End of training
Browse files- README.md +23 -15
- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- runs/Jan04_14-43-41_Edge-Ai/events.out.tfevents.1704350621.Edge-Ai.21394.0 +3 -0
- runs/Jan04_14-45-40_Edge-Ai/events.out.tfevents.1704350740.Edge-Ai.21458.0 +3 -0
- runs/Jan04_14-59-59_Edge-Ai/events.out.tfevents.1704351599.Edge-Ai.22055.0 +3 -0
- runs/Jan04_15-02-09_Edge-Ai/events.out.tfevents.1704351729.Edge-Ai.22199.0 +3 -0
- runs/Jan04_15-17-26_Edge-Ai/events.out.tfevents.1704352646.Edge-Ai.22701.0 +3 -0
- runs/Jan04_15-29-18_Edge-Ai/events.out.tfevents.1704353359.Edge-Ai.23773.0 +3 -0
- trainer_state.json +1054 -0
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,24 +1,27 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
-
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
-
|
| 7 |
-
-
|
|
|
|
| 8 |
model-index:
|
| 9 |
-
- name:
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
-
#
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Wer: 72.7331
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -51,17 +54,22 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
-
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
| 63 |
|
|
|
|
| 64 |
- Transformers 4.36.2
|
| 65 |
- Pytorch 2.1.2+cu121
|
| 66 |
- Datasets 2.16.0
|
| 67 |
-
- Tokenizers 0.15.0
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- zh
|
| 4 |
license: apache-2.0
|
| 5 |
+
library_name: peft
|
| 6 |
tags:
|
| 7 |
+
- hf-asr-leaderboard
|
| 8 |
- generated_from_trainer
|
| 9 |
+
datasets:
|
| 10 |
+
- mozilla-foundation/common_voice_15_0
|
| 11 |
+
base_model: openai/whisper-tiny
|
| 12 |
model-index:
|
| 13 |
+
- name: Whisper tiny TW - AlanDlink
|
| 14 |
results: []
|
| 15 |
---
|
| 16 |
|
| 17 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
|
| 20 |
+
# Whisper tiny TW - AlanDlink
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 15.0 dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.6078
|
|
|
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 59 |
+
| 3.3802 | 0.67 | 500 | 3.3992 |
|
| 60 |
+
| 2.1962 | 1.33 | 1000 | 2.1643 |
|
| 61 |
+
| 1.4348 | 2.0 | 1500 | 1.4068 |
|
| 62 |
+
| 0.7108 | 2.67 | 2000 | 0.6926 |
|
| 63 |
+
| 0.6801 | 3.33 | 2500 | 0.6374 |
|
| 64 |
+
| 0.6273 | 4.0 | 3000 | 0.6195 |
|
| 65 |
+
| 0.6001 | 4.67 | 3500 | 0.6106 |
|
| 66 |
+
| 0.6082 | 5.33 | 4000 | 0.6078 |
|
| 67 |
|
| 68 |
|
| 69 |
### Framework versions
|
| 70 |
|
| 71 |
+
- PEFT 0.7.1
|
| 72 |
- Transformers 4.36.2
|
| 73 |
- Pytorch 2.1.2+cu121
|
| 74 |
- Datasets 2.16.0
|
| 75 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "WhisperForConditionalGeneration",
|
| 5 |
+
"parent_library": "transformers.models.whisper.modeling_whisper"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "openai/whisper-tiny",
|
| 8 |
+
"beta1": 0.85,
|
| 9 |
+
"beta2": 0.85,
|
| 10 |
+
"bias": "none",
|
| 11 |
+
"deltaT": 10,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"init_r": 12,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 32,
|
| 20 |
+
"lora_dropout": 0.1,
|
| 21 |
+
"megatron_config": null,
|
| 22 |
+
"megatron_core": "megatron.core",
|
| 23 |
+
"modules_to_save": null,
|
| 24 |
+
"orth_reg_weight": 0.5,
|
| 25 |
+
"peft_type": "ADALORA",
|
| 26 |
+
"r": 8,
|
| 27 |
+
"rank_pattern": null,
|
| 28 |
+
"revision": null,
|
| 29 |
+
"target_modules": [
|
| 30 |
+
"k_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"v_proj",
|
| 33 |
+
"out_proj",
|
| 34 |
+
"fc1",
|
| 35 |
+
"fc2"
|
| 36 |
+
],
|
| 37 |
+
"target_r": 4,
|
| 38 |
+
