Hizy commited on
Commit
c60f0f4
·
verified ·
1 Parent(s): 4481768

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -42,3 +42,4 @@ osgenesis7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  osgenesis-llama/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  osgenesis-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  agenttrek-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
42
  osgenesis-llama/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
  osgenesis-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
  agenttrek-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ webrl-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
webrl-llama/README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: Meta-Llama/Meta-Llama-3.1-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: web_policy_sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # web_policy_sft
18
+
19
+ This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Meta-Llama-3.1-8B-Instruct](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Meta-Llama-3.1-8B-Instruct) on the web_policy_sft dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.1971
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - distributed_type: multi-GPU
45
+ - num_devices: 4
46
+ - gradient_accumulation_steps: 4
47
+ - total_train_batch_size: 16
48
+ - total_eval_batch_size: 4
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_ratio: 0.1
52
+ - num_epochs: 3.0
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:------:|:----:|:---------------:|
58
+ | 0.2843 | 0.9394 | 500 | 0.2385 |
59
+ | 0.1062 | 1.8774 | 1000 | 0.1962 |
60
+ | 0.0573 | 2.8154 | 1500 | 0.1971 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.57.1
66
+ - Pytorch 2.7.1+cu126
67
+ - Datasets 4.0.0
68
+ - Tokenizers 0.22.1
webrl-llama/all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.19709129631519318,
4
+ "eval_runtime": 138.7446,
5
+ "eval_samples_per_second": 6.818,
6
+ "eval_steps_per_second": 1.708,
7
+ "total_flos": 141952390594560.0,
8
+ "train_loss": 0.17646967794389706,
9
+ "train_runtime": 16767.1291,
10
+ "train_samples_per_second": 1.523,
11
+ "train_steps_per_second": 0.095
12
+ }
webrl-llama/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
webrl-llama/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 128009,
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
+ "pad_token_id": 128009,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "transformers_version": "4.57.1",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
webrl-llama/eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.19709129631519318,
4
+ "eval_runtime": 138.7446,
5
+ "eval_samples_per_second": 6.818,
6
+ "eval_steps_per_second": 1.708
7
+ }
webrl-llama/generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128009,
6
+ 128001,
7
+ 128008,
8
+ 128009
9
+ ],
10
+ "pad_token_id": 128009,
11
+ "temperature": 0.6,
12
+ "top_p": 0.9,
13
+ "transformers_version": "4.57.1"
14
+ }
webrl-llama/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db4fcb9bd4aaf496fc139b715d6a9da2eadf8cf2613c5c84354d33da925d0e3e
3
+ size 4976698672
webrl-llama/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:942dbb3227e9e815ddf6199b64f75d7d4cb35d321f4b7e521e5f561b35ec6333
3
+ size 4999802720
webrl-llama/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7aa32ca0b114d0cc7560a7858efaa3d44b179a6fdc57741bab3aa52b498c1f9
3
+ size 4915916176
webrl-llama/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8199c22113af7e79428cfc96c2acc29d172b97c70ba4098ae6527c63fcf4778d
3
+ size 1168138808
webrl-llama/model.safetensors.index.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 266240,
4
+ "total_size": 16060522496
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00004-of-00004.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
126
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
129
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
135
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
236
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.norm.weight": "model-00004-of-00004.safetensors"
298
+ }
299
+ }
webrl-llama/runs/Nov23_20-42-05_hgx007/events.out.tfevents.1763902779.hgx007 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9654cdef89450997d952c838dedc892f3f98a736ac54c362ac2fe4c30cf5997
3
+ size 40305
webrl-llama/runs/Nov23_20-42-05_hgx007/events.out.tfevents.1763919722.hgx007 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7df52fcc864f80ae72377db063463432795473b77cc265188e95e1bdde5d7f8
3
+ size 311
webrl-llama/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
webrl-llama/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
webrl-llama/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
webrl-llama/train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 141952390594560.0,
4
+ "train_loss": 0.17646967794389706,
5
+ "train_runtime": 16767.1291,
6
+ "train_samples_per_second": 1.523,
7
+ "train_steps_per_second": 0.095
8
+ }
webrl-llama/trainer_log.jsonl ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1599, "loss": 1.3022, "lr": 5.625e-07, "epoch": 0.018788163457022077, "percentage": 0.63, "elapsed_time": "0:02:04", "remaining_time": "5:28:27"}
2
+ {"current_steps": 20, "total_steps": 1599, "loss": 0.9208, "lr": 1.1875e-06, "epoch": 0.03757632691404415, "percentage": 1.25, "elapsed_time": "0:03:43", "remaining_time": "4:53:46"}
3
+ {"current_steps": 30, "total_steps": 1599, "loss": 0.6368, "lr": 1.8125e-06, "epoch": 0.05636449037106623, "percentage": 1.88, "elapsed_time": "0:05:22", "remaining_time": "4:41:07"}
4
+ {"current_steps": 40, "total_steps": 1599, "loss": 0.4864, "lr": 2.4375e-06, "epoch": 0.0751526538280883, "percentage": 2.5, "elapsed_time": "0:07:06", "remaining_time": "4:36:54"}
5
+ {"current_steps": 50, "total_steps": 1599, "loss": 0.413, "lr": 3.0625000000000003e-06, "epoch": 0.09394081728511038, "percentage": 3.13, "elapsed_time": "0:08:44", "remaining_time": "4:30:40"}
6
+ {"current_steps": 60, "total_steps": 1599, "loss": 0.3552, "lr": 3.6875000000000007e-06, "epoch": 0.11272898074213246, "percentage": 3.75, "elapsed_time": "0:10:26", "remaining_time": "4:27:47"}
7
+ {"current_steps": 70, "total_steps": 1599, "loss": 0.3232, "lr": 4.312500000000001e-06, "epoch": 0.13151714419915453, "percentage": 4.38, "elapsed_time": "0:12:06", "remaining_time": "4:24:18"}
8
+ {"current_steps": 80, "total_steps": 1599, "loss": 0.3995, "lr": 4.937500000000001e-06, "epoch": 0.1503053076561766, "percentage": 5.0, "elapsed_time": "0:13:51", "remaining_time": "4:23:16"}
9
+ {"current_steps": 90, "total_steps": 1599, "loss": 0.383, "lr": 5.5625000000000005e-06, "epoch": 0.1690934711131987, "percentage": 5.63, "elapsed_time": "0:15:36", "remaining_time": "4:21:42"}
10
+ {"current_steps": 100, "total_steps": 1599, "loss": 0.4042, "lr": 6.1875000000000005e-06, "epoch": 0.18788163457022075, "percentage": 6.25, "elapsed_time": "0:17:16", "remaining_time": "4:18:53"}
11
+ {"current_steps": 110, "total_steps": 1599, "loss": 0.2883, "lr": 6.8125e-06, "epoch": 0.20666979802724283, "percentage": 6.88, "elapsed_time": "0:18:52", "remaining_time": "4:15:32"}
12
+ {"current_steps": 120, "total_steps": 1599, "loss": 0.3389, "lr": 7.437500000000001e-06, "epoch": 0.22545796148426492, "percentage": 7.5, "elapsed_time": "0:20:33", "remaining_time": "4:13:23"}
13
+ {"current_steps": 130, "total_steps": 1599, "loss": 0.2971, "lr": 8.062500000000001e-06, "epoch": 0.244246124941287, "percentage": 8.13, "elapsed_time": "0:22:15", "remaining_time": "4:11:30"}
14
+ {"current_steps": 140, "total_steps": 1599, "loss": 0.3087, "lr": 8.687500000000001e-06, "epoch": 0.26303428839830906, "percentage": 8.76, "elapsed_time": "0:23:56", "remaining_time": "4:09:29"}
15
+ {"current_steps": 150, "total_steps": 1599, "loss": 0.328, "lr": 9.312500000000001e-06, "epoch": 0.28182245185533117, "percentage": 9.38, "elapsed_time": "0:25:39", "remaining_time": "4:07:52"}
16
+ {"current_steps": 160, "total_steps": 1599, "loss": 0.3183, "lr": 9.937500000000001e-06, "epoch": 0.3006106153123532, "percentage": 10.01, "elapsed_time": "0:27:31", "remaining_time": "4:07:30"}
17
+ {"current_steps": 170, "total_steps": 1599, "loss": 0.3427, "lr": 9.999034862449997e-06, "epoch": 0.3193987787693753, "percentage": 10.63, "elapsed_time": "0:29:05", "remaining_time": "4:04:30"}
18
