Model save
Browse files- README.md +16 -18
- all_results.json +4 -4
- config.json +12 -9
- generation_config.json +9 -3
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- model.safetensors.index.json +292 -292
- special_tokens_map.json +3 -21
- tokenizer.json +0 -0
- tokenizer_config.json +2039 -22
- train_results.json +4 -4
- trainer_state.json +527 -527
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
-
base_model: HuggingFaceH4/mistral-7b-sft-beta
|
| 4 |
tags:
|
| 5 |
- trl
|
| 6 |
- dpo
|
|
@@ -15,17 +13,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# zephyr-7b-dpo-full
|
| 17 |
|
| 18 |
-
This model
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Rewards/chosen: -
|
| 22 |
-
- Rewards/rejected: -
|
| 23 |
-
- Rewards/accuracies: 0.
|
| 24 |
-
- Rewards/margins: 0.
|
| 25 |
-
- Logps/rejected: -
|
| 26 |
-
- Logps/chosen: -
|
| 27 |
-
- Logits/rejected:
|
| 28 |
-
- Logits/chosen:
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
@@ -45,12 +43,12 @@ More information needed
|
|
| 45 |
|
| 46 |
The following hyperparameters were used during training:
|
| 47 |
- learning_rate: 5e-07
|
| 48 |
-
- train_batch_size:
|
| 49 |
- eval_batch_size: 8
|
| 50 |
- seed: 1
|
| 51 |
- distributed_type: multi-GPU
|
| 52 |
- num_devices: 8
|
| 53 |
-
- gradient_accumulation_steps:
|
| 54 |
- total_train_batch_size: 128
|
| 55 |
- total_eval_batch_size: 64
|
| 56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
@@ -62,10 +60,10 @@ The following hyperparameters were used during training:
|
|
| 62 |
|
| 63 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
| 64 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- trl
|
| 4 |
- dpo
|
|
|
|
| 13 |
|
| 14 |
# zephyr-7b-dpo-full
|
| 15 |
|
| 16 |
+
This model was trained from scratch on the None dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0515
|
| 19 |
+
- Rewards/chosen: -0.5698
|
| 20 |
+
- Rewards/rejected: -1.0751
|
| 21 |
+
- Rewards/accuracies: 0.7305
|
| 22 |
+
- Rewards/margins: 0.5053
|
| 23 |
+
- Logps/rejected: -473.2190
|
| 24 |
+
- Logps/chosen: -416.4288
|
| 25 |
+
- Logits/rejected: 0.8846
|
| 26 |
+
- Logits/chosen: 0.7434
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 43 |
|
| 44 |
The following hyperparameters were used during training:
|
| 45 |
- learning_rate: 5e-07
|
| 46 |
+
- train_batch_size: 4
|
| 47 |
- eval_batch_size: 8
|
| 48 |
- seed: 1
|
| 49 |
- distributed_type: multi-GPU
|
| 50 |
- num_devices: 8
|
| 51 |
+
- gradient_accumulation_steps: 4
|
| 52 |
- total_train_batch_size: 128
|
| 53 |
- total_eval_batch_size: 64
|
| 54 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
|
| 60 |
|
| 61 |
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|
| 62 |
|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
|
| 63 |
+
| 0.0993 | 0.21 | 100 | 0.1018 | -0.0745 | -0.2470 | 0.6875 | 0.1725 | -390.4119 | -366.9025 | 0.5707 | 0.5130 |
|
| 64 |
+
| 0.0553 | 0.42 | 200 | 0.0540 | -0.5063 | -0.9361 | 0.7305 | 0.4298 | -459.3217 | -410.0835 | 0.8994 | 0.7755 |
|
| 65 |
+
| 0.0503 | 0.63 | 300 | 0.0531 | -0.5353 | -1.0266 | 0.7461 | 0.4913 | -468.3688 | -412.9813 | 0.8095 | 0.6691 |
|
| 66 |
+
| 0.0537 | 0.84 | 400 | 0.0515 | -0.5698 | -1.0751 | 0.7305 | 0.5053 | -473.2190 | -416.4288 | 0.8846 | 0.7434 |
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 61134,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.06614070340397472,
|
| 4 |
+
"train_runtime": 4423.243,
|
| 5 |
"train_samples": 61134,
|
| 6 |
+
"train_samples_per_second": 13.821,
|
| 7 |
+
"train_steps_per_second": 0.108
|
| 8 |
}
|
config.json
CHANGED
|
@@ -1,25 +1,28 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
-
"
|
| 7 |
-
"
|
|
|
|
|
|
|
| 8 |
"hidden_act": "silu",
|
| 9 |
"hidden_size": 4096,
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 14336,
|
| 12 |
-
"max_position_embeddings":
|
| 13 |
-
"model_type": "
|
| 14 |
"num_attention_heads": 32,
|
| 15 |
"num_hidden_layers": 32,
|
| 16 |
"num_key_value_heads": 8,
|
|
|
|
| 17 |
"rms_norm_eps": 1e-05,
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
"tie_word_embeddings": false,
|
| 21 |
"torch_dtype": "bfloat16",
|
| 22 |
"transformers_version": "4.35.2",
|
| 23 |
"use_cache": false,
|
| 24 |
-
"vocab_size":
|
| 25 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/share5/projects/llm/finetune-accelerate/weight/Meta-Llama-3-8B-Instruct",
|
| 3 |
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128009,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
"num_attention_heads": 32,
|
| 17 |
"num_hidden_layers": 32,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000.0,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.35.2",
|
| 26 |
"use_cache": false,
|
| 27 |
+
"vocab_size": 128256
|
| 28 |
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"transformers_version": "4.35.2"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128009
|
| 7 |
+
],
|
| 8 |
+
"max_length": 4096,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
"transformers_version": "4.35.2"
|
| 12 |
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38ba70e65ee6495d6142328650a81a3d99c446c7c25f7e9f8cac187fba978d69
|
| 3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcdbaa7331284bffa3d618292207ea0cbbd9a63a92e4c00bf8ed4cbe607c5ed1
|
| 3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b5d969644264ab3fae956f1eb2d4bbdaf36aee0e6a96ece71c7e40e540b1640
|
| 3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f13c9d26d250a584eded5cc5f110f766404c41b7baee91a2cc86e8a147bda71c
|
| 3 |
size 1168138808
|
model.safetensors.index.json
CHANGED
|
@@ -1,298 +1,298 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"lm_head.weight": "model-
|
| 7 |
-
"model.embed_tokens.weight": "model-00001-of-
|
| 8 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-
|
| 9 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-
|
| 10 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-
|
| 11 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-
|
| 12 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
| 13 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-
|
| 14 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-
|
| 15 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-
|
| 16 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-
|
| 17 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-
|
| 18 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-
|
| 19 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-
|
| 20 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-
|
| 21 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-
|
| 22 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-
|
| 23 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-
|
| 24 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-
|
| 25 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-
|
| 26 |
-
"model.layers.10.input_layernorm.weight": "model-00002-of-
|
| 27 |
-
"model.layers.10.mlp.down_proj.weight": "model-00002-of-
|
| 28 |
-
"model.layers.10.mlp.gate_proj.weight": "model-
|
| 29 |
-
"model.layers.10.mlp.up_proj.weight": "model-
|
| 30 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-
|
| 31 |
-
"model.layers.10.self_attn.k_proj.weight": "model-
|
| 32 |
-
"model.layers.10.self_attn.o_proj.weight": "model-
|
| 33 |
-
"model.layers.10.self_attn.q_proj.weight": "model-
|
| 34 |
-
"model.layers.10.self_attn.v_proj.weight": "model-
|
| 35 |
-
"model.layers.11.input_layernorm.weight": "model-00002-of-
|
| 36 |
-
"model.layers.11.mlp.down_proj.weight": "model-00002-of-
|
| 37 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-
|
| 38 |
-
"model.layers.11.mlp.up_proj.weight": "model-00002-of-
|
| 39 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-
|
| 40 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-
|
| 41 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-
|
| 42 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-
|
| 43 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-
|
| 44 |
-
"model.layers.12.input_layernorm.weight": "model-00002-of-
|
| 45 |
-
"model.layers.12.mlp.down_proj.weight": "model-00002-of-
|
| 46 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-
|
| 47 |
-
"model.layers.12.mlp.up_proj.weight": "model-00002-of-
|
| 48 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-
|
| 49 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-
|
| 50 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-
|
| 51 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-
|
| 52 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-
|
| 53 |
-
"model.layers.13.input_layernorm.weight": "model-00002-of-
|
| 54 |
-
"model.layers.13.mlp.down_proj.weight": "model-00002-of-
|
| 55 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-
|
| 56 |
-
"model.layers.13.mlp.up_proj.weight": "model-00002-of-
|
| 57 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-
|
| 58 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-
|
| 59 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-
|
| 60 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-
|
| 61 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-
|
| 62 |
-
"model.layers.14.input_layernorm.weight": "model-00002-of-
|
| 63 |
-
"model.layers.14.mlp.down_proj.weight": "model-00002-of-
|
| 64 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-
|
| 65 |
-
"model.layers.14.mlp.up_proj.weight": "model-00002-of-
|
| 66 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-
|
| 67 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-
|
| 68 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-
|
| 69 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-
|
| 70 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-
|
| 71 |
-
"model.layers.15.input_layernorm.weight": "model-00002-of-
|
| 72 |
-
"model.layers.15.mlp.down_proj.weight": "model-00002-of-
|
| 73 |
-
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-
|
| 74 |
-
"model.layers.15.mlp.up_proj.weight": "model-00002-of-
|
| 75 |
-
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-
|
| 76 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-
|
| 77 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-
|
| 78 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-
|
| 79 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-
|
| 80 |
-
"model.layers.16.input_layernorm.weight": "model-00002-of-
|
| 81 |
-
"model.layers.16.mlp.down_proj.weight": "model-00002-of-
|
| 82 |
-
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-
|
| 83 |
-
"model.layers.16.mlp.up_proj.weight": "model-00002-of-
|
| 84 |
-
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-
|
| 85 |
-
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-
|
| 86 |
-
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-
|
| 87 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-
|
| 88 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-
|
| 89 |
-
"model.layers.17.input_layernorm.weight": "model-00002-of-
|
| 90 |
-
"model.layers.17.mlp.down_proj.weight": "model-00002-of-
|
| 91 |
-
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-
|
| 92 |
-
"model.layers.17.mlp.up_proj.weight": "model-00002-of-
|
| 93 |
-
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-
|
| 94 |
-
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-
|
| 95 |
-
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-
|
| 96 |
-
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-
|
| 97 |
-
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-
|
| 98 |
-
"model.layers.18.input_layernorm.weight": "model-00002-of-
|
| 99 |
-
"model.layers.18.mlp.down_proj.weight": "model-00002-of-
|
| 100 |
-
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-
|
| 101 |
-
"model.layers.18.mlp.up_proj.weight": "model-00002-of-
|
| 102 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-
|
| 103 |
-
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-
|
| 104 |
-
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-
|
| 105 |
-
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-
|
| 106 |
-
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-
|
| 107 |
-
"model.layers.19.input_layernorm.weight": "model-00002-of-
|
| 108 |
-
"model.layers.19.mlp.down_proj.weight": "model-00002-of-
|
| 109 |
-
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-
|
| 110 |
-
"model.layers.19.mlp.up_proj.weight": "model-00002-of-
|
| 111 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-
|
| 112 |
-
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-
|
| 113 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-
|
| 114 |
-
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-
|
| 115 |
-
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-
|
| 116 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-
|
| 117 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-
|
| 118 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-
|
| 119 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-
|
| 120 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-
|
| 121 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-
|
| 122 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-
|
| 123 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-
|
| 124 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-
|
| 125 |
-
"model.layers.20.input_layernorm.weight": "model-
|
| 126 |
-
"model.layers.20.mlp.down_proj.weight": "model-
|
| 127 |
-
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-
|
| 128 |
-
"model.layers.20.mlp.up_proj.weight": "model-
|
| 129 |
-
"model.layers.20.post_attention_layernorm.weight": "model-
|
| 130 |
-
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-
|
| 131 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-
|
| 132 |
-
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-
|
| 133 |
-
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-
|
| 134 |
-
"model.layers.21.input_layernorm.weight": "model-
|
| 135 |
-
"model.layers.21.mlp.down_proj.weight": "model-
|
| 136 |
-
"model.layers.21.mlp.gate_proj.weight": "model-
|
| 137 |
-
"model.layers.21.mlp.up_proj.weight": "model-
|
| 138 |
-
"model.layers.21.post_attention_layernorm.weight": "model-
|
| 139 |
-
"model.layers.21.self_attn.k_proj.weight": "model-
|
| 140 |
-
"model.layers.21.self_attn.o_proj.weight": "model-
|
| 141 |
-
"model.layers.21.self_attn.q_proj.weight": "model-
|
| 142 |
-
"model.layers.21.self_attn.v_proj.weight": "model-
|
| 143 |
-
"model.layers.22.input_layernorm.weight": "model-00003-of-
|
| 144 |
-
"model.layers.22.mlp.down_proj.weight": "model-00003-of-
|
| 145 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-
|
| 146 |
-
"model.layers.22.mlp.up_proj.weight": "model-00003-of-
|
| 147 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-
|
| 148 |
-
"model.layers.22.self_attn.k_proj.weight": "model-
|
| 149 |
-
"model.layers.22.self_attn.o_proj.weight": "model-
|
| 150 |
-
"model.layers.22.self_attn.q_proj.weight": "model-
|
| 151 |
-
"model.layers.22.self_attn.v_proj.weight": "model-
|
| 152 |
-
"model.layers.23.input_layernorm.weight": "model-00003-of-
|
| 153 |
-
"model.layers.23.mlp.down_proj.weight": "model-00003-of-
|
| 154 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-
|
| 155 |
-
"model.layers.23.mlp.up_proj.weight": "model-00003-of-
|
| 156 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-
|
| 157 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-
|
| 158 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-
|
| 159 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-
|
| 160 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-
|
| 161 |
-
"model.layers.24.input_layernorm.weight": "model-00003-of-
|
| 162 |
-
"model.layers.24.mlp.down_proj.weight": "model-00003-of-
|
| 163 |
-
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-
|
| 164 |
-
"model.layers.24.mlp.up_proj.weight": "model-00003-of-
|
| 165 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-
|
| 166 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-
|
| 167 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-
|
| 168 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-
|
| 169 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-
|
| 170 |
-
"model.layers.25.input_layernorm.weight": "model-00003-of-
|
| 171 |
-
"model.layers.25.mlp.down_proj.weight": "model-00003-of-
|
| 172 |
-
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-
|
| 173 |
-
"model.layers.25.mlp.up_proj.weight": "model-00003-of-
|
| 174 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-
|
| 175 |
-
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-
|
| 176 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-
|
| 177 |
-
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-
|
| 178 |
-
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-
|
| 179 |
-
"model.layers.26.input_layernorm.weight": "model-00003-of-
|
| 180 |
-
"model.layers.26.mlp.down_proj.weight": "model-00003-of-
|
| 181 |
-
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-
|
| 182 |
-
"model.layers.26.mlp.up_proj.weight": "model-00003-of-
|
| 183 |
-
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-
|
| 184 |
-
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-
|
| 185 |
-
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-
|
| 186 |
-
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-
|
| 187 |
-
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-
|
| 188 |
-
"model.layers.27.input_layernorm.weight": "model-00003-of-
|
| 189 |
-
"model.layers.27.mlp.down_proj.weight": "model-00003-of-
|
| 190 |
-
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-
|
| 191 |
-
"model.layers.27.mlp.up_proj.weight": "model-00003-of-
|
| 192 |
-
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-
|
| 193 |
-
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-
|
| 194 |
-
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-
|
| 195 |
-
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-
|
| 196 |
-
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-
|
| 197 |
-
"model.layers.28.input_layernorm.weight": "model-00003-of-
|
| 198 |
-
"model.layers.28.mlp.down_proj.weight": "model-00003-of-
|
| 199 |
-
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-
|
| 200 |
-
"model.layers.28.mlp.up_proj.weight": "model-00003-of-
|
| 201 |
-
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-
|
| 202 |
-
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-
|
| 203 |
-
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-
|
| 204 |
-
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-
|
| 205 |
-
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-
|
| 206 |
-
"model.layers.29.input_layernorm.weight": "model-00003-of-
|
| 207 |
-
"model.layers.29.mlp.down_proj.weight": "model-00003-of-
|
| 208 |
-
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-
|
| 209 |
-
"model.layers.29.mlp.up_proj.weight": "model-00003-of-
|
| 210 |
-
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-
|
| 211 |
-
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-
|
| 212 |
-
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-
|
| 213 |
-
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-
|
| 214 |
-
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-
|
| 215 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-
|
| 216 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-
|
| 217 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-
|
| 218 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-
|
| 219 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-
|
| 220 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-
|
| 221 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-
|
| 222 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-
|
| 223 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-
|
| 224 |
-
"model.layers.30.input_layernorm.weight": "model-00003-of-
|
| 225 |
-
"model.layers.30.mlp.down_proj.weight": "model-00003-of-
|
| 226 |
-
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-
|
| 227 |
-
"model.layers.30.mlp.up_proj.weight": "model-00003-of-
|
| 228 |
-
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-
|
| 229 |
-
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-
|
| 230 |
-
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-
|
| 231 |
-
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-
|
| 232 |
-
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-
|
| 233 |
-
"model.layers.31.input_layernorm.weight": "model-
|
| 234 |
-
"model.layers.31.mlp.down_proj.weight": "model-
|
| 235 |
-
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-
|
| 236 |
-
"model.layers.31.mlp.up_proj.weight": "model-00003-of-
|
| 237 |
-
"model.layers.31.post_attention_layernorm.weight": "model-
|
| 238 |
-
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-
|
| 239 |
-
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-
