chujiezheng
commited on
Commit
•
4b5faaf
1
Parent(s):
eef6da2
Upload folder using huggingface_hub
Browse files- all_results.json +8 -0
- config.json +26 -0
- generation_config.json +7 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +298 -0
- runs/Apr13_14-39-42_pluslab01-a100.cs.ucla.edu/events.out.tfevents.1713044517.pluslab01-a100.cs.ucla.edu +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- train_results.json +8 -0
- trainer_state.json +615 -0
- training_args.bin +3 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.590523566563092,
|
4 |
+
"train_runtime": 5198.2178,
|
5 |
+
"train_samples": 24454,
|
6 |
+
"train_samples_per_second": 4.704,
|
7 |
+
"train_steps_per_second": 0.037
|
8 |
+
}
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.39.3",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"transformers_version": "4.39.3"
|
7 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92092e4a8a032f131310b434eb039d2f0c22cde2cc0ba29b356f03f4d22cd664
|
3 |
+
size 4943162336
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49d8a62c5c3d2e44cf4125fe2583227caf4fe3e583fe9aa34c8a420542a52cb1
|
3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8307a8826519a6eade4727f2b2a5ae487e1105d46cf8a6c26c02e52cc36c444
|
3 |
+
size 4540516344
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 14483464192
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
297 |
+
}
|
298 |
+
}
|
runs/Apr13_14-39-42_pluslab01-a100.cs.ucla.edu/events.out.tfevents.1713044517.pluslab01-a100.cs.ucla.edu
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fae426e9a4ad18739f7f286493349542b3c86231503a7ca1518273749632eb01
|
3 |
+
size 31608
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.590523566563092,
|
4 |
+
"train_runtime": 5198.2178,
|
5 |
+
"train_samples": 24454,
|
6 |
+
"train_samples_per_second": 4.704,
|
7 |
+
"train_steps_per_second": 0.037
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,615 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9986928104575163,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 191,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"grad_norm": 7.632462021909978,
|
14 |
+
"learning_rate": 2.5e-08,
|
15 |
+
"logits/chosen": -2.7965219020843506,
|
16 |
+
"logits/rejected": -2.8134026527404785,
|
17 |
+
"logps/chosen": -108.48452758789062,
|
18 |
+
"logps/rejected": -117.30828094482422,
|
19 |
+
"loss": 0.6931,
|
20 |
+
"rewards/accuracies": 0.0,
|
21 |
+
"rewards/chosen": 0.0,
|
22 |
+
"rewards/margins": 0.0,
|
23 |
+
"rewards/rejected": 0.0,
|
24 |
+
"step": 1
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.03,
|
28 |
+
"grad_norm": 8.098615692629847,
|
29 |
+
"learning_rate": 1.25e-07,
|
30 |
+
"logits/chosen": -2.8768346309661865,
|
31 |
+
"logits/rejected": -2.8589253425598145,
|
32 |
+
"logps/chosen": -214.42208862304688,
|
33 |
+
"logps/rejected": -232.5906982421875,
|
34 |
+
"loss": 0.6932,
|
35 |
+
"rewards/accuracies": 0.3203125,
|
36 |
+
"rewards/chosen": -0.00048091242206282914,
|
37 |
+
"rewards/margins": -0.0004506283439695835,
|
38 |
+
"rewards/rejected": -3.0284067179309204e-05,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.05,
|
43 |
+
"grad_norm": 7.725942549672666,