"task_type": null,
|
| 39 |
+
"tfinal": 1000,
|
| 40 |
+
"tinit": 200,
|
| 41 |
+
"total_step": null
|
| 42 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5aa2de5188de449d3e07313935fc694b663aaf185889731811c43c1b433203ff
|
| 3 |
+
size 3271824
|
runs/Jan04_14-43-41_Edge-Ai/events.out.tfevents.1704350621.Edge-Ai.21394.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0da2015bdeeb2d4d27e812cf84519c7672b4dfb3eb4fa13d794d54116fa02d3
|
| 3 |
+
size 5173
|
runs/Jan04_14-45-40_Edge-Ai/events.out.tfevents.1704350740.Edge-Ai.21458.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24505eeb42cf804f8b3d2f7b6da646581f88a28b929d91ce0c6d0215a5b37b13
|
| 3 |
+
size 10026
|
runs/Jan04_14-59-59_Edge-Ai/events.out.tfevents.1704351599.Edge-Ai.22055.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ea7bf7147916a07c5553af34ff680e6ccc7d3cdabdf7f3bc065ae4357ad1f02
|
| 3 |
+
size 5494
|
runs/Jan04_15-02-09_Edge-Ai/events.out.tfevents.1704351729.Edge-Ai.22199.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf96c6335a034925dc81881b966fe311a920a95f501261a93533bfa8d1cc6385
|
| 3 |
+
size 8580
|
runs/Jan04_15-17-26_Edge-Ai/events.out.tfevents.1704352646.Edge-Ai.22701.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c6c35ebf393d6265cf409a06f628f7377e19b43378daf2a0d8778b3607c9202
|
| 3 |
+
size 8580
|
runs/Jan04_15-29-18_Edge-Ai/events.out.tfevents.1704353359.Edge-Ai.23773.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6831260c4a014e89620288926d725242f0b19adcceea10d4259801b92b5d845
|
| 3 |
+
size 32811
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1054 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6078237891197205,
|
| 3 |
+
"best_model_checkpoint": "./whisper-tiny-tw/checkpoint-4000",
|
| 4 |
+
"epoch": 5.333333333333333,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4000,
|
| 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": 4.4e-07,
|
| 14 |
+
"loss": 3.8753,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.07,
|
| 19 |
+
"learning_rate": 9.400000000000001e-07,
|
| 20 |
+
"loss": 3.7563,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.1,
|
| 25 |
+
"learning_rate": 1.44e-06,
|
| 26 |
+
"loss": 3.8738,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.13,
|
| 31 |
+
"learning_rate": 1.94e-06,
|
| 32 |
+
"loss": 3.8201,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.17,
|
| 37 |
+
"learning_rate": 2.4400000000000004e-06,
|
| 38 |
+
"loss": 3.8439,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.2,
|
| 43 |
+
"learning_rate": 2.9400000000000002e-06,
|
| 44 |
+
"loss": 3.817,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.23,
|
| 49 |
+
"learning_rate": 3.44e-06,
|
| 50 |
+
"loss": 3.8385,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.27,
|
| 55 |
+
"learning_rate": 3.94e-06,
|
| 56 |
+
"loss": 3.9375,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.3,
|
| 61 |
+
"learning_rate": 4.440000000000001e-06,
|
| 62 |
+
"loss": 3.8171,
|
| 63 |
+
"step": 225
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.33,
|
| 67 |
+
"learning_rate": 4.94e-06,
|
| 68 |
+
"loss": 3.8155,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.37,
|
| 73 |
+
"learning_rate": 5.4400000000000004e-06,
|
| 74 |
+
"loss": 3.7763,
|
| 75 |
+
"step": 275
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.4,
|
| 79 |
+
"learning_rate": 5.94e-06,
|
| 80 |
+
"loss": 3.7395,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.43,
|
| 85 |
+
"learning_rate": 6.440000000000001e-06,
|
| 86 |
+
"loss": 3.6626,
|
