nRuaif
commited on
Commit
·
614fdf5
1
Parent(s):
2ec64ca
Upload folder using huggingface_hub
Browse files- Untitled.ipynb +11 -11
- checkpoint-100/README.md +21 -0
- checkpoint-100/adapter_config.json +26 -0
- checkpoint-100/adapter_model.bin +3 -0
- checkpoint-100/adapter_model/README.md +21 -0
- checkpoint-100/adapter_model/adapter_config.json +26 -0
- checkpoint-100/adapter_model/adapter_model.bin +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/trainer_state.json +699 -0
- checkpoint-100/training_args.bin +3 -0
Untitled.ipynb
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
-
"execution_count":
|
| 6 |
"id": "127668ee-44f0-4438-9337-e7c4a486aea3",
|
| 7 |
"metadata": {},
|
| 8 |
"outputs": [
|
|
@@ -16,12 +16,12 @@
|
|
| 16 |
{
|
| 17 |
"data": {
|
| 18 |
"application/vnd.jupyter.widget-view+json": {
|
| 19 |
-
"model_id": "
|
| 20 |
"version_major": 2,
|
| 21 |
"version_minor": 0
|
| 22 |
},
|
| 23 |
"text/plain": [
|
| 24 |
-
"
|
| 25 |
]
|
| 26 |
},
|
| 27 |
"metadata": {},
|
|
@@ -30,7 +30,7 @@
|
|
| 30 |
{
|
| 31 |
"data": {
|
| 32 |
"application/vnd.jupyter.widget-view+json": {
|
| 33 |
-
"model_id": "
|
| 34 |
"version_major": 2,
|
| 35 |
"version_minor": 0
|
| 36 |
},
|
|
@@ -44,7 +44,7 @@
|
|
| 44 |
{
|
| 45 |
"data": {
|
| 46 |
"application/vnd.jupyter.widget-view+json": {
|
| 47 |
-
"model_id": "
|
| 48 |
"version_major": 2,
|
| 49 |
"version_minor": 0
|
| 50 |
},
|
|
@@ -58,12 +58,12 @@
|
|
| 58 |
{
|
| 59 |
"data": {
|
| 60 |
"application/vnd.jupyter.widget-view+json": {
|
| 61 |
-
"model_id": "
|
| 62 |
"version_major": 2,
|
| 63 |
"version_minor": 0
|
| 64 |
},
|
| 65 |
"text/plain": [
|
| 66 |
-
"
|
| 67 |
]
|
| 68 |
},
|
| 69 |
"metadata": {},
|
|
@@ -72,12 +72,12 @@
|
|
| 72 |
{
|
| 73 |
"data": {
|
| 74 |
"application/vnd.jupyter.widget-view+json": {
|
| 75 |
-
"model_id": "
|
| 76 |
"version_major": 2,
|
| 77 |
"version_minor": 0
|
| 78 |
},
|
| 79 |
"text/plain": [
|
| 80 |
-
"
|
| 81 |
]
|
| 82 |
},
|
| 83 |
"metadata": {},
|
|
@@ -86,7 +86,7 @@
|
|
| 86 |
{
|
| 87 |
"data": {
|
| 88 |
"application/vnd.jupyter.widget-view+json": {
|
| 89 |
-
"model_id": "
|
| 90 |
"version_major": 2,
|
| 91 |
"version_minor": 0
|
| 92 |
},
|
|
@@ -103,7 +103,7 @@
|
|
| 103 |
"'https://huggingface.co/nRuaif/Blind-test01/tree/main/'"
|
| 104 |
]
|
| 105 |
},
|
| 106 |
-
"execution_count":
|
| 107 |
"metadata": {},
|
| 108 |
"output_type": "execute_result"
|
| 109 |
}
|
|
|
|
| 2 |
"cells": [
|
| 3 |
{
|
| 4 |
"cell_type": "code",
|
| 5 |
+
"execution_count": 5,
|
| 6 |
"id": "127668ee-44f0-4438-9337-e7c4a486aea3",
|
| 7 |
"metadata": {},
|
| 8 |
"outputs": [
|
|
|
|
| 16 |
{
|
| 17 |
"data": {
|
| 18 |
"application/vnd.jupyter.widget-view+json": {
|
| 19 |
+
"model_id": "a5456eb0827a47208f743d419ca6357e",
|
| 20 |
"version_major": 2,
|
| 21 |
"version_minor": 0
|
| 22 |
},
|
| 23 |
"text/plain": [
|
| 24 |
+
"adapter_model.bin: 0%| | 0.00/62.8M [00:00<?, ?B/s]"
|
| 25 |
]
|
| 26 |
},
|
| 27 |
"metadata": {},
|
|
|
|
| 30 |
{
|
| 31 |
"data": {
|
| 32 |
"application/vnd.jupyter.widget-view+json": {
|
| 33 |
+
"model_id": "0512e81c2a754626b56f6f22dbd177b1",
|
| 34 |
"version_major": 2,
|
| 35 |
"version_minor": 0
|
| 36 |
},
|
|
|
|
| 44 |
{
|
| 45 |
"data": {
|
| 46 |
"application/vnd.jupyter.widget-view+json": {
|
| 47 |
+
"model_id": "7a8e119cbaf6458e98e80c346c708f84",
|
| 48 |
"version_major": 2,
|
| 49 |
"version_minor": 0