|
44 |
+
"learning_rate": 2.5e-07,
|
45 |
+
"logits/chosen": -2.829338550567627,
|
46 |
+
"logits/rejected": -2.8378331661224365,
|
47 |
+
"logps/chosen": -167.3665313720703,
|
48 |
+
"logps/rejected": -171.85272216796875,
|
49 |
+
"loss": 0.6929,
|
50 |
+
"rewards/accuracies": 0.53125,
|
51 |
+
"rewards/chosen": 0.0015454485546797514,
|
52 |
+
"rewards/margins": 0.0004239835252519697,
|
53 |
+
"rewards/rejected": 0.0011214648839086294,
|
54 |
+
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.08,
|
58 |
+
"grad_norm": 6.9736886381721375,
|
59 |
+
"learning_rate": 3.75e-07,
|
60 |
+
"logits/chosen": -2.8761913776397705,
|
61 |
+
"logits/rejected": -2.8846983909606934,
|
62 |
+
"logps/chosen": -218.0037841796875,
|
63 |
+
"logps/rejected": -215.8222198486328,
|
64 |
+
"loss": 0.6917,
|
65 |
+
"rewards/accuracies": 0.6000000238418579,
|
66 |
+
"rewards/chosen": 0.008896902203559875,
|
67 |
+
"rewards/margins": 0.002796543762087822,
|
68 |
+
"rewards/rejected": 0.006100359372794628,
|
69 |
+
"step": 15
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.1,
|
73 |
+
"grad_norm": 7.63640300699799,
|
74 |
+
"learning_rate": 5e-07,
|
75 |
+
"logits/chosen": -2.80039644241333,
|
76 |
+
"logits/rejected": -2.7947278022766113,
|
77 |
+
"logps/chosen": -214.61083984375,
|
78 |
+
"logps/rejected": -232.8736114501953,
|
79 |
+
"loss": 0.6887,
|
80 |
+
"rewards/accuracies": 0.6812499761581421,
|
81 |
+
"rewards/chosen": 0.032507818192243576,
|
82 |
+
"rewards/margins": 0.011343271471560001,
|
83 |
+
"rewards/rejected": 0.0211645495146513,
|
84 |
+
"step": 20
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.13,
|
88 |
+
"grad_norm": 7.959169453434996,
|
89 |
+
"learning_rate": 4.989459720247269e-07,
|
90 |
+
"logits/chosen": -2.8623499870300293,
|
91 |
+
"logits/rejected": -2.8744444847106934,
|
92 |
+
"logps/chosen": -213.915283203125,
|
93 |
+
"logps/rejected": -214.1200408935547,
|
94 |
+
"loss": 0.6815,
|
95 |
+
"rewards/accuracies": 0.637499988079071,
|
96 |
+
"rewards/chosen": 0.0523659810423851,
|
97 |
+
"rewards/margins": 0.024099161848425865,
|
98 |
+
"rewards/rejected": 0.028266817331314087,
|
99 |
+
"step": 25
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.16,
|
103 |
+
"grad_norm": 8.857615760241181,
|
104 |
+
"learning_rate": 4.957927758986888e-07,
|
105 |
+
"logits/chosen": -2.748969554901123,
|
106 |
+
"logits/rejected": -2.755592107772827,
|
107 |
+
"logps/chosen": -184.64889526367188,
|
108 |
+
"logps/rejected": -195.65170288085938,
|
109 |
+
"loss": 0.6713,
|
110 |
+
"rewards/accuracies": 0.706250011920929,
|
111 |
+
"rewards/chosen": 0.05236022546887398,
|
112 |
+
"rewards/margins": 0.05103861540555954,
|
113 |
+
"rewards/rejected": 0.0013216044753789902,
|
114 |
+
"step": 30
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.18,
|
118 |
+
"grad_norm": 9.787510748887732,
|
119 |
+
"learning_rate": 4.905670000773126e-07,
|
120 |
+
"logits/chosen": -2.75258207321167,
|
121 |
+
"logits/rejected": -2.7473061084747314,
|
122 |
+
"logps/chosen": -210.5746612548828,
|
123 |
+
"logps/rejected": -210.62503051757812,
|
124 |
+
"loss": 0.6628,
|
125 |
+
"rewards/accuracies": 0.625,
|
126 |
+
