Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- hvqvae.pth +3 -0
- llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/README.md +9 -0
- llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_config.json +26 -0
- llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_model.bin +3 -0
- llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/config.json +35 -0
- llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/non_lora_trainables.bin +3 -0
- llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/trainer_state.json +0 -0
- llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/README.md +9 -0
- llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_config.json +26 -0
- llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_model.bin +3 -0
- llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/config.json +35 -0
- llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/non_lora_trainables.bin +3 -0
- llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/trainer_state.json +0 -0
- llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/README.md +9 -0
- llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_config.json +26 -0
- llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_model.bin +3 -0
- llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/config.json +35 -0
- llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/non_lora_trainables.bin +3 -0
- llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/trainer_state.json +0 -0
- llama2/llava-hvqvae2-llama-2-7b-chat-pretrain/config.json +35 -0
- llama2/llava-hvqvae2-llama-2-7b-chat-pretrain/mm_projector.bin +3 -0
- llama2/llava-hvqvae2-llama-2-7b-chat-pretrain/trainer_state.json +0 -0
- llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/README.md +9 -0
- llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/adapter_config.json +26 -0
- llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/adapter_model.bin +3 -0
- llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/config.json +35 -0
- llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/non_lora_trainables.bin +3 -0
- llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/trainer_state.json +0 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/README.md +9 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/adapter_config.json +26 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/adapter_model.bin +3 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/config.json +36 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/non_lora_trainables.bin +3 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/trainer_state.json +2308 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_cyp450/README.md +9 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_cyp450/adapter_config.json +26 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_cyp450/config.json +36 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_cyp450/trainer_state.json +0 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/README.md +9 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/adapter_config.json +26 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/adapter_model.bin +3 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/config.json +36 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/non_lora_trainables.bin +3 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/trainer_state.json +0 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/README.md +9 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/adapter_config.json +26 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/adapter_model.bin +3 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/config.json +36 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/non_lora_trainables.bin +3 -0
- vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/trainer_state.json +0 -0
hvqvae.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d99e41195c50d911a00328a49192d5b8cdd2a0bd203f38ed05f931cb0c2996b4
|
| 3 |
+
size 7478074
|
llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "llama-2-7b-chat",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"gate_proj",
|
| 18 |
+
"k_proj",
|
| 19 |
+
"down_proj",
|
| 20 |
+
"v_proj",
|
| 21 |
+
"o_proj",
|
| 22 |
+
"up_proj",
|
| 23 |
+
"q_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce9e1a1a7c7ac0b957b748681edae23fac240bc27db412ae52415d78423b66a3
|
| 3 |
+
size 319970957
|
llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "llama-2-7b-chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"mm_graph_tower": "hvqvae2",
|
| 15 |
+
"mm_hidden_size": 308,
|
| 16 |
+
"mm_projector_type": "hlinear",
|
| 17 |
+
"mm_use_im_patch_token": false,
|
| 18 |
+
"mm_use_im_start_end": false,
|
| 19 |
+
"model_type": "llava_graph",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 32,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000.0,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float16",
|
| 29 |
+
"transformers_version": "4.33.2",
|
| 30 |
+
"tune_mm_mlp_adapter": false,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"use_lap_pe": true,
|
| 33 |
+
"use_mm_proj": true,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
+
}
|
llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:977e67e9cdde408a93d6da8182eb17bdb25a2f9a20452fee352a908b725ca113
|
| 3 |
+
size 11335231
|
llama2/graph-text-molgen/forward_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "llama-2-7b-chat",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"gate_proj",
|
| 18 |
+
"k_proj",
|
| 19 |
+
"o_proj",
|
| 20 |
+
"v_proj",
|
| 21 |
+
"down_proj",
|
| 22 |
+
"up_proj",
|
| 23 |
+
"q_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83e6b19a80fa1ec1f7728219cd86316b9d65b11edcd92c462d2eb11b75eae856
|
| 3 |
+
size 319970957
|
llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "llama-2-7b-chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"mm_graph_tower": "hvqvae2",
|
| 15 |
+
"mm_hidden_size": 308,
|
| 16 |
+
"mm_projector_type": "hlinear",
|
| 17 |
+
"mm_use_im_patch_token": false,
|
| 18 |
+
"mm_use_im_start_end": false,
|
| 19 |
+
"model_type": "llava_graph",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 32,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000.0,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float16",
|
| 29 |
+
"transformers_version": "4.33.2",
|
| 30 |
+
"tune_mm_mlp_adapter": false,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"use_lap_pe": true,
|
| 33 |
+
"use_mm_proj": true,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
+
}
|
llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6f533fb28b1a0dcbf3b5b8b3e9a5f60053ab3c61849cc11d2e92937e9b99e41
|
| 3 |
+
size 11335231
|
llama2/graph-text-molgen/reagent_pred-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "llama-2-7b-chat",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"v_proj",
|
| 18 |
+
"o_proj",
|
| 19 |
+
"k_proj",
|
| 20 |
+
"up_proj",
|
| 21 |
+
"q_proj",
|
| 22 |
+
"down_proj",
|
| 23 |
+
"gate_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb9b722d5cdef8ec5c5bd99953017d2df5bccf4a98c451db8aa148afd1dca572
|
| 3 |
+
size 319970957
|
llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "llama-2-7b-chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"mm_graph_tower": "hvqvae2",
|
| 15 |
+
"mm_hidden_size": 308,
|
| 16 |
+
"mm_projector_type": "hlinear",
|
| 17 |
+
"mm_use_im_patch_token": false,
|
| 18 |
+
"mm_use_im_start_end": false,
|
| 19 |
+
"model_type": "llava_graph",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 32,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000.0,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float16",
|
| 29 |
+
"transformers_version": "4.33.2",
|
| 30 |
+
"tune_mm_mlp_adapter": false,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"use_lap_pe": true,
|
| 33 |
+
"use_mm_proj": true,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
+
}
|
llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dad9674828b2165c4753e24fb36bcdd7e4e7f8d04a4254fddb701cda91c7cee
|
| 3 |
+
size 11335231
|
llama2/graph-text-molgen/retrosynthesis-llava-hvqvae2-llama-2-7b-chat-finetune_lora-5ep16bz/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama2/llava-hvqvae2-llama-2-7b-chat-pretrain/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "llama-2-7b-chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"mm_graph_tower": "hvqvae2",
|
| 15 |
+
"mm_hidden_size": 308,
|
| 16 |
+
"mm_projector_type": "hlinear",
|
| 17 |
+
"mm_use_im_patch_token": false,
|
| 18 |
+
"mm_use_im_start_end": false,
|
| 19 |
+
"model_type": "llava_graph",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 32,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000.0,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float16",
|
| 29 |
+
"transformers_version": "4.33.2",
|
| 30 |
+
"tune_mm_mlp_adapter": true,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"use_lap_pe": true,
|
| 33 |
+
"use_mm_proj": true,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
+
}
|
llama2/llava-hvqvae2-llama-2-7b-chat-pretrain/mm_projector.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca86cf37d5c3ff431e9960c06d57876b68a5d3264ffe028a0b244a63cc3aac9b
|
| 3 |
+
size 7596223
|
llama2/llava-hvqvae2-llama-2-7b-chat-pretrain/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "llama-2-7b-chat",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"gate_proj",
|
| 18 |
+
"q_proj",
|
| 19 |
+
"o_proj",
|
| 20 |
+
"up_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"v_proj",
|
| 23 |
+
