Safetensors
Thai
llama
PumeTu commited on
Commit
1ce2b5e
·
verified ·
1 Parent(s): 2e62257

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
Modelfile ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # ollama modelfile auto-generated by llamafactory
2
+
3
+ FROM .
4
+
5
+ TEMPLATE """<|begin_of_text|>{{ if .System }}<|start_header_id|>system<|end_header_id|>
6
+
7
+ {{ .System }}<|eot_id|>{{ end }}{{ range .Messages }}{{ if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
8
+
9
+ {{ .Content }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
10
+
11
+ {{ else if eq .Role "assistant" }}{{ .Content }}<|eot_id|>{{ end }}{{ end }}"""
12
+
13
+ PARAMETER stop "<|eom_id|>"
14
+ PARAMETER stop "<|end_of_text|>"
15
+ PARAMETER stop "<|eot_id|>"
16
+ PARAMETER num_ctx 4096
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/ist-project/scads/pumet/models/Meta-Llama-3.1-8B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "down_proj",
25
+ "v_proj",
26
+ "o_proj",
27
+ "q_proj",
28
+ "up_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f98c3902bbb2d6158353fe5404028a875e64f5a21fc76bc11c1d1c77b011fc29
3
+ size 83945296
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.9327803254127502,
4
+ "eval_runtime": 120.04,
5
+ "eval_samples_per_second": 43.119,
6
+ "eval_steps_per_second": 2.699,
7
+ "total_flos": 3.7446797801931407e+18,
8
+ "train_loss": 0.9387403691644634,
9
+ "train_runtime": 13836.993,
10
+ "train_samples_per_second": 10.1,
11
+ "train_steps_per_second": 0.079
12
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Meta-Llama-3.1-8B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.49.0",
34
+ "use_cache": true,
35
+ "vocab_size": 128256
36
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.9327803254127502,
4
+ "eval_runtime": 120.04,
5
+ "eval_samples_per_second": 43.119,
6
+ "eval_steps_per_second": 2.699
7
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.49.0"
9
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea82bfda5eb1e99f80300db9d54ac5cb9cd0914ff3ce192204f7463a6c8c9e17
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b022f292809d74e95a8b65abe833a9a0064ec877514286a44664285da4bd14
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c817edb8951a707b9a1b0f3b60ab12814889c5635b352b07389dfff065287d
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50072348f6b290ba8b3e4ecd47421f2fbcc327995fbf46853fe747109d79e15c
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|eot_id|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eom_id|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<|begin_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|end_of_text|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": "<|end_of_text|>"
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
tokenizer_config.json ADDED
@@ -0,0 +1,2070 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "additional_special_tokens": [
2053
+ "<|eot_id|>",
2054
+ "<|eom_id|>"
2055
+ ],
2056
+ "bos_token": "<|begin_of_text|>",
2057
+ "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2058
+ "clean_up_tokenization_spaces": true,
2059
+ "eos_token": "<|end_of_text|>",
2060
+ "extra_special_tokens": {},
2061
+ "model_input_names": [
2062
+ "input_ids",
2063
+ "attention_mask"
2064
+ ],
2065
+ "model_max_length": 131072,
2066
+ "pad_token": "<|end_of_text|>",
2067
+ "padding_side": "left",
2068
+ "split_special_tokens": false,
2069
+ "tokenizer_class": "PreTrainedTokenizer"
2070
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 3.7446797801931407e+18,
4
+ "train_loss": 0.9387403691644634,
5
+ "train_runtime": 13836.993,
6
+ "train_samples_per_second": 10.1,
7
+ "train_steps_per_second": 0.079
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1092, "loss": 1.3096, "lr": 1.8181818181818182e-05, "epoch": 0.027472527472527472, "percentage": 0.92, "elapsed_time": "0:01:20", "remaining_time": "2:25:06"}
2
+ {"current_steps": 20, "total_steps": 1092, "loss": 1.3065, "lr": 3.6363636363636364e-05, "epoch": 0.054945054945054944, "percentage": 1.83, "elapsed_time": "0:02:38", "remaining_time": "2:21:16"}
3
+ {"current_steps": 25, "total_steps": 1092, "eval_loss": 1.2722554206848145, "epoch": 0.06868131868131869, "percentage": 2.29, "elapsed_time": "0:05:16", "remaining_time": "3:44:57"}
4
+ {"current_steps": 30, "total_steps": 1092, "loss": 1.2378, "lr": 5.4545454545454546e-05, "epoch": 0.08241758241758242, "percentage": 2.75, "elapsed_time": "0:05:57", "remaining_time": "3:31:05"}
5
+ {"current_steps": 40, "total_steps": 1092, "loss": 1.1986, "lr": 7.272727272727273e-05, "epoch": 0.10989010989010989, "percentage": 3.66, "elapsed_time": "0:07:18", "remaining_time": "3:12:20"}
6
+ {"current_steps": 50, "total_steps": 1092, "loss": 1.165, "lr": 9.090909090909092e-05, "epoch": 0.13736263736263737, "percentage": 4.58, "elapsed_time": "0:08:37", "remaining_time": "2:59:41"}
7
+ {"current_steps": 50, "total_steps": 1092, "eval_loss": 1.1781517267227173, "epoch": 0.13736263736263737, "percentage": 4.58, "elapsed_time": "0:10:37", "remaining_time": "3:41:24"}
8
+ {"current_steps": 60, "total_steps": 1092, "loss": 1.1649, "lr": 0.00010909090909090909, "epoch": 0.16483516483516483, "percentage": 5.49, "elapsed_time": "0:11:56", "remaining_time": "3:25:28"}
9
+ {"current_steps": 70, "total_steps": 1092, "loss": 1.1199, "lr": 0.00012727272727272728, "epoch": 0.19230769230769232, "percentage": 6.41, "elapsed_time": "0:13:17", "remaining_time": "3:14:03"}
10
+ {"current_steps": 75, "total_steps": 1092, "eval_loss": 1.1345776319503784, "epoch": 0.20604395604395603, "percentage": 6.87, "elapsed_time": "0:15:58", "remaining_time": "3:36:30"}
11
+ {"current_steps": 80, "total_steps": 1092, "loss": 1.1184, "lr": 0.00014545454545454546, "epoch": 0.21978021978021978, "percentage": 7.33, "elapsed_time": "0:16:38", "remaining_time": "3:30:26"}
12
+ {"current_steps": 90, "total_steps": 1092, "loss": 1.0936, "lr": 0.00016363636363636366, "epoch": 0.24725274725274726, "percentage": 8.24, "elapsed_time": "0:17:56", "remaining_time": "3:19:44"}
13
+ {"current_steps": 100, "total_steps": 1092, "loss": 1.0818, "lr": 0.00018181818181818183, "epoch": 0.27472527472527475, "percentage": 9.16, "elapsed_time": "0:19:17", "remaining_time": "3:11:23"}
14
+ {"current_steps": 100, "total_steps": 1092, "eval_loss": 1.112221598625183, "epoch": 0.27472527472527475, "percentage": 9.16, "elapsed_time": "0:21:17", "remaining_time": "3:31:14"}
15
+ {"current_steps": 110, "total_steps": 1092, "loss": 1.0894, "lr": 0.0002, "epoch": 0.3021978021978022, "percentage": 10.07, "elapsed_time": "0:22:39", "remaining_time": "3:22:18"}
16
+ {"current_steps": 120, "total_steps": 1092, "loss": 1.0814, "lr": 0.00019994883066969053, "epoch": 0.32967032967032966, "percentage": 10.99, "elapsed_time": "0:23:58", "remaining_time": "3:14:13"}
17
+ {"current_steps": 125, "total_steps": 1092, "eval_loss": 1.0942074060440063, "epoch": 0.3434065934065934, "percentage": 11.45, "elapsed_time": "0:26:39", "remaining_time": "3:26:12"}
18
+ {"current_steps": 130, "total_steps": 1092, "loss": 1.0766, "lr": 0.00019979537504476944, "epoch": 0.35714285714285715, "percentage": 11.9, "elapsed_time": "0:27:18", "remaining_time": "3:22:07"}
19
+ {"current_steps": 140, "total_steps": 1092, "loss": 1.0663, "lr": 0.00019953979016966788, "epoch": 0.38461538461538464, "percentage": 12.82, "elapsed_time": "0:28:37", "remaining_time": "3:14:38"}
20
+ {"current_steps": 150, "total_steps": 1092, "loss": 1.0614, "lr": 0.0001991823376065238, "epoch": 0.41208791208791207, "percentage": 13.74, "elapsed_time": "0:30:00", "remaining_time": "3:08:24"}
21
+ {"current_steps": 150, "total_steps": 1092, "eval_loss": 1.0805188417434692, "epoch": 0.41208791208791207, "percentage": 13.74, "elapsed_time": "0:32:00", "remaining_time": "3:20:58"}
22
+ {"current_steps": 160, "total_steps": 1092, "loss": 1.0531, "lr": 0.00019872338316750265, "epoch": 0.43956043956043955, "percentage": 14.65, "elapsed_time": "0:33:19", "remaining_time": "3:14:05"}
