 1.9837448439320027e-05,
|
55 |
+
"loss": 2.607,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 2.77,
|
60 |
+
"learning_rate": 1.976620555710087e-05,
|
61 |
+
"loss": 2.6508,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 3.08,
|
66 |
+
"learning_rate": 1.9682229406025635e-05,
|
67 |
+
"loss": 3.4377,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 3.38,
|
72 |
+
"learning_rate": 1.9585629474974413e-05,
|
73 |
+
"loss": 2.3918,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 3.69,
|
78 |
+
"learning_rate": 1.9476531711828027e-05,
|
79 |
+
"loss": 0.9541,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.0,
|
84 |
+
"learning_rate": 1.935507835925601e-05,
|
85 |
+
"loss": 0.2939,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 4.31,
|
90 |
+
"learning_rate": 1.9221427769259333e-05,
|
91 |
+
"loss": 0.717,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 4.62,
|
96 |
+
"learning_rate": 1.9075754196709574e-05,
|
97 |
+
"loss": 0.3357,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 4.92,
|
102 |
+
"learning_rate": 1.8918247572153822e-05,
|
103 |
+
"loss": 0.2568,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 5.23,
|
108 |
+
"learning_rate": 1.8749113254181498e-05,
|
109 |
+
"loss": 0.1306,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 5.54,
|
114 |
+
"learning_rate": 1.8568571761675893e-05,
|
115 |
+
"loss": 0.3485,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 5.85,
|
120 |
+
"learning_rate": 1.837685848629965e-05,
|
121 |
+
"loss": 0.1659,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 6.15,
|
126 |
+
"learning_rate": 1.817422338558892e-05,
|
127 |
+
"loss": 0.6525,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 6.46,
|
132 |
+
"learning_rate": 1.796093065705644e-05,
|
133 |
+
"loss": 0.1003,
|
134 |
+
"step": 21
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 6.77,
|
138 |
+
"learning_rate": 1.7737258393728363e-05,
|
139 |
+
"loss": 0.3485,
|
140 |
+
"step": 22
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 7.08,
|
144 |
+
"learning_rate": 1.7503498221564026e-05,
|
145 |
+
"loss": 0.2097,
|
146 |
+
"step": 23
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 7.38,
|
150 |
+
"learning_rate": 1.725995491923131e-05,
|
151 |
+
"loss": 0.1424,
|
152 |
+
"step": 24
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 7.69,
|
156 |
+
"learning_rate": 1.7006946020733426e-05,
|
157 |
+
"loss": 0.1512,
|
158 |
+
"step": 25
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 8.0,
|
162 |
+
"learning_rate": 1.6744801401405138e-05,
|
163 |
+
"loss": 0.0815,
|
164 |
+
"step": 26
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 8.31,
|
168 |
+
"learning_rate": 1.647386284781828e-05,
|
169 |
+
"loss": 0.0202,
|
170 |
+
"step": 27
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 8.62,
|
174 |
+
"learning_rate": 1.6194483612157232e-05,
|
175 |
+
"loss": 0.0909,
|
176 |
+
"step": 28
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 8.92,
|
180 |
+
"learning_rate": 1.590702795164551e-05,
|
181 |
+
"loss": 0.1048,
|
182 |
+
"step": 29
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 9.23,
|
186 |
+
"learning_rate": 1.5611870653623826e-05,
|
187 |
+
"loss": 0.1186,
|
188 |
+
"step": 30
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 9.54,
|
192 |
+
"learning_rate": 1.530939654689887e-05,
|
193 |
+
"loss": 0.0219,
|
194 |
+
"step": 31
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 9.85,
|
198 |
+
"learning_rate": 1.5000000000000002e-05,
|
199 |
+
"loss": 0.0718,
|
200 |
+
"step": 32
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 10.15,
|
204 |
+
"learning_rate": 1.4684084406997903e-05,
|
205 |
+
"loss": 0.0788,
|
206 |
+
"step": 33
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 10.46,
|
210 |
+
"learning_rate": 1.4362061661555675e-05,
|
211 |
+
"loss": 0.0534,
|
212 |
+
"step": 34
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 10.77,
|
216 |
+
"learning_rate": 1.4034351619898088e-05,
|
217 |
+
"loss": 0.0225,
|
218 |
+
"step": 35
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 11.08,
|
222 |
+
"learning_rate": 1.3701381553399147e-05,
|
223 |
+
"loss": 0.0345,
|
224 |
+
"step": 36
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 11.38,
|
228 |
+
"learning_rate": 1.3363585591501751e-05,
|
229 |
+
"loss": 0.0125,
|
230 |
+
"step": 37
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 11.69,
|
234 |
+
"learning_rate": 1.3021404155695728e-05,