| 87 |
+
"step": 325
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.47,
|
| 91 |
+
"learning_rate": 6.9400000000000005e-06,
|
| 92 |
+
"loss": 3.6135,
|
| 93 |
+
"step": 350
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5,
|
| 97 |
+
"learning_rate": 7.440000000000001e-06,
|
| 98 |
+
"loss": 3.6064,
|
| 99 |
+
"step": 375
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.53,
|
| 103 |
+
"learning_rate": 7.94e-06,
|
| 104 |
+
"loss": 3.6924,
|
| 105 |
+
"step": 400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.57,
|
| 109 |
+
"learning_rate": 8.44e-06,
|
| 110 |
+
"loss": 3.5364,
|
| 111 |
+
"step": 425
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.6,
|
| 115 |
+
"learning_rate": 8.94e-06,
|
| 116 |
+
"loss": 3.621,
|
| 117 |
+
"step": 450
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.63,
|
| 121 |
+
"learning_rate": 9.42e-06,
|
| 122 |
+
"loss": 3.4745,
|
| 123 |
+
"step": 475
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.67,
|
| 127 |
+
"learning_rate": 9.920000000000002e-06,
|
| 128 |
+
"loss": 3.3802,
|
| 129 |
+
"step": 500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.67,
|
| 133 |
+
"eval_loss": 3.399221658706665,
|
| 134 |
+
"eval_runtime": 217.7852,
|
| 135 |
+
"eval_samples_per_second": 22.729,
|
| 136 |
+
"eval_steps_per_second": 5.684,
|
| 137 |
+
"step": 500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.7,
|
| 141 |
+
"learning_rate": 9.940000000000001e-06,
|
| 142 |
+
"loss": 3.3565,
|
| 143 |
+
"step": 525
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.73,
|
| 147 |
+
"learning_rate": 9.86857142857143e-06,
|
| 148 |
+
"loss": 3.2815,
|
| 149 |
+
"step": 550
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.77,
|
| 153 |
+
"learning_rate": 9.797142857142858e-06,
|
| 154 |
+
"loss": 3.252,
|
| 155 |
+
"step": 575
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.8,
|
| 159 |
+
"learning_rate": 9.725714285714287e-06,
|
| 160 |
+
"loss": 3.1434,
|
| 161 |
+
"step": 600
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.83,
|
| 165 |
+
"learning_rate": 9.654285714285716e-06,
|
| 166 |
+
"loss": 3.1253,
|
| 167 |
+
"step": 625
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.87,
|
| 171 |
+
"learning_rate": 9.582857142857143e-06,
|
| 172 |
+
"loss": 3.1106,
|
| 173 |
+
"step": 650
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.9,
|
| 177 |
+
"learning_rate": 9.511428571428572e-06,
|
| 178 |
+
"loss": 3.025,
|
| 179 |
+
"step": 675
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.93,
|
| 183 |
+
"learning_rate": 9.440000000000001e-06,
|
| 184 |
+
"loss": 2.9601,
|
| 185 |
+
"step": 700
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.97,
|
| 189 |
+
"learning_rate": 9.368571428571428e-06,
|
| 190 |
+
"loss": 2.8374,
|
| 191 |
+
"step": 725
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.0,
|
| 195 |
+
"learning_rate": 9.297142857142857e-06,
|
| 196 |
+
"loss": 2.7712,
|
| 197 |
+
"step": 750
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.03,
|
| 201 |
+
"learning_rate": 9.225714285714286e-06,
|
| 202 |
+
"loss": 2.6499,
|
| 203 |
+
"step": 775
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.07,
|
| 207 |
+
"learning_rate": 9.154285714285715e-06,
|
| 208 |
+
"loss": 2.6006,
|
| 209 |
+
"step": 800
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.1,
|
| 213 |
+
"learning_rate": 9.082857142857143e-06,
|
| 214 |
+
"loss": 2.5892,
|
| 215 |
+
"step": 825
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.13,
|