"down_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a4156fa46026e3b6db7e344c7c8e0c71269dab1e050f4e058c042028001305a
|
| 3 |
+
size 319970957
|
llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "llama-2-7b-chat",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"mm_graph_tower": "hvqvae2",
|
| 15 |
+
"mm_hidden_size": 308,
|
| 16 |
+
"mm_projector_type": "hlinear",
|
| 17 |
+
"mm_use_im_patch_token": false,
|
| 18 |
+
"mm_use_im_start_end": false,
|
| 19 |
+
"model_type": "llava_graph",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 32,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000.0,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float16",
|
| 29 |
+
"transformers_version": "4.33.2",
|
| 30 |
+
"tune_mm_mlp_adapter": false,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"use_lap_pe": true,
|
| 33 |
+
"use_mm_proj": true,
|
| 34 |
+
"vocab_size": 32000
|
| 35 |
+
}
|
llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce7a0b85f149002efc83f1e353479a2eb8b0c0ddbcab68b294b9cfccfc687de1
|
| 3 |
+
size 11335231
|
llama2/molcap-llava-hvqvae2-llama-2-7b-chat-finetune_lora-50ep/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "./vicuna-v1-3-7b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 256,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 128,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"gate_proj",
|
| 18 |
+
"v_proj",
|
| 19 |
+
"q_proj",
|
| 20 |
+
"down_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"o_proj",
|
| 23 |
+
"up_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ff93670b4d42680a8515ee55572fee64ff0286dd15b9d0b172dfe5b1078f2e2
|
| 3 |
+
size 639786637
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./vicuna-v1-3-7b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 2048,
|
| 14 |
+
"mm_graph_tower": "hvqvae2",
|
| 15 |
+
"mm_hidden_size": 308,
|
| 16 |
+
"mm_projector_type": "hlinear",
|
| 17 |
+
"mm_use_im_patch_token": false,
|
| 18 |
+
"mm_use_im_start_end": false,
|
| 19 |
+
"model_type": "llava_graph",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 32,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": null,
|
| 27 |
+
"rope_theta": 10000.0,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float16",
|
| 30 |
+
"transformers_version": "4.33.2",
|
| 31 |
+
"tune_mm_mlp_adapter": false,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"use_lap_pe": true,
|
| 34 |
+
"use_mm_proj": true,
|
| 35 |
+
"vocab_size": 32000
|
| 36 |
+
}
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48c804016822b1fcbeb5fdf1dcac9b404ab1763cae8255f273536ac9d72cbd1b
|
| 3 |
+
size 11335231
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_clintox/trainer_state.json
ADDED
|
@@ -0,0 +1,2308 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 380,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 14 |
+
"loss": 6.5781,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 6.666666666666667e-06,
|
| 20 |
+
"loss": 6.5469,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.16,
|
| 25 |
+
"learning_rate": 1e-05,
|
| 26 |
+
"loss": 6.6484,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.21,
|
| 31 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 32 |
+
"loss": 6.0312,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.26,
|
| 37 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 38 |
+
"loss": 5.1328,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.32,
|
| 43 |
+
"learning_rate": 2e-05,
|
| 44 |
+
"loss": 3.6328,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.37,
|
| 49 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 50 |
+
"loss": 2.4062,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.42,
|
| 55 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 56 |
+
"loss": 1.5195,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.47,
|
| 61 |
+
"learning_rate": 3.0000000000000004e-05,
|
| 62 |
+
"loss": 0.9883,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.53,
|
| 67 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 68 |
+
"loss": 0.6602,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.58,
|
| 73 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 74 |
+
"loss": 0.5137,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.63,
|
| 79 |
+
"learning_rate": 4e-05,
|
| 80 |
+
"loss": 0.3823,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.68,
|
| 85 |
+
"learning_rate": 3.9999271211568084e-05,
|
| 86 |
+
"loss": 0.2935,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.74,
|
| 91 |
+
"learning_rate": 3.999708489938559e-05,
|
| 92 |
+
"loss": 0.1488,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.79,
|
| 97 |
+
"learning_rate": 3.99934412227884e-05,
|
| 98 |
+
"loss": 0.2485,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.84,
|
| 103 |
+
"learning_rate": 3.998834044732348e-05,
|
| 104 |
+
"loss": 0.1338,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.89,
|
| 109 |
+
"learning_rate": 3.998178294472944e-05,
|
| 110 |
+
"loss": 0.1754,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.95,
|
| 115 |
+
"learning_rate": 3.997376919290946e-05,
|
| 116 |
+
"loss": 0.1593,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.0,
|
| 121 |
+
"learning_rate": 3.996429977589653e-05,
|
| 122 |
+
"loss": 0.1721,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.05,
|
| 127 |
+
"learning_rate": 3.995337538381079e-05,
|
| 128 |
+
"loss": 0.1564,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.11,
|
| 133 |
+
"learning_rate": 3.99409968128093e-05,
|
| 134 |
+
"loss": 0.1659,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.16,
|
| 139 |
+
"learning_rate": 3.9927164965028006e-05,
|
| 140 |
+
"loss": 0.1531,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.21,
|
| 145 |
+
"learning_rate": 3.991188084851596e-05,
|
| 146 |
+
"loss": 0.1584,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.26,
|
| 151 |
+
"learning_rate": 3.98951455771619e-05,
|
| 152 |
+
"loss": 0.1647,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.32,
|
| 157 |
+
"learning_rate": 3.987696037061304e-05,
|
| 158 |
+
"loss": 0.1562,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.37,
|
| 163 |
+
"learning_rate": 3.98573265541862e-05,
|
| 164 |
+
"loss": 0.1322,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.42,
|
| 169 |
+
"learning_rate": 3.98362455587712e-05,
|
| 170 |
+
"loss": 0.1619,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.47,
|
| 175 |
+
"learning_rate": 3.981371892072661e-05,
|
| 176 |
+
"loss": 0.1064,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.53,
|
| 181 |
+
"learning_rate": 3.9789748281767754e-05,
|
| 182 |
+
"loss": 0.1302,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.58,
|
| 187 |
+
"learning_rate": 3.976433538884706e-05,
|
| 188 |
+
"loss": 0.1328,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.63,
|
| 193 |
+
"learning_rate": 3.9737482094026764e-05,
|
| 194 |
+
"loss": 0.1242,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.68,
|
| 199 |
+
"learning_rate": 3.9709190354343936e-05,
|
| 200 |
+
"loss": 0.2114,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.74,
|
| 205 |
+
"learning_rate": 3.967946223166784e-05,
|
| 206 |
+
"loss": 0.1575,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.79,
|
| 211 |
+
"learning_rate": 3.9648299892549654e-05,
|
| 212 |
+
"loss": 0.082,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.84,
|
| 217 |
+
"learning_rate": 3.961570560806461e-05,
|
| 218 |
+
"loss": 0.1068,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.89,
|
| 223 |
+
"learning_rate": 3.958168175364646e-05,
|
| 224 |
+
"loss": 0.0997,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.95,
|
| 229 |
+
"learning_rate": 3.954623080891435e-05,
|
| 230 |
+
"loss": 0.1587,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.0,
|
| 235 |
+
"learning_rate": 3.950935535749213e-05,
|
| 236 |
+
"loss": 0.0936,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.05,
|
| 241 |
+
"learning_rate": 3.9471058086820024e-05,
|
| 242 |
+
"loss": 0.14,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.11,
|
| 247 |
+
"learning_rate": 3.943134178795883e-05,
|
| 248 |
+
"loss": 0.14,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.16,
|
| 253 |
+
"learning_rate": 3.939020935538647e-05,
|
| 254 |
+
"loss": 0.1548,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.21,
|
| 259 |
+
"learning_rate": 3.934766378678704e-05,
|
| 260 |
+
"loss": 0.1184,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.26,
|
| 265 |
+
"learning_rate": 3.930370818283235e-05,
|
| 266 |
+
"loss": 0.1104,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.32,
|
| 271 |
+
"learning_rate": 3.925834574695599e-05,
|
| 272 |
+
"loss": 0.1354,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.37,
|
| 277 |
+
"learning_rate": 3.9211579785119804e-05,
|
| 278 |
+
"loss": 0.108,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.42,
|
| 283 |
+
"learning_rate": 3.9163413705572984e-05,
|
| 284 |
+
"loss": 0.0513,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.47,
|
| 289 |
+
"learning_rate": 3.911385101860369e-05,
|
| 290 |
+
"loss": 0.1129,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.53,
|
| 295 |
+
"learning_rate": 3.906289533628322e-05,
|
| 296 |
+
"loss": 0.1,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.58,
|
| 301 |
+
"learning_rate": 3.9010550372202756e-05,
|
| 302 |
+
"loss": 0.1213,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.63,
|
| 307 |
+
"learning_rate": 3.895681994120272e-05,
|
| 308 |
+
"loss": 0.1859,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.68,
|
| 313 |
+
"learning_rate": 3.890170795909477e-05,
|
| 314 |
+