"rewards/chosen": -0.05218905210494995,
|
127 |
+
"rewards/margins": 0.06384799629449844,
|
128 |
+
"rewards/rejected": -0.1160370483994484,
|
129 |
+
"step": 35
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.21,
|
133 |
+
"grad_norm": 8.777368831216146,
|
134 |
+
"learning_rate": 4.833127094718643e-07,
|
135 |
+
"logits/chosen": -2.775714159011841,
|
136 |
+
"logits/rejected": -2.7923226356506348,
|
137 |
+
"logps/chosen": -239.29794311523438,
|
138 |
+
"logps/rejected": -238.61569213867188,
|
139 |
+
"loss": 0.6543,
|
140 |
+
"rewards/accuracies": 0.706250011920929,
|
141 |
+
"rewards/chosen": -0.011378347873687744,
|
142 |
+
"rewards/margins": 0.13017494976520538,
|
143 |
+
"rewards/rejected": -0.14155328273773193,
|
144 |
+
"step": 40
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.24,
|
148 |
+
"grad_norm": 11.157513002596966,
|
149 |
+
"learning_rate": 4.74091073884255e-07,
|
150 |
+
"logits/chosen": -2.7218103408813477,
|
151 |
+
"logits/rejected": -2.734255075454712,
|
152 |
+
"logps/chosen": -207.44918823242188,
|
153 |
+
"logps/rejected": -214.82040405273438,
|
154 |
+
"loss": 0.6408,
|
155 |
+
"rewards/accuracies": 0.581250011920929,
|
156 |
+
"rewards/chosen": -0.008733808994293213,
|
157 |
+
"rewards/margins": 0.12230522930622101,
|
158 |
+
"rewards/rejected": -0.13103903830051422,
|
159 |
+
"step": 45
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.26,
|
163 |
+
"grad_norm": 19.987767668495486,
|
164 |
+
"learning_rate": 4.6297985220958176e-07,
|
165 |
+
"logits/chosen": -2.6240291595458984,
|
166 |
+
"logits/rejected": -2.6364402770996094,
|
167 |
+
"logps/chosen": -230.0597686767578,
|
168 |
+
"logps/rejected": -247.9846649169922,
|
169 |
+
"loss": 0.6254,
|
170 |
+
"rewards/accuracies": 0.6812499761581421,
|
171 |
+
"rewards/chosen": -0.15959548950195312,
|
172 |
+
"rewards/margins": 0.19043126702308655,
|
173 |
+
"rewards/rejected": -0.3500267565250397,
|
174 |
+
"step": 50
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.29,
|
178 |
+
"grad_norm": 12.234358766227293,
|
179 |
+
"learning_rate": 4.50072736755721e-07,
|
180 |
+
"logits/chosen": -2.6890273094177246,
|
181 |
+
"logits/rejected": -2.699357509613037,
|
182 |
+
"logps/chosen": -203.8941192626953,
|
183 |
+
"logps/rejected": -245.869873046875,
|
184 |
+
"loss": 0.6224,
|
185 |
+
"rewards/accuracies": 0.6812499761581421,
|
186 |
+
"rewards/chosen": -0.14397892355918884,
|
187 |
+
"rewards/margins": 0.1972903460264206,
|
188 |
+
"rewards/rejected": -0.34126925468444824,
|
189 |
+
"step": 55
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.31,
|
193 |
+
"grad_norm": 9.53983669539952,
|
194 |
+
"learning_rate": 4.3547856320882036e-07,
|
195 |
+
"logits/chosen": -2.7587661743164062,
|
196 |
+
"logits/rejected": -2.7468841075897217,
|
197 |
+
"logps/chosen": -222.244873046875,
|
198 |
+
"logps/rejected": -258.94256591796875,
|
199 |
+
"loss": 0.6219,
|
200 |
+
"rewards/accuracies": 0.6937500238418579,
|
201 |
+
"rewards/chosen": -0.08269988000392914,
|
202 |
+
"rewards/margins": 0.23697832226753235,
|
203 |
+
"rewards/rejected": -0.3196782171726227,
|
204 |
+
"step": 60
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.34,
|
208 |
+
"grad_norm": 12.877575784727814,