| 219 |
+
"learning_rate": 9.011428571428572e-06,
|
| 220 |
+
"loss": 2.4973,
|
| 221 |
+
"step": 850
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.17,
|
| 225 |
+
"learning_rate": 8.94e-06,
|
| 226 |
+
"loss": 2.4601,
|
| 227 |
+
"step": 875
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.2,
|
| 231 |
+
"learning_rate": 8.86857142857143e-06,
|
| 232 |
+
"loss": 2.3739,
|
| 233 |
+
"step": 900
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.23,
|
| 237 |
+
"learning_rate": 8.797142857142857e-06,
|
| 238 |
+
"loss": 2.3396,
|
| 239 |
+
"step": 925
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.27,
|
| 243 |
+
"learning_rate": 8.725714285714286e-06,
|
| 244 |
+
"loss": 2.3263,
|
| 245 |
+
"step": 950
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.3,
|
| 249 |
+
"learning_rate": 8.654285714285715e-06,
|
| 250 |
+
"loss": 2.2193,
|
| 251 |
+
"step": 975
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.33,
|
| 255 |
+
"learning_rate": 8.582857142857144e-06,
|
| 256 |
+
"loss": 2.1962,
|
| 257 |
+
"step": 1000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.33,
|
| 261 |
+
"eval_loss": 2.1643242835998535,
|
| 262 |
+
"eval_runtime": 223.3057,
|
| 263 |
+
"eval_samples_per_second": 22.167,
|
| 264 |
+
"eval_steps_per_second": 5.544,
|
| 265 |
+
"step": 1000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.37,
|
| 269 |
+
"learning_rate": 8.511428571428571e-06,
|
| 270 |
+
"loss": 2.1077,
|
| 271 |
+
"step": 1025
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.4,
|
| 275 |
+
"learning_rate": 8.44e-06,
|
| 276 |
+
"loss": 2.1055,
|
| 277 |
+
"step": 1050
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.43,
|
| 281 |
+
"learning_rate": 8.36857142857143e-06,
|
| 282 |
+
"loss": 2.0465,
|
| 283 |
+
"step": 1075
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.47,
|
| 287 |
+
"learning_rate": 8.297142857142859e-06,
|
| 288 |
+
"loss": 1.9805,
|
| 289 |
+
"step": 1100
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.5,
|
| 293 |
+
"learning_rate": 8.225714285714288e-06,
|
| 294 |
+
"loss": 2.0129,
|
| 295 |
+
"step": 1125
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.53,
|
| 299 |
+
"learning_rate": 8.154285714285715e-06,
|
| 300 |
+
"loss": 1.9447,
|
| 301 |
+
"step": 1150
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.57,
|
| 305 |
+
"learning_rate": 8.082857142857144e-06,
|
| 306 |
+
"loss": 1.9103,
|
| 307 |
+
"step": 1175
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.6,
|
| 311 |
+
"learning_rate": 8.011428571428573e-06,
|
| 312 |
+
"loss": 1.8697,
|
| 313 |
+
"step": 1200
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.63,
|
| 317 |
+
"learning_rate": 7.94e-06,
|
| 318 |
+
"loss": 1.8626,
|
| 319 |
+
"step": 1225
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.67,
|
| 323 |
+
"learning_rate": 7.86857142857143e-06,
|
| 324 |
+
"loss": 1.8127,
|
| 325 |
+
"step": 1250
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.7,
|
| 329 |
+
"learning_rate": 7.797142857142858e-06,
|
| 330 |
+
"loss": 1.8026,
|
| 331 |
+
"step": 1275
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.73,
|
| 335 |
+
"learning_rate": 7.725714285714286e-06,
|
| 336 |
+
"loss": 1.7526,
|
| 337 |
+
"step": 1300
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 1.77,
|
| 341 |
+
"learning_rate": 7.654285714285715e-06,
|
| 342 |
+
"loss": 1.6291,
|
| 343 |
+
"step": 1325
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.8,
|
| 347 |
+
"learning_rate": 7.5828571428571444e-06,