"loss": 0.1483,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.74,
|
| 319 |
+
"learning_rate": 3.8845218442376416e-05,
|
| 320 |
+
"loss": 0.0887,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.79,
|
| 325 |
+
"learning_rate": 3.878735550793827e-05,
|
| 326 |
+
"loss": 0.13,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.84,
|
| 331 |
+
"learning_rate": 3.8728123372764085e-05,
|
| 332 |
+
"loss": 0.1549,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.89,
|
| 337 |
+
"learning_rate": 3.8667526353623326e-05,
|
| 338 |
+
"loss": 0.1699,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.95,
|
| 343 |
+
"learning_rate": 3.8605568866756666e-05,
|
| 344 |
+
"loss": 0.1741,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.0,
|
| 349 |
+
"learning_rate": 3.8542255427554065e-05,
|
| 350 |
+
"loss": 0.1244,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.05,
|
| 355 |
+
"learning_rate": 3.8477590650225735e-05,
|
| 356 |
+
"loss": 0.11,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.11,
|
| 361 |
+
"learning_rate": 3.8411579247465845e-05,
|
| 362 |
+
"loss": 0.1753,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.16,
|
| 367 |
+
"learning_rate": 3.834422603010906e-05,
|
| 368 |
+
"loss": 0.1378,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 3.21,
|
| 373 |
+
"learning_rate": 3.827553590677996e-05,
|
| 374 |
+
"loss": 0.1133,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 3.26,
|
| 379 |
+
"learning_rate": 3.820551388353525e-05,
|
| 380 |
+
"loss": 0.14,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.32,
|
| 385 |
+
"learning_rate": 3.813416506349899e-05,
|
| 386 |
+
"loss": 0.1765,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.37,
|
| 391 |
+
"learning_rate": 3.806149464649066e-05,
|
| 392 |
+
"loss": 0.1208,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.42,
|
| 397 |
+
"learning_rate": 3.798750792864617e-05,
|
| 398 |
+
"loss": 0.1493,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.47,
|
| 403 |
+
"learning_rate": 3.791221030203193e-05,
|
| 404 |
+
"loss": 0.1252,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.53,
|
| 409 |
+
"learning_rate": 3.783560725425188e-05,
|
| 410 |
+
"loss": 0.1162,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.58,
|
| 415 |
+
"learning_rate": 3.775770436804751e-05,
|
| 416 |
+
"loss": 0.1919,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.63,
|
| 421 |
+
"learning_rate": 3.767850732089105e-05,
|
| 422 |
+
"loss": 0.0798,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 3.68,
|
| 427 |
+
"learning_rate": 3.759802188457168e-05,
|
| 428 |
+
"loss": 0.1332,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.74,
|
| 433 |
+
"learning_rate": 3.75162539247749e-05,
|
| 434 |
+
"loss": 0.0937,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 3.79,
|
| 439 |
+
"learning_rate": 3.743320940065503e-05,
|
| 440 |
+
"loss": 0.1108,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 3.84,
|
| 445 |
+
"learning_rate": 3.7348894364400914e-05,
|
| 446 |
+
"loss": 0.116,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.89,
|
| 451 |
+
"learning_rate": 3.726331496079486e-05,
|
| 452 |
+
"loss": 0.0609,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 3.95,
|
| 457 |
+
"learning_rate": 3.71764774267648e-05,
|
| 458 |
+
"loss": 0.1792,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.0,
|
| 463 |
+
"learning_rate": 3.7088388090929776e-05,
|
| 464 |
+
"loss": 0.0847,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.05,
|
| 469 |
+
"learning_rate": 3.699905337313866e-05,
|
| 470 |
+
"loss": 0.153,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 4.11,
|
| 475 |
+
"learning_rate": 3.690847978400236e-05,
|
| 476 |
+
"loss": 0.1088,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.16,
|
| 481 |
+
"learning_rate": 3.681667392441926e-05,
|
| 482 |
+
"loss": 0.1165,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 4.21,
|
| 487 |
+
"learning_rate": 3.672364248509422e-05,
|
| 488 |
+
"loss": 0.1244,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 4.26,
|
| 493 |
+
"learning_rate": 3.662939224605091e-05,
|
| 494 |
+
"loss": 0.1249,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 4.32,
|
| 499 |
+
"learning_rate": 3.653393007613771e-05,
|
| 500 |
+
"loss": 0.1248,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 4.37,
|
| 505 |
+
"learning_rate": 3.643726293252717e-05,
|
| 506 |
+
"loss": 0.0751,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 4.42,
|
| 511 |
+
"learning_rate": 3.633939786020884e-05,
|
| 512 |
+
"loss": 0.123,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 4.47,
|
| 517 |
+
"learning_rate": 3.624034199147602e-05,
|
| 518 |
+
"loss": 0.1466,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 4.53,
|
| 523 |
+
"learning_rate": 3.614010254540581e-05,
|
| 524 |
+
"loss": 0.1448,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.58,
|
| 529 |
+
"learning_rate": 3.60386868273331e-05,
|
| 530 |
+
"loss": 0.1605,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 4.63,
|
| 535 |
+
"learning_rate": 3.593610222831809e-05,
|
| 536 |
+
"loss": 0.1544,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 4.68,
|
| 541 |
+
"learning_rate": 3.58323562246077e-05,
|
| 542 |
+
"loss": 0.0949,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 4.74,
|
| 547 |
+
"learning_rate": 3.572745637709065e-05,
|
| 548 |
+
"loss": 0.1155,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 4.79,
|
| 553 |
+
"learning_rate": 3.562141033074649e-05,
|
| 554 |
+
"loss": 0.1235,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 4.84,
|
| 559 |
+
"learning_rate": 3.55142258140884e-05,
|
| 560 |
+
"loss": 0.1772,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 4.89,
|
| 565 |
+
"learning_rate": 3.540591063859996e-05,
|
| 566 |
+
"loss": 0.1523,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 4.95,
|
| 571 |
+
"learning_rate": 3.5296472698165856e-05,
|
| 572 |
+
"loss": 0.126,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 5.0,
|
| 577 |
+
"learning_rate": 3.51859199684966e-05,
|
| 578 |
+
"loss": 0.1054,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 5.05,
|
| 583 |
+
"learning_rate": 3.5074260506547225e-05,
|
| 584 |
+
"loss": 0.1022,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 5.11,
|
| 589 |
+
"learning_rate": 3.4961502449930165e-05,
|
| 590 |
+
"loss": 0.1858,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 5.16,
|
| 595 |
+
"learning_rate": 3.484765401632214e-05,
|
| 596 |
+
"loss": 0.1566,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 5.21,
|
| 601 |
+
"learning_rate": 3.473272350286529e-05,
|
| 602 |
+
"loss": 0.1021,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 5.26,
|
| 607 |
+
"learning_rate": 3.461671928556248e-05,
|
| 608 |
+
"loss": 0.0933,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 5.32,
|
| 613 |
+
"learning_rate": 3.449964981866689e-05,
|
| 614 |
+
"loss": 0.1385,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 5.37,
|
| 619 |
+
"learning_rate": 3.438152363406582e-05,
|
| 620 |
+
"loss": 0.1249,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 5.42,
|
| 625 |
+
"learning_rate": 3.426234934065896e-05,
|
| 626 |
+
"loss": 0.1295,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 5.47,
|
| 631 |
+
"learning_rate": 3.4142135623730954e-05,
|
| 632 |
+
"loss": 0.1067,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 5.53,
|
| 637 |
+
"learning_rate": 3.402089124431843e-05,
|
| 638 |
+
"loss": 0.1349,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 5.58,
|
| 643 |
+
"learning_rate": 3.38986250385715e-05,
|
| 644 |
+
"loss": 0.1412,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 5.63,
|
| 649 |
+
"learning_rate": 3.37753459171098e-05,
|
| 650 |
+
"loss": 0.0981,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 5.68,
|
| 655 |
+
"learning_rate": 3.365106286437309e-05,
|
| 656 |
+
"loss": 0.0834,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 5.74,
|
| 661 |
+
"learning_rate": 3.3525784937966474e-05,
|
| 662 |
+
"loss": 0.1453,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 5.79,
|
| 667 |
+
"learning_rate": 3.339952126800033e-05,
|
| 668 |
+
"loss": 0.1552,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 5.84,
|
| 673 |
+
"learning_rate": 3.3272281056424854e-05,
|
| 674 |
+
"loss": 0.0876,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 5.89,
|
| 679 |
+
"learning_rate": 3.3144073576359455e-05,
|
| 680 |
+
"loss": 0.151,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 5.95,
|
| 685 |
+
"learning_rate": 3.301490817141698e-05,
|
| 686 |
+
"loss": 0.1343,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 6.0,
|
| 691 |
+
"learning_rate": 3.288479425502273e-05,
|
| 692 |
+
"loss": 0.1047,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 6.05,
|
| 697 |
+
"learning_rate": 3.27537413097284e-05,
|
| 698 |
+
"loss": 0.1417,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 6.11,
|
| 703 |
+
"learning_rate": 3.262175888652106e-05,
|
| 704 |
+
"loss": 0.0889,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 6.16,
|
| 709 |
+
"learning_rate": 3.248885660412701e-05,
|
| 710 |
+
"loss": 0.0912,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 6.21,
|
| 715 |
+
"learning_rate": 3.235504414831087e-05,
|
| 716 |
+
"loss": 0.095,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 6.26,
|
| 721 |
+
"learning_rate": 3.2220331271169614e-05,
|
| 722 |
+
"loss": 0.1486,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 6.32,
|
| 727 |
+
"learning_rate": 3.2084727790421895e-05,
|
| 728 |
+
"loss": 0.1378,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 6.37,
|