|
| 240 |
-
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-
|
| 241 |
-
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-
|
| 242 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-
|
| 243 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-
|
| 244 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-
|
| 245 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-
|
| 246 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-
|
| 247 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-
|
| 248 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-
|
| 249 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-
|
| 250 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-
|
| 251 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-
|
| 252 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-
|
| 253 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-
|
| 254 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-
|
| 255 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-
|
| 256 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-
|
| 257 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-
|
| 258 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-
|
| 259 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-
|
| 260 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-
|
| 261 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-
|
| 262 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-
|
| 263 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-
|
| 264 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-
|
| 265 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-
|
| 266 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-
|
| 267 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-
|
| 268 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-
|
| 269 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-
|
| 270 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-
|
| 271 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-
|
| 272 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-
|
| 273 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-
|
| 274 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-
|
| 275 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-
|
| 276 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-
|
| 277 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-
|
| 278 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-
|
| 279 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-
|
| 280 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-
|
| 281 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-
|
| 282 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-
|
| 283 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-
|
| 284 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-
|
| 285 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-
|
| 286 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-
|
| 287 |
-
"model.layers.9.input_layernorm.weight": "model-
|
| 288 |
-
"model.layers.9.mlp.down_proj.weight": "model-
|
| 289 |
-
"model.layers.9.mlp.gate_proj.weight": "model-
|
| 290 |
-
"model.layers.9.mlp.up_proj.weight": "model-
|
| 291 |
-
"model.layers.9.post_attention_layernorm.weight": "model-
|
| 292 |
-
"model.layers.9.self_attn.k_proj.weight": "model-
|
| 293 |
-
"model.layers.9.self_attn.o_proj.weight": "model-
|
| 294 |
-
"model.layers.9.self_attn.q_proj.weight": "model-
|
| 295 |
-
"model.layers.9.self_attn.v_proj.weight": "model-
|
| 296 |
-
"model.norm.weight": "model-
|
| 297 |
}
|
| 298 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 16060522496
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 297 |
}
|
| 298 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,35 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<unk>",
|
| 4 |
-
"<s>",
|
| 5 |
-
"</s>"
|
| 6 |
-
],
|
| 7 |
"bos_token": {
|
| 8 |
-
"content": "
|
| 9 |
"lstrip": false,
|
| 10 |
"normalized": false,
|
| 11 |
"rstrip": false,
|
| 12 |
"single_word": false
|
| 13 |
},
|
| 14 |
"eos_token": {
|
| 15 |
-
"content": "
|
| 16 |
"lstrip": false,
|
| 17 |
"normalized": false,
|
| 18 |
"rstrip": false,
|
| 19 |
"single_word": false
|
| 20 |
},
|
| 21 |
-
"pad_token":
|
| 22 |
-
"content": "</s>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false
|
| 27 |
-
},
|
| 28 |
-
"unk_token": {
|
| 29 |
-
"content": "<unk>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false
|
| 34 |
-
}
|
| 35 |
}
|
|
|
|
| 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 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,23 +1,2047 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
-
"
|
| 4 |
-
"content": "
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
-
"content": "
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
-
"content": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
|
@@ -25,22 +2049,15 @@
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
|
|
|
|
|
|
|
|
|
| 32 |
],
|
| 33 |
-
"bos_token": "<s>",
|
| 34 |
-
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 35 |
-
"clean_up_tokenization_spaces": false,
|
| 36 |
-
"eos_token": "</s>",
|
| 37 |
-
"legacy": true,
|
| 38 |
"model_max_length": 2048,
|
| 39 |
-
"pad_token": "
|
| 40 |
-
"
|
| 41 |
-
"spaces_between_special_tokens": false,
|
| 42 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
-
"truncation_side": "left",
|
| 44 |
-
"unk_token": "<unk>",
|
| 45 |
-
"use_default_system_prompt": true
|
| 46 |
}
|
|
|
|
| 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": "<|reserved_special_token_2|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_3|>",
|
| 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": "<|reserved_special_token_4|>",
|
| 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": "<|reserved_special_token_5|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_6|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_7|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_8|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_9|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_10|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_11|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_12|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_13|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_14|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_15|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_16|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_17|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_18|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_19|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_20|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_21|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_22|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_23|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_24|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_25|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_26|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_27|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_28|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_29|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_30|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_31|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_32|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_33|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_34|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_35|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_36|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_37|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_38|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_39|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_40|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_41|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_42|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_43|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_44|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_45|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_46|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_47|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_48|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_49|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_50|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_51|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_52|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_53|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_54|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_55|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_56|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_57|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_58|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_59|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_60|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_61|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_62|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_63|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_64|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_65|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_66|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_67|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_68|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_69|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_70|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_71|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_72|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_73|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_74|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_75|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_76|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_77|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_78|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_79|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_80|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_81|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_82|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_83|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_84|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_85|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_86|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_87|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_88|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_89|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_90|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_91|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_92|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_93|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_94|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_95|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_96|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_97|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_98|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_99|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_100|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_101|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_102|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_103|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_104|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_105|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_106|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_107|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_108|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_109|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_110|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_111|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_112|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_113|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_114|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_115|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_116|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_117|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_118|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_119|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_120|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_121|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_122|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_123|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_124|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_125|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_126|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_127|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_128|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_129|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_130|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_131|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_132|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_133|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_134|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_135|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_136|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_137|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_138|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_139|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_140|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_141|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_142|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_143|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_144|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_145|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_146|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_147|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_148|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_149|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_150|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_151|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_152|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_153|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_154|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_155|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_156|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_157|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_158|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_159|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_160|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_161|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_162|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_163|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_164|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_165|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_166|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_167|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_168|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_169|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_170|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_171|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_172|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_173|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_174|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_175|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_176|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_177|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_178|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_179|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_180|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_181|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_182|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_183|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_184|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_185|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_186|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_187|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_188|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_189|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_190|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_191|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_192|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_193|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_194|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_195|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_196|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_197|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_198|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_199|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_200|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_201|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_202|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_203|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_204|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_205|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_206|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_207|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_208|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_209|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_210|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_211|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_212|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_213|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_214|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_215|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_216|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_217|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_218|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_219|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_220|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_221|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_222|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_223|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_224|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_225|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_226|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_227|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_228|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_229|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_230|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_231|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_232|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_233|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_234|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_235|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_236|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_237|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_238|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_239|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_240|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_241|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_242|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_243|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_244|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_245|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_246|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_247|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_248|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_249|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_250|>",
|
| 2045 |
"lstrip": false,
|
| 2046 |
"normalized": false,
|
| 2047 |
"rstrip": false,
|
|
|
|
| 2049 |
"special": true
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2060 |
"model_max_length": 2048,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2063 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 61134,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.06614070340397472,
|
| 4 |
+
"train_runtime": 4423.243,
|
| 5 |
"train_samples": 61134,
|
| 6 |
+
"train_samples_per_second": 13.821,
|
| 7 |
+
"train_steps_per_second": 0.108
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -11,11 +11,11 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
"learning_rate": 1.0416666666666666e-08,
|
| 14 |
-
"logits/chosen":
|
| 15 |
-
"logits/rejected":
|
| 16 |
-
"logps/chosen": -
|
| 17 |
-
"logps/rejected": -
|
| 18 |
-
"loss": 0.