+ {"current_steps": 180, "total_steps": 1599, "loss": 0.3567, "lr": 9.995699062853814e-06, "epoch": 0.3381869422263974, "percentage": 11.26, "elapsed_time": "0:30:43", "remaining_time": "4:02:11"}
19
+ {"current_steps": 190, "total_steps": 1599, "loss": 0.2315, "lr": 9.989982275421674e-06, "epoch": 0.35697510568341945, "percentage": 11.88, "elapsed_time": "0:32:24", "remaining_time": "4:00:23"}
20
+ {"current_steps": 200, "total_steps": 1599, "loss": 0.3465, "lr": 9.981887224817565e-06, "epoch": 0.3757632691404415, "percentage": 12.51, "elapsed_time": "0:34:04", "remaining_time": "3:58:21"}
21
+ {"current_steps": 210, "total_steps": 1599, "loss": 0.3036, "lr": 9.971417769203639e-06, "epoch": 0.3945514325974636, "percentage": 13.13, "elapsed_time": "0:35:42", "remaining_time": "3:56:08"}
22
+ {"current_steps": 220, "total_steps": 1599, "loss": 0.314, "lr": 9.958578898401365e-06, "epoch": 0.41333959605448567, "percentage": 13.76, "elapsed_time": "0:37:17", "remaining_time": "3:53:46"}
23
+ {"current_steps": 230, "total_steps": 1599, "loss": 0.3888, "lr": 9.943376731513364e-06, "epoch": 0.4321277595115077, "percentage": 14.38, "elapsed_time": "0:38:57", "remaining_time": "3:51:53"}
24
+ {"current_steps": 240, "total_steps": 1599, "loss": 0.3072, "lr": 9.92581851400698e-06, "epoch": 0.45091592296852984, "percentage": 15.01, "elapsed_time": "0:40:47", "remaining_time": "3:50:59"}
25
+ {"current_steps": 250, "total_steps": 1599, "loss": 0.3344, "lr": 9.90591261426105e-06, "epoch": 0.4697040864255519, "percentage": 15.63, "elapsed_time": "0:42:30", "remaining_time": "3:49:21"}
26
+ {"current_steps": 260, "total_steps": 1599, "loss": 0.2927, "lr": 9.883668519577464e-06, "epoch": 0.488492249882574, "percentage": 16.26, "elapsed_time": "0:44:01", "remaining_time": "3:46:45"}
27
+ {"current_steps": 270, "total_steps": 1599, "loss": 0.2952, "lr": 9.85909683165945e-06, "epoch": 0.5072804133395961, "percentage": 16.89, "elapsed_time": "0:45:45", "remaining_time": "3:45:12"}
28
+ {"current_steps": 280, "total_steps": 1599, "loss": 0.2545, "lr": 9.832209261558707e-06, "epoch": 0.5260685767966181, "percentage": 17.51, "elapsed_time": "0:47:24", "remaining_time": "3:43:19"}
29
+ {"current_steps": 290, "total_steps": 1599, "loss": 0.2789, "lr": 9.803018624093859e-06, "epoch": 0.5448567402536402, "percentage": 18.14, "elapsed_time": "0:49:02", "remaining_time": "3:41:22"}
30
+ {"current_steps": 300, "total_steps": 1599, "loss": 0.3209, "lr": 9.771538831742785e-06, "epoch": 0.5636449037106623, "percentage": 18.76, "elapsed_time": "0:50:37", "remaining_time": "3:39:13"}
31
+ {"current_steps": 310, "total_steps": 1599, "loss": 0.2721, "lr": 9.737784888011847e-06, "epoch": 0.5824330671676844, "percentage": 19.39, "elapsed_time": "0:52:30", "remaining_time": "3:38:21"}
32
+ {"current_steps": 320, "total_steps": 1599, "loss": 0.2369, "lr": 9.701772880285098e-06, "epoch": 0.6012212306247064, "percentage": 20.01, "elapsed_time": "0:54:09", "remaining_time": "3:36:26"}
33
+ {"current_steps": 330, "total_steps": 1599, "loss": 0.327, "lr": 9.663519972156919e-06, "epoch": 0.6200093940817285, "percentage": 20.64, "elapsed_time": "0:55:53", "remaining_time": "3:34:55"}
34
+ {"current_steps": 340, "total_steps": 1599, "loss": 0.3057, "lr": 9.623044395251709e-06, "epoch": 0.6387975575387506, "percentage": 21.26, "elapsed_time": "0:57:36", "remaining_time": "3:33:20"}
35
+ {"current_steps": 350, "total_steps": 1599, "loss": 0.2397, "lr": 9.580365440534567e-06, "epoch": 0.6575857209957726, "percentage": 21.89, "elapsed_time": "0:59:15", "remaining_time": "3:31:28"}
36
+ {"current_steps": 360, "total_steps": 1599, "loss": 0.2472, "lr": 9.535503449117067e-06, "epoch": 0.6763738844527948, "percentage": 22.51, "elapsed_time": "1:01:00", "remaining_time": "3:29:58"}
37
+ {"current_steps": 370, "total_steps": 1599, "loss": 0.2861, "lr": 9.488479802562535e-06, "epoch": 0.6951620479098168, "percentage": 23.14, "elapsed_time": "1:02:37", "remaining_time": "3:28:02"}
38
+ {"current_steps": 380, "total_steps": 1599, "loss": 0.263, "lr": 9.439316912695433e-06, "epoch": 0.7139502113668389, "percentage": 23.76, "elapsed_time": "1:04:18", "remaining_time": "3:26:18"}
39
+ {"current_steps": 390, "total_steps": 1599, "loss": 0.317, "lr": 9.388038210919706e-06, "epoch": 0.732738374823861, "percentage": 24.39, "elapsed_time": "1:05:58", "remaining_time": "3:24:30"}
40
+ {"current_steps": 400, "total_steps": 1599, "loss": 0.2399, "lr": 9.334668137051213e-06, "epoch": 0.751526538280883, "percentage": 25.02, "elapsed_time": "1:07:44", "remaining_time": "3:23:03"}
41
+ {"current_steps": 410, "total_steps": 1599, "loss": 0.2855, "lr": 9.279232127669519e-06, "epoch": 0.7703147017379052, "percentage": 25.64, "elapsed_time": "1:09:27", "remaining_time": "3:21:24"}
42
+ {"current_steps": 420, "total_steps": 1599, "loss": 0.2258, "lr": 9.221756603994622e-06, "epoch": 0.7891028651949272, "percentage": 26.27, "elapsed_time": "1:11:17", "remaining_time": "3:20:08"}
43
+ {"current_steps": 430, "total_steps": 1599, "loss": 0.2501, "lr": 9.162268959294421e-06, "epoch": 0.8078910286519493, "percentage": 26.89, "elapsed_time": "1:13:08", "remaining_time": "3:18:51"}
44
+ {"current_steps": 440, "total_steps": 1599, "loss": 0.1867, "lr": 9.10079754582885e-06, "epoch": 0.8266791921089713, "percentage": 27.52, "elapsed_time": "1:14:58", "remaining_time": "3:17:28"}
45
+ {"current_steps": 450, "total_steps": 1599, "loss": 0.2623, "lr": 9.037371661337006e-06, "epoch": 0.8454673555659934, "percentage": 28.14, "elapsed_time": "1:16:32", "remaining_time": "3:15:26"}
46
+ {"current_steps": 460, "total_steps": 1599, "loss": 0.2986, "lr": 8.972021535073605e-06, "epoch": 0.8642555190230155, "percentage": 28.77, "elapsed_time": "1:18:11", "remaining_time": "3:13:37"}
47
+ {"current_steps": 470, "total_steps": 1599, "loss": 0.2536, "lr": 8.904778313401497e-06, "epoch": 0.8830436824800376, "percentage": 29.39, "elapsed_time": "1:19:55", "remaining_time": "3:11:59"}
48
+ {"current_steps": 480, "total_steps": 1599, "loss": 0.3049, "lr": 8.835674044947078e-06, "epoch": 0.9018318459370597, "percentage": 30.02, "elapsed_time": "1:21:41", "remaining_time": "3:10:27"}
49
+ {"current_steps": 490, "total_steps": 1599, "loss": 0.2319, "lr": 8.764741665325672e-06, "epoch": 0.9206200093940817, "percentage": 30.64, "elapsed_time": "1:23:25", "remaining_time": "3:08:49"}
50
+ {"current_steps": 500, "total_steps": 1599, "loss": 0.2843, "lr": 8.692014981444166e-06, "epoch": 0.9394081728511038, "percentage": 31.27, "elapsed_time": "1:25:07", "remaining_time": "3:07:05"}
51
+ {"current_steps": 500, "total_steps": 1599, "eval_loss": 0.23845727741718292, "epoch": 0.9394081728511038, "percentage": 31.27, "elapsed_time": "1:27:26", "remaining_time": "3:12:11"}
52
+ {"current_steps": 510, "total_steps": 1599, "loss": 0.2351, "lr": 8.617528655388384e-06, "epoch": 0.9581963363081258, "percentage": 31.89, "elapsed_time": "1:29:08", "remaining_time": "3:10:21"}
53
+ {"current_steps": 520, "total_steps": 1599, "loss": 0.233, "lr": 8.541318187902879e-06, "epoch": 0.976984499765148, "percentage": 32.52, "elapsed_time": "1:30:44", "remaining_time": "3:08:16"}
54
+ {"current_steps": 530, "total_steps": 1599, "loss": 0.2415, "lr": 8.463419901471002e-06, "epoch": 0.9957726632221701, "percentage": 33.15, "elapsed_time": "1:32:27", "remaining_time": "3:06:30"}
55
+ {"current_steps": 540, "total_steps": 1599, "loss": 0.2149, "lr": 8.383870923003345e-06, "epoch": 1.0131517144199154, "percentage": 33.77, "elapsed_time": "1:34:28", "remaining_time": "3:05:16"}
56
+ {"current_steps": 550, "total_steps": 1599, "loss": 0.1915, "lr": 8.302709166142765e-06, "epoch": 1.0319398778769375, "percentage": 34.4, "elapsed_time": "1:36:10", "remaining_time": "3:03:25"}
57
+ {"current_steps": 560, "total_steps": 1599, "loss": 0.1317, "lr": 8.219973313194461e-06, "epoch": 1.0507280413339597, "percentage": 35.02, "elapsed_time": "1:37:47", "remaining_time": "3:01:26"}
58
+ {"current_steps": 570, "total_steps": 1599, "loss": 0.1626, "lr": 8.135702796689693e-06, "epoch": 1.0695162047909816, "percentage": 35.65, "elapsed_time": "1:39:32", "remaining_time": "2:59:41"}
59
+ {"current_steps": 580, "total_steps": 1599, "loss": 0.1284, "lr": 8.049937780591944e-06, "epoch": 1.0883043682480038, "percentage": 36.27, "elapsed_time": "1:41:07", "remaining_time": "2:57:40"}
60
+ {"current_steps": 590, "total_steps": 1599, "loss": 0.15, "lr": 7.962719141154469e-06, "epoch": 1.1070925317050258, "percentage": 36.9, "elapsed_time": "1:42:40", "remaining_time": "2:55:35"}