|
| 50 |
},
|
|
|
|
| 58 |
{
|
| 59 |
"data": {
|
| 60 |
"application/vnd.jupyter.widget-view+json": {
|
| 61 |
+
"model_id": "3d700a1d569b449983ea1ddb3ae1cc04",
|
| 62 |
"version_major": 2,
|
| 63 |
"version_minor": 0
|
| 64 |
},
|
| 65 |
"text/plain": [
|
| 66 |
+
"rng_state.pth: 0%| | 0.00/14.6k [00:00<?, ?B/s]"
|
| 67 |
]
|
| 68 |
},
|
| 69 |
"metadata": {},
|
|
|
|
| 72 |
{
|
| 73 |
"data": {
|
| 74 |
"application/vnd.jupyter.widget-view+json": {
|
| 75 |
+
"model_id": "130538451397407c9cab9699b33c5a62",
|
| 76 |
"version_major": 2,
|
| 77 |
"version_minor": 0
|
| 78 |
},
|
| 79 |
"text/plain": [
|
| 80 |
+
"Upload 5 LFS files: 0%| | 0/5 [00:00<?, ?it/s]"
|
| 81 |
]
|
| 82 |
},
|
| 83 |
"metadata": {},
|
|
|
|
| 86 |
{
|
| 87 |
"data": {
|
| 88 |
"application/vnd.jupyter.widget-view+json": {
|
| 89 |
+
"model_id": "732072b5d2c443a6a7d306ed25621586",
|
| 90 |
"version_major": 2,
|
| 91 |
"version_minor": 0
|
| 92 |
},
|
|
|
|
| 103 |
"'https://huggingface.co/nRuaif/Blind-test01/tree/main/'"
|
| 104 |
]
|
| 105 |
},
|
| 106 |
+
"execution_count": 5,
|
| 107 |
"metadata": {},
|
| 108 |
"output_type": "execute_result"
|
| 109 |
}
|
checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: False
|
| 10 |
+
- load_in_4bit: True
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: nf4
|
| 16 |
+
- bnb_4bit_use_double_quant: True
|
| 17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": null,
|
| 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": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj",
|
| 19 |
+
"up_proj",
|
| 20 |
+
"gate_proj",
|
| 21 |
+
"o_proj",
|
| 22 |
+
"k_proj",
|
| 23 |
+
"down_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
checkpoint-100/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ca1158380ea99796227216d7452a932238214cf50ef44cd31b5a292d9984063
|
| 3 |
+
size 62788109
|
checkpoint-100/adapter_model/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: False
|
| 10 |
+
- load_in_4bit: True
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: nf4
|
| 16 |
+
- bnb_4bit_use_double_quant: True
|
| 17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-100/adapter_model/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": null,
|
| 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": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj",
|
| 19 |
+
"up_proj",
|
| 20 |
+
"gate_proj",
|
| 21 |
+
"o_proj",
|
| 22 |
+
"k_proj",
|
| 23 |
+
"down_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
checkpoint-100/adapter_model/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ca1158380ea99796227216d7452a932238214cf50ef44cd31b5a292d9984063
|
| 3 |
+
size 62788109
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b4e74a79fd8d951361913a9772c17120c9a8293dee4b77a54fde377d3e5133c
|
| 3 |
+
size 250681597
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03d06187c9399b35d9c4214283dc0b9fc38078ee2466c57de37fea6b9192e43a
|
| 3 |
+
size 14575
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d041a7e96c17819841a9a0c03258454e444965f215930b8240eeecb6ee97e88
|
| 3 |
+
size 627
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,699 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.01399302482605,
|
| 3 |
+
"best_model_checkpoint": "./qlora-out-kimiko-test2/checkpoint-100",
|
| 4 |
+
"epoch": 2.5848142164781907,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 1e-05,
|
| 14 |
+