23
+ {"current_steps": 170, "total_steps": 1092, "loss": 1.0552, "lr": 0.00019816339654043022, "epoch": 0.46703296703296704, "percentage": 15.57, "elapsed_time": "0:34:37", "remaining_time": "3:07:47"}
24
+ {"current_steps": 175, "total_steps": 1092, "eval_loss": 1.0678906440734863, "epoch": 0.4807692307692308, "percentage": 16.03, "elapsed_time": "0:37:16", "remaining_time": "3:15:19"}
25
+ {"current_steps": 180, "total_steps": 1092, "loss": 1.0707, "lr": 0.00019750295080812023, "epoch": 0.4945054945054945, "percentage": 16.48, "elapsed_time": "0:37:55", "remaining_time": "3:12:10"}
26
+ {"current_steps": 190, "total_steps": 1092, "loss": 1.0363, "lr": 0.0001967427218618893, "epoch": 0.521978021978022, "percentage": 17.4, "elapsed_time": "0:39:15", "remaining_time": "3:06:23"}
27
+ {"current_steps": 200, "total_steps": 1092, "loss": 1.0519, "lr": 0.0001958834877098586, "epoch": 0.5494505494505495, "percentage": 18.32, "elapsed_time": "0:40:36", "remaining_time": "3:01:06"}
28
+ {"current_steps": 200, "total_steps": 1092, "eval_loss": 1.0573759078979492, "epoch": 0.5494505494505495, "percentage": 18.32, "elapsed_time": "0:42:36", "remaining_time": "3:10:02"}
29
+ {"current_steps": 210, "total_steps": 1092, "loss": 1.0559, "lr": 0.00019492612768075092, "epoch": 0.5769230769230769, "percentage": 19.23, "elapsed_time": "0:43:53", "remaining_time": "3:04:21"}
30
+ {"current_steps": 220, "total_steps": 1092, "loss": 1.0568, "lr": 0.0001938716215239974, "epoch": 0.6043956043956044, "percentage": 20.15, "elapsed_time": "0:45:10", "remaining_time": "2:59:04"}
31
+ {"current_steps": 225, "total_steps": 1092, "eval_loss": 1.046871304512024, "epoch": 0.6181318681318682, "percentage": 20.6, "elapsed_time": "0:47:50", "remaining_time": "3:04:20"}
32
+ {"current_steps": 230, "total_steps": 1092, "loss": 1.0414, "lr": 0.00019272104840707487, "epoch": 0.6318681318681318, "percentage": 21.06, "elapsed_time": "0:48:27", "remaining_time": "3:01:37"}
33
+ {"current_steps": 240, "total_steps": 1092, "loss": 1.0345, "lr": 0.00019147558581110078, "epoch": 0.6593406593406593, "percentage": 21.98, "elapsed_time": "0:49:43", "remaining_time": "2:56:32"}
34
+ {"current_steps": 250, "total_steps": 1092, "loss": 1.0361, "lr": 0.00019013650832581423, "epoch": 0.6868131868131868, "percentage": 22.89, "elapsed_time": "0:51:04", "remaining_time": "2:52:00"}
35
+ {"current_steps": 250, "total_steps": 1092, "eval_loss": 1.0375587940216064, "epoch": 0.6868131868131868, "percentage": 22.89, "elapsed_time": "0:53:04", "remaining_time": "2:58:44"}
36
+ {"current_steps": 260, "total_steps": 1092, "loss": 1.0385, "lr": 0.0001887051863451784, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "0:54:22", "remaining_time": "2:54:00"}
37
+ {"current_steps": 270, "total_steps": 1092, "loss": 1.0153, "lr": 0.00018718308466493744, "epoch": 0.7417582417582418, "percentage": 24.73, "elapsed_time": "0:55:38", "remaining_time": "2:49:24"}
38
+ {"current_steps": 275, "total_steps": 1092, "eval_loss": 1.0293300151824951, "epoch": 0.7554945054945055, "percentage": 25.18, "elapsed_time": "0:58:18", "remaining_time": "2:53:12"}
39
+ {"current_steps": 280, "total_steps": 1092, "loss": 1.0185, "lr": 0.00018557176098356405, "epoch": 0.7692307692307693, "percentage": 25.64, "elapsed_time": "0:58:56", "remaining_time": "2:50:55"}
40
+ {"current_steps": 290, "total_steps": 1092, "loss": 1.0088, "lr": 0.00018387286430813208, "epoch": 0.7967032967032966, "percentage": 26.56, "elapsed_time": "1:00:17", "remaining_time": "2:46:43"}
41
+ {"current_steps": 300, "total_steps": 1092, "loss": 1.0128, "lr": 0.00018208813326674444, "epoch": 0.8241758241758241, "percentage": 27.47, "elapsed_time": "1:01:36", "remaining_time": "2:42:40"}
42
+ {"current_steps": 300, "total_steps": 1092, "eval_loss": 1.020519733428955, "epoch": 0.8241758241758241, "percentage": 27.47, "elapsed_time": "1:03:37", "remaining_time": "2:47:57"}
43
+ {"current_steps": 310, "total_steps": 1092, "loss": 1.0061, "lr": 0.00018021939432924454, "epoch": 0.8516483516483516, "percentage": 28.39, "elapsed_time": "1:04:55", "remaining_time": "2:43:47"}
44
+ {"current_steps": 320, "total_steps": 1092, "loss": 1.0064, "lr": 0.00017826855993803147, "epoch": 0.8791208791208791, "percentage": 29.3, "elapsed_time": "1:06:12", "remaining_time": "2:39:42"}
45
+ {"current_steps": 325, "total_steps": 1092, "eval_loss": 1.0121577978134155, "epoch": 0.8928571428571429, "percentage": 29.76, "elapsed_time": "1:08:50", "remaining_time": "2:42:28"}
46
+ {"current_steps": 330, "total_steps": 1092, "loss": 0.988, "lr": 0.00017623762655089207, "epoch": 0.9065934065934066, "percentage": 30.22, "elapsed_time": "1:09:31", "remaining_time": "2:40:31"}
47
+ {"current_steps": 340, "total_steps": 1092, "loss": 1.0015, "lr": 0.00017412867259785286, "epoch": 0.9340659340659341, "percentage": 31.14, "elapsed_time": "1:10:51", "remaining_time": "2:36:42"}
48
+ {"current_steps": 350, "total_steps": 1092, "loss": 0.995, "lr": 0.00017194385635414244, "epoch": 0.9615384615384616, "percentage": 32.05, "elapsed_time": "1:12:09", "remaining_time": "2:32:59"}
49
+ {"current_steps": 350, "total_steps": 1092, "eval_loss": 1.0048952102661133, "epoch": 0.9615384615384616, "percentage": 32.05, "elapsed_time": "1:14:09", "remaining_time": "2:37:13"}
50
+ {"current_steps": 360, "total_steps": 1092, "loss": 0.9934, "lr": 0.00016968541373144156, "epoch": 0.989010989010989, "percentage": 32.97, "elapsed_time": "1:15:29", "remaining_time": "2:33:29"}
51
+ {"current_steps": 370, "total_steps": 1092, "loss": 0.9443, "lr": 0.00016735565598968114, "epoch": 1.0164835164835164, "percentage": 33.88, "elapsed_time": "1:16:50", "remaining_time": "2:29:56"}
52
+ {"current_steps": 375, "total_steps": 1092, "eval_loss": 0.9992949962615967, "epoch": 1.0302197802197801, "percentage": 34.34, "elapsed_time": "1:19:28", "remaining_time": "2:31:57"}
53
+ {"current_steps": 380, "total_steps": 1092, "loss": 0.9499, "lr": 0.0001649569673717298, "epoch": 1.043956043956044, "percentage": 34.8, "elapsed_time": "1:20:07", "remaining_time": "2:30:08"}
54
+ {"current_steps": 390, "total_steps": 1092, "loss": 0.9218, "lr": 0.0001624918026633916, "epoch": 1.0714285714285714, "percentage": 35.71, "elapsed_time": "1:21:28", "remaining_time": "2:26:39"}
55
+ {"current_steps": 400, "total_steps": 1092, "loss": 0.9393, "lr": 0.00015996268468121102, "epoch": 1.098901098901099, "percentage": 36.63, "elapsed_time": "1:22:50", "remaining_time": "2:23:19"}
56
+ {"current_steps": 400, "total_steps": 1092, "eval_loss": 0.9930510520935059, "epoch": 1.098901098901099, "percentage": 36.63, "elapsed_time": "1:24:50", "remaining_time": "2:26:46"}
57
+ {"current_steps": 410, "total_steps": 1092, "loss": 0.9317, "lr": 0.00015737220169065655, "epoch": 1.1263736263736264, "percentage": 37.55, "elapsed_time": "1:26:11", "remaining_time": "2:23:21"}
58
+ {"current_steps": 420, "total_steps": 1092, "loss": 0.9223, "lr": 0.00015472300475732426, "epoch": 1.1538461538461537, "percentage": 38.46, "elapsed_time": "1:27:31", "remaining_time": "2:20:02"}
59
+ {"current_steps": 425, "total_steps": 1092, "eval_loss": 0.9878760576248169, "epoch": 1.1675824175824177, "percentage": 38.92, "elapsed_time": "1:30:10", "remaining_time": "2:21:30"}
60
+ {"current_steps": 430, "total_steps": 1092, "loss": 0.9407, "lr": 0.0001520178050338729, "epoch": 1.1813186813186813, "percentage": 39.38, "elapsed_time": "1:30:48", "remaining_time": "2:19:47"}
61
+ {"current_steps": 440, "total_steps": 1092, "loss": 0.9416, "lr": 0.00014925937098546652, "epoch": 1.2087912087912087, "percentage": 40.29, "elapsed_time": "1:32:08", "remaining_time": "2:16:32"}
62
+ {"current_steps": 450, "total_steps": 1092, "loss": 0.9248, "lr": 0.00014645052555656431, "epoch": 1.2362637362637363, "percentage": 41.21, "elapsed_time": "1:33:28", "remaining_time": "2:13:21"}
63