|
| 348 |
+
"loss": 1.6233,
|
| 349 |
+
"step": 1350
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 1.83,
|
| 353 |
+
"learning_rate": 7.511428571428572e-06,
|
| 354 |
+
"loss": 1.6377,
|
| 355 |
+
"step": 1375
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 1.87,
|
| 359 |
+
"learning_rate": 7.440000000000001e-06,
|
| 360 |
+
"loss": 1.5758,
|
| 361 |
+
"step": 1400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.9,
|
| 365 |
+
"learning_rate": 7.36857142857143e-06,
|
| 366 |
+
"loss": 1.5483,
|
| 367 |
+
"step": 1425
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.93,
|
| 371 |
+
"learning_rate": 7.297142857142858e-06,
|
| 372 |
+
"loss": 1.5166,
|
| 373 |
+
"step": 1450
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.97,
|
| 377 |
+
"learning_rate": 7.225714285714286e-06,
|
| 378 |
+
"loss": 1.4319,
|
| 379 |
+
"step": 1475
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 2.0,
|
| 383 |
+
"learning_rate": 7.154285714285715e-06,
|
| 384 |
+
"loss": 1.4348,
|
| 385 |
+
"step": 1500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.0,
|
| 389 |
+
"eval_loss": 1.4068281650543213,
|
| 390 |
+
"eval_runtime": 219.1085,
|
| 391 |
+
"eval_samples_per_second": 22.592,
|
| 392 |
+
"eval_steps_per_second": 5.65,
|
| 393 |
+
"step": 1500
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.03,
|
| 397 |
+
"learning_rate": 7.082857142857143e-06,
|
| 398 |
+
"loss": 1.3035,
|
| 399 |
+
"step": 1525
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.07,
|
| 403 |
+
"learning_rate": 7.011428571428572e-06,
|
| 404 |
+
"loss": 1.3554,
|
| 405 |
+
"step": 1550
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.1,
|
| 409 |
+
"learning_rate": 6.9400000000000005e-06,
|
| 410 |
+
"loss": 1.3143,
|
| 411 |
+
"step": 1575
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.13,
|
| 415 |
+
"learning_rate": 6.868571428571429e-06,
|
| 416 |
+
"loss": 1.2939,
|
| 417 |
+
"step": 1600
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.17,
|
| 421 |
+
"learning_rate": 6.797142857142858e-06,
|
| 422 |
+
"loss": 1.2099,
|
| 423 |
+
"step": 1625
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.2,
|
| 427 |
+
"learning_rate": 6.725714285714287e-06,
|
| 428 |
+
"loss": 1.2248,
|
| 429 |
+
"step": 1650
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.23,
|
| 433 |
+
"learning_rate": 6.654285714285716e-06,
|
| 434 |
+
"loss": 1.1217,
|
| 435 |
+
"step": 1675
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.27,
|
| 439 |
+
"learning_rate": 6.582857142857143e-06,
|
| 440 |
+
"loss": 1.1274,
|
| 441 |
+
"step": 1700
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.3,
|
| 445 |
+
"learning_rate": 6.511428571428572e-06,
|
| 446 |
+
"loss": 1.0399,
|
| 447 |
+
"step": 1725
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.33,
|
| 451 |
+
"learning_rate": 6.440000000000001e-06,
|
| 452 |
+
"loss": 1.046,
|
| 453 |
+
"step": 1750
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.37,
|
| 457 |
+
"learning_rate": 6.371428571428572e-06,
|
| 458 |
+
"loss": 0.9206,
|
| 459 |
+
"step": 1775
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.4,
|
| 463 |
+
"learning_rate": 6.300000000000001e-06,
|
| 464 |
+
"loss": 0.9125,
|
| 465 |
+
"step": 1800
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.43,
|
| 469 |
+
"learning_rate": 6.22857142857143e-06,
|
| 470 |
+
"loss": 0.9636,
|
| 471 |
+
"step": 1825
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.47,
|
| 475 |
+
"learning_rate": 6.157142857142858e-06,