"loss": 1.5707,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 2e-05,
|
| 20 |
+
"loss": 1.5621,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.08,
|
| 25 |
+
"learning_rate": 3e-05,
|
| 26 |
+
"loss": 1.4812,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.1,
|
| 31 |
+
"learning_rate": 4e-05,
|
| 32 |
+
"loss": 1.5197,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.13,
|
| 37 |
+
"learning_rate": 5e-05,
|
| 38 |
+
"loss": 1.5567,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.16,
|
| 43 |
+
"learning_rate": 5e-05,
|
| 44 |
+
"loss": 1.4645,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.18,
|
| 49 |
+
"learning_rate": 5e-05,
|
| 50 |
+
"loss": 1.6122,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21,
|
| 55 |
+
"learning_rate": 5e-05,
|
| 56 |
+
"loss": 1.5596,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.23,
|
| 61 |
+
"learning_rate": 5e-05,
|
| 62 |
+
"loss": 1.5608,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.26,
|
| 67 |
+
"learning_rate": 5e-05,
|
| 68 |
+
"loss": 1.5456,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.26,
|
| 73 |
+
"eval_loss": 2.098437547683716,
|
| 74 |
+
"eval_runtime": 119.6161,
|
| 75 |
+
"eval_samples_per_second": 1.555,
|
| 76 |
+
"eval_steps_per_second": 0.777,
|
| 77 |
+
"step": 10
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.28,
|
| 81 |
+
"learning_rate": 5e-05,
|
| 82 |
+
"loss": 1.5645,
|
| 83 |
+
"step": 11
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.31,
|
| 87 |
+
"learning_rate": 5e-05,
|
| 88 |
+
"loss": 1.538,
|
| 89 |
+
"step": 12
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.34,
|
| 93 |
+
"learning_rate": 5e-05,
|
| 94 |
+
"loss": 1.6388,
|
| 95 |
+
"step": 13
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.36,
|
| 99 |
+
"learning_rate": 5e-05,
|
| 100 |
+
"loss": 1.4943,
|
| 101 |
+
"step": 14
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.39,
|
| 105 |
+
"learning_rate": 5e-05,
|
| 106 |
+
"loss": 1.5469,
|
| 107 |
+
"step": 15
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.41,
|
| 111 |
+
"learning_rate": 5e-05,
|
| 112 |
+
"loss": 1.6149,
|
| 113 |
+
"step": 16
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.44,
|
| 117 |
+
"learning_rate": 5e-05,
|
| 118 |
+
"loss": 1.5345,
|
| 119 |
+
"step": 17
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.47,
|
| 123 |
+
"learning_rate": 5e-05,
|
| 124 |
+
"loss": 1.4903,
|
| 125 |
+
"step": 18
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.49,
|
| 129 |
+
"learning_rate": 5e-05,
|
| 130 |
+
"loss": 1.5499,
|
| 131 |
+
"step": 19
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.52,
|
| 135 |
+
"learning_rate": 5e-05,
|
| 136 |
+
"loss": 1.5934,
|
| 137 |
+
"step": 20
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.52,
|
| 141 |
+
"eval_loss": 2.066981077194214,
|
| 142 |
+
"eval_runtime": 119.5781,
|
| 143 |
+
"eval_samples_per_second": 1.555,
|
| 144 |
+
"eval_steps_per_second": 0.778,
|
| 145 |
+
"step": 20
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.54,
|
| 149 |
+
"learning_rate": 5e-05,
|
| 150 |
+
"loss": 1.4554,
|
| 151 |
+
"step": 21
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.57,
|
| 155 |
+
"learning_rate": 5e-05,
|
| 156 |
+
"loss": 1.5512,
|
| 157 |
+
"step": 22
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.59,
|
| 161 |
+
"learning_rate": 5e-05,
|
| 162 |
+
"loss": 1.4636,
|
| 163 |
+