+ {"current_steps": 450, "total_steps": 1092, "eval_loss": 0.9815701246261597, "epoch": 1.2362637362637363, "percentage": 41.21, "elapsed_time": "1:35:28", "remaining_time": "2:16:12"}
64
+ {"current_steps": 460, "total_steps": 1092, "loss": 0.9344, "lr": 0.00014359414328195703, "epoch": 1.2637362637362637, "percentage": 42.12, "elapsed_time": "1:36:47", "remaining_time": "2:12:59"}
65
+ {"current_steps": 470, "total_steps": 1092, "loss": 0.9133, "lr": 0.00014069314734500675, "epoch": 1.2912087912087913, "percentage": 43.04, "elapsed_time": "1:38:10", "remaining_time": "2:09:56"}
66
+ {"current_steps": 475, "total_steps": 1092, "eval_loss": 0.975848913192749, "epoch": 1.304945054945055, "percentage": 43.5, "elapsed_time": "1:40:51", "remaining_time": "2:11:00"}
67
+ {"current_steps": 480, "total_steps": 1092, "loss": 0.9171, "lr": 0.00013775050658609988, "epoch": 1.3186813186813187, "percentage": 43.96, "elapsed_time": "1:41:31", "remaining_time": "2:09:26"}
68
+ {"current_steps": 490, "total_steps": 1092, "loss": 0.9181, "lr": 0.0001347692324643759, "epoch": 1.3461538461538463, "percentage": 44.87, "elapsed_time": "1:42:53", "remaining_time": "2:06:24"}
69
+ {"current_steps": 500, "total_steps": 1092, "loss": 0.9271, "lr": 0.00013175237597584045, "epoch": 1.3736263736263736, "percentage": 45.79, "elapsed_time": "1:44:12", "remaining_time": "2:03:22"}
70
+ {"current_steps": 500, "total_steps": 1092, "eval_loss": 0.9721202254295349, "epoch": 1.3736263736263736, "percentage": 45.79, "elapsed_time": "1:46:12", "remaining_time": "2:05:44"}
71
+ {"current_steps": 510, "total_steps": 1092, "loss": 0.9124, "lr": 0.00012870302453101657, "epoch": 1.401098901098901, "percentage": 46.7, "elapsed_time": "1:47:28", "remaining_time": "2:02:38"}
72
+ {"current_steps": 520, "total_steps": 1092, "loss": 0.912, "lr": 0.0001256242987953306, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "1:48:50", "remaining_time": "1:59:43"}
73
+ {"current_steps": 525, "total_steps": 1092, "eval_loss": 0.9657136797904968, "epoch": 1.4423076923076923, "percentage": 48.08, "elapsed_time": "1:51:31", "remaining_time": "2:00:26"}
74
+ {"current_steps": 530, "total_steps": 1092, "loss": 0.9224, "lr": 0.00012251934949546447, "epoch": 1.456043956043956, "percentage": 48.53, "elapsed_time": "1:52:10", "remaining_time": "1:58:56"}
75
+ {"current_steps": 540, "total_steps": 1092, "loss": 0.9141, "lr": 0.00011939135419494456, "epoch": 1.4835164835164836, "percentage": 49.45, "elapsed_time": "1:53:31", "remaining_time": "1:56:02"}
76
+ {"current_steps": 550, "total_steps": 1092, "loss": 0.9074, "lr": 0.00011624351404226572, "epoch": 1.510989010989011, "percentage": 50.37, "elapsed_time": "1:54:50", "remaining_time": "1:53:10"}
77
+ {"current_steps": 550, "total_steps": 1092, "eval_loss": 0.9616743326187134, "epoch": 1.510989010989011, "percentage": 50.37, "elapsed_time": "1:56:50", "remaining_time": "1:55:08"}
78
+ {"current_steps": 560, "total_steps": 1092, "loss": 0.9093, "lr": 0.00011307905049487855, "epoch": 1.5384615384615383, "percentage": 51.28, "elapsed_time": "1:58:09", "remaining_time": "1:52:14"}
79
+ {"current_steps": 570, "total_steps": 1092, "loss": 0.9106, "lr": 0.00010990120202239324, "epoch": 1.565934065934066, "percentage": 52.2, "elapsed_time": "1:59:31", "remaining_time": "1:49:27"}
80
+ {"current_steps": 575, "total_steps": 1092, "eval_loss": 0.9570587277412415, "epoch": 1.5796703296703298, "percentage": 52.66, "elapsed_time": "2:02:13", "remaining_time": "1:49:53"}
81
+ {"current_steps": 580, "total_steps": 1092, "loss": 0.9229, "lr": 0.00010671322079237307, "epoch": 1.5934065934065935, "percentage": 53.11, "elapsed_time": "2:02:51", "remaining_time": "1:48:27"}
82
+ {"current_steps": 590, "total_steps": 1092, "loss": 0.913, "lr": 0.00010351836934210957, "epoch": 1.620879120879121, "percentage": 54.03, "elapsed_time": "2:04:10", "remaining_time": "1:45:39"}
83
+ {"current_steps": 600, "total_steps": 1092, "loss": 0.9001, "lr": 0.00010031991723978574, "epoch": 1.6483516483516483, "percentage": 54.95, "elapsed_time": "2:05:27", "remaining_time": "1:42:52"}
84
+ {"current_steps": 600, "total_steps": 1092, "eval_loss": 0.953257143497467, "epoch": 1.6483516483516483, "percentage": 54.95, "elapsed_time": "2:07:28", "remaining_time": "1:44:31"}
85
+ {"current_steps": 610, "total_steps": 1092, "loss": 0.9051, "lr": 9.712113773844361e-05, "epoch": 1.6758241758241759, "percentage": 55.86, "elapsed_time": "2:08:48", "remaining_time": "1:41:46"}
86
+ {"current_steps": 620, "total_steps": 1092, "loss": 0.9098, "lr": 9.3925304426181e-05, "epoch": 1.7032967032967035, "percentage": 56.78, "elapsed_time": "2:10:07", "remaining_time": "1:39:03"}
87
+ {"current_steps": 625, "total_steps": 1092, "eval_loss": 0.9497827887535095, "epoch": 1.7170329670329672, "percentage": 57.23, "elapsed_time": "2:12:45", "remaining_time": "1:39:11"}
88
+ {"current_steps": 630, "total_steps": 1092, "loss": 0.9174, "lr": 9.073568787600539e-05, "epoch": 1.7307692307692308, "percentage": 57.69, "elapsed_time": "2:13:28", "remaining_time": "1:37:52"}
89
+ {"current_steps": 640, "total_steps": 1092, "loss": 0.9035, "lr": 8.755555229877294e-05, "epoch": 1.7582417582417582, "percentage": 58.61, "elapsed_time": "2:14:45", "remaining_time": "1:35:10"}
90
+ {"current_steps": 650, "total_steps": 1092, "loss": 0.891, "lr": 8.438815220263941e-05, "epoch": 1.7857142857142856, "percentage": 59.52, "elapsed_time": "2:16:02", "remaining_time": "1:32:30"}
91
+ {"current_steps": 650, "total_steps": 1092, "eval_loss": 0.9457467198371887, "epoch": 1.7857142857142856, "percentage": 59.52, "elapsed_time": "2:18:02", "remaining_time": "1:33:52"}
92
+ {"current_steps": 660, "total_steps": 1092, "loss": 0.9033, "lr": 8.123672906243955e-05, "epoch": 1.8131868131868132, "percentage": 60.44, "elapsed_time": "2:19:20", "remaining_time": "1:31:12"}
93
+ {"current_steps": 670, "total_steps": 1092, "loss": 0.8877, "lr": 7.810450800240549e-05, "epoch": 1.8406593406593408, "percentage": 61.36, "elapsed_time": "2:20:41", "remaining_time": "1:28:36"}
94
+ {"current_steps": 675, "total_steps": 1092, "eval_loss": 0.9423750638961792, "epoch": 1.8543956043956045, "percentage": 61.81, "elapsed_time": "2:23:19", "remaining_time": "1:28:32"}
95
+ {"current_steps": 680, "total_steps": 1092, "loss": 0.8988, "lr": 7.499469449561769e-05, "epoch": 1.8681318681318682, "percentage": 62.27, "elapsed_time": "2:24:00", "remaining_time": "1:27:14"}
96
+ {"current_steps": 690, "total_steps": 1092, "loss": 0.9191, "lr": 7.191047108356672e-05, "epoch": 1.8956043956043955, "percentage": 63.19, "elapsed_time": "2:25:21", "remaining_time": "1:24:41"}
97
+ {"current_steps": 700, "total_steps": 1092, "loss": 0.9, "lr": 6.885499411918304e-05, "epoch": 1.9230769230769231, "percentage": 64.1, "elapsed_time": "2:26:41", "remaining_time": "1:22:08"}
98
+ {"current_steps": 700, "total_steps": 1092, "eval_loss": 0.93968266248703, "epoch": 1.9230769230769231, "percentage": 64.1, "elapsed_time": "2:28:41", "remaining_time": "1:23:16"}
99
+ {"current_steps": 710, "total_steps": 1092, "loss": 0.8944, "lr": 6.583139053666745e-05, "epoch": 1.9505494505494505, "percentage": 65.02, "elapsed_time": "2:30:01", "remaining_time": "1:20:43"}
100
+ {"current_steps": 720, "total_steps": 1092, "loss": 0.8841, "lr": 6.284275465142874e-05, "epoch": 1.978021978021978, "percentage": 65.93, "elapsed_time": "2:31:19", "remaining_time": "1:18:11"}
101
+ {"current_steps": 725, "total_steps": 1092, "eval_loss": 0.9374962449073792, "epoch": 1.9917582417582418, "percentage": 66.39, "elapsed_time": "2:33:59", "remaining_time": "1:17:57"}
102
+ {"current_steps": 730, "total_steps": 1092, "loss": 0.8657, "lr": 5.989214499340267e-05, "epoch": 2.0054945054945055, "percentage": 66.85, "elapsed_time": "2:34:36", "remaining_time": "1:16:40"}
103
+ {"current_steps": 740, "total_steps": 1092, "loss": 0.8331, "lr": 5.6982581176993335e-05, "epoch": 2.032967032967033, "percentage": 67.77, "elapsed_time": "2:35:55", "remaining_time": "1:14:09"}