|
| 476 |
+
"loss": 0.8434,
|
| 477 |
+
"step": 1850
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.5,
|
| 481 |
+
"learning_rate": 6.085714285714286e-06,
|
| 482 |
+
"loss": 0.7642,
|
| 483 |
+
"step": 1875
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.53,
|
| 487 |
+
"learning_rate": 6.014285714285715e-06,
|
| 488 |
+
"loss": 0.7749,
|
| 489 |
+
"step": 1900
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.57,
|
| 493 |
+
"learning_rate": 5.942857142857143e-06,
|
| 494 |
+
"loss": 0.7122,
|
| 495 |
+
"step": 1925
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.6,
|
| 499 |
+
"learning_rate": 5.871428571428572e-06,
|
| 500 |
+
"loss": 0.7065,
|
| 501 |
+
"step": 1950
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.63,
|
| 505 |
+
"learning_rate": 5.8e-06,
|
| 506 |
+
"loss": 0.7062,
|
| 507 |
+
"step": 1975
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.67,
|
| 511 |
+
"learning_rate": 5.7285714285714285e-06,
|
| 512 |
+
"loss": 0.7108,
|
| 513 |
+
"step": 2000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.67,
|
| 517 |
+
"eval_loss": 0.6925591230392456,
|
| 518 |
+
"eval_runtime": 219.8232,
|
| 519 |
+
"eval_samples_per_second": 22.518,
|
| 520 |
+
"eval_steps_per_second": 5.632,
|
| 521 |
+
"step": 2000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.7,
|
| 525 |
+
"learning_rate": 5.6571428571428576e-06,
|
| 526 |
+
"loss": 0.7476,
|
| 527 |
+
"step": 2025
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.73,
|
| 531 |
+
"learning_rate": 5.5857142857142866e-06,
|
| 532 |
+
"loss": 0.6809,
|
| 533 |
+
"step": 2050
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.77,
|
| 537 |
+
"learning_rate": 5.514285714285714e-06,
|
| 538 |
+
"loss": 0.625,
|
| 539 |
+
"step": 2075
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.8,
|
| 543 |
+
"learning_rate": 5.442857142857143e-06,
|
| 544 |
+
"loss": 0.6623,
|
| 545 |
+
"step": 2100
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.83,
|
| 549 |
+
"learning_rate": 5.371428571428572e-06,
|
| 550 |
+
"loss": 0.7041,
|
| 551 |
+
"step": 2125
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 2.87,
|
| 555 |
+
"learning_rate": 5.300000000000001e-06,
|
| 556 |
+
"loss": 0.6609,
|
| 557 |
+
"step": 2150
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.9,
|
| 561 |
+
"learning_rate": 5.22857142857143e-06,
|
| 562 |
+
"loss": 0.7054,
|
| 563 |
+
"step": 2175
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 2.93,
|
| 567 |
+
"learning_rate": 5.157142857142857e-06,
|
| 568 |
+
"loss": 0.694,
|
| 569 |
+
"step": 2200
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.97,
|
| 573 |
+
"learning_rate": 5.085714285714286e-06,
|
| 574 |
+
"loss": 0.702,
|
| 575 |
+
"step": 2225
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.0,
|
| 579 |
+
"learning_rate": 5.014285714285715e-06,
|
| 580 |
+
"loss": 0.6537,
|
| 581 |
+
"step": 2250
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 3.03,
|
| 585 |
+
"learning_rate": 4.9428571428571435e-06,
|
| 586 |
+
"loss": 0.6367,
|
| 587 |
+
"step": 2275
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 3.07,
|
| 591 |
+
"learning_rate": 4.871428571428572e-06,
|
| 592 |
+
"loss": 0.6481,
|
| 593 |
+
"step": 2300
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 3.1,
|
| 597 |
+
"learning_rate": 4.800000000000001e-06,
|
| 598 |
+
"loss": 0.6755,
|
| 599 |
+
"step": 2325
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 3.13,
|
| 603 |
+
"learning_rate": 4.728571428571429e-06,