"step": 23
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.62,
|
| 167 |
+
"learning_rate": 5e-05,
|
| 168 |
+
"loss": 1.5398,
|
| 169 |
+
"step": 24
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.65,
|
| 173 |
+
"learning_rate": 5e-05,
|
| 174 |
+
"loss": 1.5623,
|
| 175 |
+
"step": 25
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.67,
|
| 179 |
+
"learning_rate": 5e-05,
|
| 180 |
+
"loss": 1.4658,
|
| 181 |
+
"step": 26
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.7,
|
| 185 |
+
"learning_rate": 5e-05,
|
| 186 |
+
"loss": 1.4723,
|
| 187 |
+
"step": 27
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.72,
|
| 191 |
+
"learning_rate": 5e-05,
|
| 192 |
+
"loss": 1.432,
|
| 193 |
+
"step": 28
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.75,
|
| 197 |
+
"learning_rate": 5e-05,
|
| 198 |
+
"loss": 1.4814,
|
| 199 |
+
"step": 29
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.78,
|
| 203 |
+
"learning_rate": 5e-05,
|
| 204 |
+
"loss": 1.4924,
|
| 205 |
+
"step": 30
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.78,
|
| 209 |
+
"eval_loss": 2.046339750289917,
|
| 210 |
+
"eval_runtime": 119.5771,
|
| 211 |
+
"eval_samples_per_second": 1.555,
|
| 212 |
+
"eval_steps_per_second": 0.778,
|
| 213 |
+
"step": 30
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.8,
|
| 217 |
+
"learning_rate": 5e-05,
|
| 218 |
+
"loss": 1.5809,
|
| 219 |
+
"step": 31
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.83,
|
| 223 |
+
"learning_rate": 5e-05,
|
| 224 |
+
"loss": 1.4803,
|
| 225 |
+
"step": 32
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.85,
|
| 229 |
+
"learning_rate": 5e-05,
|
| 230 |
+
"loss": 1.4878,
|
| 231 |
+
"step": 33
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.88,
|
| 235 |
+
"learning_rate": 5e-05,
|
| 236 |
+
"loss": 1.3871,
|
| 237 |
+
"step": 34
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.9,
|
| 241 |
+
"learning_rate": 5e-05,
|
| 242 |
+
"loss": 1.5151,
|
| 243 |
+
"step": 35
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.93,
|
| 247 |
+
"learning_rate": 5e-05,
|
| 248 |
+
"loss": 1.4212,
|
| 249 |
+
"step": 36
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.96,
|
| 253 |
+
"learning_rate": 5e-05,
|
| 254 |
+
"loss": 1.6284,
|
| 255 |
+
"step": 37
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.98,
|
| 259 |
+
"learning_rate": 5e-05,
|
| 260 |
+
"loss": 1.5002,
|
| 261 |
+
"step": 38
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.01,
|
| 265 |
+
"learning_rate": 5e-05,
|
| 266 |
+
"loss": 1.4452,
|
| 267 |
+
"step": 39
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.03,
|
| 271 |
+
"learning_rate": 5e-05,
|
| 272 |
+
"loss": 1.4399,
|
| 273 |
+
"step": 40
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.03,
|
| 277 |
+
"eval_loss": 2.0354697704315186,
|
| 278 |
+
"eval_runtime": 119.5875,
|
| 279 |
+
"eval_samples_per_second": 1.555,
|
| 280 |
+
"eval_steps_per_second": 0.778,
|
| 281 |
+
"step": 40
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.06,
|
| 285 |
+
"learning_rate": 5e-05,
|
| 286 |
+
"loss": 1.465,
|
| 287 |
+
"step": 41
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.09,
|
| 291 |
+
"learning_rate": 5e-05,
|
| 292 |
+
"loss": 1.4199,
|
| 293 |
+
"step": 42
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.11,
|
| 297 |
+
"learning_rate": 5e-05,
|
| 298 |
+
"loss": 1.5403,
|
| 299 |
+