| 733 |
+
"learning_rate": 3.194824358869252e-05,
|
| 734 |
+
"loss": 0.1383,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 6.42,
|
| 739 |
+
"learning_rate": 3.181088861279222e-05,
|
| 740 |
+
"loss": 0.1015,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 6.47,
|
| 745 |
+
"learning_rate": 3.1672672872992755e-05,
|
| 746 |
+
"loss": 0.1249,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 6.53,
|
| 751 |
+
"learning_rate": 3.153360644229735e-05,
|
| 752 |
+
"loss": 0.1289,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 6.58,
|
| 757 |
+
"learning_rate": 3.139369945570659e-05,
|
| 758 |
+
"loss": 0.1287,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 6.63,
|
| 763 |
+
"learning_rate": 3.125296210947983e-05,
|
| 764 |
+
"loss": 0.1008,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 6.68,
|
| 769 |
+
"learning_rate": 3.111140466039205e-05,
|
| 770 |
+
"loss": 0.1459,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 6.74,
|
| 775 |
+
"learning_rate": 3.0969037424986376e-05,
|
| 776 |
+
"loss": 0.146,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 6.79,
|
| 781 |
+
"learning_rate": 3.082587077882225e-05,
|
| 782 |
+
"loss": 0.1721,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 6.84,
|
| 787 |
+
"learning_rate": 3.068191515571921e-05,
|
| 788 |
+
"loss": 0.1113,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 6.89,
|
| 793 |
+
"learning_rate": 3.053718104699654e-05,
|
| 794 |
+
"loss": 0.1014,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 6.95,
|
| 799 |
+
"learning_rate": 3.0391679000708673e-05,
|
| 800 |
+
"loss": 0.106,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 7.0,
|
| 805 |
+
"learning_rate": 3.024541962087641e-05,
|
| 806 |
+
"loss": 0.1711,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 7.05,
|
| 811 |
+
"learning_rate": 3.0098413566714165e-05,
|
| 812 |
+
"loss": 0.0898,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 7.11,
|
| 817 |
+
"learning_rate": 2.9950671551853094e-05,
|
| 818 |
+
"loss": 0.0875,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 7.16,
|
| 823 |
+
"learning_rate": 2.980220434356035e-05,
|
| 824 |
+
"loss": 0.126,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 7.21,
|
| 829 |
+
"learning_rate": 2.965302276195431e-05,
|
| 830 |
+
"loss": 0.1261,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 7.26,
|
| 835 |
+
"learning_rate": 2.9503137679216073e-05,
|
| 836 |
+
"loss": 0.114,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 7.32,
|
| 841 |
+
"learning_rate": 2.935256001879709e-05,
|
| 842 |
+
"loss": 0.1384,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 7.37,
|
| 847 |
+
"learning_rate": 2.9201300754623046e-05,
|
| 848 |
+
"loss": 0.1226,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 7.42,
|
| 853 |
+
"learning_rate": 2.9049370910294143e-05,
|
| 854 |
+
"loss": 0.1263,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 7.47,
|
| 859 |
+
"learning_rate": 2.8896781558281688e-05,
|
| 860 |
+
"loss": 0.1452,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 7.53,
|
| 865 |
+
"learning_rate": 2.8743543819121132e-05,
|
| 866 |
+
"loss": 0.1198,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 7.58,
|
| 871 |
+
"learning_rate": 2.8589668860601643e-05,
|
| 872 |
+
"loss": 0.1314,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 7.63,
|
| 877 |
+
"learning_rate": 2.843516789695219e-05,
|
| 878 |
+
"loss": 0.1091,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 7.68,
|
| 883 |
+
"learning_rate": 2.828005218802427e-05,
|
| 884 |
+
"loss": 0.1127,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 7.74,
|
| 889 |
+
"learning_rate": 2.812433303847133e-05,
|
| 890 |
+
"loss": 0.1125,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 7.79,
|
| 895 |
+
"learning_rate": 2.7968021796924834e-05,
|
| 896 |
+
"loss": 0.1816,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 7.84,
|
| 901 |
+
"learning_rate": 2.781112985516725e-05,
|
| 902 |
+
"loss": 0.1317,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 7.89,
|
| 907 |
+
"learning_rate": 2.7653668647301797e-05,
|
| 908 |
+
"loss": 0.0975,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 7.95,
|
| 913 |
+
"learning_rate": 2.7495649648919153e-05,
|
| 914 |
+
"loss": 0.1036,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 8.0,
|
| 919 |
+
"learning_rate": 2.7337084376261135e-05,
|
| 920 |
+
"loss": 0.0846,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 8.05,
|
| 925 |
+
"learning_rate": 2.7177984385381366e-05,
|
| 926 |
+
"loss": 0.1436,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 8.11,
|
| 931 |
+
"learning_rate": 2.701836127130314e-05,
|
| 932 |
+
"loss": 0.0847,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 8.16,
|
| 937 |
+
"learning_rate": 2.6858226667174362e-05,
|
| 938 |
+
"loss": 0.0792,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 8.21,
|
| 943 |
+
"learning_rate": 2.6697592243419723e-05,
|
| 944 |
+
"loss": 0.1567,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 8.26,
|
| 949 |
+
"learning_rate": 2.6536469706890226e-05,
|
| 950 |
+
"loss": 0.1548,
|
| 951 |
+
"step": 157
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 8.32,
|
| 955 |
+
"learning_rate": 2.637487080000992e-05,
|
| 956 |
+
"loss": 0.1852,
|
| 957 |
+
"step": 158
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 8.37,
|
| 961 |
+
"learning_rate": 2.6212807299920218e-05,
|
| 962 |
+
"loss": 0.1085,
|
| 963 |
+
"step": 159
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 8.42,
|
| 967 |
+
"learning_rate": 2.605029101762152e-05,
|
| 968 |
+
"loss": 0.1364,
|
| 969 |
+
"step": 160
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 8.47,
|
| 973 |
+
"learning_rate": 2.588733379711248e-05,
|
| 974 |
+
"loss": 0.1144,
|
| 975 |
+
"step": 161
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 8.53,
|
| 979 |
+
"learning_rate": 2.572394751452683e-05,
|
| 980 |
+
"loss": 0.1056,
|
| 981 |
+
"step": 162
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 8.58,
|
| 985 |
+
"learning_rate": 2.5560144077267826e-05,
|
| 986 |
+
"loss": 0.1411,
|
| 987 |
+
"step": 163
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 8.63,
|
| 991 |
+
"learning_rate": 2.5395935423140487e-05,
|
| 992 |
+
"loss": 0.1246,
|
| 993 |
+
"step": 164
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 8.68,
|
| 997 |
+
"learning_rate": 2.5231333519481577e-05,
|
| 998 |
+
"loss": 0.1379,
|
| 999 |
+
"step": 165
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 8.74,
|
| 1003 |
+
"learning_rate": 2.5066350362287407e-05,
|
| 1004 |
+
"loss": 0.1045,
|
| 1005 |
+
"step": 166
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 8.79,
|
| 1009 |
+
"learning_rate": 2.490099797533964e-05,
|
| 1010 |
+
"loss": 0.1032,
|
| 1011 |
+
"step": 167
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 8.84,
|
| 1015 |
+
"learning_rate": 2.4735288409328937e-05,
|
| 1016 |
+
"loss": 0.0997,
|
| 1017 |
+
"step": 168
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 8.89,
|
| 1021 |
+
"learning_rate": 2.456923374097678e-05,
|
| 1022 |
+
"loss": 0.0868,
|
| 1023 |
+
"step": 169
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 8.95,
|
| 1027 |
+
"learning_rate": 2.4402846072155313e-05,
|
| 1028 |
+
"loss": 0.0928,
|
| 1029 |
+
"step": 170
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 9.0,
|
| 1033 |
+
"learning_rate": 2.4236137529005355e-05,
|
| 1034 |
+
"loss": 0.1117,
|
| 1035 |
+
"step": 171
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 9.05,
|
| 1039 |
+
"learning_rate": 2.4069120261052682e-05,
|
| 1040 |
+
"loss": 0.1288,
|
| 1041 |
+
"step": 172
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 9.11,
|
| 1045 |
+
"learning_rate": 2.390180644032257e-05,
|
| 1046 |
+
"loss": 0.1489,
|
| 1047 |
+
"step": 173
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 9.16,
|
| 1051 |
+
"learning_rate": 2.3734208260452727e-05,
|
| 1052 |
+
"loss": 0.1038,
|
| 1053 |
+
"step": 174
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 9.21,
|
| 1057 |
+
"learning_rate": 2.356633793580463e-05,
|
| 1058 |
+
"loss": 0.1051,
|
| 1059 |
+
"step": 175
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 9.26,
|
| 1063 |
+
"learning_rate": 2.3398207700573336e-05,
|
| 1064 |
+
"loss": 0.1711,
|
| 1065 |
+
"step": 176
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 9.32,
|
| 1069 |
+
"learning_rate": 2.3229829807895904e-05,
|
| 1070 |
+
"loss": 0.0945,
|
| 1071 |
+
"step": 177
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 9.37,
|
| 1075 |
+
"learning_rate": 2.306121652895836e-05,
|
| 1076 |
+
"loss": 0.1277,
|
| 1077 |
+
"step": 178
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 9.42,
|
| 1081 |
+
"learning_rate": 2.289238015210142e-05,
|
| 1082 |
+
"loss": 0.1415,
|
| 1083 |
+
"step": 179
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 9.47,
|
| 1087 |
+
"learning_rate": 2.2723332981924937e-05,
|
| 1088 |
+
"loss": 0.0664,
|
| 1089 |
+
"step": 180
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 9.53,
|
| 1093 |
+
"learning_rate": 2.2554087338391098e-05,
|
| 1094 |
+
"loss": 0.1089,
|
| 1095 |
+
"step": 181
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 9.58,
|
| 1099 |
+
"learning_rate": 2.2384655555926625e-05,
|
| 1100 |
+
"loss": 0.1195,
|
| 1101 |
+
"step": 182
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 9.63,
|
| 1105 |
+
"learning_rate": 2.2215049982523827e-05,
|
| 1106 |
+
"loss": 0.0781,
|
| 1107 |
+
"step": 183
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 9.68,
|
| 1111 |
+
"learning_rate": 2.2045282978840684e-05,
|
| 1112 |
+
"loss": 0.1266,
|