104
+ {"current_steps": 750, "total_steps": 1092, "loss": 0.828, "lr": 5.4117040810840246e-05, "epoch": 2.0604395604395602, "percentage": 68.68, "elapsed_time": "2:37:12", "remaining_time": "1:11:41"}
105
+ {"current_steps": 750, "total_steps": 1092, "eval_loss": 0.9431478381156921, "epoch": 2.0604395604395602, "percentage": 68.68, "elapsed_time": "2:39:12", "remaining_time": "1:12:36"}
106
+ {"current_steps": 760, "total_steps": 1092, "loss": 0.8357, "lr": 5.129845645057372e-05, "epoch": 2.087912087912088, "percentage": 69.6, "elapsed_time": "2:40:33", "remaining_time": "1:10:08"}
107
+ {"current_steps": 770, "total_steps": 1092, "loss": 0.8232, "lr": 4.8529712597676426e-05, "epoch": 2.1153846153846154, "percentage": 70.51, "elapsed_time": "2:41:52", "remaining_time": "1:07:41"}
108
+ {"current_steps": 775, "total_steps": 1092, "eval_loss": 0.940683901309967, "epoch": 2.129120879120879, "percentage": 70.97, "elapsed_time": "2:44:33", "remaining_time": "1:07:18"}
109
+ {"current_steps": 780, "total_steps": 1092, "loss": 0.8351, "lr": 4.581364274752338e-05, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "2:45:14", "remaining_time": "1:06:05"}
110
+ {"current_steps": 790, "total_steps": 1092, "loss": 0.8171, "lr": 4.315302648962066e-05, "epoch": 2.17032967032967, "percentage": 72.34, "elapsed_time": "2:46:31", "remaining_time": "1:03:39"}
111
+ {"current_steps": 800, "total_steps": 1092, "loss": 0.8299, "lr": 4.055058666301087e-05, "epoch": 2.197802197802198, "percentage": 73.26, "elapsed_time": "2:47:53", "remaining_time": "1:01:16"}
112
+ {"current_steps": 800, "total_steps": 1092, "eval_loss": 0.9400618672370911, "epoch": 2.197802197802198, "percentage": 73.26, "elapsed_time": "2:49:53", "remaining_time": "1:02:00"}
113
+ {"current_steps": 810, "total_steps": 1092, "loss": 0.8303, "lr": 3.800898656975599e-05, "epoch": 2.2252747252747254, "percentage": 74.18, "elapsed_time": "2:51:14", "remaining_time": "0:59:36"}
114
+ {"current_steps": 820, "total_steps": 1092, "loss": 0.8378, "lr": 3.553082724934973e-05, "epoch": 2.2527472527472527, "percentage": 75.09, "elapsed_time": "2:52:29", "remaining_time": "0:57:13"}
115
+ {"current_steps": 825, "total_steps": 1092, "eval_loss": 0.9390351176261902, "epoch": 2.2664835164835164, "percentage": 75.55, "elapsed_time": "2:55:08", "remaining_time": "0:56:40"}
116
+ {"current_steps": 830, "total_steps": 1092, "loss": 0.8265, "lr": 3.3118644816848574e-05, "epoch": 2.28021978021978, "percentage": 76.01, "elapsed_time": "2:55:50", "remaining_time": "0:55:30"}
117
+ {"current_steps": 840, "total_steps": 1092, "loss": 0.837, "lr": 3.077490786744562e-05, "epoch": 2.3076923076923075, "percentage": 76.92, "elapsed_time": "2:57:05", "remaining_time": "0:53:07"}
118
+ {"current_steps": 850, "total_steps": 1092, "loss": 0.8328, "lr": 2.8502014950143373e-05, "epoch": 2.3351648351648353, "percentage": 77.84, "elapsed_time": "2:58:23", "remaining_time": "0:50:47"}
119
+ {"current_steps": 850, "total_steps": 1092, "eval_loss": 0.9368348121643066, "epoch": 2.3351648351648353, "percentage": 77.84, "elapsed_time": "3:00:23", "remaining_time": "0:51:21"}
120
+ {"current_steps": 860, "total_steps": 1092, "loss": 0.8202, "lr": 2.6302292113110637e-05, "epoch": 2.3626373626373627, "percentage": 78.75, "elapsed_time": "3:01:40", "remaining_time": "0:49:00"}
121
+ {"current_steps": 870, "total_steps": 1092, "loss": 0.8284, "lr": 2.4177990523236216e-05, "epoch": 2.39010989010989, "percentage": 79.67, "elapsed_time": "3:02:59", "remaining_time": "0:46:41"}
122
+ {"current_steps": 875, "total_steps": 1092, "eval_loss": 0.9366135597229004, "epoch": 2.4038461538461537, "percentage": 80.13, "elapsed_time": "3:05:39", "remaining_time": "0:46:02"}
123
+ {"current_steps": 880, "total_steps": 1092, "loss": 0.8287, "lr": 2.213128416231468e-05, "epoch": 2.4175824175824174, "percentage": 80.59, "elapsed_time": "3:06:18", "remaining_time": "0:44:52"}
124
+ {"current_steps": 890, "total_steps": 1092, "loss": 0.8298, "lr": 2.0164267602222586e-05, "epoch": 2.4450549450549453, "percentage": 81.5, "elapsed_time": "3:07:39", "remaining_time": "0:42:35"}
125
+ {"current_steps": 900, "total_steps": 1092, "loss": 0.8258, "lr": 1.827895386136166e-05, "epoch": 2.4725274725274726, "percentage": 82.42, "elapsed_time": "3:09:00", "remaining_time": "0:40:19"}
126
+ {"current_steps": 900, "total_steps": 1092, "eval_loss": 0.9355611801147461, "epoch": 2.4725274725274726, "percentage": 82.42, "elapsed_time": "3:11:00", "remaining_time": "0:40:44"}
127
+ {"current_steps": 910, "total_steps": 1092, "loss": 0.8428, "lr": 1.647727234456279e-05, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "3:12:19", "remaining_time": "0:38:27"}
128
+ {"current_steps": 920, "total_steps": 1092, "loss": 0.825, "lr": 1.4761066868558914e-05, "epoch": 2.5274725274725274, "percentage": 84.25, "elapsed_time": "3:13:37", "remaining_time": "0:36:11"}
129
+ {"current_steps": 925, "total_steps": 1092, "eval_loss": 0.9347633123397827, "epoch": 2.541208791208791, "percentage": 84.71, "elapsed_time": "3:16:18", "remaining_time": "0:35:26"}
130
+ {"current_steps": 930, "total_steps": 1092, "loss": 0.8207, "lr": 1.3132093775047615e-05, "epoch": 2.5549450549450547, "percentage": 85.16, "elapsed_time": "3:16:56", "remaining_time": "0:34:18"}
131
+ {"current_steps": 940, "total_steps": 1092, "loss": 0.8388, "lr": 1.1592020133274639e-05, "epoch": 2.5824175824175826, "percentage": 86.08, "elapsed_time": "3:18:15", "remaining_time": "0:32:03"}
132
+ {"current_steps": 950, "total_steps": 1092, "loss": 0.8259, "lr": 1.0142422033977505e-05, "epoch": 2.60989010989011, "percentage": 87.0, "elapsed_time": "3:19:36", "remaining_time": "0:29:50"}
133
+ {"current_steps": 950, "total_steps": 1092, "eval_loss": 0.9338229298591614, "epoch": 2.60989010989011, "percentage": 87.0, "elapsed_time": "3:21:36", "remaining_time": "0:30:08"}
134
+ {"current_steps": 960, "total_steps": 1092, "loss": 0.821, "lr": 8.784782976435424e-06, "epoch": 2.6373626373626373, "percentage": 87.91, "elapsed_time": "3:22:56", "remaining_time": "0:27:54"}
135
+ {"current_steps": 970, "total_steps": 1092, "loss": 0.8225, "lr": 7.520492350275876e-06, "epoch": 2.6648351648351647, "percentage": 88.83, "elapsed_time": "3:24:17", "remaining_time": "0:25:41"}
136
+ {"current_steps": 975, "total_steps": 1092, "eval_loss": 0.9337417483329773, "epoch": 2.678571428571429, "percentage": 89.29, "elapsed_time": "3:26:58", "remaining_time": "0:24:50"}
137
+ {"current_steps": 980, "total_steps": 1092, "loss": 0.8286, "lr": 6.350844013592061e-06, "epoch": 2.6923076923076925, "percentage": 89.74, "elapsed_time": "3:27:36", "remaining_time": "0:23:43"}
138
+ {"current_steps": 990, "total_steps": 1092, "loss": 0.8372, "lr": 5.277034968825667e-06, "epoch": 2.71978021978022, "percentage": 90.66, "elapsed_time": "3:28:57", "remaining_time": "0:21:31"}
139
+ {"current_steps": 1000, "total_steps": 1092, "loss": 0.8226, "lr": 4.3001641377707125e-06, "epoch": 2.7472527472527473, "percentage": 91.58, "elapsed_time": "3:30:16", "remaining_time": "0:19:20"}
140
+ {"current_steps": 1000, "total_steps": 1092, "eval_loss": 0.9329955577850342, "epoch": 2.7472527472527473, "percentage": 91.58, "elapsed_time": "3:32:16", "remaining_time": "0:19:31"}
141
+ {"current_steps": 1010, "total_steps": 1092, "loss": 0.8128, "lr": 3.4212312369516497e-06, "epoch": 2.7747252747252746, "percentage": 92.49, "elapsed_time": "3:33:37", "remaining_time": "0:17:20"}
142
+ {"current_steps": 1020, "total_steps": 1092, "loss": 0.8239, "lr": 2.6411357545269577e-06, "epoch": 2.802197802197802, "percentage": 93.41, "elapsed_time": "3:34:57", "remaining_time": "0:15:10"}
143
+ {"current_steps": 1025, "total_steps": 1092, "eval_loss": 0.9329585433006287, "epoch": 2.8159340659340657, "percentage": 93.86, "elapsed_time": "3:37:39", "remaining_time": "0:14:13"}
144