"step": 43
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.14,
|
| 303 |
+
"learning_rate": 5e-05,
|
| 304 |
+
"loss": 1.4499,
|
| 305 |
+
"step": 44
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.16,
|
| 309 |
+
"learning_rate": 5e-05,
|
| 310 |
+
"loss": 1.5751,
|
| 311 |
+
"step": 45
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.19,
|
| 315 |
+
"learning_rate": 5e-05,
|
| 316 |
+
"loss": 1.4809,
|
| 317 |
+
"step": 46
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.21,
|
| 321 |
+
"learning_rate": 5e-05,
|
| 322 |
+
"loss": 1.5022,
|
| 323 |
+
"step": 47
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.24,
|
| 327 |
+
"learning_rate": 5e-05,
|
| 328 |
+
"loss": 1.4663,
|
| 329 |
+
"step": 48
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.27,
|
| 333 |
+
"learning_rate": 5e-05,
|
| 334 |
+
"loss": 1.4435,
|
| 335 |
+
"step": 49
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.29,
|
| 339 |
+
"learning_rate": 5e-05,
|
| 340 |
+
"loss": 1.4246,
|
| 341 |
+
"step": 50
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.29,
|
| 345 |
+
"eval_loss": 2.0276732444763184,
|
| 346 |
+
"eval_runtime": 119.5811,
|
| 347 |
+
"eval_samples_per_second": 1.555,
|
| 348 |
+
"eval_steps_per_second": 0.778,
|
| 349 |
+
"step": 50
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.32,
|
| 353 |
+
"learning_rate": 5e-05,
|
| 354 |
+
"loss": 1.4877,
|
| 355 |
+
"step": 51
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.34,
|
| 359 |
+
"learning_rate": 5e-05,
|
| 360 |
+
"loss": 1.4066,
|
| 361 |
+
"step": 52
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.37,
|
| 365 |
+
"learning_rate": 5e-05,
|
| 366 |
+
"loss": 1.3559,
|
| 367 |
+
"step": 53
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.4,
|
| 371 |
+
"learning_rate": 5e-05,
|
| 372 |
+
"loss": 1.5591,
|
| 373 |
+
"step": 54
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.42,
|
| 377 |
+
"learning_rate": 5e-05,
|
| 378 |
+
"loss": 1.4942,
|
| 379 |
+
"step": 55
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 1.45,
|
| 383 |
+
"learning_rate": 5e-05,
|
| 384 |
+
"loss": 1.4685,
|
| 385 |
+
"step": 56
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 1.47,
|
| 389 |
+
"learning_rate": 5e-05,
|
| 390 |
+
"loss": 1.4165,
|
| 391 |
+
"step": 57
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.5,
|
| 395 |
+
"learning_rate": 5e-05,
|
| 396 |
+
"loss": 1.3995,
|
| 397 |
+
"step": 58
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.53,
|
| 401 |
+
"learning_rate": 5e-05,
|
| 402 |
+
"loss": 1.3931,
|
| 403 |
+
"step": 59
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.55,
|
| 407 |
+
"learning_rate": 5e-05,
|
| 408 |
+
"loss": 1.4234,
|
| 409 |
+
"step": 60
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.55,
|
| 413 |
+
"eval_loss": 2.0228564739227295,
|
| 414 |
+
"eval_runtime": 119.5715,
|
| 415 |
+
"eval_samples_per_second": 1.556,
|
| 416 |
+
"eval_steps_per_second": 0.778,
|
| 417 |
+
"step": 60
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.58,
|
| 421 |
+
"learning_rate": 5e-05,
|
| 422 |
+
"loss": 1.4732,
|
| 423 |
+
"step": 61
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.6,
|
| 427 |
+
"learning_rate": 5e-05,
|
| 428 |
+
"loss": 1.4349,
|
| 429 |
+
"step": 62
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.63,
|
| 433 |
+
"learning_rate": 5e-05,
|
| 434 |
+
"loss": 1.4548,
|
| 435 |
+