|
| 19 |
"rewards/accuracies": 0.0,
|
| 20 |
"rewards/chosen": 0.0,
|
| 21 |
"rewards/margins": 0.0,
|
|
@@ -25,737 +25,737 @@
|
|
| 25 |
{
|
| 26 |
"epoch": 0.02,
|
| 27 |
"learning_rate": 1.0416666666666667e-07,
|
| 28 |
-
"logits/chosen":
|
| 29 |
-
"logits/rejected":
|
| 30 |
-
"logps/chosen": -
|
| 31 |
-
"logps/rejected": -
|
| 32 |
-
"loss": 0.
|
| 33 |
-
"rewards/accuracies": 0.
|
| 34 |
-
"rewards/chosen":
|
| 35 |
-
"rewards/margins": 0.
|
| 36 |
-
"rewards/rejected": -0.
|
| 37 |
"step": 10
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.04,
|
| 41 |
"learning_rate": 2.0833333333333333e-07,
|
| 42 |
-
"logits/chosen":
|
| 43 |
-
"logits/rejected":
|
| 44 |
-
"logps/chosen": -
|
| 45 |
-
"logps/rejected": -
|
| 46 |
-
"loss": 0.
|
| 47 |
-
"rewards/accuracies": 0.
|
| 48 |
-
"rewards/chosen": 0.
|
| 49 |
-
"rewards/margins": 0.
|
| 50 |
-
"rewards/rejected": -0.
|
| 51 |
"step": 20
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.06,
|
| 55 |
"learning_rate": 3.1249999999999997e-07,
|
| 56 |
-
"logits/chosen":
|
| 57 |
-
"logits/rejected":
|
| 58 |
-
"logps/chosen": -
|
| 59 |
-
"logps/rejected": -
|
| 60 |
-
"loss": 0.
|
| 61 |
-
"rewards/accuracies": 0.
|
| 62 |
-
"rewards/chosen":
|
| 63 |
-
"rewards/margins": 0.
|
| 64 |
-
"rewards/rejected": -0.
|
| 65 |
"step": 30
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.08,
|
| 69 |
"learning_rate": 4.1666666666666667e-07,
|
| 70 |
-
"logits/chosen":
|
| 71 |
-
"logits/rejected":
|
| 72 |
-
"logps/chosen": -
|
| 73 |
-
"logps/rejected": -
|
| 74 |
-
"loss": 0.
|
| 75 |
-
"rewards/accuracies": 0.
|
| 76 |
-
"rewards/chosen": -0.
|
| 77 |
-
"rewards/margins": 0.
|
| 78 |
-
"rewards/rejected": -0.
|
| 79 |
"step": 40
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.1,
|
| 83 |
-
"learning_rate": 4.
|
| 84 |
-
"logits/chosen":
|
| 85 |
-
"logits/rejected":
|
| 86 |
-
"logps/chosen": -
|
| 87 |
-
"logps/rejected": -
|
| 88 |
-
"loss": 0.
|
| 89 |
-
"rewards/accuracies": 0.
|
| 90 |
-
"rewards/chosen": -0.
|
| 91 |
-
"rewards/margins": 0.
|
| 92 |
-
"rewards/rejected": -0.
|
| 93 |
"step": 50
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.13,
|
| 97 |
-
"learning_rate": 4.
|
| 98 |
-
"logits/chosen":
|
| 99 |
-
"logits/rejected":
|
| 100 |
-
"logps/chosen": -
|
| 101 |
-
"logps/rejected": -
|
| 102 |
-
"loss": 0.
|
| 103 |
-
"rewards/accuracies": 0.
|
| 104 |
-
"rewards/chosen": -0.
|
| 105 |
-
"rewards/margins": 0.
|
| 106 |
-
"rewards/rejected": -0.
|
| 107 |
"step": 60
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.15,
|
| 111 |
-
"learning_rate": 4.
|
| 112 |
-
"logits/chosen":
|
| 113 |
-
"logits/rejected":
|
| 114 |
-
"logps/chosen": -
|
| 115 |
-
"logps/rejected": -
|
| 116 |
-
"loss": 0.
|
| 117 |
-
"rewards/accuracies": 0.
|
| 118 |
-
"rewards/chosen": -0.
|
| 119 |
-
"rewards/margins": 0.
|
| 120 |
-
"rewards/rejected": -0.
|
| 121 |
"step": 70
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.17,
|
| 125 |
-
"learning_rate": 4.
|
| 126 |
-
"logits/chosen":
|
| 127 |
-
"logits/rejected":
|
| 128 |
-
"logps/chosen": -
|
| 129 |
-
"logps/rejected": -
|
| 130 |
-
"loss": 0.
|
| 131 |
-
"rewards/accuracies": 0.
|
| 132 |
-
"rewards/chosen": -0.
|
| 133 |
-
"rewards/margins": 0.
|
| 134 |
-
"rewards/rejected": -0.
|
| 135 |
"step": 80
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.19,
|
| 139 |
-
"learning_rate": 4.
|
| 140 |
-
"logits/chosen":
|
| 141 |
-
"logits/rejected":
|
| 142 |
-
"logps/chosen": -
|
| 143 |
-
"logps/rejected": -
|
| 144 |
-
"loss": 0.
|
| 145 |
-
"rewards/accuracies": 0.
|
| 146 |
-
"rewards/chosen": -0.
|
| 147 |
-
"rewards/margins": 0.
|
| 148 |
-
"rewards/rejected": -0.
|
| 149 |
"step": 90
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.21,
|
| 153 |
-
"learning_rate": 4.
|
| 154 |
-
"logits/chosen":
|
| 155 |
-
"logits/rejected":
|
| 156 |
-
"logps/chosen": -
|
| 157 |
-
"logps/rejected": -
|
| 158 |
-
"loss": 0.
|
| 159 |
-
"rewards/accuracies": 0.
|
| 160 |
-
"rewards/chosen": -0.
|
| 161 |
-
"rewards/margins": 0.
|
| 162 |
-
"rewards/rejected": -0.
|
| 163 |
"step": 100
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.21,
|
| 167 |
-
"eval_logits/chosen":
|
| 168 |
-
"eval_logits/rejected":
|
| 169 |
-
"eval_logps/chosen": -
|
| 170 |
-
"eval_logps/rejected": -
|
| 171 |
-
"eval_loss": 0.
|
| 172 |
-
"eval_rewards/accuracies": 0.
|
| 173 |
-
"eval_rewards/chosen": -0.
|
| 174 |
-
"eval_rewards/margins": 0.
|
| 175 |
-
"eval_rewards/rejected": -0.
|
| 176 |
-
"eval_runtime":
|
| 177 |
-
"eval_samples_per_second":
|
| 178 |
-
"eval_steps_per_second": 0.
|
| 179 |
"step": 100
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.23,
|
| 183 |
-
"learning_rate": 4.
|
| 184 |
-
"logits/chosen":
|
| 185 |
-
"logits/rejected":
|
| 186 |
-
"logps/chosen": -
|
| 187 |
-
"logps/rejected": -
|
| 188 |
-
"loss": 0.
|
| 189 |
-
"rewards/accuracies": 0.
|
| 190 |
-
"rewards/chosen": -0.
|
| 191 |
-
"rewards/margins": 0.
|
| 192 |
-
"rewards/rejected": -
|
| 193 |
"step": 110
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 0.25,
|
| 197 |
-
"learning_rate": 4.
|
| 198 |
-
"logits/chosen":
|
| 199 |
-
"logits/rejected":
|
| 200 |
-
"logps/chosen": -
|
| 201 |
-
"logps/rejected": -
|
| 202 |
-
"loss": 0.
|
| 203 |
-
"rewards/accuracies": 0.
|
| 204 |
-
"rewards/chosen": -0.
|
| 205 |
-
"rewards/margins": 0.
|
| 206 |
-
"rewards/rejected": -
|
| 207 |
"step": 120
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.27,
|
| 211 |
-
"learning_rate": 4.
|
| 212 |
-
"logits/chosen":
|
| 213 |
-
"logits/rejected":
|
| 214 |
-
"logps/chosen": -
|
| 215 |
-
"logps/rejected": -
|
| 216 |
-
"loss": 0.
|
| 217 |
-
"rewards/accuracies": 0.
|
| 218 |
-
"rewards/chosen": -0.
|
| 219 |
-
"rewards/margins": 0.
|
| 220 |
-
"rewards/rejected": -
|
| 221 |
"step": 130
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 0.29,
|
| 225 |
-
"learning_rate": 4.
|
| 226 |
-
"logits/chosen":
|
| 227 |
-
"logits/rejected":
|
| 228 |
-
"logps/chosen": -
|
| 229 |
-
"logps/rejected": -
|
| 230 |
-
"loss": 0.
|
| 231 |
-
"rewards/accuracies": 0.
|
| 232 |
-
"rewards/chosen": -0.
|
| 233 |
-
"rewards/margins": 0.
|
| 234 |
-
"rewards/rejected": -
|
| 235 |
"step": 140
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 0.31,
|
| 239 |
-
"learning_rate": 4.
|
| 240 |
-
"logits/chosen":
|
| 241 |
-
"logits/rejected":
|
| 242 |
-
"logps/chosen": -
|
| 243 |
-
"logps/rejected": -
|
| 244 |
-
"loss": 0.
|
| 245 |
-
"rewards/accuracies": 0.
|
| 246 |
-
"rewards/chosen": -0.
|
| 247 |
-
"rewards/margins": 0.
|
| 248 |
-
"rewards/rejected": -
|
| 249 |
"step": 150
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.33,
|
| 253 |
-
"learning_rate": 4.
|
| 254 |
-
"logits/chosen":
|
| 255 |
-
"logits/rejected":
|
| 256 |
-
"logps/chosen": -
|
| 257 |
-
"logps/rejected": -
|
| 258 |
-
"loss": 0.
|
| 259 |
-
"rewards/accuracies": 0.
|
| 260 |
-
"rewards/chosen": -0.
|
| 261 |
-
"rewards/margins": 0.
|
| 262 |
-
"rewards/rejected": -
|
| 263 |
"step": 160
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 0.36,
|
| 267 |
-
"learning_rate": 4.
|
| 268 |
-
"logits/chosen":
|
| 269 |
-
"logits/rejected":
|
| 270 |
-
"logps/chosen": -
|
| 271 |
-
"logps/rejected": -
|
| 272 |
-
"loss": 0.
|
| 273 |
-
"rewards/accuracies": 0.
|
| 274 |
-
"rewards/chosen": -
|
| 275 |
-
"rewards/margins": 0.
|
| 276 |
-
"rewards/rejected": -
|
| 277 |
"step": 170
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 0.38,
|
| 281 |
-
"learning_rate": 3.
|
| 282 |
-
"logits/chosen":
|
| 283 |
-
"logits/rejected":
|
| 284 |
-
"logps/chosen": -
|
| 285 |
-
"logps/rejected": -
|
| 286 |
-
"loss": 0.
|
| 287 |
-
"rewards/accuracies": 0.
|
| 288 |
-
"rewards/chosen": -
|
| 289 |
-
"rewards/margins": 0.
|
| 290 |
-
"rewards/rejected": -
|
| 291 |
"step": 180
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.4,
|
| 295 |
-
"learning_rate": 3.