|
209 |
+
"learning_rate": 4.193203929064353e-07,
|
210 |
+
"logits/chosen": -2.702998399734497,
|
211 |
+
"logits/rejected": -2.725602149963379,
|
212 |
+
"logps/chosen": -195.07113647460938,
|
213 |
+
"logps/rejected": -241.1154022216797,
|
214 |
+
"loss": 0.6141,
|
215 |
+
"rewards/accuracies": 0.737500011920929,
|
216 |
+
"rewards/chosen": -0.13330955803394318,
|
217 |
+
"rewards/margins": 0.3229420483112335,
|
218 |
+
"rewards/rejected": -0.4562516212463379,
|
219 |
+
"step": 65
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.37,
|
223 |
+
"grad_norm": 18.557640610201624,
|
224 |
+
"learning_rate": 4.0173447515678915e-07,
|
225 |
+
"logits/chosen": -2.698917865753174,
|
226 |
+
"logits/rejected": -2.696554660797119,
|
227 |
+
"logps/chosen": -211.00540161132812,
|
228 |
+
"logps/rejected": -240.03512573242188,
|
229 |
+
"loss": 0.603,
|
230 |
+
"rewards/accuracies": 0.731249988079071,
|
231 |
+
"rewards/chosen": -0.25489380955696106,
|
232 |
+
"rewards/margins": 0.2834622263908386,
|
233 |
+
"rewards/rejected": -0.5383560061454773,
|
234 |
+
"step": 70
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.39,
|
238 |
+
"grad_norm": 12.118908690233818,
|
239 |
+
"learning_rate": 3.82869098354114e-07,
|
240 |
+
"logits/chosen": -2.664738416671753,
|
241 |
+
"logits/rejected": -2.6815037727355957,
|
242 |
+
"logps/chosen": -210.94235229492188,
|
243 |
+
"logps/rejected": -244.6395263671875,
|
244 |
+
"loss": 0.5971,
|
245 |
+
"rewards/accuracies": 0.6937500238418579,
|
246 |
+
"rewards/chosen": -0.19208934903144836,
|
247 |
+
"rewards/margins": 0.3050723075866699,
|
248 |
+
"rewards/rejected": -0.4971615672111511,
|
249 |
+
"step": 75
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.42,
|
253 |
+
"grad_norm": 15.597624887690841,
|
254 |
+
"learning_rate": 3.6288333957772234e-07,
|
255 |
+
"logits/chosen": -2.6601226329803467,
|
256 |
+
"logits/rejected": -2.6666078567504883,
|
257 |
+
"logps/chosen": -220.9784698486328,
|
258 |
+
"logps/rejected": -261.5680847167969,
|
259 |
+
"loss": 0.6004,
|
260 |
+
"rewards/accuracies": 0.6625000238418579,
|
261 |
+
"rewards/chosen": -0.2644396424293518,
|
262 |
+
"rewards/margins": 0.3234052360057831,
|
263 |
+
"rewards/rejected": -0.587844967842102,
|
264 |
+
"step": 80
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.44,
|
268 |
+
"grad_norm": 19.2075260268852,
|
269 |
+
"learning_rate": 3.419457232184733e-07,
|
270 |
+
"logits/chosen": -2.60345721244812,
|
271 |
+
"logits/rejected": -2.5938727855682373,
|
272 |
+
"logps/chosen": -225.29891967773438,
|
273 |
+
"logps/rejected": -283.8168029785156,
|
274 |
+
"loss": 0.5789,
|
275 |
+
"rewards/accuracies": 0.6937500238418579,
|
276 |
+
"rewards/chosen": -0.4199010729789734,
|
277 |
+
"rewards/margins": 0.4167444705963135,
|
278 |
+
"rewards/rejected": -0.8366454839706421,
|
279 |
+
"step": 85
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.47,
|
283 |
+
"grad_norm": 22.569025736787044,
|
284 |
+
"learning_rate": 3.2023279994339236e-07,
|
285 |
+
"logits/chosen": -2.443169355392456,
|
286 |
+
"logits/rejected": -2.4476258754730225,
|
287 |
+
"logps/chosen": -240.2940673828125,
|
288 |
+
"logps/rejected": -293.4192810058594,