"step": 63
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.65,
|
| 439 |
+
"learning_rate": 5e-05,
|
| 440 |
+
"loss": 1.48,
|
| 441 |
+
"step": 64
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.68,
|
| 445 |
+
"learning_rate": 5e-05,
|
| 446 |
+
"loss": 1.3789,
|
| 447 |
+
"step": 65
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.71,
|
| 451 |
+
"learning_rate": 5e-05,
|
| 452 |
+
"loss": 1.3915,
|
| 453 |
+
"step": 66
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.73,
|
| 457 |
+
"learning_rate": 5e-05,
|
| 458 |
+
"loss": 1.3789,
|
| 459 |
+
"step": 67
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.76,
|
| 463 |
+
"learning_rate": 5e-05,
|
| 464 |
+
"loss": 1.5206,
|
| 465 |
+
"step": 68
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.78,
|
| 469 |
+
"learning_rate": 5e-05,
|
| 470 |
+
"loss": 1.4851,
|
| 471 |
+
"step": 69
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.81,
|
| 475 |
+
"learning_rate": 5e-05,
|
| 476 |
+
"loss": 1.5251,
|
| 477 |
+
"step": 70
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.81,
|
| 481 |
+
"eval_loss": 2.0199856758117676,
|
| 482 |
+
"eval_runtime": 119.5994,
|
| 483 |
+
"eval_samples_per_second": 1.555,
|
| 484 |
+
"eval_steps_per_second": 0.778,
|
| 485 |
+
"step": 70
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 1.84,
|
| 489 |
+
"learning_rate": 5e-05,
|
| 490 |
+
"loss": 1.4152,
|
| 491 |
+
"step": 71
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 1.86,
|
| 495 |
+
"learning_rate": 5e-05,
|
| 496 |
+
"loss": 1.4262,
|
| 497 |
+
"step": 72
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.89,
|
| 501 |
+
"learning_rate": 5e-05,
|
| 502 |
+
"loss": 1.5563,
|
| 503 |
+
"step": 73
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.91,
|
| 507 |
+
"learning_rate": 5e-05,
|
| 508 |
+
"loss": 1.42,
|
| 509 |
+
"step": 74
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.94,
|
| 513 |
+
"learning_rate": 5e-05,
|
| 514 |
+
"loss": 1.4407,
|
| 515 |
+
"step": 75
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.96,
|
| 519 |
+
"learning_rate": 5e-05,
|
| 520 |
+
"loss": 1.3953,
|
| 521 |
+
"step": 76
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.99,
|
| 525 |
+
"learning_rate": 5e-05,
|
| 526 |
+
"loss": 1.4186,
|
| 527 |
+
"step": 77
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.02,
|
| 531 |
+
"learning_rate": 5e-05,
|
| 532 |
+
"loss": 1.3863,
|
| 533 |
+
"step": 78
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.04,
|
| 537 |
+
"learning_rate": 5e-05,
|
| 538 |
+
"loss": 1.3907,
|
| 539 |
+
"step": 79
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.07,
|
| 543 |
+
"learning_rate": 5e-05,
|
| 544 |
+
"loss": 1.5147,
|
| 545 |
+
"step": 80
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.07,
|
| 549 |
+
"eval_loss": 2.0174262523651123,
|
| 550 |
+
"eval_runtime": 119.6245,
|
| 551 |
+
"eval_samples_per_second": 1.555,
|
| 552 |
+
"eval_steps_per_second": 0.777,
|
| 553 |
+
"step": 80
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.09,
|
| 557 |
+
"learning_rate": 5e-05,
|
| 558 |
+
"loss": 1.3683,
|
| 559 |
+
"step": 81
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.12,
|
| 563 |
+
"learning_rate": 5e-05,
|
| 564 |
+
"loss": 1.4289,
|
| 565 |
+
"step": 82
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 2.15,
|
| 569 |
+
"learning_rate": 5e-05,
|
| 570 |
+
"loss": 1.4033,
|
| 571 |
+