| 1113 |
+
"step": 184
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 9.74,
|
| 1117 |
+
"learning_rate": 2.1875366917300057e-05,
|
| 1118 |
+
"loss": 0.155,
|
| 1119 |
+
"step": 185
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 9.79,
|
| 1123 |
+
"learning_rate": 2.1705314181187922e-05,
|
| 1124 |
+
"loss": 0.1202,
|
| 1125 |
+
"step": 186
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 9.84,
|
| 1129 |
+
"learning_rate": 2.153513716375099e-05,
|
| 1130 |
+
"loss": 0.1676,
|
| 1131 |
+
"step": 187
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 9.89,
|
| 1135 |
+
"learning_rate": 2.1364848267293424e-05,
|
| 1136 |
+
"loss": 0.0894,
|
| 1137 |
+
"step": 188
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 9.95,
|
| 1141 |
+
"learning_rate": 2.1194459902272997e-05,
|
| 1142 |
+
"loss": 0.1196,
|
| 1143 |
+
"step": 189
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 10.0,
|
| 1147 |
+
"learning_rate": 2.102398448639667e-05,
|
| 1148 |
+
"loss": 0.0975,
|
| 1149 |
+
"step": 190
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 10.05,
|
| 1153 |
+
"learning_rate": 2.085343444371551e-05,
|
| 1154 |
+
"loss": 0.1364,
|
| 1155 |
+
"step": 191
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 10.11,
|
| 1159 |
+
"learning_rate": 2.068282220371936e-05,
|
| 1160 |
+
"loss": 0.108,
|
| 1161 |
+
"step": 192
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 10.16,
|
| 1165 |
+
"learning_rate": 2.0512160200430896e-05,
|
| 1166 |
+
"loss": 0.0727,
|
| 1167 |
+
"step": 193
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 10.21,
|
| 1171 |
+
"learning_rate": 2.03414608714995e-05,
|
| 1172 |
+
"loss": 0.1112,
|
| 1173 |
+
"step": 194
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 10.26,
|
| 1177 |
+
"learning_rate": 2.017073665729479e-05,
|
| 1178 |
+
"loss": 0.135,
|
| 1179 |
+
"step": 195
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 10.32,
|
| 1183 |
+
"learning_rate": 2e-05,
|
| 1184 |
+
"loss": 0.1162,
|
| 1185 |
+
"step": 196
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 10.37,
|
| 1189 |
+
"learning_rate": 1.982926334270522e-05,
|
| 1190 |
+
"loss": 0.1771,
|
| 1191 |
+
"step": 197
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 10.42,
|
| 1195 |
+
"learning_rate": 1.9658539128500507e-05,
|
| 1196 |
+
"loss": 0.0685,
|
| 1197 |
+
"step": 198
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 10.47,
|
| 1201 |
+
"learning_rate": 1.948783979956911e-05,
|
| 1202 |
+
"loss": 0.1078,
|
| 1203 |
+
"step": 199
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 10.53,
|
| 1207 |
+
"learning_rate": 1.9317177796280643e-05,
|
| 1208 |
+
"loss": 0.1307,
|
| 1209 |
+
"step": 200
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 10.58,
|
| 1213 |
+
"learning_rate": 1.9146565556284492e-05,
|
| 1214 |
+
"loss": 0.113,
|
| 1215 |
+
"step": 201
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 10.63,
|
| 1219 |
+
"learning_rate": 1.8976015513603344e-05,
|
| 1220 |
+
"loss": 0.0933,
|
| 1221 |
+
"step": 202
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 10.68,
|
| 1225 |
+
"learning_rate": 1.8805540097727003e-05,
|
| 1226 |
+
"loss": 0.1012,
|
| 1227 |
+
"step": 203
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 10.74,
|
| 1231 |
+
"learning_rate": 1.8635151732706586e-05,
|
| 1232 |
+
"loss": 0.1204,
|
| 1233 |
+
"step": 204
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 10.79,
|
| 1237 |
+
"learning_rate": 1.8464862836249014e-05,
|
| 1238 |
+
"loss": 0.1306,
|
| 1239 |
+
"step": 205
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 10.84,
|
| 1243 |
+
"learning_rate": 1.829468581881208e-05,
|
| 1244 |
+
"loss": 0.1296,
|
| 1245 |
+
"step": 206
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 10.89,
|
| 1249 |
+
"learning_rate": 1.8124633082699956e-05,
|
| 1250 |
+
"loss": 0.1087,
|
| 1251 |
+
"step": 207
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 10.95,
|
| 1255 |
+
"learning_rate": 1.7954717021159316e-05,
|
| 1256 |
+
"loss": 0.1519,
|
| 1257 |
+
"step": 208
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 11.0,
|
| 1261 |
+
"learning_rate": 1.778495001747618e-05,
|
| 1262 |
+
"loss": 0.1353,
|
| 1263 |
+
"step": 209
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 11.05,
|
| 1267 |
+
"learning_rate": 1.7615344444073385e-05,
|
| 1268 |
+
"loss": 0.1101,
|
| 1269 |
+
"step": 210
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 11.11,
|
| 1273 |
+
"learning_rate": 1.7445912661608912e-05,
|
| 1274 |
+
"loss": 0.1388,
|
| 1275 |
+
"step": 211
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 11.16,
|
| 1279 |
+
"learning_rate": 1.7276667018075073e-05,
|
| 1280 |
+
"loss": 0.1658,
|
| 1281 |
+
"step": 212
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 11.21,
|
| 1285 |
+
"learning_rate": 1.710761984789858e-05,
|
| 1286 |
+
"loss": 0.1342,
|
| 1287 |
+
"step": 213
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 11.26,
|
| 1291 |
+
"learning_rate": 1.6938783471041647e-05,
|
| 1292 |
+
"loss": 0.1012,
|
| 1293 |
+
"step": 214
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 11.32,
|
| 1297 |
+
"learning_rate": 1.6770170192104107e-05,
|
| 1298 |
+
"loss": 0.149,
|
| 1299 |
+
"step": 215
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 11.37,
|
| 1303 |
+
"learning_rate": 1.6601792299426668e-05,
|
| 1304 |
+
"loss": 0.1259,
|
| 1305 |
+
"step": 216
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 11.42,
|
| 1309 |
+
"learning_rate": 1.6433662064195378e-05,
|
| 1310 |
+
"loss": 0.093,
|
| 1311 |
+
"step": 217
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 11.47,
|
| 1315 |
+
"learning_rate": 1.6265791739547276e-05,
|
| 1316 |
+
"loss": 0.123,
|
| 1317 |
+
"step": 218
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 11.53,
|
| 1321 |
+
"learning_rate": 1.609819355967744e-05,
|
| 1322 |
+
"loss": 0.1042,
|
| 1323 |
+
"step": 219
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 11.58,
|
| 1327 |
+
"learning_rate": 1.5930879738947328e-05,
|
| 1328 |
+
"loss": 0.0735,
|
| 1329 |
+
"step": 220
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 11.63,
|
| 1333 |
+
"learning_rate": 1.576386247099465e-05,
|
| 1334 |
+
"loss": 0.0945,
|
| 1335 |
+
"step": 221
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 11.68,
|
| 1339 |
+
"learning_rate": 1.5597153927844693e-05,
|
| 1340 |
+
"loss": 0.0979,
|
| 1341 |
+
"step": 222
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 11.74,
|
| 1345 |
+
"learning_rate": 1.543076625902322e-05,
|
| 1346 |
+
"loss": 0.1059,
|
| 1347 |
+
"step": 223
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 11.79,
|
| 1351 |
+
"learning_rate": 1.5264711590671067e-05,
|
| 1352 |
+
"loss": 0.1222,
|
| 1353 |
+
"step": 224
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 11.84,
|
| 1357 |
+
"learning_rate": 1.5099002024660368e-05,
|
| 1358 |
+
"loss": 0.0948,
|
| 1359 |
+
"step": 225
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 11.89,
|
| 1363 |
+
"learning_rate": 1.4933649637712593e-05,
|
| 1364 |
+
"loss": 0.1166,
|
| 1365 |
+
"step": 226
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 11.95,
|
| 1369 |
+
"learning_rate": 1.4768666480518432e-05,
|
| 1370 |
+
"loss": 0.1295,
|
| 1371 |
+
"step": 227
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 12.0,
|
| 1375 |
+
"learning_rate": 1.4604064576859513e-05,
|
| 1376 |
+
"loss": 0.0759,
|
| 1377 |
+
"step": 228
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 12.05,
|
| 1381 |
+
"learning_rate": 1.4439855922732182e-05,
|
| 1382 |
+
"loss": 0.1631,
|
| 1383 |
+
"step": 229
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 12.11,
|
| 1387 |
+
"learning_rate": 1.4276052485473177e-05,
|
| 1388 |
+
"loss": 0.1216,
|
| 1389 |
+
"step": 230
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 12.16,
|
| 1393 |
+
"learning_rate": 1.4112666202887522e-05,
|
| 1394 |
+
"loss": 0.1101,
|
| 1395 |
+
"step": 231
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 12.21,
|
| 1399 |
+
"learning_rate": 1.3949708982378487e-05,
|
| 1400 |
+
"loss": 0.0963,
|
| 1401 |
+
"step": 232
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 12.26,
|
| 1405 |
+
"learning_rate": 1.3787192700079792e-05,
|
| 1406 |
+
"loss": 0.1061,
|
| 1407 |
+
"step": 233
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 12.32,
|
| 1411 |
+
"learning_rate": 1.3625129199990083e-05,
|
| 1412 |
+
"loss": 0.1411,
|
| 1413 |
+
"step": 234
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 12.37,
|
| 1417 |
+
"learning_rate": 1.3463530293109783e-05,
|
| 1418 |
+
"loss": 0.0859,
|
| 1419 |
+
"step": 235
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 12.42,
|
| 1423 |
+
"learning_rate": 1.3302407756580278e-05,
|
| 1424 |
+
"loss": 0.0946,
|
| 1425 |
+
"step": 236
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 12.47,
|
| 1429 |
+
"learning_rate": 1.3141773332825647e-05,
|
| 1430 |
+
"loss": 0.077,
|
| 1431 |
+
"step": 237
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 12.53,
|
| 1435 |
+
"learning_rate": 1.2981638728696868e-05,
|
| 1436 |
+
"loss": 0.0906,
|
| 1437 |
+
"step": 238
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 12.58,
|
| 1441 |
+
"learning_rate": 1.282201561461864e-05,
|
| 1442 |
+
"loss": 0.1389,
|
| 1443 |
+
"step": 239
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 12.63,
|
| 1447 |
+
"learning_rate": 1.2662915623738874e-05,
|
| 1448 |
+
"loss": 0.1498,
|
| 1449 |
+
"step": 240
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 12.68,
|
| 1453 |
+
"learning_rate": 1.2504350351080845e-05,
|
| 1454 |
+
"loss": 0.1659,
|
| 1455 |
+