|
289 |
+
"loss": 0.5571,
|
290 |
+
"rewards/accuracies": 0.7124999761581421,
|
291 |
+
"rewards/chosen": -0.4993715286254883,
|
292 |
+
"rewards/margins": 0.5386183857917786,
|
293 |
+
"rewards/rejected": -1.037989854812622,
|
294 |
+
"step": 90
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.5,
|
298 |
+
"grad_norm": 24.018902464460997,
|
299 |
+
"learning_rate": 2.979276579809346e-07,
|
300 |
+
"logits/chosen": -2.3657853603363037,
|
301 |
+
"logits/rejected": -2.3687679767608643,
|
302 |
+
"logps/chosen": -289.3427734375,
|
303 |
+
"logps/rejected": -334.8695068359375,
|
304 |
+
"loss": 0.5686,
|
305 |
+
"rewards/accuracies": 0.7250000238418579,
|
306 |
+
"rewards/chosen": -0.6699068546295166,
|
307 |
+
"rewards/margins": 0.483262836933136,
|
308 |
+
"rewards/rejected": -1.1531696319580078,
|
309 |
+
"step": 95
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.52,
|
313 |
+
"grad_norm": 26.501758420825617,
|
314 |
+
"learning_rate": 2.752183792800671e-07,
|
315 |
+
"logits/chosen": -2.306899070739746,
|
316 |
+
"logits/rejected": -2.302125930786133,
|
317 |
+
"logps/chosen": -247.7756805419922,
|
318 |
+
"logps/rejected": -336.0014343261719,
|
319 |
+
"loss": 0.5798,
|
320 |
+
"rewards/accuracies": 0.7562500238418579,
|
321 |
+
"rewards/chosen": -0.5823773145675659,
|
322 |
+
"rewards/margins": 0.7221489548683167,
|
323 |
+
"rewards/rejected": -1.3045262098312378,
|
324 |
+
"step": 100
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.55,
|
328 |
+
"grad_norm": 28.132693943971592,
|
329 |
+
"learning_rate": 2.522964535611816e-07,
|
330 |
+
"logits/chosen": -2.304361343383789,
|
331 |
+
"logits/rejected": -2.304105043411255,
|
332 |
+
"logps/chosen": -274.34808349609375,
|
333 |
+
"logps/rejected": -327.9083557128906,
|
334 |
+
"loss": 0.5455,
|
335 |
+
"rewards/accuracies": 0.668749988079071,
|
336 |
+
"rewards/chosen": -0.698980450630188,
|
337 |
+
"rewards/margins": 0.6040951013565063,
|
338 |
+
"rewards/rejected": -1.3030755519866943,
|
339 |
+
"step": 105
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.58,
|
343 |
+
"grad_norm": 24.175970284687118,
|
344 |
+
"learning_rate": 2.2935516363191693e-07,
|
345 |
+
"logits/chosen": -2.308105230331421,
|
346 |
+
"logits/rejected": -2.314586639404297,
|
347 |
+
"logps/chosen": -286.6155090332031,
|
348 |
+
"logps/rejected": -360.39141845703125,
|
349 |
+
"loss": 0.5655,
|
350 |
+
"rewards/accuracies": 0.699999988079071,
|
351 |
+
"rewards/chosen": -0.6548763513565063,
|
352 |
+
"rewards/margins": 0.5790941119194031,
|
353 |
+
"rewards/rejected": -1.2339705228805542,
|
354 |
+
"step": 110
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.6,
|
358 |
+
"grad_norm": 21.26580024010301,
|
359 |
+
"learning_rate": 2.065879555832674e-07,
|
360 |
+
"logits/chosen": -2.2688331604003906,
|
361 |
+
"logits/rejected": -2.2680087089538574,
|
362 |
+
"logps/chosen": -276.52972412109375,
|
363 |
+
"logps/rejected": -326.67901611328125,
|
364 |
+
"loss": 0.5511,
|
365 |
+
"rewards/accuracies": 0.65625,
|
366 |
+
"rewards/chosen": -0.7125495076179504,
|
367 |
+
"rewards/margins": 0.5782502293586731,
|
368 |
+
"rewards/rejected": -1.290799617767334,
|
369 |
+
"step": 115
