Uploaded checkpoint-2500
Browse files- config.json +31 -0
- generation_config.json +6 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +226 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +396 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 32013,
|
9 |
+
"eos_token_id": 32021,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5504,
|
14 |
+
"max_position_embeddings": 16384,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 24,
|
18 |
+
"num_key_value_heads": 16,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": {
|
22 |
+
"factor": 4.0,
|
23 |
+
"type": "linear"
|
24 |
+
},
|
25 |
+
"rope_theta": 100000,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.38.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 32256
|
31 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 32013,
|
4 |
+
"eos_token_id": 32021,
|
5 |
+
"transformers_version": "4.38.2"
|
6 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5bd02ef83525b34694bc97ccd2fb6acedf4a01b1617be4bb645ce9d3fba4f1a
|
3 |
+
size 4986380064
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51ea8213f434f66992397fcec5ad578f46f862ce1c0c205cc27a1d344f5b7f18
|
3 |
+
size 399532808
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 5385887744
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
26 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
35 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
44 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
62 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
71 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
80 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
89 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
98 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
107 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
125 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
134 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
143 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
152 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
161 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
162 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
163 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
164 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
166 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
169 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
170 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
171 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
172 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
173 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
174 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
175 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
176 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
177 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
178 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
180 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
181 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
182 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
183 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
184 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
186 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
188 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
189 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
190 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
191 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
192 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
193 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
194 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
195 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
196 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
197 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
198 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
199 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
200 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
201 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
202 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
203 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
204 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
205 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
206 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