|
235 |
+
"loss": 0.0211,
|
236 |
+
"step": 38
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 12.0,
|
240 |
+
"learning_rate": 1.2675283385292212e-05,
|
241 |
+
"loss": 0.0998,
|
242 |
+
"step": 39
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 12.31,
|
246 |
+
"learning_rate": 1.2325674555743106e-05,
|
247 |
+
"loss": 0.0139,
|
248 |
+
"step": 40
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 12.62,
|
252 |
+
"learning_rate": 1.1973033490264e-05,
|
253 |
+
"loss": 0.0052,
|
254 |
+
"step": 41
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 12.92,
|
258 |
+
"learning_rate": 1.161781996552765e-05,
|
259 |
+
"loss": 0.0069,
|
260 |
+
"step": 42
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 13.23,
|
264 |
+
"learning_rate": 1.1260497112202895e-05,
|
265 |
+
"loss": 0.1117,
|
266 |
+
"step": 43
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 13.54,
|
270 |
+
"learning_rate": 1.0901530811120655e-05,
|
271 |
+
"loss": 0.0081,
|
272 |
+
"step": 44
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 13.85,
|
276 |
+
"learning_rate": 1.0541389085854177e-05,
|
277 |
+
"loss": 0.009,
|
278 |
+
"step": 45
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 14.15,
|
282 |
+
"learning_rate": 1.0180541492505605e-05,
|
283 |
+
"loss": 0.0019,
|
284 |
+
"step": 46
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 14.46,
|
288 |
+
"learning_rate": 9.819458507494395e-06,
|
289 |
+
"loss": 0.0309,
|
290 |
+
"step": 47
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 14.77,
|
294 |
+
"learning_rate": 9.458610914145826e-06,
|
295 |
+
"loss": 0.0016,
|
296 |
+
"step": 48
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 15.08,
|
300 |
+
"learning_rate": 9.098469188879348e-06,
|
301 |
+
"loss": 0.0158,
|
302 |
+
"step": 49
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 15.38,
|
306 |
+
"learning_rate": 8.739502887797108e-06,
|
307 |
+
"loss": 0.0013,
|
308 |
+
"step": 50
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 15.69,
|
312 |
+
"learning_rate": 8.382180034472353e-06,
|
313 |
+
"loss": 0.0056,
|
314 |
+
"step": 51
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 16.0,
|
318 |
+
"learning_rate": 8.026966509736001e-06,
|
319 |
+
"loss": 0.0311,
|
320 |
+
"step": 52
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 16.31,
|
324 |
+
"learning_rate": 7.674325444256899e-06,
|
325 |
+
"loss": 0.0198,
|
326 |
+
"step": 53
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 16.62,
|
330 |
+
"learning_rate": 7.324716614707794e-06,
|
331 |
+
"loss": 0.0032,
|
332 |
+
"step": 54
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 16.92,
|
336 |
+
"learning_rate": 6.978595844304272e-06,
|
337 |
+
"loss": 0.0011,
|
338 |
+
"step": 55
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 17.23,
|
342 |
+
"learning_rate": 6.636414408498249e-06,
|
343 |
+
"loss": 0.0038,
|
344 |
+
"step": 56
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 17.54,
|
348 |
+
"learning_rate": 6.298618446600856e-06,
|
349 |
+
"loss": 0.011,
|
350 |
+
"step": 57
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 17.85,
|
354 |
+
"learning_rate": 5.965648380101916e-06,
|
355 |
+
"loss": 0.023,
|
356 |
+
"step": 58
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 18.15,
|
360 |
+
"learning_rate": 5.637938338444325e-06,
|
361 |
+
"loss": 0.0005,
|
362 |
+
"step": 59
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 18.46,
|
366 |
+
"learning_rate": 5.3159155930021e-06,
|
367 |
+
"loss": 0.0007,
|
368 |
+
"step": 60
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 18.77,
|
372 |
+
"learning_rate": 5.000000000000003e-06,
|
373 |
+
"loss": 0.0063,
|
374 |
+
"step": 61
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 19.08,
|
378 |
+
"learning_rate": 4.690603453101134e-06,
|
379 |
+
"loss": 0.0009,
|
380 |
+
"step": 62
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 19.38,
|
384 |
+
"learning_rate": 4.388129346376177e-06,
|
385 |
+
"loss": 0.0021,
|
386 |
+
"step": 63
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 19.69,
|
390 |
+
"learning_rate": 4.092972048354491e-06,
|
391 |
+
"loss": 0.02,
|
392 |
+
"step": 64
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 20.0,
|
396 |
+
"learning_rate": 3.8055163878427703e-06,
|
397 |
+
"loss": 0.001,
|
398 |
+
"step": 65
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 20.31,
|
402 |
+
"learning_rate": 3.5261371521817247e-06,
|
403 |
+