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.63,
|
373 |
+
"grad_norm": 23.746243959703744,
|
374 |
+
"learning_rate": 1.8418680760885024e-07,
|
375 |
+
"logits/chosen": -2.218527317047119,
|
376 |
+
"logits/rejected": -2.221980333328247,
|
377 |
+
"logps/chosen": -261.77569580078125,
|
378 |
+
"logps/rejected": -335.24017333984375,
|
379 |
+
"loss": 0.5532,
|
380 |
+
"rewards/accuracies": 0.65625,
|
381 |
+
"rewards/chosen": -0.7097143530845642,
|
382 |
+
"rewards/margins": 0.6005780100822449,
|
383 |
+
"rewards/rejected": -1.310292363166809,
|
384 |
+
"step": 120
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.65,
|
388 |
+
"grad_norm": 29.782548003529655,
|
389 |
+
"learning_rate": 1.6234061120181143e-07,
|
390 |
+
"logits/chosen": -2.195814609527588,
|
391 |
+
"logits/rejected": -2.187227964401245,
|
392 |
+
"logps/chosen": -272.974853515625,
|
393 |
+
"logps/rejected": -351.69970703125,
|
394 |
+
"loss": 0.5631,
|
395 |
+
"rewards/accuracies": 0.6937500238418579,
|
396 |
+
"rewards/chosen": -0.7646051645278931,
|
397 |
+
"rewards/margins": 0.6365951895713806,
|
398 |
+
"rewards/rejected": -1.4012004137039185,
|
399 |
+
"step": 125
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.68,
|
403 |
+
"grad_norm": 26.29706381032987,
|
404 |
+
"learning_rate": 1.4123357837948176e-07,
|
405 |
+
"logits/chosen": -2.1339738368988037,
|
406 |
+
"logits/rejected": -2.1486494541168213,
|
407 |
+
"logps/chosen": -270.99737548828125,
|
408 |
+
"logps/rejected": -353.390380859375,
|
409 |
+
"loss": 0.5582,
|
410 |
+
"rewards/accuracies": 0.6812499761581421,
|
411 |
+
"rewards/chosen": -0.852789580821991,
|
412 |
+
"rewards/margins": 0.6374956369400024,
|
413 |
+
"rewards/rejected": -1.4902852773666382,
|
414 |
+
"step": 130
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.71,
|
418 |
+
"grad_norm": 24.19850768514201,
|
419 |
+
"learning_rate": 1.2104368836641906e-07,
|
420 |
+
"logits/chosen": -2.2046804428100586,
|
421 |
+
"logits/rejected": -2.2131218910217285,
|
422 |
+
"logps/chosen": -283.3597106933594,
|
423 |
+
"logps/rejected": -341.37310791015625,
|
424 |
+
"loss": 0.5644,
|
425 |
+
"rewards/accuracies": 0.6625000238418579,
|
426 |
+
"rewards/chosen": -0.8999420404434204,
|
427 |
+
"rewards/margins": 0.5441323518753052,
|
428 |
+
"rewards/rejected": -1.4440743923187256,
|
429 |
+
"step": 135
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.73,
|
433 |
+
"grad_norm": 24.56811685462707,
|
434 |
+
"learning_rate": 1.0194118683375502e-07,
|
435 |
+
"logits/chosen": -2.1356701850891113,
|
436 |
+
"logits/rejected": -2.1463379859924316,
|
437 |
+
"logps/chosen": -286.03912353515625,
|
438 |
+
"logps/rejected": -366.0921936035156,
|
439 |
+
"loss": 0.5346,
|
440 |
+
"rewards/accuracies": 0.706250011920929,
|
441 |
+
"rewards/chosen": -0.8500736355781555,
|
442 |
+
"rewards/margins": 0.7081271409988403,
|
443 |
+
"rewards/rejected": -1.5582005977630615,
|
444 |
+
"step": 140
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.76,
|
448 |
+
"grad_norm": 22.093032695536095,
|
449 |
+
"learning_rate": 8.408715034959468e-08,
|
450 |
+
"logits/chosen": -2.2413618564605713,
|
451 |
+
"logits/rejected": -2.238342761993408,