|
| 296 |
-
"logits/chosen":
|
| 297 |
-
"logits/rejected":
|
| 298 |
-
"logps/chosen": -
|
| 299 |
-
"logps/rejected": -
|
| 300 |
-
"loss": 0.
|
| 301 |
-
"rewards/accuracies": 0.
|
| 302 |
-
"rewards/chosen": -
|
| 303 |
-
"rewards/margins": 0.
|
| 304 |
-
"rewards/rejected": -
|
| 305 |
"step": 190
|
| 306 |
},
|
| 307 |
{
|
| 308 |
"epoch": 0.42,
|
| 309 |
-
"learning_rate": 3.
|
| 310 |
-
"logits/chosen":
|
| 311 |
-
"logits/rejected":
|
| 312 |
-
"logps/chosen": -
|
| 313 |
-
"logps/rejected": -
|
| 314 |
-
"loss": 0.
|
| 315 |
-
"rewards/accuracies": 0.
|
| 316 |
-
"rewards/chosen": -0.
|
| 317 |
-
"rewards/margins": 0.
|
| 318 |
-
"rewards/rejected": -
|
| 319 |
"step": 200
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 0.42,
|
| 323 |
-
"eval_logits/chosen":
|
| 324 |
-
"eval_logits/rejected":
|
| 325 |
-
"eval_logps/chosen": -
|
| 326 |
-
"eval_logps/rejected": -
|
| 327 |
-
"eval_loss": 0.
|
| 328 |
-
"eval_rewards/accuracies": 0.
|
| 329 |
-
"eval_rewards/chosen": -0.
|
| 330 |
-
"eval_rewards/margins": 0.
|
| 331 |
-
"eval_rewards/rejected": -
|
| 332 |
-
"eval_runtime":
|
| 333 |
-
"eval_samples_per_second":
|
| 334 |
-
"eval_steps_per_second": 0.
|
| 335 |
"step": 200
|
| 336 |
},
|
| 337 |
{
|
| 338 |
"epoch": 0.44,
|
| 339 |
-
"learning_rate": 3.
|
| 340 |
-
"logits/chosen":
|
| 341 |
-
"logits/rejected":
|
| 342 |
-
"logps/chosen": -
|
| 343 |
-
"logps/rejected": -
|
| 344 |
-
"loss": 0.
|
| 345 |
-
"rewards/accuracies": 0.
|
| 346 |
-
"rewards/chosen": -
|
| 347 |
-
"rewards/margins": 0.
|
| 348 |
-
"rewards/rejected": -
|
| 349 |
"step": 210
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 0.46,
|
| 353 |
-
"learning_rate": 3.
|
| 354 |
-
"logits/chosen":
|
| 355 |
-
"logits/rejected":
|
| 356 |
-
"logps/chosen": -
|
| 357 |
-
"logps/rejected": -
|
| 358 |
-
"loss": 0.
|
| 359 |
-
"rewards/accuracies": 0.
|
| 360 |
-
"rewards/chosen": -
|
| 361 |
-
"rewards/margins": 0.
|
| 362 |
-
"rewards/rejected": -
|
| 363 |
"step": 220
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.48,
|
| 367 |
-
"learning_rate": 3.
|
| 368 |
-
"logits/chosen":
|
| 369 |
-
"logits/rejected":
|
| 370 |
-
"logps/chosen": -
|
| 371 |
-
"logps/rejected": -
|
| 372 |
-
"loss": 0.
|
| 373 |
-
"rewards/accuracies": 0.
|
| 374 |
-
"rewards/chosen": -
|
| 375 |
-
"rewards/margins": 0.
|
| 376 |
-
"rewards/rejected": -
|
| 377 |
"step": 230
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 0.5,
|
| 381 |
-
"learning_rate": 2.
|
| 382 |
-
"logits/chosen":
|
| 383 |
-
"logits/rejected":
|
| 384 |
-
"logps/chosen": -
|
| 385 |
-
"logps/rejected": -
|
| 386 |
-
"loss": 0.
|
| 387 |
-
"rewards/accuracies": 0.
|
| 388 |
-
"rewards/chosen": -
|
| 389 |
-
"rewards/margins": 0.
|
| 390 |
-
"rewards/rejected": -
|
| 391 |
"step": 240
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 0.52,
|
| 395 |
-
"learning_rate": 2.
|
| 396 |
-
"logits/chosen":
|
| 397 |
-
"logits/rejected":
|
| 398 |
-
"logps/chosen": -
|
| 399 |
-
"logps/rejected": -
|
| 400 |
-
"loss": 0.
|
| 401 |
-
"rewards/accuracies": 0.
|
| 402 |
-
"rewards/chosen": -
|
| 403 |
-
"rewards/margins": 0.
|
| 404 |
-
"rewards/rejected": -
|
| 405 |
"step": 250
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 0.54,
|
| 409 |
-
"learning_rate": 2.
|
| 410 |
-
"logits/chosen":
|
| 411 |
-
"logits/rejected":
|
| 412 |
-
"logps/chosen": -
|
| 413 |
-
"logps/rejected": -
|
| 414 |
-
"loss": 0.
|
| 415 |
-
"rewards/accuracies": 0.
|
| 416 |
-
"rewards/chosen": -
|
| 417 |
-
"rewards/margins": 0.
|
| 418 |
-
"rewards/rejected": -
|
| 419 |
"step": 260
|
| 420 |
},
|
| 421 |
{
|
| 422 |
-
"epoch": 0.
|
| 423 |
-
"learning_rate": 2.
|
| 424 |
-
"logits/chosen":
|
| 425 |
-
"logits/rejected":
|
| 426 |
-
"logps/chosen": -
|
| 427 |
-
"logps/rejected": -
|
| 428 |
-
"loss": 0.
|
| 429 |
-
"rewards/accuracies": 0.
|
| 430 |
-
"rewards/chosen": -
|
| 431 |
-
"rewards/margins": 0.
|
| 432 |
-
"rewards/rejected": -
|
| 433 |
"step": 270
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 0.59,
|
| 437 |
-
"learning_rate": 2.
|
| 438 |
-
"logits/chosen":
|
| 439 |
-
"logits/rejected":
|
| 440 |
-
"logps/chosen": -
|
| 441 |
-
"logps/rejected": -
|
| 442 |
-
"loss": 0.
|
| 443 |
-
"rewards/accuracies": 0.
|
| 444 |
-
"rewards/chosen": -
|
| 445 |
-
"rewards/margins": 0.
|
| 446 |
-
"rewards/rejected": -
|
| 447 |
"step": 280
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 0.61,
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"logits/chosen":
|
| 453 |
-
"logits/rejected":
|
| 454 |
-
"logps/chosen": -
|
| 455 |
-
"logps/rejected": -
|
| 456 |
-
"loss": 0.
|
| 457 |
-
"rewards/accuracies": 0.
|
| 458 |
-
"rewards/chosen": -
|
| 459 |
-
"rewards/margins": 0.
|
| 460 |
-
"rewards/rejected": -
|
| 461 |
"step": 290
|
| 462 |
},
|
| 463 |
{
|
| 464 |
"epoch": 0.63,
|
| 465 |
-
"learning_rate": 1.
|
| 466 |
-
"logits/chosen":
|
| 467 |
-
"logits/rejected":
|
| 468 |
-
"logps/chosen": -
|
| 469 |
-
"logps/rejected": -
|
| 470 |
-
"loss": 0.
|
| 471 |
-
"rewards/accuracies": 0.
|
| 472 |
-
"rewards/chosen": -
|
| 473 |
-
"rewards/margins": 0.
|
| 474 |
-
"rewards/rejected": -
|
| 475 |
"step": 300
|
| 476 |
},
|
| 477 |
{
|
| 478 |
"epoch": 0.63,
|
| 479 |
-
"eval_logits/chosen":
|
| 480 |
-
"eval_logits/rejected":
|
| 481 |
-
"eval_logps/chosen": -
|
| 482 |
-
"eval_logps/rejected": -
|
| 483 |
-
"eval_loss": 0.
|
| 484 |
-
"eval_rewards/accuracies": 0.
|
| 485 |
-
"eval_rewards/chosen": -
|
| 486 |
-
"eval_rewards/margins": 0.
|
| 487 |
-
"eval_rewards/rejected": -
|
| 488 |
-
"eval_runtime":
|
| 489 |
-
"eval_samples_per_second":
|
| 490 |
-
"eval_steps_per_second": 0.
|
| 491 |
"step": 300
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 0.65,
|
| 495 |
-
"learning_rate": 1.
|
| 496 |
-
"logits/chosen":
|
| 497 |
-
"logits/rejected":
|
| 498 |
-
"logps/chosen": -
|
| 499 |
-
"logps/rejected": -
|
| 500 |
-
"loss": 0.
|
| 501 |
-
"rewards/accuracies": 0.
|
| 502 |
-
"rewards/chosen": -
|
| 503 |
-
"rewards/margins": 0.
|
| 504 |
-
"rewards/rejected": -
|
| 505 |
"step": 310
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 0.67,
|
| 509 |
-
"learning_rate": 1.
|
| 510 |
-
"logits/chosen":
|
| 511 |
-
"logits/rejected":
|
| 512 |
-
"logps/chosen": -
|
| 513 |
-
"logps/rejected": -
|
| 514 |
-
"loss": 0.
|
| 515 |
-
"rewards/accuracies": 0.
|
| 516 |
-
"rewards/chosen": -
|
| 517 |
-
"rewards/margins": 0.
|
| 518 |
-
"rewards/rejected": -
|
| 519 |
"step": 320
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 0.69,
|
| 523 |
-
"learning_rate": 1.
|
| 524 |
-
"logits/chosen":
|
| 525 |
-
"logits/rejected":
|
| 526 |
-
"logps/chosen": -
|
| 527 |
-
"logps/rejected": -
|
| 528 |
-
"loss": 0.
|
| 529 |
-
"rewards/accuracies": 0.
|
| 530 |
-
"rewards/chosen": -
|
| 531 |
-
"rewards/margins": 0.
|
| 532 |
-
"rewards/rejected": -
|
| 533 |
"step": 330
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 0.71,
|
| 537 |
-
"learning_rate": 1.
|
| 538 |
-
"logits/chosen":
|
| 539 |
-
"logits/rejected":
|
| 540 |
-
"logps/chosen": -
|
| 541 |
-
"logps/rejected": -
|
| 542 |
-
"loss": 0.
|
| 543 |
"rewards/accuracies": 0.699999988079071,
|
| 544 |
-
"rewards/chosen": -
|
| 545 |
-
"rewards/margins": 0.
|
| 546 |
-
"rewards/rejected": -
|
| 547 |
"step": 340
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 0.73,
|
| 551 |
-
"learning_rate": 1.
|
| 552 |
-
"logits/chosen":
|
| 553 |
-
"logits/rejected":
|
| 554 |
-
"logps/chosen": -
|
| 555 |
-
"logps/rejected": -
|
| 556 |
-
"loss": 0.
|
| 557 |
-
"rewards/accuracies": 0.
|
| 558 |
-
"rewards/chosen": -
|
| 559 |
-
"rewards/margins": 0.
|
| 560 |
-
"rewards/rejected": -
|
| 561 |
"step": 350
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 0.75,
|
| 565 |
-
"learning_rate": 8.
|
| 566 |
-
"logits/chosen":
|
| 567 |
-
"logits/rejected":
|
| 568 |
-
"logps/chosen": -
|
| 569 |
-
"logps/rejected": -
|
| 570 |
-
"loss": 0.
|
| 571 |
-
"rewards/accuracies": 0.
|
| 572 |
-
"rewards/chosen": -
|
| 573 |
-
"rewards/margins": 0.
|
| 574 |
-
"rewards/rejected": -
|
| 575 |
"step": 360
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 0.77,
|
| 579 |
-
"learning_rate": 7.
|
| 580 |
-
"logits/chosen":
|
| 581 |
-
"logits/rejected":
|
| 582 |
-
"logps/chosen": -
|
| 583 |
-
"logps/rejected": -
|
| 584 |
-
"loss": 0.