207 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
208 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
209 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
210 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
211 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
212 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
213 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
214 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
215 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
216 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
217 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
218 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
219 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
220 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
221 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
222 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
223 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
224 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
225 |
+
}
|
226 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e018c4eb53830317c1f95ca42c944372f3f1c5df5c64829e62629ce4134ca1c1
|
3 |
+
size 2699039674
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b07f599d18b490c55cac64640a11117e1d90973d0c87b2688a01864c5778af86
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b02e80c80580d87c5ff39cb04205ae4e434bebaac5d159f2f573cc994135335a
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,396 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0625,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 2500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 11.075758934020996,
|
14 |
+
"learning_rate": 4.000000000000001e-06,
|
15 |
+
"loss": 1.4211,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"eval_loss": 1.2334846258163452,
|
21 |
+
"eval_runtime": 95.5143,
|
22 |
+
"eval_samples_per_second": 10.47,
|
23 |
+
"eval_steps_per_second": 10.47,
|
24 |
+
"step": 100
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.01,
|
28 |
+
"grad_norm": 19.510242462158203,
|
29 |
+
"learning_rate": 8.000000000000001e-06,
|
30 |
+
"loss": 1.2244,
|
31 |
+
"step": 200
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.01,
|
35 |
+
"eval_loss": 1.1949360370635986,
|
36 |
+
"eval_runtime": 95.601,
|
37 |
+
"eval_samples_per_second": 10.46,
|
38 |
+
"eval_steps_per_second": 10.46,
|
39 |
+
"step": 200
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.01,
|
43 |
+
"grad_norm": 6.514332294464111,
|
44 |
+
"learning_rate": 1.2e-05,
|
45 |
+
"loss": 1.2025,
|
46 |
+
"step": 300
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.01,
|
50 |
+
"eval_loss": 1.1998025178909302,
|
51 |
+
"eval_runtime": 95.7133,
|
52 |
+
"eval_samples_per_second": 10.448,
|
53 |
+
"eval_steps_per_second": 10.448,
|
54 |
+
"step": 300
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.01,
|
58 |
+
"grad_norm": 14.404813766479492,
|
59 |
+
"learning_rate": 1.6000000000000003e-05,
|
60 |
+
"loss": 1.2387,
|
61 |
+
"step": 400
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.01,
|
65 |
+
"eval_loss": 1.2146040201187134,
|
66 |
+
"eval_runtime": 95.6405,
|
67 |
+
"eval_samples_per_second": 10.456,
|
68 |
+
"eval_steps_per_second": 10.456,
|
69 |
+
"step": 400
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.01,
|
73 |
+
"grad_norm": 12.25019645690918,
|
74 |
+
"learning_rate": 2e-05,
|
75 |
+
"loss": 1.2359,
|
76 |
+
"step": 500
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 0.01,
|
80 |
+
"eval_loss": 1.232546329498291,
|
81 |
+
"eval_runtime": 95.701,
|
82 |
+
"eval_samples_per_second": 10.449,
|
83 |
+
"eval_steps_per_second": 10.449,
|
84 |
+
"step": 500
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.01,
|
88 |
+
"grad_norm": 5.677526473999023,
|
89 |
+
"learning_rate": 1.98974358974359e-05,
|
90 |
+
"loss": 1.2189,
|
91 |
+
"step": 600
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.01,
|
95 |
+
"eval_loss": 1.2301095724105835,
|
96 |
+
"eval_runtime": 93.7117,
|
97 |
+
"eval_samples_per_second": 10.671,
|
98 |
+
"eval_steps_per_second": 10.671,
|
99 |
+
"step": 600
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.02,
|
103 |
+
"grad_norm": 13.75782585144043,
|
104 |
+
"learning_rate": 1.9794871794871798e-05,
|
105 |
+
"loss": 1.1982,
|
106 |
+
"step": 700
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.02,