61
+ {"current_steps": 600, "total_steps": 1599, "loss": 0.139, "lr": 7.874088447438366e-06, "epoch": 1.125880695162048, "percentage": 37.52, "elapsed_time": "1:44:22", "remaining_time": "2:53:47"}
62
+ {"current_steps": 610, "total_steps": 1599, "loss": 0.1519, "lr": 7.784087941500446e-06, "epoch": 1.1446688586190699, "percentage": 38.15, "elapsed_time": "1:46:00", "remaining_time": "2:51:52"}
63
+ {"current_steps": 620, "total_steps": 1599, "loss": 0.1084, "lr": 7.692760518260355e-06, "epoch": 1.163457022076092, "percentage": 38.77, "elapsed_time": "1:47:40", "remaining_time": "2:50:00"}
64
+ {"current_steps": 630, "total_steps": 1599, "loss": 0.1348, "lr": 7.6001497050565256e-06, "epoch": 1.1822451855331142, "percentage": 39.4, "elapsed_time": "1:49:21", "remaining_time": "2:48:12"}
65
+ {"current_steps": 640, "total_steps": 1599, "loss": 0.1598, "lr": 7.506299640900725e-06, "epoch": 1.2010333489901361, "percentage": 40.03, "elapsed_time": "1:51:05", "remaining_time": "2:46:28"}
66
+ {"current_steps": 650, "total_steps": 1599, "loss": 0.1691, "lr": 7.411255055441064e-06, "epoch": 1.2198215124471583, "percentage": 40.65, "elapsed_time": "1:52:53", "remaining_time": "2:44:49"}
67
+ {"current_steps": 660, "total_steps": 1599, "loss": 0.1755, "lr": 7.315061247643518e-06, "epoch": 1.2386096759041805, "percentage": 41.28, "elapsed_time": "1:54:37", "remaining_time": "2:43:04"}
68
+ {"current_steps": 670, "total_steps": 1599, "loss": 0.1706, "lr": 7.2177640642020875e-06, "epoch": 1.2573978393612024, "percentage": 41.9, "elapsed_time": "1:56:27", "remaining_time": "2:41:29"}
69
+ {"current_steps": 680, "total_steps": 1599, "loss": 0.1444, "lr": 7.119409877687923e-06, "epoch": 1.2761860028182246, "percentage": 42.53, "elapsed_time": "1:58:09", "remaining_time": "2:39:41"}
70
+ {"current_steps": 690, "total_steps": 1599, "loss": 0.1028, "lr": 7.0200455644478105e-06, "epoch": 1.2949741662752465, "percentage": 43.15, "elapsed_time": "1:59:45", "remaining_time": "2:37:45"}
71
+ {"current_steps": 700, "total_steps": 1599, "loss": 0.1614, "lr": 6.91971848226255e-06, "epoch": 1.3137623297322687, "percentage": 43.78, "elapsed_time": "2:01:22", "remaining_time": "2:35:53"}
72
+ {"current_steps": 710, "total_steps": 1599, "loss": 0.14, "lr": 6.818476447775873e-06, "epoch": 1.3325504931892906, "percentage": 44.4, "elapsed_time": "2:03:03", "remaining_time": "2:34:05"}
73
+ {"current_steps": 720, "total_steps": 1599, "loss": 0.1737, "lr": 6.7163677137046855e-06, "epoch": 1.3513386566463128, "percentage": 45.03, "elapsed_time": "2:04:50", "remaining_time": "2:32:25"}
74
+ {"current_steps": 730, "total_steps": 1599, "loss": 0.1878, "lr": 6.6134409458414415e-06, "epoch": 1.370126820103335, "percentage": 45.65, "elapsed_time": "2:06:35", "remaining_time": "2:30:41"}
75
+ {"current_steps": 740, "total_steps": 1599, "loss": 0.1495, "lr": 6.50974519985967e-06, "epoch": 1.388914983560357, "percentage": 46.28, "elapsed_time": "2:08:10", "remaining_time": "2:28:47"}
76
+ {"current_steps": 750, "total_steps": 1599, "loss": 0.1128, "lr": 6.405329897933669e-06, "epoch": 1.407703147017379, "percentage": 46.9, "elapsed_time": "2:09:53", "remaining_time": "2:27:01"}
77
+ {"current_steps": 760, "total_steps": 1599, "loss": 0.1226, "lr": 6.300244805183524e-06, "epoch": 1.4264913104744013, "percentage": 47.53, "elapsed_time": "2:11:39", "remaining_time": "2:25:20"}
78
+ {"current_steps": 770, "total_steps": 1599, "loss": 0.1484, "lr": 6.194540005956675e-06, "epoch": 1.4452794739314232, "percentage": 48.16, "elapsed_time": "2:13:21", "remaining_time": "2:23:34"}
79
+ {"current_steps": 780, "total_steps": 1599, "loss": 0.1491, "lr": 6.088265879957345e-06, "epoch": 1.4640676373884451, "percentage": 48.78, "elapsed_time": "2:14:55", "remaining_time": "2:21:40"}
80
+ {"current_steps": 790, "total_steps": 1599, "loss": 0.1166, "lr": 5.981473078235186e-06, "epoch": 1.4828558008454673, "percentage": 49.41, "elapsed_time": "2:16:47", "remaining_time": "2:20:05"}
81
+ {"current_steps": 800, "total_steps": 1599, "loss": 0.1531, "lr": 5.874212499044609e-06, "epoch": 1.5016439643024895, "percentage": 50.03, "elapsed_time": "2:18:26", "remaining_time": "2:18:16"}
82
+ {"current_steps": 810, "total_steps": 1599, "loss": 0.1398, "lr": 5.7665352635862945e-06, "epoch": 1.5204321277595114, "percentage": 50.66, "elapsed_time": "2:20:04", "remaining_time": "2:16:26"}
83
+ {"current_steps": 820, "total_steps": 1599, "loss": 0.1391, "lr": 5.658492691642443e-06, "epoch": 1.5392202912165336, "percentage": 51.28, "elapsed_time": "2:21:44", "remaining_time": "2:14:39"}
84
+ {"current_steps": 830, "total_steps": 1599, "loss": 0.1418, "lr": 5.550136277117375e-06, "epoch": 1.5580084546735558, "percentage": 51.91, "elapsed_time": "2:23:27", "remaining_time": "2:12:55"}
85
+ {"current_steps": 840, "total_steps": 1599, "loss": 0.1381, "lr": 5.4415176634951515e-06, "epoch": 1.5767966181305777, "percentage": 52.53, "elapsed_time": "2:25:07", "remaining_time": "2:11:07"}
86
+ {"current_steps": 850, "total_steps": 1599, "loss": 0.1238, "lr": 5.332688619225903e-06, "epoch": 1.5955847815875999, "percentage": 53.16, "elapsed_time": "2:26:47", "remaining_time": "2:09:20"}
87
+ {"current_steps": 860, "total_steps": 1599, "loss": 0.1119, "lr": 5.22370101305259e-06, "epoch": 1.614372945044622, "percentage": 53.78, "elapsed_time": "2:28:27", "remaining_time": "2:07:34"}
88
+ {"current_steps": 870, "total_steps": 1599, "loss": 0.1622, "lr": 5.114606789289973e-06, "epoch": 1.633161108501644, "percentage": 54.41, "elapsed_time": "2:30:13", "remaining_time": "2:05:52"}
89
+ {"current_steps": 880, "total_steps": 1599, "loss": 0.1192, "lr": 5.005457943067561e-06, "epoch": 1.651949271958666, "percentage": 55.03, "elapsed_time": "2:31:54", "remaining_time": "2:04:07"}
90
+ {"current_steps": 890, "total_steps": 1599, "loss": 0.1039, "lr": 4.896306495548334e-06, "epoch": 1.670737435415688, "percentage": 55.66, "elapsed_time": "2:33:36", "remaining_time": "2:02:22"}
91
+ {"current_steps": 900, "total_steps": 1599, "loss": 0.1375, "lr": 4.7872044691350735e-06, "epoch": 1.6895255988727103, "percentage": 56.29, "elapsed_time": "2:35:18", "remaining_time": "2:00:37"}
92
+ {"current_steps": 910, "total_steps": 1599, "loss": 0.1092, "lr": 4.678203862676091e-06, "epoch": 1.7083137623297322, "percentage": 56.91, "elapsed_time": "2:36:58", "remaining_time": "1:58:51"}
93
+ {"current_steps": 920, "total_steps": 1599, "loss": 0.1239, "lr": 4.569356626682181e-06, "epoch": 1.7271019257867544, "percentage": 57.54, "elapsed_time": "2:38:52", "remaining_time": "1:57:15"}
94
+ {"current_steps": 930, "total_steps": 1599, "loss": 0.1387, "lr": 4.4607146385666145e-06, "epoch": 1.7458900892437765, "percentage": 58.16, "elapsed_time": "2:40:31", "remaining_time": "1:55:28"}
95
+ {"current_steps": 940, "total_steps": 1599, "loss": 0.1595, "lr": 4.352329677919983e-06, "epoch": 1.7646782527007985, "percentage": 58.79, "elapsed_time": "2:42:09", "remaining_time": "1:53:41"}
96
+ {"current_steps": 950, "total_steps": 1599, "loss": 0.11, "lr": 4.244253401831646e-06, "epoch": 1.7834664161578204, "percentage": 59.41, "elapsed_time": "2:43:47", "remaining_time": "1:51:53"}
97
+ {"current_steps": 960, "total_steps": 1599, "loss": 0.1205, "lr": 4.136537320269571e-06, "epoch": 1.8022545796148428, "percentage": 60.04, "elapsed_time": "2:45:37", "remaining_time": "1:50:14"}
98
+ {"current_steps": 970, "total_steps": 1599, "loss": 0.1134, "lr": 4.029232771530306e-06, "epoch": 1.8210427430718648, "percentage": 60.66, "elapsed_time": "2:47:08", "remaining_time": "1:48:22"}
99
+ {"current_steps": 980, "total_steps": 1599, "loss": 0.1123, "lr": 3.92239089777075e-06, "epoch": 1.8398309065288867, "percentage": 61.29, "elapsed_time": "2:48:49", "remaining_time": "1:46:37"}
100
+ {"current_steps": 990, "total_steps": 1599, "loss": 0.1188, "lr": 3.816062620633414e-06, "epoch": 1.8586190699859089, "percentage": 61.91, "elapsed_time": "2:50:29", "remaining_time": "1:44:52"}
101
+ {"current_steps": 1000, "total_steps": 1599, "loss": 0.1062, "lr": 3.7102986169767954e-06, "epoch": 1.877407233442931, "percentage": 62.54, "elapsed_time": "2:52:13", "remaining_time": "1:43:09"}
102
+ {"current_steps": 1000, "total_steps": 1599, "eval_loss": 0.19623179733753204, "epoch": 1.877407233442931, "percentage": 62.54, "elapsed_time": "2:54:32", "remaining_time": "1:44:32"}
103