+ {"current_steps": 1030, "total_steps": 1092, "loss": 0.8437, "lr": 1.960676029764874e-06, "epoch": 2.82967032967033, "percentage": 94.32, "elapsed_time": "3:38:18", "remaining_time": "0:13:08"}
145
+ {"current_steps": 1040, "total_steps": 1092, "loss": 0.8104, "lr": 1.3805484360337906e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "3:39:39", "remaining_time": "0:10:58"}
146
+ {"current_steps": 1050, "total_steps": 1092, "loss": 0.8169, "lr": 9.013466681429994e-07, "epoch": 2.8846153846153846, "percentage": 96.15, "elapsed_time": "3:40:58", "remaining_time": "0:08:50"}
147
+ {"current_steps": 1050, "total_steps": 1092, "eval_loss": 0.9328103065490723, "epoch": 2.8846153846153846, "percentage": 96.15, "elapsed_time": "3:42:58", "remaining_time": "0:08:55"}
148
+ {"current_steps": 1060, "total_steps": 1092, "loss": 0.8123, "lr": 5.235611347634172e-07, "epoch": 2.912087912087912, "percentage": 97.07, "elapsed_time": "3:44:18", "remaining_time": "0:06:46"}
149
+ {"current_steps": 1070, "total_steps": 1092, "loss": 0.8175, "lr": 2.4757845654992397e-07, "epoch": 2.9395604395604398, "percentage": 97.99, "elapsed_time": "3:45:37", "remaining_time": "0:04:38"}
150
+ {"current_steps": 1075, "total_steps": 1092, "eval_loss": 0.9328309893608093, "epoch": 2.9532967032967035, "percentage": 98.44, "elapsed_time": "3:48:18", "remaining_time": "0:03:36"}
151
+ {"current_steps": 1080, "total_steps": 1092, "loss": 0.8333, "lr": 7.368107047894812e-08, "epoch": 2.967032967032967, "percentage": 98.9, "elapsed_time": "3:48:58", "remaining_time": "0:02:32"}
152
+ {"current_steps": 1090, "total_steps": 1092, "loss": 0.8162, "lr": 2.046940806244013e-09, "epoch": 2.9945054945054945, "percentage": 99.82, "elapsed_time": "3:50:18", "remaining_time": "0:00:25"}
153
+ {"current_steps": 1092, "total_steps": 1092, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:50:33", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,1149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 25,
6
+ "global_step": 1092,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.027472527472527472,
13
+ "grad_norm": 0.30766117572784424,
14
+ "learning_rate": 1.8181818181818182e-05,
15
+ "loss": 1.3096,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.054945054945054944,
20
+ "grad_norm": 0.27449363470077515,
21
+ "learning_rate": 3.6363636363636364e-05,
22
+ "loss": 1.3065,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06868131868131869,
27
+ "eval_loss": 1.2722554206848145,
28
+ "eval_runtime": 120.0918,
29
+ "eval_samples_per_second": 43.1,
30
+ "eval_steps_per_second": 2.698,
31
+ "step": 25
32
+ },
33
+ {
34
+ "epoch": 0.08241758241758242,
35
+ "grad_norm": 0.29537826776504517,
36
+ "learning_rate": 5.4545454545454546e-05,
37
+ "loss": 1.2378,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 0.10989010989010989,
42
+ "grad_norm": 0.25553378462791443,
43
+ "learning_rate": 7.272727272727273e-05,
44
+ "loss": 1.1986,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 0.13736263736263737,
49
+ "grad_norm": 0.27968353033065796,
50
+ "learning_rate": 9.090909090909092e-05,
51
+ "loss": 1.165,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 0.13736263736263737,
56
+ "eval_loss": 1.1781517267227173,
57
+ "eval_runtime": 120.0866,
58
+ "eval_samples_per_second": 43.102,
59
+ "eval_steps_per_second": 2.698,
60
+ "step": 50
61
+ },
62
+ {
63
+ "epoch": 0.16483516483516483,
64
+ "grad_norm": 0.3039194643497467,
65
+ "learning_rate": 0.00010909090909090909,
66
+ "loss": 1.1649,
67
+ "step": 60
68
+ },
69
+ {
70
+ "epoch": 0.19230769230769232,
71
+ "grad_norm": 0.2939436435699463,
72
+ "learning_rate": 0.00012727272727272728,
73
+ "loss": 1.1199,
74
+ "step": 70
75
+ },
76
+ {
77
+ "epoch": 0.20604395604395603,
78
+ "eval_loss": 1.1345776319503784,
79
+ "eval_runtime": 120.0914,
80
+ "eval_samples_per_second": 43.1,
81
+ "eval_steps_per_second": 2.698,
82
+ "step": 75
83
+ },
84
+ {
85
+ "epoch": 0.21978021978021978,
86
+ "grad_norm": 0.31279808282852173,
87
+ "learning_rate": 0.00014545454545454546,
88
+ "loss": 1.1184,
89
+ "step": 80
90
+ },
91
+ {
92
+ "epoch": 0.24725274725274726,
93
+ "grad_norm": 0.3539753556251526,
94
+ "learning_rate": 0.00016363636363636366,
95
+ "loss": 1.0936,
96
+ "step": 90
97
+ },
98
+ {
99
+ "epoch": 0.27472527472527475,
100
+ "grad_norm": 0.32932248711586,
101
+ "learning_rate": 0.00018181818181818183,
102
+ "loss": 1.0818,
103
+ "step": 100
104
+ },
105
+ {
106
+ "epoch": 0.27472527472527475,
107
+ "eval_loss": 1.112221598625183,
108
+ "eval_runtime": 120.0873,
109
+ "eval_samples_per_second": 43.102,
110
+ "eval_steps_per_second": 2.698,
111
+ "step": 100
112
+ },
113
+ {
114
+ "epoch": 0.3021978021978022,
115
+ "grad_norm": 0.3215370178222656,
116
+ "learning_rate": 0.0002,
117
+ "loss": 1.0894,
118
+ "step": 110
119
+ },
120
+ {
121
+ "epoch": 0.32967032967032966,
122
+ "grad_norm": 0.3059958517551422,
123
+ "learning_rate": 0.00019994883066969053,
124
+ "loss": 1.0814,
125
+ "step": 120
126
+ },
127
+ {
128
+ "epoch": 0.3434065934065934,
129
+ "eval_loss": 1.0942074060440063,
130
+ "eval_runtime": 120.096,
131
+ "eval_samples_per_second": 43.099,
132
+ "eval_steps_per_second": 2.698,
133
+ "step": 125
134
+ },
135
+ {
136
+ "epoch": 0.35714285714285715,
137
+ "grad_norm": 0.3109903037548065,
138
+ "learning_rate": 0.00019979537504476944,
139
+ "loss": 1.0766,
140
+ "step": 130
141
+ },
142
+ {
143
+ "epoch": 0.38461538461538464,
144
+ "grad_norm": 0.32679346203804016,
145
+ "learning_rate": 0.00019953979016966788,
146
+ "loss": 1.0663,
147
+ "step": 140
148
+ },
149
+ {
150
+ "epoch": 0.41208791208791207,
151
+ "grad_norm": 0.32413366436958313,
152
+ "learning_rate": 0.0001991823376065238,
153
+ "loss": 1.0614,
154
+ "step": 150
155
+ },
156
+ {
157
+ "epoch": 0.41208791208791207,
158
+ "eval_loss": 1.0805188417434692,
159
+ "eval_runtime": 120.1022,
160
+ "eval_samples_per_second": 43.097,
161
+ "eval_steps_per_second": 2.698,
162
+ "step": 150
163
+ },
164
+ {
165
+ "epoch": 0.43956043956043955,
166
+ "grad_norm": 0.27476972341537476,
167
+ "learning_rate": 0.00019872338316750265,
168
+ "loss": 1.0531,
169
+ "step": 160
170
+ },
171
+ {
172
+ "epoch": 0.46703296703296704,
173
+ "grad_norm": 0.2732694447040558,
174
+ "learning_rate": 0.00019816339654043022,
175
+ "loss": 1.0552,
176
+ "step": 170
177
+ },
178
+ {
179
+ "epoch": 0.4807692307692308,
180
+ "eval_loss": 1.0678906440734863,
181
+ "eval_runtime": 120.1049,
182
+ "eval_samples_per_second": 43.096,
183
+ "eval_steps_per_second": 2.698,
184
+ "step": 175
185
+ },
186
+ {
187
+ "epoch": 0.4945054945054945,
188
+ "grad_norm": 0.31261274218559265,
189
+ "learning_rate": 0.00019750295080812023,
190
+ "loss": 1.0707,
191
+ "step": 180
192
+ },
193
+ {
194
+ "epoch": 0.521978021978022,
195
+ "grad_norm": 0.31733250617980957,
196
+ "learning_rate": 0.0001967427218618893,
197
+ "loss": 1.0363,
198
+ "step": 190
199
+ },
200
+ {
201
+ "epoch": 0.5494505494505495,
202
+ "grad_norm": 0.31759801506996155,
203
+ "learning_rate": 0.0001958834877098586,
204
+ "loss": 1.0519,
205
+ "step": 200
206
+ },
207
+ {
208
+ "epoch": 0.5494505494505495,
209
+ "eval_loss": 1.0573759078979492,
210
+ "eval_runtime": 120.091,
211
+ "eval_samples_per_second": 43.101,
212
+ "eval_steps_per_second": 2.698,
213
+ "step": 200
214
+ },
215
+ {
216
+ "epoch": 0.5769230769230769,
217
+ "grad_norm": 0.2911220192909241,
218
+ "learning_rate": 0.00019492612768075092,
219
+ "loss": 1.0559,
220
+ "step": 210
221
+ },
222
+ {
223
+ "epoch": 0.6043956043956044,
224
+ "grad_norm": 0.2815748155117035,
225
+ "learning_rate": 0.0001938716215239974,
226
+ "loss": 1.0568,
227
+ "step": 220
228
+ },
229
+ {
230
+ "epoch": 0.6181318681318682,
231
+ "eval_loss": 1.046871304512024,
232
+ "eval_runtime": 120.0941,
233
+ "eval_samples_per_second": 43.1,
234
+ "eval_steps_per_second": 2.698,
235
+ "step": 225
236
+ },
237
+ {
238
+ "epoch": 0.6318681318681318,
239
+ "grad_norm": 0.2947179079055786,
240
+ "learning_rate": 0.00019272104840707487,
241