|
110 |
+
"eval_loss": 1.2097805738449097,
|
111 |
+
"eval_runtime": 95.0989,
|
112 |
+
"eval_samples_per_second": 10.515,
|
113 |
+
"eval_steps_per_second": 10.515,
|
114 |
+
"step": 700
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.02,
|
118 |
+
"grad_norm": 7.497257232666016,
|
119 |
+
"learning_rate": 1.9692307692307696e-05,
|
120 |
+
"loss": 1.178,
|
121 |
+
"step": 800
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.02,
|
125 |
+
"eval_loss": 1.1660981178283691,
|
126 |
+
"eval_runtime": 95.0124,
|
127 |
+
"eval_samples_per_second": 10.525,
|
128 |
+
"eval_steps_per_second": 10.525,
|
129 |
+
"step": 800
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.02,
|
133 |
+
"grad_norm": 6.337695121765137,
|
134 |
+
"learning_rate": 1.958974358974359e-05,
|
135 |
+
"loss": 1.1852,
|
136 |
+
"step": 900
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.02,
|
140 |
+
"eval_loss": 1.1449871063232422,
|
141 |
+
"eval_runtime": 94.9978,
|
142 |
+
"eval_samples_per_second": 10.527,
|
143 |
+
"eval_steps_per_second": 10.527,
|
144 |
+
"step": 900
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.03,
|
148 |
+
"grad_norm": 4.1737895011901855,
|
149 |
+
"learning_rate": 1.9487179487179488e-05,
|
150 |
+
"loss": 1.1056,
|
151 |
+
"step": 1000
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.03,
|
155 |
+
"eval_loss": 1.1298564672470093,
|
156 |
+
"eval_runtime": 94.9792,
|
157 |
+
"eval_samples_per_second": 10.529,
|
158 |
+
"eval_steps_per_second": 10.529,
|
159 |
+
"step": 1000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.03,
|
163 |
+
"grad_norm": 6.821949481964111,
|
164 |
+
"learning_rate": 1.9384615384615386e-05,
|
165 |
+
"loss": 1.1681,
|
166 |
+
"step": 1100
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 0.03,
|
170 |
+
"eval_loss": 1.1448038816452026,
|
171 |
+
"eval_runtime": 94.8638,
|
172 |
+
"eval_samples_per_second": 10.541,
|
173 |
+
"eval_steps_per_second": 10.541,
|
174 |
+
"step": 1100
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.03,
|
178 |
+
"grad_norm": 3.908639907836914,
|
179 |
+
"learning_rate": 1.9282051282051284e-05,
|
180 |
+
"loss": 1.1311,
|
181 |
+
"step": 1200
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.03,
|
185 |
+
"eval_loss": 1.0957874059677124,
|
186 |
+
"eval_runtime": 94.6454,
|
187 |
+
"eval_samples_per_second": 10.566,
|
188 |
+
"eval_steps_per_second": 10.566,
|
189 |
+
"step": 1200
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.03,
|
193 |
+
"grad_norm": 5.896665096282959,
|
194 |
+
"learning_rate": 1.9179487179487182e-05,
|
195 |
+
"loss": 1.134,
|
196 |
+
"step": 1300
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 0.03,
|
200 |
+
"eval_loss": 1.0930886268615723,
|
201 |
+
"eval_runtime": 94.6326,
|
202 |
+
"eval_samples_per_second": 10.567,
|
203 |
+
"eval_steps_per_second": 10.567,
|
204 |
+
"step": 1300
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 0.04,
|
208 |
+
"grad_norm": 5.936835765838623,
|
209 |
+
"learning_rate": 1.907692307692308e-05,
|
210 |
+
"loss": 1.0822,
|
211 |
+
"step": 1400
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"epoch": 0.04,
|
215 |
+
"eval_loss": 1.1114310026168823,
|
216 |
+
"eval_runtime": 94.6679,
|
217 |
+
"eval_samples_per_second": 10.563,
|
218 |
+
"eval_steps_per_second": 10.563,
|
219 |
+
"step": 1400
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.04,
|
223 |
+
"grad_norm": 4.07722806930542,
|
224 |
+
"learning_rate": 1.8974358974358975e-05,
|
225 |
+
"loss": 1.0924,
|
226 |
+
"step": 1500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.04,
|
230 |
+
"eval_loss": 1.1060781478881836,
|
231 |
+
"eval_runtime": 94.6419,
|
232 |
+
"eval_samples_per_second": 10.566,
|
233 |
+
"eval_steps_per_second": 10.566,
|
234 |
+
"step": 1500
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.04,
|
238 |
+
"grad_norm": 8.239760398864746,
|
239 |
+
"learning_rate": 1.8871794871794873e-05,
|
240 |
+
"loss": 1.0801,
|
241 |
+
"step": 1600
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.04,
|
245 |
+
"eval_loss": 1.0673882961273193,
|
246 |
+
"eval_runtime": 94.6026,
|
247 |
+
"eval_samples_per_second": 10.571,
|
248 |
+
"eval_steps_per_second": 10.571,
|
249 |
+
"step": 1600
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.04,
|
253 |
+
"grad_norm": 4.63267707824707,
|
254 |
+