+ {"current_steps": 1010, "total_steps": 1599, "loss": 0.1055, "lr": 3.605149294722392e-06, "epoch": 1.896195396899953, "percentage": 63.16, "elapsed_time": "2:56:12", "remaining_time": "1:42:45"}
104
+ {"current_steps": 1020, "total_steps": 1599, "loss": 0.125, "lr": 3.500664768829908e-06, "epoch": 1.9149835603569751, "percentage": 63.79, "elapsed_time": "2:57:51", "remaining_time": "1:40:57"}
105
+ {"current_steps": 1030, "total_steps": 1599, "loss": 0.1046, "lr": 3.3968948374120958e-06, "epoch": 1.9337717238139973, "percentage": 64.42, "elapsed_time": "2:59:35", "remaining_time": "1:39:12"}
106
+ {"current_steps": 1040, "total_steps": 1599, "loss": 0.1308, "lr": 3.2938889580005932e-06, "epoch": 1.9525598872710193, "percentage": 65.04, "elapsed_time": "3:01:20", "remaining_time": "1:37:28"}
107
+ {"current_steps": 1050, "total_steps": 1599, "loss": 0.1195, "lr": 3.191696223974084e-06, "epoch": 1.9713480507280412, "percentage": 65.67, "elapsed_time": "3:02:57", "remaining_time": "1:35:39"}
108
+ {"current_steps": 1060, "total_steps": 1599, "loss": 0.119, "lr": 3.090365341160041e-06, "epoch": 1.9901362141850634, "percentage": 66.29, "elapsed_time": "3:04:41", "remaining_time": "1:33:54"}
109
+ {"current_steps": 1070, "total_steps": 1599, "loss": 0.1082, "lr": 2.989944604621148e-06, "epoch": 2.0075152653828088, "percentage": 66.92, "elapsed_time": "3:06:48", "remaining_time": "1:32:21"}
110
+ {"current_steps": 1080, "total_steps": 1599, "loss": 0.0649, "lr": 2.8904818756375076e-06, "epoch": 2.0263034288398307, "percentage": 67.54, "elapsed_time": "3:08:23", "remaining_time": "1:30:32"}
111
+ {"current_steps": 1090, "total_steps": 1599, "loss": 0.0671, "lr": 2.792024558895606e-06, "epoch": 2.045091592296853, "percentage": 68.17, "elapsed_time": "3:10:05", "remaining_time": "1:28:45"}
112
+ {"current_steps": 1100, "total_steps": 1599, "loss": 0.0597, "lr": 2.6946195798948755e-06, "epoch": 2.063879755753875, "percentage": 68.79, "elapsed_time": "3:11:39", "remaining_time": "1:26:56"}
113
+ {"current_steps": 1110, "total_steps": 1599, "loss": 0.0582, "lr": 2.598313362582639e-06, "epoch": 2.082667919210897, "percentage": 69.42, "elapsed_time": "3:13:25", "remaining_time": "1:25:12"}
114
+ {"current_steps": 1120, "total_steps": 1599, "loss": 0.0609, "lr": 2.5031518072281236e-06, "epoch": 2.1014560826679194, "percentage": 70.04, "elapsed_time": "3:15:08", "remaining_time": "1:23:27"}
115
+ {"current_steps": 1130, "total_steps": 1599, "loss": 0.0664, "lr": 2.4091802685460336e-06, "epoch": 2.1202442461249413, "percentage": 70.67, "elapsed_time": "3:16:51", "remaining_time": "1:21:42"}
116
+ {"current_steps": 1140, "total_steps": 1599, "loss": 0.0675, "lr": 2.3164435340801574e-06, "epoch": 2.1390324095819633, "percentage": 71.29, "elapsed_time": "3:18:30", "remaining_time": "1:19:55"}
117
+ {"current_steps": 1150, "total_steps": 1599, "loss": 0.0453, "lr": 2.224985802857284e-06, "epoch": 2.1578205730389852, "percentage": 71.92, "elapsed_time": "3:20:13", "remaining_time": "1:18:10"}
118
+ {"current_steps": 1160, "total_steps": 1599, "loss": 0.0625, "lr": 2.134850664321617e-06, "epoch": 2.1766087364960076, "percentage": 72.55, "elapsed_time": "3:21:51", "remaining_time": "1:16:23"}
119
+ {"current_steps": 1170, "total_steps": 1599, "loss": 0.0565, "lr": 2.046081077559707e-06, "epoch": 2.1953968999530296, "percentage": 73.17, "elapsed_time": "3:23:39", "remaining_time": "1:14:40"}
120
+ {"current_steps": 1180, "total_steps": 1599, "loss": 0.051, "lr": 1.9587193508258415e-06, "epoch": 2.2141850634100515, "percentage": 73.8, "elapsed_time": "3:25:15", "remaining_time": "1:12:53"}
121
+ {"current_steps": 1190, "total_steps": 1599, "loss": 0.048, "lr": 1.8728071213776028e-06, "epoch": 2.232973226867074, "percentage": 74.42, "elapsed_time": "3:26:49", "remaining_time": "1:11:05"}
122
+ {"current_steps": 1200, "total_steps": 1599, "loss": 0.0575, "lr": 1.7883853356312375e-06, "epoch": 2.251761390324096, "percentage": 75.05, "elapsed_time": "3:28:26", "remaining_time": "1:09:18"}
123
+ {"current_steps": 1210, "total_steps": 1599, "loss": 0.0708, "lr": 1.7054942296462895e-06, "epoch": 2.270549553781118, "percentage": 75.67, "elapsed_time": "3:30:11", "remaining_time": "1:07:34"}
124
+ {"current_steps": 1220, "total_steps": 1599, "loss": 0.0513, "lr": 1.6241733099487888e-06, "epoch": 2.2893377172381397, "percentage": 76.3, "elapsed_time": "3:31:54", "remaining_time": "1:05:49"}
125
+ {"current_steps": 1230, "total_steps": 1599, "loss": 0.0562, "lr": 1.5444613347021392e-06, "epoch": 2.308125880695162, "percentage": 76.92, "elapsed_time": "3:33:38", "remaining_time": "1:04:05"}
126
+ {"current_steps": 1240, "total_steps": 1599, "loss": 0.0507, "lr": 1.4663962952346938e-06, "epoch": 2.326914044152184, "percentage": 77.55, "elapsed_time": "3:35:21", "remaining_time": "1:02:20"}
127
+ {"current_steps": 1250, "total_steps": 1599, "loss": 0.0577, "lr": 1.3900153979327951e-06, "epoch": 2.3457022076092064, "percentage": 78.17, "elapsed_time": "3:37:01", "remaining_time": "1:00:35"}
128
+ {"current_steps": 1260, "total_steps": 1599, "loss": 0.0648, "lr": 1.315355046507934e-06, "epoch": 2.3644903710662284, "percentage": 78.8, "elapsed_time": "3:38:50", "remaining_time": "0:58:52"}
129
+ {"current_steps": 1270, "total_steps": 1599, "loss": 0.0558, "lr": 1.2424508246464635e-06, "epoch": 2.3832785345232503, "percentage": 79.42, "elapsed_time": "3:40:29", "remaining_time": "0:57:07"}
130
+ {"current_steps": 1280, "total_steps": 1599, "loss": 0.061, "lr": 1.171337479050148e-06, "epoch": 2.4020666979802723, "percentage": 80.05, "elapsed_time": "3:42:07", "remaining_time": "0:55:21"}
131
+ {"current_steps": 1290, "total_steps": 1599, "loss": 0.0521, "lr": 1.1020489028756243e-06, "epoch": 2.4208548614372947, "percentage": 80.68, "elapsed_time": "3:43:56", "remaining_time": "0:53:38"}
132
+ {"current_steps": 1300, "total_steps": 1599, "loss": 0.0583, "lr": 1.0346181195806614e-06, "epoch": 2.4396430248943166, "percentage": 81.3, "elapsed_time": "3:45:37", "remaining_time": "0:51:53"}
133
+ {"current_steps": 1310, "total_steps": 1599, "loss": 0.0546, "lr": 9.690772671849403e-07, "epoch": 2.4584311883513386, "percentage": 81.93, "elapsed_time": "3:47:23", "remaining_time": "0:50:09"}
134
+ {"current_steps": 1320, "total_steps": 1599, "loss": 0.0551, "lr": 9.054575829528251e-07, "epoch": 2.477219351808361, "percentage": 82.55, "elapsed_time": "3:49:08", "remaining_time": "0:48:25"}
135
+ {"current_steps": 1330, "total_steps": 1599, "loss": 0.0517, "lr": 8.437893885054504e-07, "epoch": 2.496007515265383, "percentage": 83.18, "elapsed_time": "3:50:57", "remaining_time": "0:46:42"}
136
+ {"current_steps": 1340, "total_steps": 1599, "loss": 0.0545, "lr": 7.841020753692058e-07, "epoch": 2.514795678722405, "percentage": 83.8, "elapsed_time": "3:52:46", "remaining_time": "0:44:59"}
137
+ {"current_steps": 1350, "total_steps": 1599, "loss": 0.0472, "lr": 7.264240909675174e-07, "epoch": 2.533583842179427, "percentage": 84.43, "elapsed_time": "3:54:22", "remaining_time": "0:43:13"}
138
+ {"current_steps": 1360, "total_steps": 1599, "loss": 0.0446, "lr": 6.707829250625825e-07, "epoch": 2.552372005636449, "percentage": 85.05, "elapsed_time": "3:56:06", "remaining_time": "0:41:29"}
139
+ {"current_steps": 1370, "total_steps": 1599, "loss": 0.0542, "lr": 6.172050966535514e-07, "epoch": 2.571160169093471, "percentage": 85.68, "elapsed_time": "3:57:43", "remaining_time": "0:39:44"}
140
+ {"current_steps": 1380, "total_steps": 1599, "loss": 0.0469, "lr": 5.65716141337368e-07, "epoch": 2.589948332550493, "percentage": 86.3, "elapsed_time": "3:59:27", "remaining_time": "0:37:59"}
141
+ {"current_steps": 1390, "total_steps": 1599, "loss": 0.0425, "lr": 5.163405991383114e-07, "epoch": 2.6087364960075154, "percentage": 86.93, "elapsed_time": "4:01:07", "remaining_time": "0:36:15"}
142
+ {"current_steps": 1400, "total_steps": 1599, "loss": 0.0504, "lr": 4.6910200281203523e-07, "epoch": 2.6275246594645374, "percentage": 87.55, "elapsed_time": "4:02:50", "remaining_time": "0:34:31"}
143
+ {"current_steps": 1410, "total_steps": 1599, "loss": 0.0634, "lr": 4.240228666296825e-07, "epoch": 2.6463128229215593, "percentage": 88.18, "elapsed_time": "4:04:26", "remaining_time": "0:32:45"}
144
+ {"current_steps": 1420, "total_steps": 1599, "loss": 0.0573, "lr": 3.8112467564740796e-07, "epoch": 2.6651009863785813, "percentage": 88.81, "elapsed_time": "4:06:08", "remaining_time": "0:31:01"}