"loss": 0.0008,
|
404 |
+
"step": 66
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 20.62,
|
408 |
+
"learning_rate": 3.255198598594862e-06,
|
409 |
+
"loss": 0.0098,
|
410 |
+
"step": 67
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 20.92,
|
414 |
+
"learning_rate": 2.9930539792665767e-06,
|
415 |
+
"loss": 0.0014,
|
416 |
+
"step": 68
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 21.23,
|
420 |
+
"learning_rate": 2.740045080768694e-06,
|
421 |
+
"loss": 0.0015,
|
422 |
+
"step": 69
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 21.54,
|
426 |
+
"learning_rate": 2.496501778435977e-06,
|
427 |
+
"loss": 0.0006,
|
428 |
+
"step": 70
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 21.85,
|
432 |
+
"learning_rate": 2.2627416062716366e-06,
|
433 |
+
"loss": 0.0064,
|
434 |
+
"step": 71
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 22.15,
|
438 |
+
"learning_rate": 2.0390693429435626e-06,
|
439 |
+
"loss": 0.0007,
|
440 |
+
"step": 72
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 22.46,
|
444 |
+
"learning_rate": 1.8257766144110823e-06,
|
445 |
+
"loss": 0.0015,
|
446 |
+
"step": 73
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 22.77,
|
450 |
+
"learning_rate": 1.6231415137003536e-06,
|
451 |
+
"loss": 0.0089,
|
452 |
+
"step": 74
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 23.08,
|
456 |
+
"learning_rate": 1.4314282383241097e-06,
|
457 |
+
"loss": 0.0022,
|
458 |
+
"step": 75
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 23.38,
|
462 |
+
"learning_rate": 1.2508867458185037e-06,
|
463 |
+
"loss": 0.0076,
|
464 |
+
"step": 76
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 23.69,
|
468 |
+
"learning_rate": 1.0817524278461777e-06,
|
469 |
+
"loss": 0.0004,
|
470 |
+
"step": 77
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 24.0,
|
474 |
+
"learning_rate": 9.242458032904311e-07,
|
475 |
+
"loss": 0.0005,
|
476 |
+
"step": 78
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 24.31,
|
480 |
+
"learning_rate": 7.785722307406685e-07,
|
481 |
+
"loss": 0.0004,
|
482 |
+
"step": 79
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 24.62,
|
486 |
+
"learning_rate": 6.449216407439906e-07,
|
487 |
+
"loss": 0.0049,
|
488 |
+
"step": 80
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 24.92,
|
492 |
+
"learning_rate": 5.234682881719766e-07,
|
493 |
+
"loss": 0.004,
|
494 |
+
"step": 81
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 25.23,
|
498 |
+
"learning_rate": 4.1437052502558693e-07,
|
499 |
+
"loss": 0.0037,
|
500 |
+
"step": 82
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 25.54,
|
504 |
+
"learning_rate": 3.1777059397436693e-07,
|
505 |
+
"loss": 0.0099,
|
506 |
+
"step": 83
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 25.85,
|
510 |
+
"learning_rate": 2.3379444289913344e-07,
|
511 |
+
"loss": 0.001,
|
512 |
+
"step": 84
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 26.15,
|
516 |
+
"learning_rate": 1.6255156067997325e-07,
|
517 |
+
"loss": 0.0004,
|
518 |
+
"step": 85
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 26.46,
|
522 |
+
"learning_rate": 1.041348344436277e-07,
|
523 |
+
"loss": 0.0021,
|
524 |
+
"step": 86
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 26.77,
|
528 |
+
"learning_rate": 5.862042845640403e-08,
|
529 |
+
"loss": 0.0052,
|
530 |
+
"step": 87
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 27.08,
|
534 |
+
"learning_rate": 2.606768482050215e-08,
|
535 |
+
"loss": 0.0047,
|
536 |
+
"step": 88
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 27.38,
|
540 |
+
"learning_rate": 6.5190461032305085e-09,
|
541 |
+
"loss": 0.0004,
|
542 |
+
"step": 89
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 27.69,
|
546 |
+
"learning_rate": 0.0,
|
547 |
+
"loss": 0.0003,
|
548 |
+
"step": 90
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 27.69,
|
552 |
+
"step": 90,
|
553 |
+
"total_flos": 9963642317438976.0,
|
554 |
+
"train_loss": 0.7193527906240585,
|
555 |
+
"train_runtime": 2724.9841,
|
556 |
+
"train_samples_per_second": 1.134,
|
557 |
+
"train_steps_per_second": 0.033
|
558 |
+
}
|
559 |
+
],
|
560 |
+
"max_steps": 90,
|
561 |
+
"num_train_epochs": 30,
|
562 |
+
"total_flos": 9963642317438976.0,
|
563 |
+
"trial_name": null,
|
564 |
+
"trial_params": null
|
565 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:759b49e67f15f9362339e98a862e0285b6eaa8da92381955d099480520c8c022
|
3 |
+
size 3707
|