|
| 585 |
"rewards/accuracies": 0.71875,
|
| 586 |
-
"rewards/chosen": -
|
| 587 |
-
"rewards/margins": 0.
|
| 588 |
-
"rewards/rejected": -
|
| 589 |
"step": 370
|
| 590 |
},
|
| 591 |
{
|
| 592 |
-
"epoch": 0.
|
| 593 |
-
"learning_rate": 6.
|
| 594 |
-
"logits/chosen":
|
| 595 |
-
"logits/rejected":
|
| 596 |
-
"logps/chosen": -
|
| 597 |
-
"logps/rejected": -
|
| 598 |
-
"loss": 0.
|
| 599 |
-
"rewards/accuracies": 0.
|
| 600 |
-
"rewards/chosen": -
|
| 601 |
-
"rewards/margins": 0.
|
| 602 |
-
"rewards/rejected": -
|
| 603 |
"step": 380
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.82,
|
| 607 |
-
"learning_rate": 4.
|
| 608 |
-
"logits/chosen":
|
| 609 |
-
"logits/rejected":
|
| 610 |
-
"logps/chosen": -
|
| 611 |
-
"logps/rejected": -
|
| 612 |
-
"loss": 0.
|
| 613 |
-
"rewards/accuracies": 0.
|
| 614 |
-
"rewards/chosen": -
|
| 615 |
-
"rewards/margins": 0.
|
| 616 |
-
"rewards/rejected": -
|
| 617 |
"step": 390
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 0.84,
|
| 621 |
-
"learning_rate": 3.
|
| 622 |
-
"logits/chosen":
|
| 623 |
-
"logits/rejected":
|
| 624 |
-
"logps/chosen": -
|
| 625 |
-
"logps/rejected": -
|
| 626 |
-
"loss": 0.
|
| 627 |
-
"rewards/accuracies": 0.
|
| 628 |
-
"rewards/chosen": -
|
| 629 |
-
"rewards/margins": 0.
|
| 630 |
-
"rewards/rejected": -
|
| 631 |
"step": 400
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 0.84,
|
| 635 |
-
"eval_logits/chosen":
|
| 636 |
-
"eval_logits/rejected":
|
| 637 |
-
"eval_logps/chosen": -
|
| 638 |
-
"eval_logps/rejected": -
|
| 639 |
-
"eval_loss": 0.
|
| 640 |
-
"eval_rewards/accuracies": 0.
|
| 641 |
-
"eval_rewards/chosen": -
|
| 642 |
-
"eval_rewards/margins": 0.
|
| 643 |
-
"eval_rewards/rejected": -
|
| 644 |
-
"eval_runtime":
|
| 645 |
-
"eval_samples_per_second":
|
| 646 |
-
"eval_steps_per_second": 0.
|
| 647 |
"step": 400
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 0.86,
|
| 651 |
-
"learning_rate":
|
| 652 |
-
"logits/chosen":
|
| 653 |
-
"logits/rejected":
|
| 654 |
-
"logps/chosen": -
|
| 655 |
-
"logps/rejected": -
|
| 656 |
-
"loss": 0.
|
| 657 |
-
"rewards/accuracies": 0.
|
| 658 |
-
"rewards/chosen": -
|
| 659 |
-
"rewards/margins": 0.
|
| 660 |
-
"rewards/rejected": -
|
| 661 |
"step": 410
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 0.88,
|
| 665 |
-
"learning_rate": 2.
|
| 666 |
-
"logits/chosen":
|
| 667 |
-
"logits/rejected":
|
| 668 |
-
"logps/chosen": -
|
| 669 |
-
"logps/rejected": -
|
| 670 |
-
"loss": 0.
|
| 671 |
-
"rewards/accuracies": 0.
|
| 672 |
-
"rewards/chosen": -
|
| 673 |
-
"rewards/margins": 0.
|
| 674 |
-
"rewards/rejected": -
|
| 675 |
"step": 420
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.9,
|
| 679 |
-
"learning_rate": 1.
|
| 680 |
-
"logits/chosen":
|
| 681 |
-
"logits/rejected":
|
| 682 |
-
"logps/chosen": -
|
| 683 |
-
"logps/rejected": -
|
| 684 |
-
"loss": 0.
|
| 685 |
-
"rewards/accuracies": 0.
|
| 686 |
-
"rewards/chosen": -
|
| 687 |
-
"rewards/margins": 0.
|
| 688 |
-
"rewards/rejected": -
|
| 689 |
"step": 430
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 0.92,
|
| 693 |
-
"learning_rate": 9.
|
| 694 |
-
"logits/chosen":
|
| 695 |
-
"logits/rejected":
|
| 696 |
-
"logps/chosen": -
|
| 697 |
-
"logps/rejected": -
|
| 698 |
-
"loss": 0.
|
| 699 |
-
"rewards/accuracies": 0.
|
| 700 |
-
"rewards/chosen": -
|
| 701 |
-
"rewards/margins": 0.
|
| 702 |
-
"rewards/rejected": -
|
| 703 |
"step": 440
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 0.94,
|
| 707 |
-
"learning_rate":
|
| 708 |
-
"logits/chosen":
|
| 709 |
-
"logits/rejected":
|
| 710 |
-
"logps/chosen": -
|
| 711 |
-
"logps/rejected": -
|
| 712 |
-
"loss": 0.
|
| 713 |
-
"rewards/accuracies": 0.
|
| 714 |
-
"rewards/chosen": -
|
| 715 |
-
"rewards/margins": 0.
|
| 716 |
-
"rewards/rejected": -
|
| 717 |
"step": 450
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 0.96,
|
| 721 |
-
"learning_rate":
|
| 722 |
-
"logits/chosen":
|
| 723 |
-
"logits/rejected":
|
| 724 |
-
"logps/chosen": -
|
| 725 |
-
"logps/rejected": -
|
| 726 |
-
"loss": 0.
|
| 727 |
-
"rewards/accuracies": 0.
|
| 728 |
-
"rewards/chosen": -
|
| 729 |
-
"rewards/margins": 0.
|
| 730 |
-
"rewards/rejected": -
|
| 731 |
"step": 460
|
| 732 |
},
|
| 733 |
{
|
| 734 |
"epoch": 0.98,
|
| 735 |
-
"learning_rate":
|
| 736 |
-
"logits/chosen":
|
| 737 |
-
"logits/rejected":
|
| 738 |
-
"logps/chosen": -
|
| 739 |
-
"logps/rejected": -
|
| 740 |
-
"loss": 0.
|
| 741 |
-
"rewards/accuracies": 0.
|
| 742 |
-
"rewards/chosen": -
|
| 743 |
-
"rewards/margins": 0.
|
| 744 |
-
"rewards/rejected": -
|
| 745 |
"step": 470
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 1.0,
|
| 749 |
-
"step":
|
| 750 |
"total_flos": 0.0,
|
| 751 |
-
"train_loss": 0.
|
| 752 |
-
"train_runtime":
|
| 753 |
-
"train_samples_per_second":
|
| 754 |
-
"train_steps_per_second": 0.
|
| 755 |
}
|
| 756 |
],
|
| 757 |
"logging_steps": 10,
|
| 758 |
-
"max_steps":
|
| 759 |
"num_train_epochs": 1,
|
| 760 |
"save_steps": 1000,
|
| 761 |
"total_flos": 0.0,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9984301412872841,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 477,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
"learning_rate": 1.0416666666666666e-08,
|
| 14 |
+
"logits/chosen": 0.07429073005914688,
|
| 15 |
+
"logits/rejected": 0.11598015576601028,
|
| 16 |
+
"logps/chosen": -422.86004638671875,
|
| 17 |
+
"logps/rejected": -414.8901672363281,
|
| 18 |
+
"loss": 0.1089,
|
| 19 |
"rewards/accuracies": 0.0,
|
| 20 |
"rewards/chosen": 0.0,
|
| 21 |
"rewards/margins": 0.0,
|
|
|
|
| 25 |
{
|
| 26 |
"epoch": 0.02,
|
| 27 |
"learning_rate": 1.0416666666666667e-07,
|
| 28 |
+
"logits/chosen": 0.30265143513679504,
|
| 29 |
+
"logits/rejected": 0.37510383129119873,
|
| 30 |
+
"logps/chosen": -376.6183166503906,
|
| 31 |
+
"logps/rejected": -346.707275390625,
|
| 32 |
+
"loss": 0.1038,
|
| 33 |
+
"rewards/accuracies": 0.3958333432674408,
|
| 34 |
+
"rewards/chosen": -0.0007193544879555702,
|
| 35 |
+
"rewards/margins": -0.00018897267000284046,
|
| 36 |
+
"rewards/rejected": -0.0005303816869854927,
|
| 37 |
"step": 10
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.04,
|
| 41 |
"learning_rate": 2.0833333333333333e-07,
|
| 42 |
+
"logits/chosen": 0.19012752175331116,
|
| 43 |
+
"logits/rejected": 0.29147377610206604,
|
| 44 |
+
"logps/chosen": -427.39190673828125,
|
| 45 |
+
"logps/rejected": -371.12261962890625,
|
| 46 |
+
"loss": 0.107,
|
| 47 |
+
"rewards/accuracies": 0.5,
|
| 48 |
+
"rewards/chosen": 0.0001767327485140413,
|
| 49 |
+
"rewards/margins": 0.0014846216654404998,
|
| 50 |
+
"rewards/rejected": -0.0013078890042379498,
|
| 51 |
"step": 20
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.06,
|
| 55 |
"learning_rate": 3.1249999999999997e-07,
|
| 56 |
+
"logits/chosen": 0.20171578228473663,
|
| 57 |
+
"logits/rejected": 0.31732800602912903,
|
| 58 |
+
"logps/chosen": -399.6023254394531,
|
| 59 |
+
"logps/rejected": -374.3086853027344,
|
| 60 |
+
"loss": 0.1094,
|
| 61 |
+
"rewards/accuracies": 0.581250011920929,
|
| 62 |
+
"rewards/chosen": -0.0014916183426976204,
|
| 63 |
+
"rewards/margins": 0.001707876450382173,
|
| 64 |
+
"rewards/rejected": -0.0031994946766644716,
|
| 65 |
"step": 30
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.08,
|
| 69 |
"learning_rate": 4.1666666666666667e-07,
|
| 70 |
+
"logits/chosen": 0.24505770206451416,
|
| 71 |
+
"logits/rejected": 0.3264174163341522,
|
| 72 |
+
"logps/chosen": -363.1432189941406,
|
| 73 |
+
"logps/rejected": -371.2718200683594,
|
| 74 |
+
"loss": 0.1094,
|
| 75 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 76 |
+
"rewards/chosen": -0.0007695726817473769,
|
| 77 |
+
"rewards/margins": 0.006053343415260315,
|
| 78 |
+
"rewards/rejected": -0.006822916213423014,
|
| 79 |
"step": 40
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.1,
|
| 83 |
+
"learning_rate": 4.999731868769026e-07,
|
| 84 |
+
"logits/chosen": 0.26892322301864624,
|
| 85 |
+
"logits/rejected": 0.34712380170822144,
|
| 86 |
+
"logps/chosen": -378.1469421386719,
|
| 87 |
+
"logps/rejected": -348.55352783203125,
|
| 88 |
+
"loss": 0.105,
|
| 89 |
+
"rewards/accuracies": 0.668749988079071,
|
| 90 |
+
"rewards/chosen": -0.0007855228031985462,
|
| 91 |
+
"rewards/margins": 0.022909890860319138,
|
| 92 |
+
"rewards/rejected": -0.023695414885878563,
|
| 93 |
"step": 50
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.13,
|
| 97 |
+
"learning_rate": 4.990353313429303e-07,
|
| 98 |
+
"logits/chosen": 0.3134162127971649,
|
| 99 |
+
"logits/rejected": 0.36972466111183167,
|
| 100 |
+
"logps/chosen": -317.57965087890625,
|
| 101 |
+
"logps/rejected": -317.5392761230469,
|
| 102 |
+
"loss": 0.1049,
|
| 103 |
+
"rewards/accuracies": 0.65625,
|
| 104 |
+
"rewards/chosen": -0.008349133655428886,
|
| 105 |
+
"rewards/margins": 0.035110391676425934,
|
| 106 |
+