145
+ {"current_steps": 1430, "total_steps": 1599, "loss": 0.07, "lr": 3.4042787546644305e-07, "epoch": 2.6838891498356037, "percentage": 89.43, "elapsed_time": "4:07:53", "remaining_time": "0:29:17"}
146
+ {"current_steps": 1440, "total_steps": 1599, "loss": 0.0448, "lr": 3.0195186248856866e-07, "epoch": 2.7026773132926256, "percentage": 90.06, "elapsed_time": "4:09:36", "remaining_time": "0:27:33"}
147
+ {"current_steps": 1450, "total_steps": 1599, "loss": 0.058, "lr": 2.6571497467164033e-07, "epoch": 2.7214654767496476, "percentage": 90.68, "elapsed_time": "4:11:16", "remaining_time": "0:25:49"}
148
+ {"current_steps": 1460, "total_steps": 1599, "loss": 0.0654, "lr": 2.3173448278958178e-07, "epoch": 2.74025364020667, "percentage": 91.31, "elapsed_time": "4:13:01", "remaining_time": "0:24:05"}
149
+ {"current_steps": 1470, "total_steps": 1599, "loss": 0.0556, "lr": 2.0002658220100334e-07, "epoch": 2.759041803663692, "percentage": 91.93, "elapsed_time": "4:14:45", "remaining_time": "0:22:21"}
150
+ {"current_steps": 1480, "total_steps": 1599, "loss": 0.0558, "lr": 1.7060638513037076e-07, "epoch": 2.777829967120714, "percentage": 92.56, "elapsed_time": "4:16:18", "remaining_time": "0:20:36"}
151
+ {"current_steps": 1490, "total_steps": 1599, "loss": 0.0496, "lr": 1.434879134654077e-07, "epoch": 2.796618130577736, "percentage": 93.18, "elapsed_time": "4:18:06", "remaining_time": "0:18:52"}
152
+ {"current_steps": 1500, "total_steps": 1599, "loss": 0.0573, "lr": 1.186840920741561e-07, "epoch": 2.815406294034758, "percentage": 93.81, "elapsed_time": "4:19:41", "remaining_time": "0:17:08"}
153
+ {"current_steps": 1500, "total_steps": 1599, "eval_loss": 0.19711866974830627, "epoch": 2.815406294034758, "percentage": 93.81, "elapsed_time": "4:22:02", "remaining_time": "0:17:17"}
154
+ {"current_steps": 1510, "total_steps": 1599, "loss": 0.0548, "lr": 9.620674264488594e-08, "epoch": 2.83419445749178, "percentage": 94.43, "elapsed_time": "4:23:48", "remaining_time": "0:15:32"}
155
+ {"current_steps": 1520, "total_steps": 1599, "loss": 0.063, "lr": 7.606657805179274e-08, "epoch": 2.8529826209488025, "percentage": 95.06, "elapsed_time": "4:25:37", "remaining_time": "0:13:48"}
156
+ {"current_steps": 1530, "total_steps": 1599, "loss": 0.0514, "lr": 5.827319724915959e-08, "epoch": 2.8717707844058245, "percentage": 95.68, "elapsed_time": "4:27:24", "remaining_time": "0:12:03"}
157
+ {"current_steps": 1540, "total_steps": 1599, "loss": 0.0467, "lr": 4.283508069641951e-08, "epoch": 2.8905589478628464, "percentage": 96.31, "elapsed_time": "4:29:06", "remaining_time": "0:10:18"}
158
+ {"current_steps": 1550, "total_steps": 1599, "loss": 0.0483, "lr": 2.975958631631082e-08, "epoch": 2.9093471113198683, "percentage": 96.94, "elapsed_time": "4:30:51", "remaining_time": "0:08:33"}
159
+ {"current_steps": 1560, "total_steps": 1599, "loss": 0.0427, "lr": 1.9052945988030648e-08, "epoch": 2.9281352747768903, "percentage": 97.56, "elapsed_time": "4:32:29", "remaining_time": "0:06:48"}
160
+ {"current_steps": 1570, "total_steps": 1599, "loss": 0.0493, "lr": 1.0720262577076923e-08, "epoch": 2.9469234382339127, "percentage": 98.19, "elapsed_time": "4:34:14", "remaining_time": "0:05:03"}
161
+ {"current_steps": 1580, "total_steps": 1599, "loss": 0.0542, "lr": 4.76550750318383e-09, "epoch": 2.9657116016909346, "percentage": 98.81, "elapsed_time": "4:35:52", "remaining_time": "0:03:19"}
162
+ {"current_steps": 1590, "total_steps": 1599, "loss": 0.04, "lr": 1.1915188475125627e-09, "epoch": 2.984499765147957, "percentage": 99.44, "elapsed_time": "4:37:30", "remaining_time": "0:01:34"}
163
+ {"current_steps": 1599, "total_steps": 1599, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "4:39:27", "remaining_time": "0:00:00"}
webrl-llama/trainer_state.json ADDED
@@ -0,0 +1,1180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1599,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.018788163457022077,
14
+ "grad_norm": 38.902539143522475,
15
+ "learning_rate": 5.625e-07,
16
+ "loss": 1.3022,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.03757632691404415,
21
+ "grad_norm": 25.841390543115104,
22
+ "learning_rate": 1.1875e-06,
23
+ "loss": 0.9208,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.05636449037106623,
28
+ "grad_norm": 12.835104883604552,
29
+ "learning_rate": 1.8125e-06,
30
+ "loss": 0.6368,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 0.0751526538280883,
35
+ "grad_norm": 14.597848294473495,
36
+ "learning_rate": 2.4375e-06,
37
+ "loss": 0.4864,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 0.09394081728511038,
42
+ "grad_norm": 10.147065718110532,
43
+ "learning_rate": 3.0625000000000003e-06,
44
+ "loss": 0.413,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 0.11272898074213246,
49
+ "grad_norm": 7.953678589468881,
50
+ "learning_rate": 3.6875000000000007e-06,
51
+ "loss": 0.3552,
52
+ "step": 60
53
+ },
54
+ {
55
+ "epoch": 0.13151714419915453,
56
+ "grad_norm": 15.497275455908772,
57
+ "learning_rate": 4.312500000000001e-06,
58
+ "loss": 0.3232,
59
+ "step": 70
60
+ },
61
+ {
62
+ "epoch": 0.1503053076561766,
63
+ "grad_norm": 10.684325762714469,
64
+ "learning_rate": 4.937500000000001e-06,
65
+ "loss": 0.3995,
66
+ "step": 80
67
+ },
68
+ {
69
+ "epoch": 0.1690934711131987,
70
+ "grad_norm": 5.578373425613698,
71
+ "learning_rate": 5.5625000000000005e-06,
72
+ "loss": 0.383,
73
+ "step": 90
74
+ },
75
+ {
76
+ "epoch": 0.18788163457022075,
77
+ "grad_norm": 6.8251720225201336,
78
+ "learning_rate": 6.1875000000000005e-06,
79
+ "loss": 0.4042,
80
+ "step": 100
81
+ },
82
+ {
83
+ "epoch": 0.20666979802724283,
84
+ "grad_norm": 6.671521431411895,
85
+ "learning_rate": 6.8125e-06,
86
+ "loss": 0.2883,
87
+ "step": 110
88
+ },
89
+ {
90
+ "epoch": 0.22545796148426492,
91
+ "grad_norm": 5.055948701380774,
92
+ "learning_rate": 7.437500000000001e-06,
93
+ "loss": 0.3389,
94
+ "step": 120
95
+ },
96
+ {
97
+ "epoch": 0.244246124941287,
98
+ "grad_norm": 6.217541233533783,
99
+ "learning_rate": 8.062500000000001e-06,
100
+ "loss": 0.2971,
101
+ "step": 130
102
+ },
103
+ {
104
+ "epoch": 0.26303428839830906,
105
+ "grad_norm": 4.948590364279342,
106
+ "learning_rate": 8.687500000000001e-06,
107
+ "loss": 0.3087,
108
+ "step": 140
109
+ },
110
+ {
111
+ "epoch": 0.28182245185533117,
112
+ "grad_norm": 9.515982957654412,
113
+ "learning_rate": 9.312500000000001e-06,
114
+ "loss": 0.328,
115
+ "step": 150
116
+ },
117
+ {
118
+ "epoch": 0.3006106153123532,
119
+ "grad_norm": 5.588586595769071,
120
+ "learning_rate": 9.937500000000001e-06,
121
+ "loss": 0.3183,
122
+ "step": 160
123
+ },
124
+ {
125
+ "epoch": 0.3193987787693753,
126
+ "grad_norm": 6.382027734743243,
127
+ "learning_rate": 9.999034862449997e-06,
128
+ "loss": 0.3427,
129
+ "step": 170
130
+ },
131
+ {
132
+ "epoch": 0.3381869422263974,
133
+ "grad_norm": 7.190427289350578,
134
+ "learning_rate": 9.995699062853814e-06,
135
+ "loss": 0.3567,
136
+ "step": 180
137
+ },
138
+ {
139
+ "epoch": 0.35697510568341945,
140
+ "grad_norm": 7.34935653943741,
141
+ "learning_rate": 9.989982275421674e-06,
142
+ "loss": 0.2315,
143
+ "step": 190
144
+ },
145
+ {
146
+ "epoch": 0.3757632691404415,
147
+ "grad_norm": 6.295235795739874,
148
+ "learning_rate": 9.981887224817565e-06,
149
+ "loss": 0.3465,
150
+ "step": 200
151
+ },
152
+ {
153
+ "epoch": 0.3945514325974636,
154
+ "grad_norm": 6.275130440505698,
155
+ "learning_rate": 9.971417769203639e-06,
156
+ "loss": 0.3036,
157
+ "step": 210
158
+ },
159
+ {
160
+ "epoch": 0.41333959605448567,
161
+ "grad_norm": 7.6581869277864465,
162
+ "learning_rate": 9.958578898401365e-06,
163
+ "loss": 0.314,
164
+ "step": 220
165
+ },
166
+ {
167
+ "epoch": 0.4321277595115077,
168
+ "grad_norm": 4.7865555589430535,
169
+ "learning_rate": 9.943376731513364e-06,
170
+ "loss": 0.3888,
171
+ "step": 230
172
+ },
173
+ {
174
+ "epoch": 0.45091592296852984,
175
+ "grad_norm": 5.5592205355180155,
176
+ "learning_rate": 9.92581851400698e-06,
177
+ "loss": 0.3072,
178
+ "step": 240
179
+ },
180
+ {
181
+ "epoch": 0.4697040864255519,
182
+ "grad_norm": 7.370996615746405,
183
+ "learning_rate": 9.90591261426105e-06,
184
+ "loss": 0.3344,
185
+ "step": 250
186
+ },
187
+ {
188
+ "epoch": 0.488492249882574,
189
+ "grad_norm": 5.867505322765833,
190
+ "learning_rate": 9.883668519577464e-06,
191
+ "loss": 0.2927,
192
+ "step": 260
193
+ },
194
+ {
195
+ "epoch": 0.5072804133395961,
196