"step": 241
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 12.74,
|
| 1459 |
+
"learning_rate": 1.2346331352698206e-05,
|
| 1460 |
+
"loss": 0.0935,
|
| 1461 |
+
"step": 242
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 12.79,
|
| 1465 |
+
"learning_rate": 1.2188870144832758e-05,
|
| 1466 |
+
"loss": 0.1377,
|
| 1467 |
+
"step": 243
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 12.84,
|
| 1471 |
+
"learning_rate": 1.2031978203075172e-05,
|
| 1472 |
+
"loss": 0.0899,
|
| 1473 |
+
"step": 244
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 12.89,
|
| 1477 |
+
"learning_rate": 1.1875666961528679e-05,
|
| 1478 |
+
"loss": 0.0848,
|
| 1479 |
+
"step": 245
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 12.95,
|
| 1483 |
+
"learning_rate": 1.1719947811975732e-05,
|
| 1484 |
+
"loss": 0.0976,
|
| 1485 |
+
"step": 246
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 13.0,
|
| 1489 |
+
"learning_rate": 1.1564832103047818e-05,
|
| 1490 |
+
"loss": 0.1545,
|
| 1491 |
+
"step": 247
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 13.05,
|
| 1495 |
+
"learning_rate": 1.1410331139398365e-05,
|
| 1496 |
+
"loss": 0.0834,
|
| 1497 |
+
"step": 248
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 13.11,
|
| 1501 |
+
"learning_rate": 1.1256456180878867e-05,
|
| 1502 |
+
"loss": 0.0946,
|
| 1503 |
+
"step": 249
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 13.16,
|
| 1507 |
+
"learning_rate": 1.110321844171832e-05,
|
| 1508 |
+
"loss": 0.1459,
|
| 1509 |
+
"step": 250
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 13.21,
|
| 1513 |
+
"learning_rate": 1.0950629089705857e-05,
|
| 1514 |
+
"loss": 0.1298,
|
| 1515 |
+
"step": 251
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 13.26,
|
| 1519 |
+
"learning_rate": 1.0798699245376959e-05,
|
| 1520 |
+
"loss": 0.1202,
|
| 1521 |
+
"step": 252
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 13.32,
|
| 1525 |
+
"learning_rate": 1.0647439981202918e-05,
|
| 1526 |
+
"loss": 0.0473,
|
| 1527 |
+
"step": 253
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 13.37,
|
| 1531 |
+
"learning_rate": 1.0496862320783926e-05,
|
| 1532 |
+
"loss": 0.0822,
|
| 1533 |
+
"step": 254
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 13.42,
|
| 1537 |
+
"learning_rate": 1.0346977238045699e-05,
|
| 1538 |
+
"loss": 0.0879,
|
| 1539 |
+
"step": 255
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 13.47,
|
| 1543 |
+
"learning_rate": 1.0197795656439662e-05,
|
| 1544 |
+
"loss": 0.1451,
|
| 1545 |
+
"step": 256
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 13.53,
|
| 1549 |
+
"learning_rate": 1.0049328448146908e-05,
|
| 1550 |
+
"loss": 0.1359,
|
| 1551 |
+
"step": 257
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 13.58,
|
| 1555 |
+
"learning_rate": 9.901586433285845e-06,
|
| 1556 |
+
"loss": 0.1129,
|
| 1557 |
+
"step": 258
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 13.63,
|
| 1561 |
+
"learning_rate": 9.75458037912359e-06,
|
| 1562 |
+
"loss": 0.1344,
|
| 1563 |
+
"step": 259
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 13.68,
|
| 1567 |
+
"learning_rate": 9.608320999291333e-06,
|
| 1568 |
+
"loss": 0.1667,
|
| 1569 |
+
"step": 260
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 13.74,
|
| 1573 |
+
"learning_rate": 9.462818953003465e-06,
|
| 1574 |
+
"loss": 0.1226,
|
| 1575 |
+
"step": 261
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 13.79,
|
| 1579 |
+
"learning_rate": 9.318084844280798e-06,
|
| 1580 |
+
"loss": 0.1144,
|
| 1581 |
+
"step": 262
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 13.84,
|
| 1585 |
+
"learning_rate": 9.174129221177762e-06,
|
| 1586 |
+
"loss": 0.1069,
|
| 1587 |
+
"step": 263
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 13.89,
|
| 1591 |
+
"learning_rate": 9.030962575013622e-06,
|
| 1592 |
+
"loss": 0.0981,
|
| 1593 |
+
"step": 264
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 13.95,
|
| 1597 |
+
"learning_rate": 8.888595339607961e-06,
|
| 1598 |
+
"loss": 0.1045,
|
| 1599 |
+
"step": 265
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 14.0,
|
| 1603 |
+
"learning_rate": 8.74703789052018e-06,
|
| 1604 |
+
"loss": 0.0757,
|
| 1605 |
+
"step": 266
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 14.05,
|
| 1609 |
+
"learning_rate": 8.606300544293412e-06,
|
| 1610 |
+
"loss": 0.0715,
|
| 1611 |
+
"step": 267
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 14.11,
|
| 1615 |
+
"learning_rate": 8.466393557702659e-06,
|
| 1616 |
+
"loss": 0.0791,
|
| 1617 |
+
"step": 268
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 14.16,
|
| 1621 |
+
"learning_rate": 8.327327127007247e-06,
|
| 1622 |
+
"loss": 0.1019,
|
| 1623 |
+
"step": 269
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 14.21,
|
| 1627 |
+
"learning_rate": 8.189111387207782e-06,
|
| 1628 |
+
"loss": 0.0872,
|
| 1629 |
+
"step": 270
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 14.26,
|
| 1633 |
+
"learning_rate": 8.051756411307494e-06,
|
| 1634 |
+
"loss": 0.0925,
|
| 1635 |
+
"step": 271
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 14.32,
|
| 1639 |
+
"learning_rate": 7.915272209578112e-06,
|
| 1640 |
+
"loss": 0.1394,
|
| 1641 |
+
"step": 272
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 14.37,
|
| 1645 |
+
"learning_rate": 7.779668728830389e-06,
|
| 1646 |
+
"loss": 0.1261,
|
| 1647 |
+
"step": 273
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 14.42,
|
| 1651 |
+
"learning_rate": 7.644955851689129e-06,
|
| 1652 |
+
"loss": 0.1342,
|
| 1653 |
+
"step": 274
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 14.47,
|
| 1657 |
+
"learning_rate": 7.511143395872986e-06,
|
| 1658 |
+
"loss": 0.1777,
|
| 1659 |
+
"step": 275
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 14.53,
|
| 1663 |
+
"learning_rate": 7.37824111347895e-06,
|
| 1664 |
+
"loss": 0.0706,
|
| 1665 |
+
"step": 276
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 14.58,
|
| 1669 |
+
"learning_rate": 7.246258690271599e-06,
|
| 1670 |
+
"loss": 0.1198,
|
| 1671 |
+
"step": 277
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 14.63,
|
| 1675 |
+
"learning_rate": 7.115205744977276e-06,
|
| 1676 |
+
"loss": 0.1486,
|
| 1677 |
+
"step": 278
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 14.68,
|
| 1681 |
+
"learning_rate": 6.985091828583024e-06,
|
| 1682 |
+
"loss": 0.1417,
|
| 1683 |
+
"step": 279
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 14.74,
|
| 1687 |
+
"learning_rate": 6.855926423640549e-06,
|
| 1688 |
+
"loss": 0.0808,
|
| 1689 |
+
"step": 280
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 14.79,
|
| 1693 |
+
"learning_rate": 6.727718943575161e-06,
|
| 1694 |
+
"loss": 0.1207,
|
| 1695 |
+
"step": 281
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 14.84,
|
| 1699 |
+
"learning_rate": 6.6004787319996714e-06,
|
| 1700 |
+
"loss": 0.1378,
|
| 1701 |
+
"step": 282
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 14.89,
|
| 1705 |
+
"learning_rate": 6.474215062033527e-06,
|
| 1706 |
+
"loss": 0.0938,
|
| 1707 |
+
"step": 283
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 14.95,
|
| 1711 |
+
"learning_rate": 6.348937135626922e-06,
|
| 1712 |
+
"loss": 0.0977,
|
| 1713 |
+
"step": 284
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 15.0,
|
| 1717 |
+
"learning_rate": 6.224654082890207e-06,
|
| 1718 |
+
"loss": 0.0988,
|
| 1719 |
+
"step": 285
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 15.05,
|
| 1723 |
+
"learning_rate": 6.101374961428512e-06,
|
| 1724 |
+
"loss": 0.104,
|
| 1725 |
+
"step": 286
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 15.11,
|
| 1729 |
+
"learning_rate": 5.979108755681575e-06,
|
| 1730 |
+
"loss": 0.098,
|
| 1731 |
+
"step": 287
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 15.16,
|
| 1735 |
+
"learning_rate": 5.857864376269051e-06,
|
| 1736 |
+
"loss": 0.1224,
|
| 1737 |
+
"step": 288
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 15.21,
|
| 1741 |
+
"learning_rate": 5.737650659341048e-06,
|
| 1742 |
+
"loss": 0.1119,
|
| 1743 |
+
"step": 289
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 15.26,
|
| 1747 |
+
"learning_rate": 5.618476365934184e-06,
|
| 1748 |
+
"loss": 0.0853,
|
| 1749 |
+
"step": 290
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 15.32,
|
| 1753 |
+
"learning_rate": 5.500350181333121e-06,
|
| 1754 |
+
"loss": 0.132,
|
| 1755 |
+
"step": 291
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 15.37,
|
| 1759 |
+
"learning_rate": 5.383280714437518e-06,
|
| 1760 |
+
"loss": 0.097,
|
| 1761 |
+
"step": 292
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 15.42,
|
| 1765 |
+
"learning_rate": 5.267276497134715e-06,
|
| 1766 |
+
"loss": 0.1141,
|
| 1767 |
+
"step": 293
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 15.47,
|
| 1771 |
+
"learning_rate": 5.152345983677866e-06,
|
| 1772 |
+
"loss": 0.0679,
|
| 1773 |
+
"step": 294
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 15.53,
|
| 1777 |
+
"learning_rate": 5.038497550069836e-06,
|
| 1778 |
+
"loss": 0.1497,
|
| 1779 |
+
"step": 295
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 15.58,
|
| 1783 |
+
"learning_rate": 4.925739493452783e-06,
|
| 1784 |
+
"loss": 0.1241,
|
| 1785 |
+
"step": 296
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 15.63,
|
| 1789 |
+
"learning_rate": 4.814080031503407e-06,
|
| 1790 |
+
"loss": 0.1188,
|
| 1791 |
+
"step": 297
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 15.68,
|
| 1795 |
+
"learning_rate": 4.703527301834148e-06,
|
| 1796 |
+
"loss": 0.1086,
|
| 1797 |
+
"step": 298