|
452 |
+
"logps/chosen": -269.3088073730469,
|
453 |
+
"logps/rejected": -338.8702087402344,
|
454 |
+
"loss": 0.5355,
|
455 |
+
"rewards/accuracies": 0.699999988079071,
|
456 |
+
"rewards/chosen": -0.7305900454521179,
|
457 |
+
"rewards/margins": 0.5677007436752319,
|
458 |
+
"rewards/rejected": -1.2982908487319946,
|
459 |
+
"step": 145
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.78,
|
463 |
+
"grad_norm": 26.974043137085268,
|
464 |
+
"learning_rate": 6.763212814534483e-08,
|
465 |
+
"logits/chosen": -2.120349884033203,
|
466 |
+
"logits/rejected": -2.1195971965789795,
|
467 |
+
"logps/chosen": -241.08816528320312,
|
468 |
+
"logps/rejected": -324.95501708984375,
|
469 |
+
"loss": 0.5188,
|
470 |
+
"rewards/accuracies": 0.768750011920929,
|
471 |
+
"rewards/chosen": -0.6961054801940918,
|
472 |
+
"rewards/margins": 0.7996633648872375,
|
473 |
+
"rewards/rejected": -1.4957687854766846,
|
474 |
+
"step": 150
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.81,
|
478 |
+
"grad_norm": 23.827648297755715,
|
479 |
+
"learning_rate": 5.271487265090163e-08,
|
480 |
+
"logits/chosen": -2.125883102416992,
|
481 |
+
"logits/rejected": -2.1427865028381348,
|
482 |
+
"logps/chosen": -284.70928955078125,
|
483 |
+
"logps/rejected": -355.811279296875,
|
484 |
+
"loss": 0.5376,
|
485 |
+
"rewards/accuracies": 0.6812499761581421,
|
486 |
+
"rewards/chosen": -0.8156154751777649,
|
487 |
+
"rewards/margins": 0.6232105493545532,
|
488 |
+
"rewards/rejected": -1.438826084136963,
|
489 |
+
"step": 155
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.84,
|
493 |
+
"grad_norm": 24.279380848256523,
|
494 |
+
"learning_rate": 3.94611695031086e-08,
|
495 |
+
"logits/chosen": -2.1862270832061768,
|
496 |
+
"logits/rejected": -2.1674563884735107,
|
497 |
+
"logps/chosen": -310.10052490234375,
|
498 |
+
"logps/rejected": -389.71978759765625,
|
499 |
+
"loss": 0.5317,
|
500 |
+
"rewards/accuracies": 0.706250011920929,
|
501 |
+
"rewards/chosen": -0.9326030611991882,
|
502 |
+
"rewards/margins": 0.6839269995689392,
|
503 |
+
"rewards/rejected": -1.616530179977417,
|
504 |
+
"step": 160
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 0.86,
|
508 |
+
"grad_norm": 25.827053325333576,
|
509 |
+
"learning_rate": 2.7982776893115624e-08,
|
510 |
+
"logits/chosen": -2.201906681060791,
|
511 |
+
"logits/rejected": -2.209010601043701,
|
512 |
+
"logps/chosen": -283.83642578125,
|
513 |
+
"logps/rejected": -354.58819580078125,
|
514 |
+
"loss": 0.5563,
|
515 |
+
"rewards/accuracies": 0.699999988079071,
|
516 |
+
"rewards/chosen": -0.8339606523513794,
|
517 |
+
"rewards/margins": 0.6891152262687683,
|
518 |
+
"rewards/rejected": -1.523075819015503,
|
519 |
+
"step": 165
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.89,
|
523 |
+
"grad_norm": 38.39676777599807,
|
524 |
+
"learning_rate": 1.8376483196299558e-08,
|
525 |
+
"logits/chosen": -2.1251769065856934,
|
526 |
+
"logits/rejected": -2.129974842071533,
|
527 |
+
"logps/chosen": -263.50958251953125,
|
528 |
+
"logps/rejected": -376.3040466308594,
|
529 |
+
"loss": 0.5264,
|
530 |
+
"rewards/accuracies": 0.7124999761581421,
|
531 |
+
"rewards/chosen": -0.9548496007919312,
|
532 |
+