+ "grad_norm": 5.191413529518597,
197
+ "learning_rate": 9.85909683165945e-06,
198
+ "loss": 0.2952,
199
+ "step": 270
200
+ },
201
+ {
202
+ "epoch": 0.5260685767966181,
203
+ "grad_norm": 19.97325422873732,
204
+ "learning_rate": 9.832209261558707e-06,
205
+ "loss": 0.2545,
206
+ "step": 280
207
+ },
208
+ {
209
+ "epoch": 0.5448567402536402,
210
+ "grad_norm": 4.341682760199477,
211
+ "learning_rate": 9.803018624093859e-06,
212
+ "loss": 0.2789,
213
+ "step": 290
214
+ },
215
+ {
216
+ "epoch": 0.5636449037106623,
217
+ "grad_norm": 5.155418355116268,
218
+ "learning_rate": 9.771538831742785e-06,
219
+ "loss": 0.3209,
220
+ "step": 300
221
+ },
222
+ {
223
+ "epoch": 0.5824330671676844,
224
+ "grad_norm": 5.585775233082983,
225
+ "learning_rate": 9.737784888011847e-06,
226
+ "loss": 0.2721,
227
+ "step": 310
228
+ },
229
+ {
230
+ "epoch": 0.6012212306247064,
231
+ "grad_norm": 6.011924955720608,
232
+ "learning_rate": 9.701772880285098e-06,
233
+ "loss": 0.2369,
234
+ "step": 320
235
+ },
236
+ {
237
+ "epoch": 0.6200093940817285,
238
+ "grad_norm": 3.464693811617661,
239
+ "learning_rate": 9.663519972156919e-06,
240
+ "loss": 0.327,
241
+ "step": 330
242
+ },
243
+ {
244
+ "epoch": 0.6387975575387506,
245
+ "grad_norm": 3.9209881919217473,
246
+ "learning_rate": 9.623044395251709e-06,
247
+ "loss": 0.3057,
248
+ "step": 340
249
+ },
250
+ {
251
+ "epoch": 0.6575857209957726,
252
+ "grad_norm": 3.4697639872647668,
253
+ "learning_rate": 9.580365440534567e-06,
254
+ "loss": 0.2397,
255
+ "step": 350
256
+ },
257
+ {
258
+ "epoch": 0.6763738844527948,
259
+ "grad_norm": 3.7401214735406234,
260
+ "learning_rate": 9.535503449117067e-06,
261
+ "loss": 0.2472,
262
+ "step": 360
263
+ },
264
+ {
265
+ "epoch": 0.6951620479098168,
266
+ "grad_norm": 6.346162811263442,
267
+ "learning_rate": 9.488479802562535e-06,
268
+ "loss": 0.2861,
269
+ "step": 370
270
+ },
271
+ {
272
+ "epoch": 0.7139502113668389,
273
+ "grad_norm": 3.159937104618782,
274
+ "learning_rate": 9.439316912695433e-06,
275
+ "loss": 0.263,
276
+ "step": 380
277
+ },
278
+ {
279
+ "epoch": 0.732738374823861,
280
+ "grad_norm": 4.840970300357461,
281
+ "learning_rate": 9.388038210919706e-06,
282
+ "loss": 0.317,
283
+ "step": 390
284
+ },
285
+ {
286
+ "epoch": 0.751526538280883,
287
+ "grad_norm": 3.7912950448134284,
288
+ "learning_rate": 9.334668137051213e-06,
289
+ "loss": 0.2399,
290
+ "step": 400
291
+ },
292
+ {
293
+ "epoch": 0.7703147017379052,
294
+ "grad_norm": 3.6544447000330536,
295
+ "learning_rate": 9.279232127669519e-06,
296
+ "loss": 0.2855,
297
+ "step": 410
298
+ },
299
+ {
300
+ "epoch": 0.7891028651949272,
301
+ "grad_norm": 3.415036837035855,
302
+ "learning_rate": 9.221756603994622e-06,
303
+ "loss": 0.2258,
304
+ "step": 420
305
+ },
306
+ {
307
+ "epoch": 0.8078910286519493,
308
+ "grad_norm": 4.076375098278762,
309
+ "learning_rate": 9.162268959294421e-06,
310
+ "loss": 0.2501,
311
+ "step": 430
312
+ },
313
+ {
314
+ "epoch": 0.8266791921089713,
315
+ "grad_norm": 3.496486007224735,
316
+ "learning_rate": 9.10079754582885e-06,
317
+ "loss": 0.1867,
318
+ "step": 440
319
+ },
320
+ {
321
+ "epoch": 0.8454673555659934,
322
+ "grad_norm": 3.469220654012647,
323
+ "learning_rate": 9.037371661337006e-06,
324
+ "loss": 0.2623,
325
+ "step": 450
326
+ },
327
+ {
328
+ "epoch": 0.8642555190230155,
329
+ "grad_norm": 5.445833530786857,
330
+ "learning_rate": 8.972021535073605e-06,
331
+ "loss": 0.2986,
332
+ "step": 460
333
+ },
334
+ {
335
+ "epoch": 0.8830436824800376,
336
+ "grad_norm": 2.807672252814633,
337
+ "learning_rate": 8.904778313401497e-06,
338
+ "loss": 0.2536,
339
+ "step": 470
340
+ },
341
+ {
342
+ "epoch": 0.9018318459370597,
343
+ "grad_norm": 7.9424075184306755,
344
+ "learning_rate": 8.835674044947078e-06,
345
+ "loss": 0.3049,
346
+ "step": 480
347
+ },
348
+ {
349
+ "epoch": 0.9206200093940817,
350
+ "grad_norm": 4.713848985031599,
351
+ "learning_rate": 8.764741665325672e-06,
352
+ "loss": 0.2319,
353
+ "step": 490
354
+ },
355
+ {
356
+ "epoch": 0.9394081728511038,
357
+ "grad_norm": 4.413441646714263,
358
+ "learning_rate": 8.692014981444166e-06,
359
+ "loss": 0.2843,
360
+ "step": 500
361
+ },
362
+ {
363
+ "epoch": 0.9394081728511038,
364
+ "eval_loss": 0.23845727741718292,
365
+ "eval_runtime": 139.1371,
366
+ "eval_samples_per_second": 6.799,
367
+ "eval_steps_per_second": 1.703,
368
+ "step": 500
369
+ },
370
+ {
371
+ "epoch": 0.9581963363081258,
372
+ "grad_norm": 1.9799881256140055,
373
+ "learning_rate": 8.617528655388384e-06,
374
+ "loss": 0.2351,
375
+ "step": 510
376
+ },
377
+ {
378
+ "epoch": 0.976984499765148,
379
+ "grad_norm": 5.12487715924031,
380
+ "learning_rate": 8.541318187902879e-06,
381
+ "loss": 0.233,
382
+ "step": 520
383
+ },
384
+ {
385
+ "epoch": 0.9957726632221701,
386
+ "grad_norm": 3.19651743083849,
387
+ "learning_rate": 8.463419901471002e-06,
388
+ "loss": 0.2415,
389
+ "step": 530
390
+ },
391
+ {
392
+ "epoch": 1.0131517144199154,
393
+ "grad_norm": 3.1257162430007224,
394
+ "learning_rate": 8.383870923003345e-06,
395
+ "loss": 0.2149,
396
+ "step": 540
397
+ },
398
+ {
399
+ "epoch": 1.0319398778769375,
400
+ "grad_norm": 3.45631296377837,
401
+ "learning_rate": 8.302709166142765e-06,
402
+ "loss": 0.1915,
403
+ "step": 550
404
+ },
405
+ {
406
+ "epoch": 1.0507280413339597,
407
+ "grad_norm": 2.286180863936669,
408
+ "learning_rate": 8.219973313194461e-06,
409
+ "loss": 0.1317,
410
+ "step": 560
411
+ },
412
+ {
413
+ "epoch": 1.0695162047909816,
414
+ "grad_norm": 2.9540247439256673,
415
+ "learning_rate": 8.135702796689693e-06,
416
+ "loss": 0.1626,
417
+ "step": 570
418
+ },
419
+ {
420
+ "epoch": 1.0883043682480038,
421
+ "grad_norm": 2.1567801477380066,
422
+ "learning_rate": 8.049937780591944e-06,
423
+ "loss": 0.1284,
424
+ "step": 580
425
+ },
426
+ {
427
+ "epoch": 1.1070925317050258,
428
+ "grad_norm": 3.3038946448126256,
429
+ "learning_rate": 7.962719141154469e-06,
430
+ "loss": 0.15,
431
+ "step": 590
432
+ },
433
+ {
434
+ "epoch": 1.125880695162048,
435
+ "grad_norm": 3.0873807975498635,
436
+ "learning_rate": 7.874088447438366e-06,
437
+ "loss": 0.139,
438
+ "step": 600
439
+ },
440
+ {
441
+ "epoch": 1.1446688586190699,
442
+ "grad_norm": 2.051043815446488,
443
+ "learning_rate": 7.784087941500446e-06,
444
+ "loss": 0.1519,
445
+ "step": 610
446
+ },
447
+ {
448
+ "epoch": 1.163457022076092,
449
+ "grad_norm": 2.4617892609619143,
450
+ "learning_rate": 7.692760518260355e-06,
451
+ "loss": 0.1084,
452
+ "step": 620
453
+ },
454
+ {
455
+ "epoch": 1.1822451855331142,
456
+ "grad_norm": 1.7623637548791922,
457
+ "learning_rate": 7.6001497050565256e-06,
458
+ "loss": 0.1348,
459
+ "step": 630
460
+ },
461
+ {
462
+ "epoch": 1.2010333489901361,
463
+ "grad_norm": 3.2507782557395206,
464
+ "learning_rate": 7.506299640900725e-06,
465
+ "loss": 0.1598,
466
+ "step": 640
467
+ },
468
+ {
469
+ "epoch": 1.2198215124471583,
470
+ "grad_norm": 4.2496165791641864,
471
+ "learning_rate": 7.411255055441064e-06,
472
+ "loss": 0.1691,
473
+ "step": 650
474
+ },
475
+ {
476
+ "epoch": 1.2386096759041805,
477
+ "grad_norm": 6.841696105552823,
478
+ "learning_rate": 7.315061247643518e-06,
479
+ "loss": 0.1755,
480
+ "step": 660
481
+ },
482
+ {
483
+ "epoch": 1.2573978393612024,
484
+ "grad_norm": 2.5825812551037224,
485
+ "learning_rate": 7.2177640642020875e-06,
486
+ "loss": 0.1706,
487
+ "step": 670
488
+ },
489
+ {
490
+ "epoch": 1.2761860028182246,
491
+ "grad_norm": 3.371098422024725,
492
+ "learning_rate": 7.119409877687923e-06,
493
+ "loss": 0.1444,
494
+ "step": 680
495
+ },
496
+ {
497
+ "epoch": 1.2949741662752465,
498
+ "grad_norm": 2.590100923291357,
499
+ "learning_rate": 7.0200455644478105e-06,
500
+ "loss": 0.1028,
501
+ "step": 690
502
+ },
503
+ {
504
+ "epoch": 1.3137623297322687,
505
+ "grad_norm": 2.481043190681829,
506
+ "learning_rate": 6.91971848226255e-06,
507
+ "loss": 0.1614,
508
+ "step": 700
509
+ },
510
+ {
511
+ "epoch": 1.3325504931892906,
512
+ "grad_norm": 2.329271785947211,
513
+ "learning_rate": 6.818476447775873e-06,
514
+ "loss": 0.14,
515
+ "step": 710
516
+ },
517
+ {
518
+ "epoch": 1.3513386566463128,
519
+ "grad_norm": 2.646993250936894,
520
+ "learning_rate": 6.7163677137046855e-06,
521
+ "loss": 0.1737,
522
+ "step": 720
523
+ },
524
+ {
525
+ "epoch": 1.370126820103335,
526
+ "grad_norm": 5.413980223824179,
527
+ "learning_rate": 6.6134409458414415e-06,
528
+ "loss": 0.1878,
529
+ "step": 730
530
+ },