"step": 83
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.17,
|
| 575 |
+
"learning_rate": 5e-05,
|
| 576 |
+
"loss": 1.384,
|
| 577 |
+
"step": 84
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 2.2,
|
| 581 |
+
"learning_rate": 5e-05,
|
| 582 |
+
"loss": 1.3379,
|
| 583 |
+
"step": 85
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.22,
|
| 587 |
+
"learning_rate": 5e-05,
|
| 588 |
+
"loss": 1.3916,
|
| 589 |
+
"step": 86
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.25,
|
| 593 |
+
"learning_rate": 5e-05,
|
| 594 |
+
"loss": 1.5267,
|
| 595 |
+
"step": 87
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 2.27,
|
| 599 |
+
"learning_rate": 5e-05,
|
| 600 |
+
"loss": 1.4465,
|
| 601 |
+
"step": 88
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.3,
|
| 605 |
+
"learning_rate": 5e-05,
|
| 606 |
+
"loss": 1.4349,
|
| 607 |
+
"step": 89
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 2.33,
|
| 611 |
+
"learning_rate": 5e-05,
|
| 612 |
+
"loss": 1.4927,
|
| 613 |
+
"step": 90
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.33,
|
| 617 |
+
"eval_loss": 2.0155017375946045,
|
| 618 |
+
"eval_runtime": 119.6021,
|
| 619 |
+
"eval_samples_per_second": 1.555,
|
| 620 |
+
"eval_steps_per_second": 0.778,
|
| 621 |
+
"step": 90
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.35,
|
| 625 |
+
"learning_rate": 5e-05,
|
| 626 |
+
"loss": 1.3299,
|
| 627 |
+
"step": 91
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.38,
|
| 631 |
+
"learning_rate": 5e-05,
|
| 632 |
+
"loss": 1.5347,
|
| 633 |
+
"step": 92
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.4,
|
| 637 |
+
"learning_rate": 5e-05,
|
| 638 |
+
"loss": 1.4727,
|
| 639 |
+
"step": 93
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.43,
|
| 643 |
+
"learning_rate": 5e-05,
|
| 644 |
+
"loss": 1.4209,
|
| 645 |
+
"step": 94
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.46,
|
| 649 |
+
"learning_rate": 5e-05,
|
| 650 |
+
"loss": 1.42,
|
| 651 |
+
"step": 95
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 2.48,
|
| 655 |
+
"learning_rate": 5e-05,
|
| 656 |
+
"loss": 1.3787,
|
| 657 |
+
"step": 96
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.51,
|
| 661 |
+
"learning_rate": 5e-05,
|
| 662 |
+
"loss": 1.4292,
|
| 663 |
+
"step": 97
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 2.53,
|
| 667 |
+
"learning_rate": 5e-05,
|
| 668 |
+
"loss": 1.4144,
|
| 669 |
+
"step": 98
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.56,
|
| 673 |
+
"learning_rate": 5e-05,
|
| 674 |
+
"loss": 1.3595,
|
| 675 |
+
"step": 99
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.58,
|
| 679 |
+
"learning_rate": 5e-05,
|
| 680 |
+
"loss": 1.3445,
|
| 681 |
+
"step": 100
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.58,
|
| 685 |
+
"eval_loss": 2.01399302482605,
|
| 686 |
+
"eval_runtime": 119.5983,
|
| 687 |
+
"eval_samples_per_second": 1.555,
|
| 688 |
+
"eval_steps_per_second": 0.778,
|
| 689 |
+
"step": 100
|
| 690 |
+
}
|
| 691 |
+
],
|
| 692 |
+
"logging_steps": 1,
|
| 693 |
+
"max_steps": 114,
|
| 694 |
+
"num_train_epochs": 3,
|
| 695 |
+
"save_steps": 10,
|
| 696 |
+
"total_flos": 4.5795234960900096e+17,
|
| 697 |
+
"trial_name": null,
|
| 698 |
+
"trial_params": null
|
| 699 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca362c6e6a1bbe2523b2190a501c92d6dbb3db6186bef551619d83852cca3df1
|
| 3 |
+
size 4219
|