"rewards/rejected": -0.04345952719449997,
|
| 107 |
"step": 60
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.15,
|
| 111 |
+
"learning_rate": 4.967625656594781e-07,
|
| 112 |
+
"logits/chosen": 0.23508644104003906,
|
| 113 |
+
"logits/rejected": 0.30452126264572144,
|
| 114 |
+
"logps/chosen": -359.3031311035156,
|
| 115 |
+
"logps/rejected": -345.0860900878906,
|
| 116 |
+
"loss": 0.1082,
|
| 117 |
+
"rewards/accuracies": 0.625,
|
| 118 |
+
"rewards/chosen": -0.01529479306191206,
|
| 119 |
+
"rewards/margins": 0.044887155294418335,
|
| 120 |
+
"rewards/rejected": -0.06018194556236267,
|
| 121 |
"step": 70
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.17,
|
| 125 |
+
"learning_rate": 4.93167072587771e-07,
|
| 126 |
+
"logits/chosen": 0.33254843950271606,
|
| 127 |
+
"logits/rejected": 0.3818221688270569,
|
| 128 |
+
"logps/chosen": -367.01129150390625,
|
| 129 |
+
"logps/rejected": -355.1100158691406,
|
| 130 |
+
"loss": 0.1028,
|
| 131 |
+
"rewards/accuracies": 0.762499988079071,
|
| 132 |
+
"rewards/chosen": -0.01488255150616169,
|
| 133 |
+
"rewards/margins": 0.08553680032491684,
|
| 134 |
+
"rewards/rejected": -0.10041935741901398,
|
| 135 |
"step": 80
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.19,
|
| 139 |
+
"learning_rate": 4.882681251368548e-07,
|
| 140 |
+
"logits/chosen": 0.3798341751098633,
|
| 141 |
+
"logits/rejected": 0.4554978311061859,
|
| 142 |
+
"logps/chosen": -369.4306640625,
|
| 143 |
+
"logps/rejected": -350.7769470214844,
|
| 144 |
+
"loss": 0.1031,
|
| 145 |
+
"rewards/accuracies": 0.668749988079071,
|
| 146 |
+
"rewards/chosen": -0.04546991363167763,
|
| 147 |
+
"rewards/margins": 0.09270831197500229,
|
| 148 |
+
"rewards/rejected": -0.1381782442331314,
|
| 149 |
"step": 90
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.21,
|
| 153 |
+
"learning_rate": 4.820919832540181e-07,
|
| 154 |
+
"logits/chosen": 0.4522795081138611,
|
| 155 |
+
"logits/rejected": 0.5922520756721497,
|
| 156 |
+
"logps/chosen": -379.4673767089844,
|
| 157 |
+
"logps/rejected": -347.5188903808594,
|
| 158 |
+
"loss": 0.0993,
|
| 159 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 160 |
+
"rewards/chosen": -0.062339335680007935,
|
| 161 |
+
"rewards/margins": 0.1438979208469391,
|
| 162 |
+
"rewards/rejected": -0.20623722672462463,
|
| 163 |
"step": 100
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.21,
|
| 167 |
+
"eval_logits/chosen": 0.5129754543304443,
|
| 168 |
+
"eval_logits/rejected": 0.5706519484519958,
|
| 169 |
+
"eval_logps/chosen": -366.9024963378906,
|
| 170 |
+
"eval_logps/rejected": -390.411865234375,
|
| 171 |
+
"eval_loss": 0.10182792693376541,
|
| 172 |
+
"eval_rewards/accuracies": 0.6875,
|
| 173 |
+
"eval_rewards/chosen": -0.07451306283473969,
|
| 174 |
+
"eval_rewards/margins": 0.17251166701316833,
|
| 175 |
+
"eval_rewards/rejected": -0.2470247447490692,
|
| 176 |
+
"eval_runtime": 75.2158,
|
| 177 |
+
"eval_samples_per_second": 26.59,
|
| 178 |
+
"eval_steps_per_second": 0.425,
|
| 179 |
"step": 100
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.23,
|
| 183 |
+
"learning_rate": 4.7467175306295647e-07,
|
| 184 |
+
"logits/chosen": 0.47333478927612305,
|
| 185 |
+
"logits/rejected": 0.5572434663772583,
|
| 186 |
+
"logps/chosen": -408.17938232421875,
|
| 187 |
+
"logps/rejected": -431.2904357910156,
|
| 188 |
+
"loss": 0.0955,
|
| 189 |
+
"rewards/accuracies": 0.731249988079071,
|
| 190 |
+
"rewards/chosen": -0.12534171342849731,
|
| 191 |
+
"rewards/margins": 0.16846705973148346,
|
| 192 |
+
"rewards/rejected": -0.2938087582588196,
|
| 193 |
"step": 110
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 0.25,
|
| 197 |
+
"learning_rate": 4.6604720940421207e-07,
|
| 198 |
+
"logits/chosen": 0.49355560541152954,
|
| 199 |
+
"logits/rejected": 0.625954270362854,
|
| 200 |
+
"logps/chosen": -393.81842041015625,
|
| 201 |
+
"logps/rejected": -401.51202392578125,
|
| 202 |
+
"loss": 0.0822,
|
| 203 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 204 |
+
"rewards/chosen": -0.14783725142478943,
|
| 205 |
+
"rewards/margins": 0.23524054884910583,
|
| 206 |
+
"rewards/rejected": -0.38307780027389526,
|
| 207 |
"step": 120
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.27,
|
| 211 |
+
"learning_rate": 4.5626458262912735e-07,
|
| 212 |
+
"logits/chosen": 0.5241672396659851,
|
| 213 |
+
"logits/rejected": 0.8548004031181335,
|
| 214 |
+
"logps/chosen": -435.3441467285156,
|
| 215 |
+
"logps/rejected": -357.9606018066406,
|
| 216 |
+
"loss": 0.0797,
|
| 217 |
+
"rewards/accuracies": 0.606249988079071,
|
| 218 |
+
"rewards/chosen": -0.31069421768188477,
|
| 219 |
+
"rewards/margins": 0.1076047271490097,
|
| 220 |
+
"rewards/rejected": -0.41829895973205566,
|
| 221 |
"step": 130
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 0.29,
|
| 225 |
+
"learning_rate": 4.453763107901675e-07,
|
| 226 |
+
"logits/chosen": 0.5490397810935974,
|
| 227 |
+
"logits/rejected": 0.7539095282554626,
|
| 228 |
+
"logps/chosen": -413.84002685546875,
|
| 229 |
+
"logps/rejected": -386.32379150390625,
|
| 230 |
+
"loss": 0.0682,
|
| 231 |
+
"rewards/accuracies": 0.625,
|
| 232 |
+
"rewards/chosen": -0.3854388892650604,
|
| 233 |
+
"rewards/margins": 0.1845283955335617,
|
| 234 |
+
"rewards/rejected": -0.5699672698974609,
|
| 235 |
"step": 140
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 0.31,
|
| 239 |
+
"learning_rate": 4.3344075855595097e-07,
|
| 240 |
+
"logits/chosen": 0.6215056777000427,
|
| 241 |
+
"logits/rejected": 0.7831140756607056,
|
| 242 |
+
"logps/chosen": -419.662841796875,
|
| 243 |
+
"logps/rejected": -391.9927673339844,
|
| 244 |
+
"loss": 0.0704,
|
| 245 |
+
"rewards/accuracies": 0.65625,
|
| 246 |
+
"rewards/chosen": -0.35133233666419983,
|
| 247 |
+
"rewards/margins": 0.202161505818367,
|
| 248 |
+
"rewards/rejected": -0.553493857383728,
|
| 249 |
"step": 150
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 0.33,
|
| 253 |
+
"learning_rate": 4.2052190435769554e-07,
|
| 254 |
+
"logits/chosen": 0.7069424390792847,
|
| 255 |
+
"logits/rejected": 0.8614177703857422,
|
| 256 |
+
"logps/chosen": -384.68463134765625,
|
| 257 |
+
"logps/rejected": -374.79144287109375,
|
| 258 |
+
"loss": 0.0684,
|
| 259 |
+
"rewards/accuracies": 0.668749988079071,
|
| 260 |
+
"rewards/chosen": -0.2964687943458557,
|
| 261 |
+
"rewards/margins": 0.2469368427991867,
|
| 262 |
+
"rewards/rejected": -0.5434056520462036,
|
| 263 |
"step": 160
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 0.36,
|
| 267 |
+
"learning_rate": 4.0668899744407567e-07,
|
| 268 |
+
"logits/chosen": 0.6795724034309387,
|
| 269 |
+
"logits/rejected": 0.788532555103302,
|
| 270 |
+
"logps/chosen": -407.76092529296875,
|
| 271 |
+
"logps/rejected": -429.6249084472656,
|
| 272 |
+
"loss": 0.065,
|
| 273 |
+
"rewards/accuracies": 0.6875,
|
| 274 |
+
"rewards/chosen": -0.38756096363067627,
|
| 275 |
+
"rewards/margins": 0.3297034204006195,
|
| 276 |
+
"rewards/rejected": -0.7172644734382629,
|
| 277 |
"step": 170
|
| 278 |
},
|
| 279 |
{
|
| 280 |
"epoch": 0.38,
|
| 281 |
+
"learning_rate": 3.920161866827889e-07,
|
| 282 |
+
"logits/chosen": 0.6546531319618225,
|
| 283 |
+
"logits/rejected": 0.8610761761665344,
|
| 284 |
+
"logps/chosen": -399.92608642578125,
|
| 285 |
+
"logps/rejected": -425.089599609375,
|
| 286 |
+
"loss": 0.059,
|
| 287 |
+
"rewards/accuracies": 0.699999988079071,
|
| 288 |
+
"rewards/chosen": -0.45196419954299927,
|
| 289 |
+
"rewards/margins": 0.27189016342163086,
|
| 290 |
+
"rewards/rejected": -0.7238543033599854,
|
| 291 |
"step": 180
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 0.4,
|
| 295 |
+
"learning_rate": 3.765821230985757e-07,
|
| 296 |
+
"logits/chosen": 0.694263756275177,
|
| 297 |
+
"logits/rejected": 0.9027630090713501,
|
| 298 |
+
"logps/chosen": -411.06268310546875,
|
| 299 |
+
"logps/rejected": -397.81097412109375,
|
| 300 |
+
"loss": 0.0616,
|
| 301 |
+
"rewards/accuracies": 0.625,
|
| 302 |
+
"rewards/chosen": -0.46890345215797424,
|
| 303 |
+
"rewards/margins": 0.21999216079711914,
|
| 304 |
+
"rewards/rejected": -0.688895583152771,
|
| 305 |
"step": 190
|
| 306 |
},
|
| 307 |
{
|
| 308 |
"epoch": 0.42,
|
| 309 |
+
"learning_rate": 3.604695382782159e-07,
|
| 310 |
+
"logits/chosen": 0.6648334264755249,
|
| 311 |
+
"logits/rejected": 0.9266846776008606,
|
| 312 |
+
"logps/chosen": -450.61871337890625,
|
| 313 |
+
"logps/rejected": -451.17596435546875,
|
| 314 |
+
"loss": 0.0553,
|
| 315 |
+
"rewards/accuracies": 0.71875,
|
| 316 |
+
"rewards/chosen": -0.5313616394996643,
|
| 317 |
+
"rewards/margins": 0.4010355472564697,
|
| 318 |
+
"rewards/rejected": -0.9323970675468445,
|
| 319 |
"step": 200
|
| 320 |
},
|
| 321 |
{
|
| 322 |
"epoch": 0.42,
|
| 323 |
+
"eval_logits/chosen": 0.7755414247512817,
|
| 324 |
+
"eval_logits/rejected": 0.8994145393371582,
|
| 325 |
+
"eval_logps/chosen": -410.08349609375,