531
+ {
532
+ "epoch": 1.388914983560357,
533
+ "grad_norm": 2.1714036144692934,
534
+ "learning_rate": 6.50974519985967e-06,
535
+ "loss": 0.1495,
536
+ "step": 740
537
+ },
538
+ {
539
+ "epoch": 1.407703147017379,
540
+ "grad_norm": 3.133663498685042,
541
+ "learning_rate": 6.405329897933669e-06,
542
+ "loss": 0.1128,
543
+ "step": 750
544
+ },
545
+ {
546
+ "epoch": 1.4264913104744013,
547
+ "grad_norm": 6.167890536629415,
548
+ "learning_rate": 6.300244805183524e-06,
549
+ "loss": 0.1226,
550
+ "step": 760
551
+ },
552
+ {
553
+ "epoch": 1.4452794739314232,
554
+ "grad_norm": 2.676375029014761,
555
+ "learning_rate": 6.194540005956675e-06,
556
+ "loss": 0.1484,
557
+ "step": 770
558
+ },
559
+ {
560
+ "epoch": 1.4640676373884451,
561
+ "grad_norm": 2.475835214596877,
562
+ "learning_rate": 6.088265879957345e-06,
563
+ "loss": 0.1491,
564
+ "step": 780
565
+ },
566
+ {
567
+ "epoch": 1.4828558008454673,
568
+ "grad_norm": 2.2436437435088723,
569
+ "learning_rate": 5.981473078235186e-06,
570
+ "loss": 0.1166,
571
+ "step": 790
572
+ },
573
+ {
574
+ "epoch": 1.5016439643024895,
575
+ "grad_norm": 2.132099788544184,
576
+ "learning_rate": 5.874212499044609e-06,
577
+ "loss": 0.1531,
578
+ "step": 800
579
+ },
580
+ {
581
+ "epoch": 1.5204321277595114,
582
+ "grad_norm": 4.079361340018406,
583
+ "learning_rate": 5.7665352635862945e-06,
584
+ "loss": 0.1398,
585
+ "step": 810
586
+ },
587
+ {
588
+ "epoch": 1.5392202912165336,
589
+ "grad_norm": 1.9003215983018618,
590
+ "learning_rate": 5.658492691642443e-06,
591
+ "loss": 0.1391,
592
+ "step": 820
593
+ },
594
+ {
595
+ "epoch": 1.5580084546735558,
596
+ "grad_norm": 2.6377367761402586,
597
+ "learning_rate": 5.550136277117375e-06,
598
+ "loss": 0.1418,
599
+ "step": 830
600
+ },
601
+ {
602
+ "epoch": 1.5767966181305777,
603
+ "grad_norm": 3.1017028365243995,
604
+ "learning_rate": 5.4415176634951515e-06,
605
+ "loss": 0.1381,
606
+ "step": 840
607
+ },
608
+ {
609
+ "epoch": 1.5955847815875999,
610
+ "grad_norm": 2.6515166581373504,
611
+ "learning_rate": 5.332688619225903e-06,
612
+ "loss": 0.1238,
613
+ "step": 850
614
+ },
615
+ {
616
+ "epoch": 1.614372945044622,
617
+ "grad_norm": 1.922819738710662,
618
+ "learning_rate": 5.22370101305259e-06,
619
+ "loss": 0.1119,
620
+ "step": 860
621
+ },
622
+ {
623
+ "epoch": 1.633161108501644,
624
+ "grad_norm": 2.529225306976089,
625
+ "learning_rate": 5.114606789289973e-06,
626
+ "loss": 0.1622,
627
+ "step": 870
628
+ },
629
+ {
630
+ "epoch": 1.651949271958666,
631
+ "grad_norm": 1.288640339335927,
632
+ "learning_rate": 5.005457943067561e-06,
633
+ "loss": 0.1192,
634
+ "step": 880
635
+ },
636
+ {
637
+ "epoch": 1.670737435415688,
638
+ "grad_norm": 3.4037089339443782,
639
+ "learning_rate": 4.896306495548334e-06,
640
+ "loss": 0.1039,
641
+ "step": 890
642
+ },
643
+ {
644
+ "epoch": 1.6895255988727103,
645
+ "grad_norm": 3.9649233321606805,
646
+ "learning_rate": 4.7872044691350735e-06,
647
+ "loss": 0.1375,
648
+ "step": 900
649
+ },
650
+ {
651
+ "epoch": 1.7083137623297322,
652
+ "grad_norm": 2.5965801580755286,
653
+ "learning_rate": 4.678203862676091e-06,
654
+ "loss": 0.1092,
655
+ "step": 910
656
+ },
657
+ {
658
+ "epoch": 1.7271019257867544,
659
+ "grad_norm": 2.5786254690111265,
660
+ "learning_rate": 4.569356626682181e-06,
661
+ "loss": 0.1239,
662
+ "step": 920
663
+ },
664
+ {
665
+ "epoch": 1.7458900892437765,
666
+ "grad_norm": 3.8696436706505435,
667
+ "learning_rate": 4.4607146385666145e-06,
668
+ "loss": 0.1387,
669
+ "step": 930
670
+ },
671
+ {
672
+ "epoch": 1.7646782527007985,
673
+ "grad_norm": 2.851127249549094,
674
+ "learning_rate": 4.352329677919983e-06,
675
+ "loss": 0.1595,
676
+ "step": 940
677
+ },
678
+ {
679
+ "epoch": 1.7834664161578204,
680
+ "grad_norm": 2.2742219632834795,
681
+ "learning_rate": 4.244253401831646e-06,
682
+ "loss": 0.11,
683
+ "step": 950
684
+ },
685
+ {
686
+ "epoch": 1.8022545796148428,
687
+ "grad_norm": 1.9123730074854848,
688
+ "learning_rate": 4.136537320269571e-06,
689
+ "loss": 0.1205,
690
+ "step": 960
691
+ },
692
+ {
693
+ "epoch": 1.8210427430718648,
694
+ "grad_norm": 2.5825751840603277,
695
+ "learning_rate": 4.029232771530306e-06,
696
+ "loss": 0.1134,
697
+ "step": 970
698
+ },
699
+ {
700
+ "epoch": 1.8398309065288867,
701
+ "grad_norm": 2.471433944974579,
702
+ "learning_rate": 3.92239089777075e-06,
703
+ "loss": 0.1123,
704
+ "step": 980
705
+ },
706
+ {
707
+ "epoch": 1.8586190699859089,
708
+ "grad_norm": 3.5281114838659686,
709
+ "learning_rate": 3.816062620633414e-06,
710
+ "loss": 0.1188,
711
+ "step": 990
712
+ },
713
+ {
714
+ "epoch": 1.877407233442931,
715
+ "grad_norm": 1.9634958487628664,
716
+ "learning_rate": 3.7102986169767954e-06,
717
+ "loss": 0.1062,
718
+ "step": 1000
719
+ },
720
+ {
721
+ "epoch": 1.877407233442931,
722
+ "eval_loss": 0.19623179733753204,
723
+ "eval_runtime": 139.2435,
724
+ "eval_samples_per_second": 6.794,
725
+ "eval_steps_per_second": 1.702,
726
+ "step": 1000
727
+ },
728
+ {
729
+ "epoch": 1.896195396899953,
730
+ "grad_norm": 3.6853787421863164,
731
+ "learning_rate": 3.605149294722392e-06,
732
+ "loss": 0.1055,
733
+ "step": 1010
734
+ },
735
+ {
736
+ "epoch": 1.9149835603569751,
737
+ "grad_norm": 3.7066247620003168,
738
+ "learning_rate": 3.500664768829908e-06,
739
+ "loss": 0.125,
740
+ "step": 1020
741
+ },
742
+ {
743
+ "epoch": 1.9337717238139973,
744
+ "grad_norm": 1.9487521917157127,
745
+ "learning_rate": 3.3968948374120958e-06,
746
+ "loss": 0.1046,
747
+ "step": 1030
748
+ },
749
+ {
750
+ "epoch": 1.9525598872710193,
751
+ "grad_norm": 1.7787524143692979,
752
+ "learning_rate": 3.2938889580005932e-06,
753
+ "loss": 0.1308,
754
+ "step": 1040
755
+ },
756
+ {
757
+ "epoch": 1.9713480507280412,
758
+ "grad_norm": 2.4115181227326383,
759
+ "learning_rate": 3.191696223974084e-06,
760
+ "loss": 0.1195,
761
+ "step": 1050
762
+ },
763
+ {
764
+ "epoch": 1.9901362141850634,
765
+ "grad_norm": 1.8676954461633957,
766
+ "learning_rate": 3.090365341160041e-06,
767
+ "loss": 0.119,
768
+ "step": 1060
769
+ },
770
+ {
771
+ "epoch": 2.0075152653828088,
772
+ "grad_norm": 2.0403175416536157,
773
+ "learning_rate": 2.989944604621148e-06,
774
+ "loss": 0.1082,
775
+ "step": 1070
776
+ },
777
+ {
778
+ "epoch": 2.0263034288398307,
779
+ "grad_norm": 1.8796687540004382,
780
+ "learning_rate": 2.8904818756375076e-06,
781
+ "loss": 0.0649,
782
+ "step": 1080
783
+ },
784
+ {
785
+ "epoch": 2.045091592296853,
786
+ "grad_norm": 1.6678868897065664,
787
+ "learning_rate": 2.792024558895606e-06,
788
+ "loss": 0.0671,
789
+ "step": 1090
790
+ },
791
+ {
792
+ "epoch": 2.063879755753875,
793
+ "grad_norm": 3.1485507384660547,
794
+ "learning_rate": 2.6946195798948755e-06,
795
+ "loss": 0.0597,
796
+ "step": 1100
797
+ },
798
+ {
799
+ "epoch": 2.082667919210897,
800
+ "grad_norm": 0.966514290803291,
801
+ "learning_rate": 2.598313362582639e-06,
802
+ "loss": 0.0582,
803
+ "step": 1110
804
+ },
805
+ {
806
+ "epoch": 2.1014560826679194,
807
+ "grad_norm": 1.3610544972984766,
808
+ "learning_rate": 2.5031518072281236e-06,
809
+ "loss": 0.0609,
810
+ "step": 1120
811
+ },
812
+ {
813
+ "epoch": 2.1202442461249413,
814
+ "grad_norm": 1.5921330796712605,
815
+ "learning_rate": 2.4091802685460336e-06,
816
+ "loss": 0.0664,
817
+ "step": 1130
818
+ },
819
+ {
820
+ "epoch": 2.1390324095819633,
821
+ "grad_norm": 2.3312224294157025,
822
+ "learning_rate": 2.3164435340801574e-06,
823
+ "loss": 0.0675,
824
+ "step": 1140
825
+ },
826
+ {
827
+ "epoch": 2.1578205730389852,
828
+ "grad_norm": 1.7103466660833229,
829
+ "learning_rate": 2.224985802857284e-06,
830
+ "loss": 0.0453,
831
+ "step": 1150
832
+ },
833
+ {
834
+ "epoch": 2.1766087364960076,
835
+ "grad_norm": 2.060481882429091,
836
+ "learning_rate": 2.134850664321617e-06,
837
+ "loss": 0.0625,
838
+ "step": 1160
839
+ },
840
+ {
841
+ "epoch": 2.1953968999530296,
842
+ "grad_norm": 0.9427782782833426,
843
+ "learning_rate": 2.046081077559707e-06,
844
+ "loss": 0.0565,
845
+ "step": 1170
846
+ },
847
+ {
848
+ "epoch": 2.2141850634100515,
849
+ "grad_norm": 1.9240741575863745,
850
+ "learning_rate": 1.9587193508258415e-06,
851
+ "loss": 0.051,
852
+ "step": 1180
853
+ },
854
+ {
855
+ "epoch": 2.232973226867074,
856
+ "grad_norm": 1.2001636500769781,
857
+ "learning_rate": 1.8728071213776028e-06,
858
+ "loss": 0.048,
859
+ "step": 1190
860
+ },
861
+ {
862
+ "epoch": 2.251761390324096,
863
+ "grad_norm": 1.8036945101434407,