"rewards/margins": 0.8713960647583008,
|
533 |
+
"rewards/rejected": -1.826245665550232,
|
534 |
+
"step": 170
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.92,
|
538 |
+
"grad_norm": 29.646751845133494,
|
539 |
+
"learning_rate": 1.072329083102147e-08,
|
540 |
+
"logits/chosen": -2.1439247131347656,
|
541 |
+
"logits/rejected": -2.1595120429992676,
|
542 |
+
"logps/chosen": -285.36895751953125,
|
543 |
+
"logps/rejected": -353.172119140625,
|
544 |
+
"loss": 0.5656,
|
545 |
+
"rewards/accuracies": 0.7437499761581421,
|
546 |
+
"rewards/chosen": -0.9187411069869995,
|
547 |
+
"rewards/margins": 0.6375783681869507,
|
548 |
+
"rewards/rejected": -1.5563193559646606,
|
549 |
+
"step": 175
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.94,
|
553 |
+
"grad_norm": 25.10520312818217,
|
554 |
+
"learning_rate": 5.087733228106517e-09,
|
555 |
+
"logits/chosen": -2.1849255561828613,
|
556 |
+
"logits/rejected": -2.1818103790283203,
|
557 |
+
"logps/chosen": -334.8546142578125,
|
558 |
+
"logps/rejected": -423.3223571777344,
|
559 |
+
"loss": 0.5344,
|
560 |
+
"rewards/accuracies": 0.7124999761581421,
|
561 |
+
"rewards/chosen": -0.9850701093673706,
|
562 |
+
"rewards/margins": 0.7517432570457458,
|
563 |
+
"rewards/rejected": -1.7368133068084717,
|
564 |
+
"step": 180
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 0.97,
|
568 |
+
"grad_norm": 30.431746994283188,
|
569 |
+
"learning_rate": 1.5173306705126287e-09,
|
570 |
+
"logits/chosen": -2.051201343536377,
|
571 |
+
"logits/rejected": -2.058706045150757,
|
572 |
+
"logps/chosen": -267.4794616699219,
|
573 |
+
"logps/rejected": -324.93109130859375,
|
574 |
+
"loss": 0.5379,
|
575 |
+
"rewards/accuracies": 0.699999988079071,
|
576 |
+
"rewards/chosen": -0.8862212896347046,
|
577 |
+
"rewards/margins": 0.6717046499252319,
|
578 |
+
"rewards/rejected": -1.5579259395599365,
|
579 |
+
"step": 185
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.99,
|
583 |
+
"grad_norm": 30.54437903718355,
|
584 |
+
"learning_rate": 4.2189591669322674e-11,
|
585 |
+
"logits/chosen": -2.094390869140625,
|
586 |
+
"logits/rejected": -2.1068897247314453,
|
587 |
+
"logps/chosen": -294.10125732421875,
|
588 |
+
"logps/rejected": -360.81256103515625,
|
589 |
+
"loss": 0.5301,
|
590 |
+
"rewards/accuracies": 0.6875,
|
591 |
+
"rewards/chosen": -1.0059906244277954,
|
592 |
+
"rewards/margins": 0.6718493700027466,
|
593 |
+
"rewards/rejected": -1.677839994430542,
|
594 |
+
"step": 190
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 1.0,
|
598 |
+
"step": 191,
|
599 |
+
"total_flos": 0.0,
|
600 |
+
"train_loss": 0.590523566563092,
|
601 |
+
"train_runtime": 5198.2178,
|
602 |
+
"train_samples_per_second": 4.704,
|
603 |
+
"train_steps_per_second": 0.037
|
604 |
+
}
|
605 |
+
],
|
606 |
+
"logging_steps": 5,
|
607 |
+
"max_steps": 191,
|
608 |
+
"num_input_tokens_seen": 0,
|
609 |
+
"num_train_epochs": 1,
|
610 |
+
"save_steps": 500,
|
611 |
+
"total_flos": 0.0,
|
612 |
+
"train_batch_size": 8,
|
613 |
+
"trial_name": null,
|
614 |
+
"trial_params": null
|
615 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a2edca0c4187a4d72e3ead4627a1ed386a1b2ebaf93eaa1d8d6e9f41ffa85ff
|
3 |
+
size 6136
|