|
| 326 |
+
"eval_logps/rejected": -459.32171630859375,
|
| 327 |
+
"eval_loss": 0.05395492538809776,
|
| 328 |
+
"eval_rewards/accuracies": 0.73046875,
|
| 329 |
+
"eval_rewards/chosen": -0.5063228607177734,
|
| 330 |
+
"eval_rewards/margins": 0.42980003356933594,
|
| 331 |
+
"eval_rewards/rejected": -0.9361228942871094,
|
| 332 |
+
"eval_runtime": 75.0793,
|
| 333 |
+
"eval_samples_per_second": 26.638,
|
| 334 |
+
"eval_steps_per_second": 0.426,
|
| 335 |
"step": 200
|
| 336 |
},
|
| 337 |
{
|
| 338 |
"epoch": 0.44,
|
| 339 |
+
"learning_rate": 3.4376480090239047e-07,
|
| 340 |
+
"logits/chosen": 0.740880012512207,
|
| 341 |
+
"logits/rejected": 0.9735954999923706,
|
| 342 |
+
"logps/chosen": -407.00970458984375,
|
| 343 |
+
"logps/rejected": -405.5915832519531,
|
| 344 |
+
"loss": 0.0517,
|
| 345 |
+
"rewards/accuracies": 0.6187499761581421,
|
| 346 |
+
"rewards/chosen": -0.6327391266822815,
|
| 347 |
+
"rewards/margins": 0.24419736862182617,
|
| 348 |
+
"rewards/rejected": -0.8769365549087524,
|
| 349 |
"step": 210
|
| 350 |
},
|
| 351 |
{
|
| 352 |
"epoch": 0.46,
|
| 353 |
+
"learning_rate": 3.265574537815398e-07,
|
| 354 |
+
"logits/chosen": 0.5885998606681824,
|
| 355 |
+
"logits/rejected": 0.8313006162643433,
|
| 356 |
+
"logps/chosen": -449.39251708984375,
|
| 357 |
+
"logps/rejected": -427.76641845703125,
|
| 358 |
+
"loss": 0.0537,
|
| 359 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 360 |
+
"rewards/chosen": -0.5039619207382202,
|
| 361 |
+
"rewards/margins": 0.33774858713150024,
|
| 362 |
+
"rewards/rejected": -0.8417104482650757,
|
| 363 |
"step": 220
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 0.48,
|
| 367 |
+
"learning_rate": 3.0893973387735683e-07,
|
| 368 |
+
"logits/chosen": 0.5277591347694397,
|
| 369 |
+
"logits/rejected": 0.7385606169700623,
|
| 370 |
+
"logps/chosen": -428.235595703125,
|
| 371 |
+
"logps/rejected": -417.846923828125,
|
| 372 |
+
"loss": 0.054,
|
| 373 |
+
"rewards/accuracies": 0.643750011920929,
|
| 374 |
+
"rewards/chosen": -0.5545467138290405,
|
| 375 |
+
"rewards/margins": 0.3285568654537201,
|
| 376 |
+
"rewards/rejected": -0.8831035494804382,
|
| 377 |
"step": 230
|
| 378 |
},
|
| 379 |
{
|
| 380 |
"epoch": 0.5,
|
| 381 |
+
"learning_rate": 2.910060778827554e-07,
|
| 382 |
+
"logits/chosen": 0.5636624693870544,
|
| 383 |
+
"logits/rejected": 0.7239071130752563,
|
| 384 |
+
"logps/chosen": -410.8172302246094,
|
| 385 |
+
"logps/rejected": -453.8780822753906,
|
| 386 |
+
"loss": 0.0517,
|
| 387 |
+
"rewards/accuracies": 0.625,
|
| 388 |
+
"rewards/chosen": -0.6257103085517883,
|
| 389 |
+
"rewards/margins": 0.3102150559425354,
|
| 390 |
+
"rewards/rejected": -0.9359253644943237,
|
| 391 |
"step": 240
|
| 392 |
},
|
| 393 |
{
|
| 394 |
"epoch": 0.52,
|
| 395 |
+
"learning_rate": 2.7285261601056697e-07,
|
| 396 |
+
"logits/chosen": 0.6507786512374878,
|
| 397 |
+
"logits/rejected": 0.7937926054000854,
|
| 398 |
+
"logps/chosen": -399.25531005859375,
|
| 399 |
+
"logps/rejected": -428.21173095703125,
|
| 400 |
+
"loss": 0.0482,
|
| 401 |
+
"rewards/accuracies": 0.71875,
|
| 402 |
+
"rewards/chosen": -0.5876737236976624,
|
| 403 |
+
"rewards/margins": 0.42669692635536194,
|
| 404 |
+
"rewards/rejected": -1.0143706798553467,
|
| 405 |
"step": 250
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 0.54,
|
| 409 |
+
"learning_rate": 2.5457665670441937e-07,
|
| 410 |
+
"logits/chosen": 0.7192268967628479,
|
| 411 |
+
"logits/rejected": 0.9365060925483704,
|
| 412 |
+
"logps/chosen": -442.73931884765625,
|
| 413 |
+
"logps/rejected": -429.482421875,
|
| 414 |
+
"loss": 0.0515,
|
| 415 |
+
"rewards/accuracies": 0.606249988079071,
|
| 416 |
+
"rewards/chosen": -0.7237201929092407,
|
| 417 |
+
"rewards/margins": 0.23805689811706543,
|
| 418 |
+
"rewards/rejected": -0.9617769122123718,
|
| 419 |
"step": 260
|
| 420 |
},
|
| 421 |
{
|
| 422 |
+
"epoch": 0.57,
|
| 423 |
+
"learning_rate": 2.3627616503391812e-07,
|
| 424 |
+
"logits/chosen": 0.8510295748710632,
|
| 425 |
+
"logits/rejected": 1.0050238370895386,
|
| 426 |
+
"logps/chosen": -445.4356384277344,
|
| 427 |
+
"logps/rejected": -501.38287353515625,
|
| 428 |
+
"loss": 0.0505,
|
| 429 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 430 |
+
"rewards/chosen": -0.6589037179946899,
|
| 431 |
+
"rewards/margins": 0.45235753059387207,
|
| 432 |
+
"rewards/rejected": -1.111261248588562,
|
| 433 |
"step": 270
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 0.59,
|
| 437 |
+
"learning_rate": 2.1804923757009882e-07,
|
| 438 |
+
"logits/chosen": 0.7827587723731995,
|
| 439 |
+
"logits/rejected": 0.8751026391983032,
|
| 440 |
+
"logps/chosen": -394.4527282714844,
|
| 441 |
+
"logps/rejected": -438.7657165527344,
|
| 442 |
+
"loss": 0.0514,
|
| 443 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 444 |
+
"rewards/chosen": -0.6062650084495544,
|
| 445 |
+
"rewards/margins": 0.3552294373512268,
|
| 446 |
+
"rewards/rejected": -0.9614945650100708,
|
| 447 |
"step": 280
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 0.61,
|
| 451 |
+
"learning_rate": 1.9999357655598891e-07,
|
| 452 |
+
"logits/chosen": 0.6437442898750305,
|
| 453 |
+
"logits/rejected": 0.9078620672225952,
|
| 454 |
+
"logps/chosen": -437.314697265625,
|
| 455 |
+
"logps/rejected": -448.2724609375,
|
| 456 |
+
"loss": 0.0493,
|
| 457 |
+
"rewards/accuracies": 0.675000011920929,
|
| 458 |
+
"rewards/chosen": -0.6567361950874329,
|
| 459 |
+
"rewards/margins": 0.38017868995666504,
|
| 460 |
+
"rewards/rejected": -1.0369149446487427,
|
| 461 |
"step": 290
|
| 462 |
},
|
| 463 |
{
|
| 464 |
"epoch": 0.63,
|
| 465 |
+
"learning_rate": 1.8220596619089573e-07,
|
| 466 |
+
"logits/chosen": 0.6364871263504028,
|
| 467 |
+
"logits/rejected": 0.8500644564628601,
|
| 468 |
+
"logps/chosen": -384.7347412109375,
|
| 469 |
+
"logps/rejected": -401.3032531738281,
|
| 470 |
+
"loss": 0.0503,
|
| 471 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 472 |
+
"rewards/chosen": -0.5907383561134338,
|
| 473 |
+
"rewards/margins": 0.31186026334762573,
|
| 474 |
+
"rewards/rejected": -0.9025986790657043,
|
| 475 |
"step": 300
|
| 476 |
},
|
| 477 |
{
|
| 478 |
"epoch": 0.63,
|
| 479 |
+
"eval_logits/chosen": 0.6691160202026367,
|
| 480 |
+
"eval_logits/rejected": 0.8094965219497681,
|
| 481 |
+
"eval_logps/chosen": -412.98126220703125,
|
| 482 |
+
"eval_logps/rejected": -468.3688049316406,
|
| 483 |
+
"eval_loss": 0.05308157950639725,
|
| 484 |
+
"eval_rewards/accuracies": 0.74609375,
|
| 485 |
+
"eval_rewards/chosen": -0.5353004932403564,
|
| 486 |
+
"eval_rewards/margins": 0.4912930727005005,
|
| 487 |
+
"eval_rewards/rejected": -1.0265936851501465,
|
| 488 |
+
"eval_runtime": 75.2339,
|
| 489 |
+
"eval_samples_per_second": 26.584,
|
| 490 |
+
"eval_steps_per_second": 0.425,
|
| 491 |
"step": 300
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 0.65,
|
| 495 |
+
"learning_rate": 1.647817538357072e-07,
|
| 496 |
+
"logits/chosen": 0.5804156064987183,
|
| 497 |
+
"logits/rejected": 0.8023425936698914,
|
| 498 |
+
"logps/chosen": -431.28790283203125,
|
| 499 |
+
"logps/rejected": -459.8777770996094,
|
| 500 |
+
"loss": 0.0547,
|
| 501 |
+
"rewards/accuracies": 0.699999988079071,
|
| 502 |
+
"rewards/chosen": -0.5415506958961487,
|
| 503 |
+
"rewards/margins": 0.43213915824890137,
|
| 504 |
+
"rewards/rejected": -0.97368985414505,
|
| 505 |
"step": 310
|
| 506 |
},
|
| 507 |
{
|
| 508 |
"epoch": 0.67,
|
| 509 |
+
"learning_rate": 1.478143389201113e-07,
|
| 510 |
+
"logits/chosen": 0.5641556978225708,
|
| 511 |
+
"logits/rejected": 0.7904598712921143,
|
| 512 |
+
"logps/chosen": -419.69329833984375,
|
| 513 |
+
"logps/rejected": -420.63629150390625,
|
| 514 |
+
"loss": 0.0512,
|
| 515 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 516 |
+
"rewards/chosen": -0.5348724126815796,
|
| 517 |
+
"rewards/margins": 0.3764938712120056,
|
| 518 |
+
"rewards/rejected": -0.9113662838935852,
|
| 519 |
"step": 320
|
| 520 |
},
|
| 521 |
{
|
| 522 |
"epoch": 0.69,
|
| 523 |
+
"learning_rate": 1.3139467229135998e-07,
|
| 524 |
+
"logits/chosen": 0.7080197334289551,
|
| 525 |
+
"logits/rejected": 0.8454129099845886,
|
| 526 |
+
"logps/chosen": -395.1232604980469,
|
| 527 |
+
"logps/rejected": -457.27978515625,
|
| 528 |
+
"loss": 0.0486,
|
| 529 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 530 |
+
"rewards/chosen": -0.5784841775894165,
|
| 531 |
+
"rewards/margins": 0.39547181129455566,
|
| 532 |
+
"rewards/rejected": -0.9739561080932617,
|
| 533 |
"step": 330
|
| 534 |
},
|
| 535 |
{
|
| 536 |
"epoch": 0.71,
|
| 537 |
+
"learning_rate": 1.1561076868822755e-07,
|
| 538 |
+
"logits/chosen": 0.7032380700111389,
|
| 539 |
+
"logits/rejected": 0.8845696449279785,
|
| 540 |
+
"logps/chosen": -421.2705078125,
|
| 541 |
+
"logps/rejected": -432.5623474121094,
|
| 542 |
+
"loss": 0.0532,
|
| 543 |
"rewards/accuracies": 0.699999988079071,