864
+ "learning_rate": 1.7883853356312375e-06,
865
+ "loss": 0.0575,
866
+ "step": 1200
867
+ },
868
+ {
869
+ "epoch": 2.270549553781118,
870
+ "grad_norm": 1.2865058971634646,
871
+ "learning_rate": 1.7054942296462895e-06,
872
+ "loss": 0.0708,
873
+ "step": 1210
874
+ },
875
+ {
876
+ "epoch": 2.2893377172381397,
877
+ "grad_norm": 1.9144408525509076,
878
+ "learning_rate": 1.6241733099487888e-06,
879
+ "loss": 0.0513,
880
+ "step": 1220
881
+ },
882
+ {
883
+ "epoch": 2.308125880695162,
884
+ "grad_norm": 1.7106138783392042,
885
+ "learning_rate": 1.5444613347021392e-06,
886
+ "loss": 0.0562,
887
+ "step": 1230
888
+ },
889
+ {
890
+ "epoch": 2.326914044152184,
891
+ "grad_norm": 1.2128475292175165,
892
+ "learning_rate": 1.4663962952346938e-06,
893
+ "loss": 0.0507,
894
+ "step": 1240
895
+ },
896
+ {
897
+ "epoch": 2.3457022076092064,
898
+ "grad_norm": 1.321730273201786,
899
+ "learning_rate": 1.3900153979327951e-06,
900
+ "loss": 0.0577,
901
+ "step": 1250
902
+ },
903
+ {
904
+ "epoch": 2.3644903710662284,
905
+ "grad_norm": 2.7875274955613745,
906
+ "learning_rate": 1.315355046507934e-06,
907
+ "loss": 0.0648,
908
+ "step": 1260
909
+ },
910
+ {
911
+ "epoch": 2.3832785345232503,
912
+ "grad_norm": 1.8288963759953032,
913
+ "learning_rate": 1.2424508246464635e-06,
914
+ "loss": 0.0558,
915
+ "step": 1270
916
+ },
917
+ {
918
+ "epoch": 2.4020666979802723,
919
+ "grad_norm": 1.537482323897175,
920
+ "learning_rate": 1.171337479050148e-06,
921
+ "loss": 0.061,
922
+ "step": 1280
923
+ },
924
+ {
925
+ "epoch": 2.4208548614372947,
926
+ "grad_norm": 2.1795553061277357,
927
+ "learning_rate": 1.1020489028756243e-06,
928
+ "loss": 0.0521,
929
+ "step": 1290
930
+ },
931
+ {
932
+ "epoch": 2.4396430248943166,
933
+ "grad_norm": 1.75277898274252,
934
+ "learning_rate": 1.0346181195806614e-06,
935
+ "loss": 0.0583,
936
+ "step": 1300
937
+ },
938
+ {
939
+ "epoch": 2.4584311883513386,
940
+ "grad_norm": 1.7605887217641596,
941
+ "learning_rate": 9.690772671849403e-07,
942
+ "loss": 0.0546,
943
+ "step": 1310
944
+ },
945
+ {
946
+ "epoch": 2.477219351808361,
947
+ "grad_norm": 1.447955784872353,
948
+ "learning_rate": 9.054575829528251e-07,
949
+ "loss": 0.0551,
950
+ "step": 1320
951
+ },
952
+ {
953
+ "epoch": 2.496007515265383,
954
+ "grad_norm": 5.225313476562762,
955
+ "learning_rate": 8.437893885054504e-07,
956
+ "loss": 0.0517,
957
+ "step": 1330
958
+ },
959
+ {
960
+ "epoch": 2.514795678722405,
961
+ "grad_norm": 1.5717503369334935,
962
+ "learning_rate": 7.841020753692058e-07,
963
+ "loss": 0.0545,
964
+ "step": 1340
965
+ },
966
+ {
967
+ "epoch": 2.533583842179427,
968
+ "grad_norm": 2.6343667579863963,
969
+ "learning_rate": 7.264240909675174e-07,
970
+ "loss": 0.0472,
971
+ "step": 1350
972
+ },
973
+ {
974
+ "epoch": 2.552372005636449,
975
+ "grad_norm": 2.023557390851674,
976
+ "learning_rate": 6.707829250625825e-07,
977
+ "loss": 0.0446,
978
+ "step": 1360
979
+ },
980
+ {
981
+ "epoch": 2.571160169093471,
982
+ "grad_norm": 1.6290921730514096,
983
+ "learning_rate": 6.172050966535514e-07,
984
+ "loss": 0.0542,
985
+ "step": 1370
986
+ },
987
+ {
988
+ "epoch": 2.589948332550493,
989
+ "grad_norm": 1.712949974396625,
990
+ "learning_rate": 5.65716141337368e-07,
991
+ "loss": 0.0469,
992
+ "step": 1380
993
+ },
994
+ {
995
+ "epoch": 2.6087364960075154,
996
+ "grad_norm": 1.3027380061751708,
997
+ "learning_rate": 5.163405991383114e-07,
998
+ "loss": 0.0425,
999
+ "step": 1390
1000
+ },
1001
+ {
1002
+ "epoch": 2.6275246594645374,
1003
+ "grad_norm": 1.065265515773574,
1004
+ "learning_rate": 4.6910200281203523e-07,
1005
+ "loss": 0.0504,
1006
+ "step": 1400
1007
+ },
1008
+ {
1009
+ "epoch": 2.6463128229215593,
1010
+ "grad_norm": 1.9478720946650225,
1011
+ "learning_rate": 4.240228666296825e-07,
1012
+ "loss": 0.0634,
1013
+ "step": 1410
1014
+ },
1015
+ {
1016
+ "epoch": 2.6651009863785813,
1017
+ "grad_norm": 2.5865600012088326,
1018
+ "learning_rate": 3.8112467564740796e-07,
1019
+ "loss": 0.0573,
1020
+ "step": 1420
1021
+ },
1022
+ {
1023
+ "epoch": 2.6838891498356037,
1024
+ "grad_norm": 2.0098060853151702,
1025
+ "learning_rate": 3.4042787546644305e-07,
1026
+ "loss": 0.07,
1027
+ "step": 1430
1028
+ },
1029
+ {
1030
+ "epoch": 2.7026773132926256,
1031
+ "grad_norm": 1.1444888015196577,
1032
+ "learning_rate": 3.0195186248856866e-07,
1033
+ "loss": 0.0448,
1034
+ "step": 1440
1035
+ },
1036
+ {
1037
+ "epoch": 2.7214654767496476,
1038
+ "grad_norm": 1.0223331183810753,
1039
+ "learning_rate": 2.6571497467164033e-07,
1040
+ "loss": 0.058,
1041
+ "step": 1450
1042
+ },
1043
+ {
1044
+ "epoch": 2.74025364020667,
1045
+ "grad_norm": 1.4130933630125946,
1046
+ "learning_rate": 2.3173448278958178e-07,
1047
+ "loss": 0.0654,
1048
+ "step": 1460
1049
+ },
1050
+ {
1051
+ "epoch": 2.759041803663692,
1052
+ "grad_norm": 1.2949137507027924,
1053
+ "learning_rate": 2.0002658220100334e-07,
1054
+ "loss": 0.0556,
1055
+ "step": 1470
1056
+ },
1057
+ {
1058
+ "epoch": 2.777829967120714,
1059
+ "grad_norm": 1.5805556155196185,
1060
+ "learning_rate": 1.7060638513037076e-07,
1061
+ "loss": 0.0558,
1062
+ "step": 1480
1063
+ },
1064
+ {
1065
+ "epoch": 2.796618130577736,
1066
+ "grad_norm": 2.0964534267823725,
1067
+ "learning_rate": 1.434879134654077e-07,
1068
+ "loss": 0.0496,
1069
+ "step": 1490
1070
+ },
1071
+ {
1072
+ "epoch": 2.815406294034758,
1073
+ "grad_norm": 1.464233077890015,
1074
+ "learning_rate": 1.186840920741561e-07,
1075
+ "loss": 0.0573,
1076
+ "step": 1500
1077
+ },
1078
+ {
1079
+ "epoch": 2.815406294034758,
1080
+ "eval_loss": 0.19711866974830627,
1081
+ "eval_runtime": 140.2242,
1082
+ "eval_samples_per_second": 6.746,
1083
+ "eval_steps_per_second": 1.69,
1084
+ "step": 1500
1085
+ },
1086
+ {
1087
+ "epoch": 2.83419445749178,
1088
+ "grad_norm": 0.969822959813251,
1089
+ "learning_rate": 9.620674264488594e-08,
1090
+ "loss": 0.0548,
1091
+ "step": 1510
1092
+ },
1093
+ {
1094
+ "epoch": 2.8529826209488025,
1095
+ "grad_norm": 1.8413122290273847,
1096
+ "learning_rate": 7.606657805179274e-08,
1097
+ "loss": 0.063,
1098
+ "step": 1520
1099
+ },
1100
+ {
1101
+ "epoch": 2.8717707844058245,
1102
+ "grad_norm": 0.7665376382039885,
1103
+ "learning_rate": 5.827319724915959e-08,
1104
+ "loss": 0.0514,
1105
+ "step": 1530
1106
+ },
1107
+ {
1108
+ "epoch": 2.8905589478628464,
1109
+ "grad_norm": 0.8215067982809356,
1110
+ "learning_rate": 4.283508069641951e-08,
1111
+ "loss": 0.0467,
1112
+ "step": 1540
1113
+ },
1114
+ {
1115
+ "epoch": 2.9093471113198683,
1116
+ "grad_norm": 2.021014987559278,
1117
+ "learning_rate": 2.975958631631082e-08,
1118
+ "loss": 0.0483,
1119
+ "step": 1550
1120
+ },
1121
+ {
1122
+ "epoch": 2.9281352747768903,
1123
+ "grad_norm": 1.4695240828377725,
1124
+ "learning_rate": 1.9052945988030648e-08,
1125
+ "loss": 0.0427,
1126
+ "step": 1560
1127
+ },
1128
+ {
1129
+ "epoch": 2.9469234382339127,
1130
+ "grad_norm": 1.1451618059955273,
1131
+ "learning_rate": 1.0720262577076923e-08,
1132
+ "loss": 0.0493,
1133
+ "step": 1570
1134
+ },
1135
+ {
1136
+ "epoch": 2.9657116016909346,
1137
+ "grad_norm": 2.9129055521839895,
1138
+ "learning_rate": 4.76550750318383e-09,
1139
+ "loss": 0.0542,
1140
+ "step": 1580
1141
+ },
1142
+ {
1143
+ "epoch": 2.984499765147957,
1144
+ "grad_norm": 1.7988477080352803,
1145
+ "learning_rate": 1.1915188475125627e-09,
1146
+ "loss": 0.04,
1147
+ "step": 1590
1148
+ },
1149
+ {
1150
+ "epoch": 3.0,
1151
+ "step": 1599,
1152
+ "total_flos": 141952390594560.0,
1153
+ "train_loss": 0.17646967794389706,
1154
+ "train_runtime": 16767.1291,
1155
+ "train_samples_per_second": 1.523,
1156
+ "train_steps_per_second": 0.095
1157
+ }
1158
+ ],
1159
+ "logging_steps": 10,
1160
+ "max_steps": 1599,
1161
+ "num_input_tokens_seen": 0,
1162
+ "num_train_epochs": 3,
1163
+ "save_steps": 500,
1164
+ "stateful_callbacks": {
1165
+ "TrainerControl": {
1166
+ "args": {
1167
+ "should_epoch_stop": false,
1168
+ "should_evaluate": false,
1169
+ "should_log": false,
1170
+ "should_save": true,
1171
+ "should_training_stop": true
1172
+ },
1173
+ "attributes": {}
1174
+ }
1175
+ },
1176
+ "total_flos": 141952390594560.0,
1177
+ "train_batch_size": 1,
1178
+ "trial_name": null,
1179
+ "trial_params": null
1180
+ }
webrl-llama/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640a7001351e8f2633216b27e57e0b9bb300f91a2cc9b9af49bc6b7c6507894e
3
+ size 8081
webrl-llama/training_eval_loss.png ADDED
webrl-llama/training_loss.png ADDED