+ "loss": 1.0414,
242
+ "step": 230
243
+ },
244
+ {
245
+ "epoch": 0.6593406593406593,
246
+ "grad_norm": 0.2895919680595398,
247
+ "learning_rate": 0.00019147558581110078,
248
+ "loss": 1.0345,
249
+ "step": 240
250
+ },
251
+ {
252
+ "epoch": 0.6868131868131868,
253
+ "grad_norm": 0.2915903329849243,
254
+ "learning_rate": 0.00019013650832581423,
255
+ "loss": 1.0361,
256
+ "step": 250
257
+ },
258
+ {
259
+ "epoch": 0.6868131868131868,
260
+ "eval_loss": 1.0375587940216064,
261
+ "eval_runtime": 120.0823,
262
+ "eval_samples_per_second": 43.104,
263
+ "eval_steps_per_second": 2.698,
264
+ "step": 250
265
+ },
266
+ {
267
+ "epoch": 0.7142857142857143,
268
+ "grad_norm": 0.30468592047691345,
269
+ "learning_rate": 0.0001887051863451784,
270
+ "loss": 1.0385,
271
+ "step": 260
272
+ },
273
+ {
274
+ "epoch": 0.7417582417582418,
275
+ "grad_norm": 0.3248215913772583,
276
+ "learning_rate": 0.00018718308466493744,
277
+ "loss": 1.0153,
278
+ "step": 270
279
+ },
280
+ {
281
+ "epoch": 0.7554945054945055,
282
+ "eval_loss": 1.0293300151824951,
283
+ "eval_runtime": 120.0939,
284
+ "eval_samples_per_second": 43.1,
285
+ "eval_steps_per_second": 2.698,
286
+ "step": 275
287
+ },
288
+ {
289
+ "epoch": 0.7692307692307693,
290
+ "grad_norm": 0.29462930560112,
291
+ "learning_rate": 0.00018557176098356405,
292
+ "loss": 1.0185,
293
+ "step": 280
294
+ },
295
+ {
296
+ "epoch": 0.7967032967032966,
297
+ "grad_norm": 0.2817062437534332,
298
+ "learning_rate": 0.00018387286430813208,
299
+ "loss": 1.0088,
300
+ "step": 290
301
+ },
302
+ {
303
+ "epoch": 0.8241758241758241,
304
+ "grad_norm": 0.3126353621482849,
305
+ "learning_rate": 0.00018208813326674444,
306
+ "loss": 1.0128,
307
+ "step": 300
308
+ },
309
+ {
310
+ "epoch": 0.8241758241758241,
311
+ "eval_loss": 1.020519733428955,
312
+ "eval_runtime": 120.0922,
313
+ "eval_samples_per_second": 43.1,
314
+ "eval_steps_per_second": 2.698,
315
+ "step": 300
316
+ },
317
+ {
318
+ "epoch": 0.8516483516483516,
319
+ "grad_norm": 0.31813979148864746,
320
+ "learning_rate": 0.00018021939432924454,
321
+ "loss": 1.0061,
322
+ "step": 310
323
+ },
324
+ {
325
+ "epoch": 0.8791208791208791,
326
+ "grad_norm": 0.3094867467880249,
327
+ "learning_rate": 0.00017826855993803147,
328
+ "loss": 1.0064,
329
+ "step": 320
330
+ },
331
+ {
332
+ "epoch": 0.8928571428571429,
333
+ "eval_loss": 1.0121577978134155,
334
+ "eval_runtime": 120.1095,
335
+ "eval_samples_per_second": 43.094,
336
+ "eval_steps_per_second": 2.698,
337
+ "step": 325
338
+ },
339
+ {
340
+ "epoch": 0.9065934065934066,
341
+ "grad_norm": 0.3104652464389801,
342
+ "learning_rate": 0.00017623762655089207,
343
+ "loss": 0.988,
344
+ "step": 330
345
+ },
346
+ {
347
+ "epoch": 0.9340659340659341,
348
+ "grad_norm": 0.2933966815471649,
349
+ "learning_rate": 0.00017412867259785286,
350
+ "loss": 1.0015,
351
+ "step": 340
352
+ },
353
+ {
354
+ "epoch": 0.9615384615384616,
355
+ "grad_norm": 0.31546550989151,
356
+ "learning_rate": 0.00017194385635414244,
357
+ "loss": 0.995,
358
+ "step": 350
359
+ },
360
+ {
361
+ "epoch": 0.9615384615384616,
362
+ "eval_loss": 1.0048952102661133,
363
+ "eval_runtime": 120.0899,
364
+ "eval_samples_per_second": 43.101,
365
+ "eval_steps_per_second": 2.698,
366
+ "step": 350
367
+ },
368
+ {
369
+ "epoch": 0.989010989010989,
370
+ "grad_norm": 0.3239256739616394,
371
+ "learning_rate": 0.00016968541373144156,
372
+ "loss": 0.9934,
373
+ "step": 360
374
+ },
375
+ {
376
+ "epoch": 1.0164835164835164,
377
+ "grad_norm": 0.3171522617340088,
378
+ "learning_rate": 0.00016735565598968114,
379
+ "loss": 0.9443,
380
+ "step": 370
381
+ },
382
+ {
383
+ "epoch": 1.0302197802197801,
384
+ "eval_loss": 0.9992949962615967,
385
+ "eval_runtime": 120.0895,
386
+ "eval_samples_per_second": 43.101,
387
+ "eval_steps_per_second": 2.698,
388
+ "step": 375
389
+ },
390
+ {
391
+ "epoch": 1.043956043956044,
392
+ "grad_norm": 0.32471972703933716,
393
+ "learning_rate": 0.0001649569673717298,
394
+ "loss": 0.9499,
395
+ "step": 380
396
+ },
397
+ {
398
+ "epoch": 1.0714285714285714,
399
+ "grad_norm": 0.3332098126411438,
400
+ "learning_rate": 0.0001624918026633916,
401
+ "loss": 0.9218,
402
+ "step": 390
403
+ },
404
+ {
405
+ "epoch": 1.098901098901099,
406
+ "grad_norm": 0.30731338262557983,
407
+ "learning_rate": 0.00015996268468121102,
408
+ "loss": 0.9393,
409
+ "step": 400
410
+ },
411
+ {
412
+ "epoch": 1.098901098901099,
413
+ "eval_loss": 0.9930510520935059,
414
+ "eval_runtime": 120.092,
415
+ "eval_samples_per_second": 43.1,
416
+ "eval_steps_per_second": 2.698,
417
+ "step": 400
418
+ },
419
+ {
420
+ "epoch": 1.1263736263736264,
421
+ "grad_norm": 0.3216601014137268,
422
+ "learning_rate": 0.00015737220169065655,
423
+ "loss": 0.9317,
424
+ "step": 410
425
+ },
426
+ {
427
+ "epoch": 1.1538461538461537,
428
+ "grad_norm": 0.3047005534172058,
429
+ "learning_rate": 0.00015472300475732426,
430
+ "loss": 0.9223,
431
+ "step": 420
432
+ },
433
+ {
434
+ "epoch": 1.1675824175824177,
435
+ "eval_loss": 0.9878760576248169,
436
+ "eval_runtime": 120.095,
437
+ "eval_samples_per_second": 43.099,
438
+ "eval_steps_per_second": 2.698,
439
+ "step": 425
440
+ },
441
+ {
442
+ "epoch": 1.1813186813186813,
443
+ "grad_norm": 0.3375983238220215,
444
+ "learning_rate": 0.0001520178050338729,
445
+ "loss": 0.9407,
446
+ "step": 430
447
+ },
448
+ {
449
+ "epoch": 1.2087912087912087,
450
+ "grad_norm": 0.35231560468673706,
451
+ "learning_rate": 0.00014925937098546652,
452
+ "loss": 0.9416,
453
+ "step": 440
454
+ },
455
+ {
456
+ "epoch": 1.2362637362637363,
457
+ "grad_norm": 0.32709598541259766,
458
+ "learning_rate": 0.00014645052555656431,
459
+ "loss": 0.9248,
460
+ "step": 450
461
+ },
462
+ {
463
+ "epoch": 1.2362637362637363,
464
+ "eval_loss": 0.9815701246261597,
465
+ "eval_runtime": 120.0756,
466
+ "eval_samples_per_second": 43.106,
467
+ "eval_steps_per_second": 2.698,
468
+ "step": 450
469
+ },
470
+ {
471
+ "epoch": 1.2637362637362637,
472
+ "grad_norm": 0.34425875544548035,
473
+ "learning_rate": 0.00014359414328195703,
474
+ "loss": 0.9344,
475
+ "step": 460
476
+ },
477
+ {
478
+ "epoch": 1.2912087912087913,
479
+ "grad_norm": 0.3243270814418793,
480
+ "learning_rate": 0.00014069314734500675,
481
+ "loss": 0.9133,
482
+ "step": 470
483
+ },
484
+ {
485
+ "epoch": 1.304945054945055,
486
+ "eval_loss": 0.975848913192749,
487
+ "eval_runtime": 120.0935,
488
+ "eval_samples_per_second": 43.1,
489
+ "eval_steps_per_second": 2.698,
490
+ "step": 475
491
+ },
492
+ {
493
+ "epoch": 1.3186813186813187,
494
+ "grad_norm": 0.3632093667984009,
495
+ "learning_rate": 0.00013775050658609988,
496
+ "loss": 0.9171,
497
+ "step": 480
498
+ },
499
+ {
500
+ "epoch": 1.3461538461538463,
501
+ "grad_norm": 0.3164936900138855,
502
+ "learning_rate": 0.0001347692324643759,
503
+ "loss": 0.9181,
504
+ "step": 490
505
+ },
506
+ {
507
+ "epoch": 1.3736263736263736,
508
+ "grad_norm": 0.3294355869293213,
509
+ "learning_rate": 0.00013175237597584045,
510
+ "loss": 0.9271,
511
+ "step": 500
512
+ },
513
+ {
514
+ "epoch": 1.3736263736263736,
515
+ "eval_loss": 0.9721202254295349,
516
+ "eval_runtime": 120.1002,
517
+ "eval_samples_per_second": 43.097,
518
+ "eval_steps_per_second": 2.698,
519
+ "step": 500
520
+ },
521
+ {
522
+ "epoch": 1.401098901098901,
523
+ "grad_norm": 0.36658838391304016,
524
+ "learning_rate": 0.00012870302453101657,
525
+ "loss": 0.9124,
526
+ "step": 510
527
+ },
528
+ {
529
+ "epoch": 1.4285714285714286,
530
+ "grad_norm": 0.327544242143631,
531
+ "learning_rate": 0.0001256242987953306,
532
+ "loss": 0.912,
533
+ "step": 520
534
+ },
535
+ {
536
+ "epoch": 1.4423076923076923,
537
+ "eval_loss": 0.9657136797904968,
538
+ "eval_runtime": 120.1092,
539
+ "eval_samples_per_second": 43.094,
540
+ "eval_steps_per_second": 2.698,
541
+ "step": 525
542
+ },
543
+ {
544
+ "epoch": 1.456043956043956,
545
+ "grad_norm": 0.35890278220176697,
546
+ "learning_rate": 0.00012251934949546447,
547
+ "loss": 0.9224,