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 15.74,
|
| 1801 |
+
"learning_rate": 4.594089361400047e-06,
|
| 1802 |
+
"loss": 0.0771,
|
| 1803 |
+
"step": 299
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 15.79,
|
| 1807 |
+
"learning_rate": 4.4857741859116024e-06,
|
| 1808 |
+
"loss": 0.0798,
|
| 1809 |
+
"step": 300
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 15.84,
|
| 1813 |
+
"learning_rate": 4.3785896692535165e-06,
|
| 1814 |
+
"loss": 0.1273,
|
| 1815 |
+
"step": 301
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 15.89,
|
| 1819 |
+
"learning_rate": 4.272543622909355e-06,
|
| 1820 |
+
"loss": 0.1525,
|
| 1821 |
+
"step": 302
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 15.95,
|
| 1825 |
+
"learning_rate": 4.167643775392305e-06,
|
| 1826 |
+
"loss": 0.1028,
|
| 1827 |
+
"step": 303
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 16.0,
|
| 1831 |
+
"learning_rate": 4.0638977716819105e-06,
|
| 1832 |
+
"loss": 0.1076,
|
| 1833 |
+
"step": 304
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 16.05,
|
| 1837 |
+
"learning_rate": 3.961313172666898e-06,
|
| 1838 |
+
"loss": 0.1121,
|
| 1839 |
+
"step": 305
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 16.11,
|
| 1843 |
+
"learning_rate": 3.859897454594192e-06,
|
| 1844 |
+
"loss": 0.1235,
|
| 1845 |
+
"step": 306
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 16.16,
|
| 1849 |
+
"learning_rate": 3.7596580085239897e-06,
|
| 1850 |
+
"loss": 0.0991,
|
| 1851 |
+
"step": 307
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 16.21,
|
| 1855 |
+
"learning_rate": 3.6606021397911605e-06,
|
| 1856 |
+
"loss": 0.0968,
|
| 1857 |
+
"step": 308
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 16.26,
|
| 1861 |
+
"learning_rate": 3.562737067472841e-06,
|
| 1862 |
+
"loss": 0.1037,
|
| 1863 |
+
"step": 309
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 16.32,
|
| 1867 |
+
"learning_rate": 3.466069923862283e-06,
|
| 1868 |
+
"loss": 0.1241,
|
| 1869 |
+
"step": 310
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 16.37,
|
| 1873 |
+
"learning_rate": 3.3706077539490933e-06,
|
| 1874 |
+
"loss": 0.1168,
|
| 1875 |
+
"step": 311
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 16.42,
|
| 1879 |
+
"learning_rate": 3.276357514905788e-06,
|
| 1880 |
+
"loss": 0.1035,
|
| 1881 |
+
"step": 312
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 16.47,
|
| 1885 |
+
"learning_rate": 3.1833260755807392e-06,
|
| 1886 |
+
"loss": 0.0432,
|
| 1887 |
+
"step": 313
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 16.53,
|
| 1891 |
+
"learning_rate": 3.0915202159976453e-06,
|
| 1892 |
+
"loss": 0.1074,
|
| 1893 |
+
"step": 314
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 16.58,
|
| 1897 |
+
"learning_rate": 3.0009466268613384e-06,
|
| 1898 |
+
"loss": 0.1264,
|
| 1899 |
+
"step": 315
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 16.63,
|
| 1903 |
+
"learning_rate": 2.911611909070229e-06,
|
| 1904 |
+
"loss": 0.123,
|
| 1905 |
+
"step": 316
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 16.68,
|
| 1909 |
+
"learning_rate": 2.8235225732352043e-06,
|
| 1910 |
+
"loss": 0.1694,
|
| 1911 |
+
"step": 317
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 16.74,
|
| 1915 |
+
"learning_rate": 2.7366850392051468e-06,
|
| 1916 |
+
"loss": 0.113,
|
| 1917 |
+
"step": 318
|
| 1918 |
+
},
|
| 1919 |
+
{
|
| 1920 |
+
"epoch": 16.79,
|
| 1921 |
+
"learning_rate": 2.651105635599094e-06,
|
| 1922 |
+
"loss": 0.0794,
|
| 1923 |
+
"step": 319
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 16.84,
|
| 1927 |
+
"learning_rate": 2.566790599344973e-06,
|
| 1928 |
+
"loss": 0.1141,
|
| 1929 |
+
"step": 320
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 16.89,
|
| 1933 |
+
"learning_rate": 2.4837460752251e-06,
|
| 1934 |
+
"loss": 0.1049,
|
| 1935 |
+
"step": 321
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 16.95,
|
| 1939 |
+
"learning_rate": 2.401978115428325e-06,
|
| 1940 |
+
"loss": 0.0822,
|
| 1941 |
+
"step": 322
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 17.0,
|
| 1945 |
+
"learning_rate": 2.3214926791089563e-06,
|
| 1946 |
+
"loss": 0.0925,
|
| 1947 |
+
"step": 323
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 17.05,
|
| 1951 |
+
"learning_rate": 2.242295631952496e-06,
|
| 1952 |
+
"loss": 0.1565,
|
| 1953 |
+
"step": 324
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 17.11,
|
| 1957 |
+
"learning_rate": 2.164392745748125e-06,
|
| 1958 |
+
"loss": 0.0919,
|
| 1959 |
+
"step": 325
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 17.16,
|
| 1963 |
+
"learning_rate": 2.0877896979680654e-06,
|
| 1964 |
+
"loss": 0.0696,
|
| 1965 |
+
"step": 326
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 17.21,
|
| 1969 |
+
"learning_rate": 2.0124920713538378e-06,
|
| 1970 |
+
"loss": 0.1249,
|
| 1971 |
+
"step": 327
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 17.26,
|
| 1975 |
+
"learning_rate": 1.9385053535093455e-06,
|
| 1976 |
+
"loss": 0.0936,
|
| 1977 |
+
"step": 328
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 17.32,
|
| 1981 |
+
"learning_rate": 1.865834936501012e-06,
|
| 1982 |
+
"loss": 0.1407,
|
| 1983 |
+
"step": 329
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 17.37,
|
| 1987 |
+
"learning_rate": 1.7944861164647576e-06,
|
| 1988 |
+
"loss": 0.0899,
|
| 1989 |
+
"step": 330
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 17.42,
|
| 1993 |
+
"learning_rate": 1.7244640932200484e-06,
|
| 1994 |
+
"loss": 0.0845,
|
| 1995 |
+
"step": 331
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 17.47,
|
| 1999 |
+
"learning_rate": 1.6557739698909436e-06,
|
| 2000 |
+
"loss": 0.1045,
|
| 2001 |
+
"step": 332
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 17.53,
|
| 2005 |
+
"learning_rate": 1.5884207525341566e-06,
|
| 2006 |
+
"loss": 0.0789,
|
| 2007 |
+
"step": 333
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 17.58,
|
| 2011 |
+
"learning_rate": 1.5224093497742654e-06,
|
| 2012 |
+
"loss": 0.1224,
|
| 2013 |
+
"step": 334
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 17.63,
|
| 2017 |
+
"learning_rate": 1.4577445724459382e-06,
|
| 2018 |
+
"loss": 0.1201,
|
| 2019 |
+
"step": 335
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 17.68,
|
| 2023 |
+
"learning_rate": 1.3944311332433368e-06,
|
| 2024 |
+
"loss": 0.1676,
|
| 2025 |
+
"step": 336
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 17.74,
|
| 2029 |
+
"learning_rate": 1.3324736463766775e-06,
|
| 2030 |
+
"loss": 0.0922,
|
| 2031 |
+
"step": 337
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 17.79,
|
| 2035 |
+
"learning_rate": 1.2718766272359195e-06,
|
| 2036 |
+
"loss": 0.096,
|
| 2037 |
+
"step": 338
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 17.84,
|
| 2041 |
+
"learning_rate": 1.2126444920617297e-06,
|
| 2042 |
+
"loss": 0.115,
|
| 2043 |
+
"step": 339
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 17.89,
|
| 2047 |
+
"learning_rate": 1.154781557623592e-06,
|
| 2048 |
+
"loss": 0.0891,
|
| 2049 |
+
"step": 340
|
| 2050 |
+
},
|
| 2051 |
+
{
|
| 2052 |
+
"epoch": 17.95,
|
| 2053 |
+
"learning_rate": 1.0982920409052312e-06,
|
| 2054 |
+
"loss": 0.0937,
|
| 2055 |
+
"step": 341
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 18.0,
|
| 2059 |
+
"learning_rate": 1.0431800587972862e-06,
|
| 2060 |
+
"loss": 0.144,
|
| 2061 |
+
"step": 342
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 18.05,
|
| 2065 |
+
"learning_rate": 9.894496277972498e-07,
|
| 2066 |
+
"loss": 0.1003,
|
| 2067 |
+
"step": 343
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 18.11,
|
| 2071 |
+
"learning_rate": 9.371046637167835e-07,
|
| 2072 |
+
"loss": 0.0836,
|
| 2073 |
+
"step": 344
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 18.16,
|
| 2077 |
+
"learning_rate": 8.861489813963154e-07,
|
| 2078 |
+
"loss": 0.09,
|
| 2079 |
+
"step": 345
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 18.21,
|
| 2083 |
+
"learning_rate": 8.365862944270243e-07,
|
| 2084 |
+
"loss": 0.1049,
|
| 2085 |
+
"step": 346
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 18.26,
|
| 2089 |
+
"learning_rate": 7.884202148802056e-07,
|
| 2090 |
+
"loss": 0.0909,
|
| 2091 |
+
"step": 347
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 18.32,
|
| 2095 |
+
"learning_rate": 7.416542530440174e-07,
|
| 2096 |
+
"loss": 0.1455,
|
| 2097 |
+
"step": 348
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 18.37,
|
| 2101 |
+
"learning_rate": 6.962918171676536e-07,
|
| 2102 |
+
"loss": 0.0975,
|
| 2103 |
+
"step": 349
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 18.42,
|
| 2107 |
+
"learning_rate": 6.523362132129718e-07,
|
| 2108 |
+
"loss": 0.1263,
|
| 2109 |
+
"step": 350
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 18.47,
|
| 2113 |
+
"learning_rate": 6.097906446135349e-07,
|
| 2114 |
+
"loss": 0.101,
|
| 2115 |
+
"step": 351
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 18.53,
|
| 2119 |
+
"learning_rate": 5.68658212041171e-07,
|
| 2120 |
+
"loss": 0.1289,
|
| 2121 |
+
"step": 352
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 18.58,
|
| 2125 |
+
"learning_rate": 5.289419131799811e-07,
|
| 2126 |
+
"loss": 0.1259,
|
| 2127 |
+
"step": 353
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 18.63,
|
| 2131 |
+
"learning_rate": 4.906446425078782e-07,
|
| 2132 |
+
"loss": 0.1038,
|
| 2133 |
+
"step": 354
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 18.68,
|
| 2137 |
+
"learning_rate": 4.5376919108565345e-07,
|
| 2138 |
+
"loss": 0.0813,
|
| 2139 |
+
"step": 355