|
| 544 |
+
"rewards/chosen": -0.6043194532394409,
|
| 545 |
+
"rewards/margins": 0.37815985083580017,
|
| 546 |
+
"rewards/rejected": -0.9824793934822083,
|
| 547 |
"step": 340
|
| 548 |
},
|
| 549 |
{
|
| 550 |
"epoch": 0.73,
|
| 551 |
+
"learning_rate": 1.0054723495346482e-07,
|
| 552 |
+
"logits/chosen": 0.7004996538162231,
|
| 553 |
+
"logits/rejected": 0.8182412981987,
|
| 554 |
+
"logps/chosen": -392.1104431152344,
|
| 555 |
+
"logps/rejected": -416.94415283203125,
|
| 556 |
+
"loss": 0.0467,
|
| 557 |
+
"rewards/accuracies": 0.637499988079071,
|
| 558 |
+
"rewards/chosen": -0.6616944074630737,
|
| 559 |
+
"rewards/margins": 0.3355887532234192,
|
| 560 |
+
"rewards/rejected": -0.9972831606864929,
|
| 561 |
"step": 350
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 0.75,
|
| 565 |
+
"learning_rate": 8.628481651367875e-08,
|
| 566 |
+
"logits/chosen": 0.6653555631637573,
|
| 567 |
+
"logits/rejected": 0.8546744585037231,
|
| 568 |
+
"logps/chosen": -370.65008544921875,
|
| 569 |
+
"logps/rejected": -413.5162048339844,
|
| 570 |
+
"loss": 0.0484,
|
| 571 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 572 |
+
"rewards/chosen": -0.529220461845398,
|
| 573 |
+
"rewards/margins": 0.42656245827674866,
|
| 574 |
+
"rewards/rejected": -0.9557830095291138,
|
| 575 |
"step": 360
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 0.77,
|
| 579 |
+
"learning_rate": 7.289996455765748e-08,
|
| 580 |
+
"logits/chosen": 0.6534770131111145,
|
| 581 |
+
"logits/rejected": 0.7723512053489685,
|
| 582 |
+
"logps/chosen": -436.49346923828125,
|
| 583 |
+
"logps/rejected": -463.48577880859375,
|
| 584 |
+
"loss": 0.0486,
|
| 585 |
"rewards/accuracies": 0.71875,
|
| 586 |
+
"rewards/chosen": -0.5268007516860962,
|
| 587 |
+
"rewards/margins": 0.5095833539962769,
|
| 588 |
+
"rewards/rejected": -1.0363839864730835,
|
| 589 |
"step": 370
|
| 590 |
},
|
| 591 |
{
|
| 592 |
+
"epoch": 0.8,
|
| 593 |
+
"learning_rate": 6.046442623320145e-08,
|
| 594 |
+
"logits/chosen": 0.7045032978057861,
|
| 595 |
+
"logits/rejected": 0.7946165800094604,
|
| 596 |
+
"logps/chosen": -398.9028625488281,
|
| 597 |
+
"logps/rejected": -436.78515625,
|
| 598 |
+
"loss": 0.0499,
|
| 599 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 600 |
+
"rewards/chosen": -0.5992251634597778,
|
| 601 |
+
"rewards/margins": 0.39836931228637695,
|
| 602 |
+
"rewards/rejected": -0.9975944757461548,
|
| 603 |
"step": 380
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 0.82,
|
| 607 |
+
"learning_rate": 4.904486005914027e-08,
|
| 608 |
+
"logits/chosen": 0.5793179869651794,
|
| 609 |
+
"logits/rejected": 0.7902762293815613,
|
| 610 |
+
"logps/chosen": -427.8744201660156,
|
| 611 |
+
"logps/rejected": -456.980224609375,
|
| 612 |
+
"loss": 0.0472,
|
| 613 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 614 |
+
"rewards/chosen": -0.541319727897644,
|
| 615 |
+
"rewards/margins": 0.55488520860672,
|
| 616 |
+
"rewards/rejected": -1.0962049961090088,
|
| 617 |
"step": 390
|
| 618 |
},
|
| 619 |
{
|
| 620 |
"epoch": 0.84,
|
| 621 |
+
"learning_rate": 3.8702478614051345e-08,
|
| 622 |
+
"logits/chosen": 0.6567720174789429,
|
| 623 |
+
"logits/rejected": 0.8759796023368835,
|
| 624 |
+
"logps/chosen": -413.21124267578125,
|
| 625 |
+
"logps/rejected": -466.8826599121094,
|
| 626 |
+
"loss": 0.0537,
|
| 627 |
+
"rewards/accuracies": 0.668749988079071,
|
| 628 |
+
"rewards/chosen": -0.5818170309066772,
|
| 629 |
+
"rewards/margins": 0.48379120230674744,
|
| 630 |
+
"rewards/rejected": -1.065608263015747,
|
| 631 |
"step": 400
|
| 632 |
},
|
| 633 |
{
|
| 634 |
"epoch": 0.84,
|
| 635 |
+
"eval_logits/chosen": 0.7434472441673279,
|
| 636 |
+
"eval_logits/rejected": 0.8845732808113098,
|
| 637 |
+
"eval_logps/chosen": -416.42877197265625,
|
| 638 |
+
"eval_logps/rejected": -473.2190246582031,
|
| 639 |
+
"eval_loss": 0.05153993144631386,
|
| 640 |
+
"eval_rewards/accuracies": 0.73046875,
|
| 641 |
+
"eval_rewards/chosen": -0.5697759985923767,
|
| 642 |
+
"eval_rewards/margins": 0.5053197145462036,
|
| 643 |
+
"eval_rewards/rejected": -1.075095772743225,
|
| 644 |
+
"eval_runtime": 76.6604,
|
| 645 |
+
"eval_samples_per_second": 26.089,
|
| 646 |
+
"eval_steps_per_second": 0.417,
|
| 647 |
"step": 400
|
| 648 |
},
|
| 649 |
{
|
| 650 |
"epoch": 0.86,
|
| 651 |
+
"learning_rate": 2.9492720416985e-08,
|
| 652 |
+
"logits/chosen": 0.6941822171211243,
|
| 653 |
+
"logits/rejected": 0.8047625422477722,
|
| 654 |
+
"logps/chosen": -401.1028137207031,
|
| 655 |
+
"logps/rejected": -427.03302001953125,
|
| 656 |
+
"loss": 0.0478,
|
| 657 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 658 |
+
"rewards/chosen": -0.576189398765564,
|
| 659 |
+
"rewards/margins": 0.39370283484458923,
|
| 660 |
+
"rewards/rejected": -0.969892144203186,
|
| 661 |
"step": 410
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 0.88,
|
| 665 |
+
"learning_rate": 2.1464952759020856e-08,
|
| 666 |
+
"logits/chosen": 0.7099225521087646,
|
| 667 |
+
"logits/rejected": 0.8760135769844055,
|
| 668 |
+
"logps/chosen": -388.6665954589844,
|
| 669 |
+
"logps/rejected": -421.422607421875,
|
| 670 |
+
"loss": 0.0477,
|
| 671 |
+
"rewards/accuracies": 0.6625000238418579,
|
| 672 |
+
"rewards/chosen": -0.5949358344078064,
|
| 673 |
+
"rewards/margins": 0.3995293378829956,
|
| 674 |
+
"rewards/rejected": -0.9944650530815125,
|
| 675 |
"step": 420
|
| 676 |
},
|
| 677 |
{
|
| 678 |
"epoch": 0.9,
|
| 679 |
+
"learning_rate": 1.4662207078575684e-08,
|
| 680 |
+
"logits/chosen": 0.6152527332305908,
|
| 681 |
+
"logits/rejected": 0.7688241600990295,
|
| 682 |
+
"logps/chosen": -453.6767578125,
|
| 683 |
+
"logps/rejected": -463.40863037109375,
|
| 684 |
+
"loss": 0.0527,
|
| 685 |
+
"rewards/accuracies": 0.699999988079071,
|
| 686 |
+
"rewards/chosen": -0.613703727722168,
|
| 687 |
+
"rewards/margins": 0.43121272325515747,
|
| 688 |
+
"rewards/rejected": -1.0449163913726807,
|
| 689 |
"step": 430
|
| 690 |
},
|
| 691 |
{
|
| 692 |
"epoch": 0.92,
|
| 693 |
+
"learning_rate": 9.12094829893642e-09,
|
| 694 |
+
"logits/chosen": 0.7038220167160034,
|
| 695 |
+
"logits/rejected": 0.8598071932792664,
|
| 696 |
+
"logps/chosen": -436.53082275390625,
|
| 697 |
+
"logps/rejected": -434.2837829589844,
|
| 698 |
+
"loss": 0.0484,
|
| 699 |
+
"rewards/accuracies": 0.6937500238418579,
|
| 700 |
+
"rewards/chosen": -0.6220607161521912,
|
| 701 |
+
"rewards/margins": 0.44049739837646484,
|
| 702 |
+
"rewards/rejected": -1.0625581741333008,
|
| 703 |
"step": 440
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 0.94,
|
| 707 |
+
"learning_rate": 4.8708793644441086e-09,
|
| 708 |
+
"logits/chosen": 0.6375268697738647,
|
| 709 |
+
"logits/rejected": 0.8610206842422485,
|
| 710 |
+
"logps/chosen": -462.42449951171875,
|
| 711 |
+
"logps/rejected": -464.8294372558594,
|
| 712 |
+
"loss": 0.0474,
|
| 713 |
+
"rewards/accuracies": 0.7124999761581421,
|
| 714 |
+
"rewards/chosen": -0.685294508934021,
|
| 715 |
+
"rewards/margins": 0.4343951344490051,
|
| 716 |
+
"rewards/rejected": -1.119689702987671,
|
| 717 |
"step": 450
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 0.96,
|
| 721 |
+
"learning_rate": 1.9347820230782295e-09,
|
| 722 |
+
"logits/chosen": 0.6665740013122559,
|
| 723 |
+
"logits/rejected": 0.8705039024353027,
|
| 724 |
+
"logps/chosen": -409.6141662597656,
|
| 725 |
+
"logps/rejected": -419.2763671875,
|
| 726 |
+
"loss": 0.0457,
|
| 727 |
+
"rewards/accuracies": 0.6812499761581421,
|
| 728 |
+
"rewards/chosen": -0.5975238084793091,
|
| 729 |
+
"rewards/margins": 0.3504991829395294,
|
| 730 |
+
"rewards/rejected": -0.9480230212211609,
|
| 731 |
"step": 460
|
| 732 |
},
|
| 733 |
{
|
| 734 |
"epoch": 0.98,
|
| 735 |
+
"learning_rate": 3.2839470889836627e-10,
|
| 736 |
+
"logits/chosen": 0.5994333028793335,
|
| 737 |
+
"logits/rejected": 0.8693232536315918,
|
| 738 |
+
"logps/chosen": -446.9803771972656,
|
| 739 |
+
"logps/rejected": -442.191650390625,
|
| 740 |
+
"loss": 0.0495,
|
| 741 |
+
"rewards/accuracies": 0.706250011920929,
|
| 742 |
+
"rewards/chosen": -0.5732464790344238,
|
| 743 |
+
"rewards/margins": 0.4613564610481262,
|
| 744 |
+
"rewards/rejected": -1.0346029996871948,
|
| 745 |
"step": 470
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 1.0,
|
| 749 |
+
"step": 477,
|
| 750 |
"total_flos": 0.0,
|
| 751 |
+
"train_loss": 0.06614070340397472,
|
| 752 |
+
"train_runtime": 4423.243,
|
| 753 |
+
"train_samples_per_second": 13.821,
|
| 754 |
+
"train_steps_per_second": 0.108
|
| 755 |
}
|
| 756 |
],
|
| 757 |
"logging_steps": 10,
|
| 758 |
+
"max_steps": 477,
|
| 759 |
"num_train_epochs": 1,
|
| 760 |
"save_steps": 1000,
|
| 761 |
"total_flos": 0.0,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5944
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c78334661030348bcfc61a245be57890af303020f8351feceea1b36f368cb134
|
| 3 |
size 5944
|