548
+ "step": 530
549
+ },
550
+ {
551
+ "epoch": 1.4835164835164836,
552
+ "grad_norm": 0.3336729109287262,
553
+ "learning_rate": 0.00011939135419494456,
554
+ "loss": 0.9141,
555
+ "step": 540
556
+ },
557
+ {
558
+ "epoch": 1.510989010989011,
559
+ "grad_norm": 0.3688167631626129,
560
+ "learning_rate": 0.00011624351404226572,
561
+ "loss": 0.9074,
562
+ "step": 550
563
+ },
564
+ {
565
+ "epoch": 1.510989010989011,
566
+ "eval_loss": 0.9616743326187134,
567
+ "eval_runtime": 120.0995,
568
+ "eval_samples_per_second": 43.098,
569
+ "eval_steps_per_second": 2.698,
570
+ "step": 550
571
+ },
572
+ {
573
+ "epoch": 1.5384615384615383,
574
+ "grad_norm": 0.3265407681465149,
575
+ "learning_rate": 0.00011307905049487855,
576
+ "loss": 0.9093,
577
+ "step": 560
578
+ },
579
+ {
580
+ "epoch": 1.565934065934066,
581
+ "grad_norm": 0.34465736150741577,
582
+ "learning_rate": 0.00010990120202239324,
583
+ "loss": 0.9106,
584
+ "step": 570
585
+ },
586
+ {
587
+ "epoch": 1.5796703296703298,
588
+ "eval_loss": 0.9570587277412415,
589
+ "eval_runtime": 120.0802,
590
+ "eval_samples_per_second": 43.105,
591
+ "eval_steps_per_second": 2.698,
592
+ "step": 575
593
+ },
594
+ {
595
+ "epoch": 1.5934065934065935,
596
+ "grad_norm": 0.34950023889541626,
597
+ "learning_rate": 0.00010671322079237307,
598
+ "loss": 0.9229,
599
+ "step": 580
600
+ },
601
+ {
602
+ "epoch": 1.620879120879121,
603
+ "grad_norm": 0.34105509519577026,
604
+ "learning_rate": 0.00010351836934210957,
605
+ "loss": 0.913,
606
+ "step": 590
607
+ },
608
+ {
609
+ "epoch": 1.6483516483516483,
610
+ "grad_norm": 0.34221306443214417,
611
+ "learning_rate": 0.00010031991723978574,
612
+ "loss": 0.9001,
613
+ "step": 600
614
+ },
615
+ {
616
+ "epoch": 1.6483516483516483,
617
+ "eval_loss": 0.953257143497467,
618
+ "eval_runtime": 120.1011,
619
+ "eval_samples_per_second": 43.097,
620
+ "eval_steps_per_second": 2.698,
621
+ "step": 600
622
+ },
623
+ {
624
+ "epoch": 1.6758241758241759,
625
+ "grad_norm": 0.3518592119216919,
626
+ "learning_rate": 9.712113773844361e-05,
627
+ "loss": 0.9051,
628
+ "step": 610
629
+ },
630
+ {
631
+ "epoch": 1.7032967032967035,
632
+ "grad_norm": 0.32816919684410095,
633
+ "learning_rate": 9.3925304426181e-05,
634
+ "loss": 0.9098,
635
+ "step": 620
636
+ },
637
+ {
638
+ "epoch": 1.7170329670329672,
639
+ "eval_loss": 0.9497827887535095,
640
+ "eval_runtime": 120.0995,
641
+ "eval_samples_per_second": 43.098,
642
+ "eval_steps_per_second": 2.698,
643
+ "step": 625
644
+ },
645
+ {
646
+ "epoch": 1.7307692307692308,
647
+ "grad_norm": 0.3299916982650757,
648
+ "learning_rate": 9.073568787600539e-05,
649
+ "loss": 0.9174,
650
+ "step": 630
651
+ },
652
+ {
653
+ "epoch": 1.7582417582417582,
654
+ "grad_norm": 0.3412216305732727,
655
+ "learning_rate": 8.755555229877294e-05,
656
+ "loss": 0.9035,
657
+ "step": 640
658
+ },
659
+ {
660
+ "epoch": 1.7857142857142856,
661
+ "grad_norm": 0.3167659044265747,
662
+ "learning_rate": 8.438815220263941e-05,
663
+ "loss": 0.891,
664
+ "step": 650
665
+ },
666
+ {
667
+ "epoch": 1.7857142857142856,
668
+ "eval_loss": 0.9457467198371887,
669
+ "eval_runtime": 120.0762,
670
+ "eval_samples_per_second": 43.106,
671
+ "eval_steps_per_second": 2.698,
672
+ "step": 650
673
+ },
674
+ {
675
+ "epoch": 1.8131868131868132,
676
+ "grad_norm": 0.338913232088089,
677
+ "learning_rate": 8.123672906243955e-05,
678
+ "loss": 0.9033,
679
+ "step": 660
680
+ },
681
+ {
682
+ "epoch": 1.8406593406593408,
683
+ "grad_norm": 0.3298161029815674,
684
+ "learning_rate": 7.810450800240549e-05,
685
+ "loss": 0.8877,
686
+ "step": 670
687
+ },
688
+ {
689
+ "epoch": 1.8543956043956045,
690
+ "eval_loss": 0.9423750638961792,
691
+ "eval_runtime": 120.1002,
692
+ "eval_samples_per_second": 43.097,
693
+ "eval_steps_per_second": 2.698,
694
+ "step": 675
695
+ },
696
+ {
697
+ "epoch": 1.8681318681318682,
698
+ "grad_norm": 0.334606409072876,
699
+ "learning_rate": 7.499469449561769e-05,
700
+ "loss": 0.8988,
701
+ "step": 680
702
+ },
703
+ {
704
+ "epoch": 1.8956043956043955,
705
+ "grad_norm": 0.34457749128341675,
706
+ "learning_rate": 7.191047108356672e-05,
707
+ "loss": 0.9191,
708
+ "step": 690
709
+ },
710
+ {
711
+ "epoch": 1.9230769230769231,
712
+ "grad_norm": 0.3466154634952545,
713
+ "learning_rate": 6.885499411918304e-05,
714
+ "loss": 0.9,
715
+ "step": 700
716
+ },
717
+ {
718
+ "epoch": 1.9230769230769231,
719
+ "eval_loss": 0.93968266248703,
720
+ "eval_runtime": 120.1019,
721
+ "eval_samples_per_second": 43.097,
722
+ "eval_steps_per_second": 2.698,
723
+ "step": 700
724
+ },
725
+ {
726
+ "epoch": 1.9505494505494505,
727
+ "grad_norm": 0.3775443136692047,
728
+ "learning_rate": 6.583139053666745e-05,
729
+ "loss": 0.8944,
730
+ "step": 710
731
+ },
732
+ {
733
+ "epoch": 1.978021978021978,
734
+ "grad_norm": 0.34448450803756714,
735
+ "learning_rate": 6.284275465142874e-05,
736
+ "loss": 0.8841,
737
+ "step": 720
738
+ },
739
+ {
740
+ "epoch": 1.9917582417582418,
741
+ "eval_loss": 0.9374962449073792,
742
+ "eval_runtime": 120.0877,
743
+ "eval_samples_per_second": 43.102,
744
+ "eval_steps_per_second": 2.698,
745
+ "step": 725
746
+ },
747
+ {
748
+ "epoch": 2.0054945054945055,
749
+ "grad_norm": 0.3557426333427429,
750
+ "learning_rate": 5.989214499340267e-05,
751
+ "loss": 0.8657,
752
+ "step": 730
753
+ },
754
+ {
755
+ "epoch": 2.032967032967033,
756
+ "grad_norm": 0.3379885256290436,
757
+ "learning_rate": 5.6982581176993335e-05,
758
+ "loss": 0.8331,
759
+ "step": 740
760
+ },
761
+ {
762
+ "epoch": 2.0604395604395602,
763
+ "grad_norm": 0.34215247631073,
764
+ "learning_rate": 5.4117040810840246e-05,
765
+ "loss": 0.828,
766
+ "step": 750
767
+ },
768
+ {
769
+ "epoch": 2.0604395604395602,
770
+ "eval_loss": 0.9431478381156921,
771
+ "eval_runtime": 120.0958,
772
+ "eval_samples_per_second": 43.099,
773
+ "eval_steps_per_second": 2.698,
774
+ "step": 750
775
+ },
776
+ {
777
+ "epoch": 2.087912087912088,
778
+ "grad_norm": 0.360781192779541,
779
+ "learning_rate": 5.129845645057372e-05,
780
+ "loss": 0.8357,
781
+ "step": 760
782
+ },
783
+ {
784
+ "epoch": 2.1153846153846154,
785
+ "grad_norm": 0.3744048774242401,
786
+ "learning_rate": 4.8529712597676426e-05,
787
+ "loss": 0.8232,
788
+ "step": 770
789
+ },
790
+ {
791
+ "epoch": 2.129120879120879,
792
+ "eval_loss": 0.940683901309967,
793
+ "eval_runtime": 120.0962,
794
+ "eval_samples_per_second": 43.099,
795
+ "eval_steps_per_second": 2.698,
796
+ "step": 775
797
+ },
798
+ {
799
+ "epoch": 2.142857142857143,
800
+ "grad_norm": 0.3741873502731323,
801
+ "learning_rate": 4.581364274752338e-05,
802
+ "loss": 0.8351,
803
+ "step": 780
804
+ },
805
+ {
806
+ "epoch": 2.17032967032967,
807
+ "grad_norm": 0.37572070956230164,
808
+ "learning_rate": 4.315302648962066e-05,
809
+ "loss": 0.8171,
810
+ "step": 790
811
+ },
812
+ {
813
+ "epoch": 2.197802197802198,
814
+ "grad_norm": 0.365060418844223,
815
+ "learning_rate": 4.055058666301087e-05,
816
+ "loss": 0.8299,
817
+ "step": 800
818
+ },
819
+ {
820
+ "epoch": 2.197802197802198,
821
+ "eval_loss": 0.9400618672370911,
822
+ "eval_runtime": 120.1003,
823
+ "eval_samples_per_second": 43.097,
824
+ "eval_steps_per_second": 2.698,
825
+ "step": 800
826
+ },
827
+ {
828
+ "epoch": 2.2252747252747254,
829
+ "grad_norm": 0.3707464933395386,
830
+ "learning_rate": 3.800898656975599e-05,
831
+ "loss": 0.8303,
832
+ "step": 810
833
+ },
834
+ {
835
+ "epoch": 2.2527472527472527,
836
+ "grad_norm": 0.3521062433719635,
837
+ "learning_rate": 3.553082724934973e-05,
838
+ "loss": 0.8378,
839
+ "step": 820
840
+ },
841
+ {
842
+ "epoch": 2.2664835164835164,
843
+ "eval_loss": 0.9390351176261902,
844
+ "eval_runtime": 120.0755,
845
+ "eval_samples_per_second": 43.106,
846
+ "eval_steps_per_second": 2.698,
847
+ "step": 825
848
+ },
849
+ {
850
+ "epoch": 2.28021978021978,
851
+ "grad_norm": 0.3930257260799408,
852
+ "learning_rate": 3.3118644816848574e-05,
853
+ "loss": 0.8265,
854
+ "step": 830