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 18.74,
|
| 2143 |
+
"learning_rate": 4.183182463535418e-07,
|
| 2144 |
+
"loss": 0.1128,
|
| 2145 |
+
"step": 356
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 18.79,
|
| 2149 |
+
"learning_rate": 3.842943919353914e-07,
|
| 2150 |
+
"loss": 0.1093,
|
| 2151 |
+
"step": 357
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 18.84,
|
| 2155 |
+
"learning_rate": 3.517001074503501e-07,
|
| 2156 |
+
"loss": 0.0865,
|
| 2157 |
+
"step": 358
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 18.89,
|
| 2161 |
+
"learning_rate": 3.2053776833216533e-07,
|
| 2162 |
+
"loss": 0.0916,
|
| 2163 |
+
"step": 359
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 18.95,
|
| 2167 |
+
"learning_rate": 2.9080964565606273e-07,
|
| 2168 |
+
"loss": 0.1151,
|
| 2169 |
+
"step": 360
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 19.0,
|
| 2173 |
+
"learning_rate": 2.625179059732341e-07,
|
| 2174 |
+
"loss": 0.1344,
|
| 2175 |
+
"step": 361
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 19.05,
|
| 2179 |
+
"learning_rate": 2.356646111529415e-07,
|
| 2180 |
+
"loss": 0.1064,
|
| 2181 |
+
"step": 362
|
| 2182 |
+
},
|
| 2183 |
+
{
|
| 2184 |
+
"epoch": 19.11,
|
| 2185 |
+
"learning_rate": 2.102517182322483e-07,
|
| 2186 |
+
"loss": 0.1053,
|
| 2187 |
+
"step": 363
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 19.16,
|
| 2191 |
+
"learning_rate": 1.862810792733849e-07,
|
| 2192 |
+
"loss": 0.0972,
|
| 2193 |
+
"step": 364
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 19.21,
|
| 2197 |
+
"learning_rate": 1.6375444122879613e-07,
|
| 2198 |
+
"loss": 0.0987,
|
| 2199 |
+
"step": 365
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 19.26,
|
| 2203 |
+
"learning_rate": 1.4267344581380127e-07,
|
| 2204 |
+
"loss": 0.1519,
|
| 2205 |
+
"step": 366
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 19.32,
|
| 2209 |
+
"learning_rate": 1.2303962938696068e-07,
|
| 2210 |
+
"loss": 0.0834,
|
| 2211 |
+
"step": 367
|
| 2212 |
+
},
|
| 2213 |
+
{
|
| 2214 |
+
"epoch": 19.37,
|
| 2215 |
+
"learning_rate": 1.0485442283810321e-07,
|
| 2216 |
+
"loss": 0.1057,
|
| 2217 |
+
"step": 368
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 19.42,
|
| 2221 |
+
"learning_rate": 8.811915148404294e-08,
|
| 2222 |
+
"loss": 0.0887,
|
| 2223 |
+
"step": 369
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 19.47,
|
| 2227 |
+
"learning_rate": 7.283503497200083e-08,
|
| 2228 |
+
"loss": 0.0955,
|
| 2229 |
+
"step": 370
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 19.53,
|
| 2233 |
+
"learning_rate": 5.900318719070264e-08,
|
| 2234 |
+
"loss": 0.1124,
|
| 2235 |
+
"step": 371
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 19.58,
|
| 2239 |
+
"learning_rate": 4.6624616189214765e-08,
|
| 2240 |
+
"loss": 0.1663,
|
| 2241 |
+
"step": 372
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 19.63,
|
| 2245 |
+
"learning_rate": 3.570022410347651e-08,
|
| 2246 |
+
"loss": 0.1356,
|
| 2247 |
+
"step": 373
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 19.68,
|
| 2251 |
+
"learning_rate": 2.623080709054149e-08,
|
| 2252 |
+
"loss": 0.1042,
|
| 2253 |
+
"step": 374
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 19.74,
|
| 2257 |
+
"learning_rate": 1.8217055270568497e-08,
|
| 2258 |
+
"loss": 0.0729,
|
| 2259 |
+
"step": 375
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 19.79,
|
| 2263 |
+
"learning_rate": 1.1659552676519525e-08,
|
| 2264 |
+
"loss": 0.0972,
|
| 2265 |
+
"step": 376
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 19.84,
|
| 2269 |
+
"learning_rate": 6.558777211598255e-09,
|
| 2270 |
+
"loss": 0.1289,
|
| 2271 |
+
"step": 377
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 19.89,
|
| 2275 |
+
"learning_rate": 2.9151006144201298e-09,
|
| 2276 |
+
"loss": 0.1013,
|
| 2277 |
+
"step": 378
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 19.95,
|
| 2281 |
+
"learning_rate": 7.287884319184813e-10,
|
| 2282 |
+
"loss": 0.0726,
|
| 2283 |
+
"step": 379
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 20.0,
|
| 2287 |
+
"learning_rate": 0.0,
|
| 2288 |
+
"loss": 0.1038,
|
| 2289 |
+
"step": 380
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 20.0,
|
| 2293 |
+
"step": 380,
|
| 2294 |
+
"total_flos": 1.2544198305644544e+17,
|
| 2295 |
+
"train_loss": 0.2236757378829153,
|
| 2296 |
+
"train_runtime": 2520.2948,
|
| 2297 |
+
"train_samples_per_second": 18.744,
|
| 2298 |
+
"train_steps_per_second": 0.151
|
| 2299 |
+
}
|
| 2300 |
+
],
|
| 2301 |
+
"logging_steps": 1.0,
|
| 2302 |
+
"max_steps": 380,
|
| 2303 |
+
"num_train_epochs": 20,
|
| 2304 |
+
"save_steps": 500,
|
| 2305 |
+
"total_flos": 1.2544198305644544e+17,
|
| 2306 |
+
"trial_name": null,
|
| 2307 |
+
"trial_params": null
|
| 2308 |
+
}
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_cyp450/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_cyp450/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "./vicuna-v1-3-7b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 256,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 128,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"gate_proj",
|
| 18 |
+
"down_proj",
|
| 19 |
+
"q_proj",
|
| 20 |
+
"v_proj",
|
| 21 |
+
"o_proj",
|
| 22 |
+
"up_proj",
|
| 23 |
+
"k_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_cyp450/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./vicuna-v1-3-7b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 2048,
|
| 14 |
+
"mm_graph_tower": "hvqvae2",
|
| 15 |
+
"mm_hidden_size": 308,
|
| 16 |
+
"mm_projector_type": "hlinear",
|
| 17 |
+
"mm_use_im_patch_token": false,
|
| 18 |
+
"mm_use_im_start_end": false,
|
| 19 |
+
"model_type": "llava_graph",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 32,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": null,
|
| 27 |
+
"rope_theta": 10000.0,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float16",
|
| 30 |
+
"transformers_version": "4.33.2",
|
| 31 |
+
"tune_mm_mlp_adapter": false,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"use_lap_pe": true,
|
| 34 |
+
"use_mm_proj": true,
|
| 35 |
+
"vocab_size": 32000
|
| 36 |
+
}
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_cyp450/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "./vicuna-v1-3-7b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 256,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 128,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"gate_proj",
|
| 18 |
+
"v_proj",
|
| 19 |
+
"down_proj",
|
| 20 |
+
"up_proj",
|
| 21 |
+
"q_proj",
|
| 22 |
+
"k_proj",
|
| 23 |
+
"o_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:328cad954d1e8571e2c38737f610c22e395c2d50f4398c5d3dc58c559d143c86
|
| 3 |
+
size 639786637
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./vicuna-v1-3-7b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 2048,
|
| 14 |
+
"mm_graph_tower": "hvqvae2",
|
| 15 |
+
"mm_hidden_size": 308,
|
| 16 |
+
"mm_projector_type": "hlinear",
|
| 17 |
+
"mm_use_im_patch_token": false,
|
| 18 |
+
"mm_use_im_start_end": false,
|
| 19 |
+
"model_type": "llava_graph",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 32,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": null,
|
| 27 |
+
"rope_theta": 10000.0,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float16",
|
| 30 |
+
"transformers_version": "4.33.2",
|
| 31 |
+
"tune_mm_mlp_adapter": false,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"use_lap_pe": true,
|
| 34 |
+
"use_mm_proj": true,
|
| 35 |
+
"vocab_size": 32000
|
| 36 |
+
}
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05ba3c951e28a452dea5de42afef15c938838efdcfc7ace6367d07642be1cc06
|
| 3 |
+
size 11335231
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_muv/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "./vicuna-v1-3-7b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 256,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 128,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"up_proj",
|
| 18 |
+
"v_proj",
|
| 19 |
+
"q_proj",
|
| 20 |
+
"o_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"gate_proj",
|
| 23 |
+
"down_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6685fba4bef8bb80482d235d034bd1d5cc1e443e3b5dc01f299d510d01db2f3d
|
| 3 |
+
size 639786637
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./vicuna-v1-3-7b",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 2048,
|
| 14 |
+
"mm_graph_tower": "hvqvae2",
|
| 15 |
+
"mm_hidden_size": 308,
|
| 16 |
+
"mm_projector_type": "hlinear",
|
| 17 |
+
"mm_use_im_patch_token": false,
|
| 18 |
+
"mm_use_im_start_end": false,
|
| 19 |
+
"model_type": "llava_graph",
|
| 20 |
+
"num_attention_heads": 32,
|
| 21 |
+
"num_hidden_layers": 32,
|
| 22 |
+
"num_key_value_heads": 32,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"pretraining_tp": 1,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": null,
|
| 27 |
+
"rope_theta": 10000.0,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float16",
|
| 30 |
+
"transformers_version": "4.33.2",
|
| 31 |
+
"tune_mm_mlp_adapter": false,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"use_lap_pe": true,
|
| 34 |
+
"use_mm_proj": true,
|
| 35 |
+
"vocab_size": 32000
|
| 36 |
+
}
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/non_lora_trainables.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96dd77e8eaf9d0f27d20361dcbfef3a531b1f7ca98a7f87c55234c6542f914d4
|
| 3 |
+
size 11335231
|
vicuna/MoleculeNet-llava-hvqvae2-vicuna-v1-3-7b-finetune_lora-large_gimlet_sider/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|