"learning_rate": 1.876923076923077e-05,
|
255 |
+
"loss": 1.1051,
|
256 |
+
"step": 1700
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.04,
|
260 |
+
"eval_loss": 1.0620085000991821,
|
261 |
+
"eval_runtime": 94.6137,
|
262 |
+
"eval_samples_per_second": 10.569,
|
263 |
+
"eval_steps_per_second": 10.569,
|
264 |
+
"step": 1700
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 0.04,
|
268 |
+
"grad_norm": 5.941944122314453,
|
269 |
+
"learning_rate": 1.866666666666667e-05,
|
270 |
+
"loss": 1.081,
|
271 |
+
"step": 1800
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.04,
|
275 |
+
"eval_loss": 1.0232795476913452,
|
276 |
+
"eval_runtime": 94.6201,
|
277 |
+
"eval_samples_per_second": 10.569,
|
278 |
+
"eval_steps_per_second": 10.569,
|
279 |
+
"step": 1800
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.05,
|
283 |
+
"grad_norm": 4.456423282623291,
|
284 |
+
"learning_rate": 1.8564102564102567e-05,
|
285 |
+
"loss": 1.0303,
|
286 |
+
"step": 1900
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 0.05,
|
290 |
+
"eval_loss": 1.052198052406311,
|
291 |
+
"eval_runtime": 94.6135,
|
292 |
+
"eval_samples_per_second": 10.569,
|
293 |
+
"eval_steps_per_second": 10.569,
|
294 |
+
"step": 1900
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.05,
|
298 |
+
"grad_norm": 8.572375297546387,
|
299 |
+
"learning_rate": 1.8461538461538465e-05,
|
300 |
+
"loss": 1.048,
|
301 |
+
"step": 2000
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.05,
|
305 |
+
"eval_loss": 1.0538784265518188,
|
306 |
+
"eval_runtime": 94.6091,
|
307 |
+
"eval_samples_per_second": 10.57,
|
308 |
+
"eval_steps_per_second": 10.57,
|
309 |
+
"step": 2000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.05,
|
313 |
+
"grad_norm": 4.592229843139648,
|
314 |
+
"learning_rate": 1.835897435897436e-05,
|
315 |
+
"loss": 1.0623,
|
316 |
+
"step": 2100
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.05,
|
320 |
+
"eval_loss": 1.0412269830703735,
|
321 |
+
"eval_runtime": 94.6145,
|
322 |
+
"eval_samples_per_second": 10.569,
|
323 |
+
"eval_steps_per_second": 10.569,
|
324 |
+
"step": 2100
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.06,
|
328 |
+
"grad_norm": 3.802849054336548,
|
329 |
+
"learning_rate": 1.8256410256410257e-05,
|
330 |
+
"loss": 1.0699,
|
331 |
+
"step": 2200
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.06,
|
335 |
+
"eval_loss": 1.0224683284759521,
|
336 |
+
"eval_runtime": 94.6257,
|
337 |
+
"eval_samples_per_second": 10.568,
|
338 |
+
"eval_steps_per_second": 10.568,
|
339 |
+
"step": 2200
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.06,
|
343 |
+
"grad_norm": 4.145386695861816,
|
344 |
+
"learning_rate": 1.8153846153846155e-05,
|
345 |
+
"loss": 0.9979,
|
346 |
+
"step": 2300
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.06,
|
350 |
+
"eval_loss": 1.0313537120819092,
|
351 |
+
"eval_runtime": 94.6038,
|
352 |
+
"eval_samples_per_second": 10.57,
|
353 |
+
"eval_steps_per_second": 10.57,
|
354 |
+
"step": 2300
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.06,
|
358 |
+
"grad_norm": 4.273189067840576,
|
359 |
+
"learning_rate": 1.8051282051282053e-05,
|
360 |
+
"loss": 1.052,
|
361 |
+
"step": 2400
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.06,
|
365 |
+
"eval_loss": 1.0333129167556763,
|
366 |
+
"eval_runtime": 94.5812,
|
367 |
+
"eval_samples_per_second": 10.573,
|
368 |
+
"eval_steps_per_second": 10.573,
|
369 |
+
"step": 2400
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.06,
|
373 |
+
"grad_norm": 6.093295574188232,
|
374 |
+
"learning_rate": 1.794871794871795e-05,
|
375 |
+
"loss": 1.0025,
|
376 |
+
"step": 2500
|
377 |
+
},
|
378 |
+
{
|
379 |
+
"epoch": 0.06,
|
380 |
+
"eval_loss": 0.9930676817893982,
|
381 |
+
"eval_runtime": 94.5844,
|
382 |
+
"eval_samples_per_second": 10.573,
|
383 |
+
"eval_steps_per_second": 10.573,
|
384 |
+
"step": 2500
|
385 |
+
}
|
386 |
+
],
|
387 |
+
"logging_steps": 100,
|
388 |
+
"max_steps": 20000,
|
389 |
+
"num_input_tokens_seen": 0,
|
390 |
+
"num_train_epochs": 1,
|
391 |
+
"save_steps": 2500,
|
392 |
+
"total_flos": 3.933424582656e+16,
|
393 |
+
"train_batch_size": 1,
|
394 |
+
"trial_name": null,
|
395 |
+
"trial_params": null
|
396 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58f96cee7b3928934c63b8523b5cd7bdf09666d503f89f715c81697ecd9b70dd
|
3 |
+
size 5048
|