855
+ },
856
+ {
857
+ "epoch": 2.3076923076923075,
858
+ "grad_norm": 0.37315958738327026,
859
+ "learning_rate": 3.077490786744562e-05,
860
+ "loss": 0.837,
861
+ "step": 840
862
+ },
863
+ {
864
+ "epoch": 2.3351648351648353,
865
+ "grad_norm": 0.3660902976989746,
866
+ "learning_rate": 2.8502014950143373e-05,
867
+ "loss": 0.8328,
868
+ "step": 850
869
+ },
870
+ {
871
+ "epoch": 2.3351648351648353,
872
+ "eval_loss": 0.9368348121643066,
873
+ "eval_runtime": 120.1125,
874
+ "eval_samples_per_second": 43.093,
875
+ "eval_steps_per_second": 2.697,
876
+ "step": 850
877
+ },
878
+ {
879
+ "epoch": 2.3626373626373627,
880
+ "grad_norm": 0.3826388418674469,
881
+ "learning_rate": 2.6302292113110637e-05,
882
+ "loss": 0.8202,
883
+ "step": 860
884
+ },
885
+ {
886
+ "epoch": 2.39010989010989,
887
+ "grad_norm": 0.39540669322013855,
888
+ "learning_rate": 2.4177990523236216e-05,
889
+ "loss": 0.8284,
890
+ "step": 870
891
+ },
892
+ {
893
+ "epoch": 2.4038461538461537,
894
+ "eval_loss": 0.9366135597229004,
895
+ "eval_runtime": 120.1013,
896
+ "eval_samples_per_second": 43.097,
897
+ "eval_steps_per_second": 2.698,
898
+ "step": 875
899
+ },
900
+ {
901
+ "epoch": 2.4175824175824174,
902
+ "grad_norm": 0.39717695116996765,
903
+ "learning_rate": 2.213128416231468e-05,
904
+ "loss": 0.8287,
905
+ "step": 880
906
+ },
907
+ {
908
+ "epoch": 2.4450549450549453,
909
+ "grad_norm": 0.3701748847961426,
910
+ "learning_rate": 2.0164267602222586e-05,
911
+ "loss": 0.8298,
912
+ "step": 890
913
+ },
914
+ {
915
+ "epoch": 2.4725274725274726,
916
+ "grad_norm": 0.3669058680534363,
917
+ "learning_rate": 1.827895386136166e-05,
918
+ "loss": 0.8258,
919
+ "step": 900
920
+ },
921
+ {
922
+ "epoch": 2.4725274725274726,
923
+ "eval_loss": 0.9355611801147461,
924
+ "eval_runtime": 120.0907,
925
+ "eval_samples_per_second": 43.101,
926
+ "eval_steps_per_second": 2.698,
927
+ "step": 900
928
+ },
929
+ {
930
+ "epoch": 2.5,
931
+ "grad_norm": 0.3532375395298004,
932
+ "learning_rate": 1.647727234456279e-05,
933
+ "loss": 0.8428,
934
+ "step": 910
935
+ },
936
+ {
937
+ "epoch": 2.5274725274725274,
938
+ "grad_norm": 0.35455724596977234,
939
+ "learning_rate": 1.4761066868558914e-05,
940
+ "loss": 0.825,
941
+ "step": 920
942
+ },
943
+ {
944
+ "epoch": 2.541208791208791,
945
+ "eval_loss": 0.9347633123397827,
946
+ "eval_runtime": 120.0905,
947
+ "eval_samples_per_second": 43.101,
948
+ "eval_steps_per_second": 2.698,
949
+ "step": 925
950
+ },
951
+ {
952
+ "epoch": 2.5549450549450547,
953
+ "grad_norm": 0.3676817715167999,
954
+ "learning_rate": 1.3132093775047615e-05,
955
+ "loss": 0.8207,
956
+ "step": 930
957
+ },
958
+ {
959
+ "epoch": 2.5824175824175826,
960
+ "grad_norm": 0.41484078764915466,
961
+ "learning_rate": 1.1592020133274639e-05,
962
+ "loss": 0.8388,
963
+ "step": 940
964
+ },
965
+ {
966
+ "epoch": 2.60989010989011,
967
+ "grad_norm": 0.3522408604621887,
968
+ "learning_rate": 1.0142422033977505e-05,
969
+ "loss": 0.8259,
970
+ "step": 950
971
+ },
972
+ {
973
+ "epoch": 2.60989010989011,
974
+ "eval_loss": 0.9338229298591614,
975
+ "eval_runtime": 120.1021,
976
+ "eval_samples_per_second": 43.097,
977
+ "eval_steps_per_second": 2.698,
978
+ "step": 950
979
+ },
980
+ {
981
+ "epoch": 2.6373626373626373,
982
+ "grad_norm": 0.34244734048843384,
983
+ "learning_rate": 8.784782976435424e-06,
984
+ "loss": 0.821,
985
+ "step": 960
986
+ },
987
+ {
988
+ "epoch": 2.6648351648351647,
989
+ "grad_norm": 0.37353935837745667,
990
+ "learning_rate": 7.520492350275876e-06,
991
+ "loss": 0.8225,
992
+ "step": 970
993
+ },
994
+ {
995
+ "epoch": 2.678571428571429,
996
+ "eval_loss": 0.9337417483329773,
997
+ "eval_runtime": 120.1024,
998
+ "eval_samples_per_second": 43.097,
999
+ "eval_steps_per_second": 2.698,
1000
+ "step": 975
1001
+ },
1002
+ {
1003
+ "epoch": 2.6923076923076925,
1004
+ "grad_norm": 0.3811197876930237,
1005
+ "learning_rate": 6.350844013592061e-06,
1006
+ "loss": 0.8286,
1007
+ "step": 980
1008
+ },
1009
+ {
1010
+ "epoch": 2.71978021978022,
1011
+ "grad_norm": 0.3932379186153412,
1012
+ "learning_rate": 5.277034968825667e-06,
1013
+ "loss": 0.8372,
1014
+ "step": 990
1015
+ },
1016
+ {
1017
+ "epoch": 2.7472527472527473,
1018
+ "grad_norm": 0.3701821267604828,
1019
+ "learning_rate": 4.3001641377707125e-06,
1020
+ "loss": 0.8226,
1021
+ "step": 1000
1022
+ },
1023
+ {
1024
+ "epoch": 2.7472527472527473,
1025
+ "eval_loss": 0.9329955577850342,
1026
+ "eval_runtime": 120.0945,
1027
+ "eval_samples_per_second": 43.099,
1028
+ "eval_steps_per_second": 2.698,
1029
+ "step": 1000
1030
+ },
1031
+ {
1032
+ "epoch": 2.7747252747252746,
1033
+ "grad_norm": 0.3506335914134979,
1034
+ "learning_rate": 3.4212312369516497e-06,
1035
+ "loss": 0.8128,
1036
+ "step": 1010
1037
+ },
1038
+ {
1039
+ "epoch": 2.802197802197802,
1040
+ "grad_norm": 0.3670129179954529,
1041
+ "learning_rate": 2.6411357545269577e-06,
1042
+ "loss": 0.8239,
1043
+ "step": 1020
1044
+ },
1045
+ {
1046
+ "epoch": 2.8159340659340657,
1047
+ "eval_loss": 0.9329585433006287,
1048
+ "eval_runtime": 120.0978,
1049
+ "eval_samples_per_second": 43.098,
1050
+ "eval_steps_per_second": 2.698,
1051
+ "step": 1025
1052
+ },
1053
+ {
1054
+ "epoch": 2.82967032967033,
1055
+ "grad_norm": 0.35776689648628235,
1056
+ "learning_rate": 1.960676029764874e-06,
1057
+ "loss": 0.8437,
1058
+ "step": 1030
1059
+ },
1060
+ {
1061
+ "epoch": 2.857142857142857,
1062
+ "grad_norm": 0.3504193127155304,
1063
+ "learning_rate": 1.3805484360337906e-06,
1064
+ "loss": 0.8104,
1065
+ "step": 1040
1066
+ },
1067
+ {
1068
+ "epoch": 2.8846153846153846,
1069
+ "grad_norm": 0.366804301738739,
1070
+ "learning_rate": 9.013466681429994e-07,
1071
+ "loss": 0.8169,
1072
+ "step": 1050
1073
+ },
1074
+ {
1075
+ "epoch": 2.8846153846153846,
1076
+ "eval_loss": 0.9328103065490723,
1077
+ "eval_runtime": 120.1161,
1078
+ "eval_samples_per_second": 43.092,
1079
+ "eval_steps_per_second": 2.697,
1080
+ "step": 1050
1081
+ },
1082
+ {
1083
+ "epoch": 2.912087912087912,
1084
+ "grad_norm": 0.3706912100315094,
1085
+ "learning_rate": 5.235611347634172e-07,
1086
+ "loss": 0.8123,
1087
+ "step": 1060
1088
+ },
1089
+ {
1090
+ "epoch": 2.9395604395604398,
1091
+ "grad_norm": 0.3953019380569458,
1092
+ "learning_rate": 2.4757845654992397e-07,
1093
+ "loss": 0.8175,
1094
+ "step": 1070
1095
+ },
1096
+ {
1097
+ "epoch": 2.9532967032967035,
1098
+ "eval_loss": 0.9328309893608093,
1099
+ "eval_runtime": 120.1081,
1100
+ "eval_samples_per_second": 43.095,
1101
+ "eval_steps_per_second": 2.698,
1102
+ "step": 1075
1103
+ },
1104
+ {
1105
+ "epoch": 2.967032967032967,
1106
+ "grad_norm": 0.40803447365760803,
1107
+ "learning_rate": 7.368107047894812e-08,
1108
+ "loss": 0.8333,
1109
+ "step": 1080
1110
+ },
1111
+ {
1112
+ "epoch": 2.9945054945054945,
1113
+ "grad_norm": 0.3288993835449219,
1114
+ "learning_rate": 2.046940806244013e-09,
1115
+ "loss": 0.8162,
1116
+ "step": 1090
1117
+ },
1118
+ {
1119
+ "epoch": 3.0,
1120
+ "step": 1092,
1121
+ "total_flos": 3.7446797801931407e+18,
1122
+ "train_loss": 0.9387403691644634,
1123
+ "train_runtime": 13836.993,
1124
+ "train_samples_per_second": 10.1,
1125
+ "train_steps_per_second": 0.079
1126
+ }
1127
+ ],
1128
+ "logging_steps": 10,
1129
+ "max_steps": 1092,
1130
+ "num_input_tokens_seen": 0,
1131
+ "num_train_epochs": 3,
1132
+ "save_steps": 250,
1133
+ "stateful_callbacks": {
1134
+ "TrainerControl": {
1135
+ "args": {
1136
+ "should_epoch_stop": false,
1137
+ "should_evaluate": false,
1138
+ "should_log": false,
1139
+ "should_save": true,
1140
+ "should_training_stop": true
1141
+ },
1142
+ "attributes": {}
1143
+ }
1144
+ },
1145
+ "total_flos": 3.7446797801931407e+18,
1146
+ "train_batch_size": 4,
1147
+ "trial_name": null,
1148
+ "trial_params": null
1149
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e71ea86e74a5b825d4bda5a6f82e34ccfb9838740582d5d61dc105bc0c91d0d
3
+ size 5688
training_eval_loss.png ADDED
training_loss.png ADDED