|
| 604 |
+
"loss": 0.6257,
|
| 605 |
+
"step": 2350
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 3.17,
|
| 609 |
+
"learning_rate": 4.657142857142857e-06,
|
| 610 |
+
"loss": 0.6438,
|
| 611 |
+
"step": 2375
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.2,
|
| 615 |
+
"learning_rate": 4.585714285714286e-06,
|
| 616 |
+
"loss": 0.7029,
|
| 617 |
+
"step": 2400
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.23,
|
| 621 |
+
"learning_rate": 4.514285714285714e-06,
|
| 622 |
+
"loss": 0.6453,
|
| 623 |
+
"step": 2425
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 3.27,
|
| 627 |
+
"learning_rate": 4.442857142857143e-06,
|
| 628 |
+
"loss": 0.6728,
|
| 629 |
+
"step": 2450
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 3.3,
|
| 633 |
+
"learning_rate": 4.371428571428572e-06,
|
| 634 |
+
"loss": 0.6667,
|
| 635 |
+
"step": 2475
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 3.33,
|
| 639 |
+
"learning_rate": 4.3e-06,
|
| 640 |
+
"loss": 0.6801,
|
| 641 |
+
"step": 2500
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.33,
|
| 645 |
+
"eval_loss": 0.6374496221542358,
|
| 646 |
+
"eval_runtime": 222.1867,
|
| 647 |
+
"eval_samples_per_second": 22.279,
|
| 648 |
+
"eval_steps_per_second": 5.572,
|
| 649 |
+
"step": 2500
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 3.37,
|
| 653 |
+
"learning_rate": 4.228571428571429e-06,
|
| 654 |
+
"loss": 0.6021,
|
| 655 |
+
"step": 2525
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 3.4,
|
| 659 |
+
"learning_rate": 4.1571428571428575e-06,
|
| 660 |
+
"loss": 0.6657,
|
| 661 |
+
"step": 2550
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 3.43,
|
| 665 |
+
"learning_rate": 4.0857142857142865e-06,
|
| 666 |
+
"loss": 0.6338,
|
| 667 |
+
"step": 2575
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.47,
|
| 671 |
+
"learning_rate": 4.014285714285715e-06,
|
| 672 |
+
"loss": 0.6559,
|
| 673 |
+
"step": 2600
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 3.5,
|
| 677 |
+
"learning_rate": 3.942857142857143e-06,
|
| 678 |
+
"loss": 0.6559,
|
| 679 |
+
"step": 2625
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 3.53,
|
| 683 |
+
"learning_rate": 3.871428571428572e-06,
|
| 684 |
+
"loss": 0.6894,
|
| 685 |
+
"step": 2650
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 3.57,
|
| 689 |
+
"learning_rate": 3.8000000000000005e-06,
|
| 690 |
+
"loss": 0.6422,
|
| 691 |
+
"step": 2675
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 3.6,
|
| 695 |
+
"learning_rate": 3.7285714285714286e-06,
|
| 696 |
+
"loss": 0.6211,
|
| 697 |
+
"step": 2700
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 3.63,
|
| 701 |
+
"learning_rate": 3.6571428571428576e-06,
|
| 702 |
+
"loss": 0.6228,
|
| 703 |
+
"step": 2725
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 3.67,
|
| 707 |
+
"learning_rate": 3.5857142857142862e-06,
|
| 708 |
+
"loss": 0.5956,
|
| 709 |
+
"step": 2750
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 3.7,
|
| 713 |
+
"learning_rate": 3.5142857142857144e-06,
|
| 714 |
+
"loss": 0.6002,
|
| 715 |
+
"step": 2775
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 3.73,
|
| 719 |
+
"learning_rate": 3.4428571428571434e-06,
|
| 720 |
+
"loss": 0.6384,
|
| 721 |
+
"step": 2800
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 3.77,
|
| 725 |
+
"learning_rate": 3.3714285714285716e-06,
|
| 726 |
+
"loss": 0.6283,
|
| 727 |
+
"step": 2825
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 3.8,
|
| 731 |
+
"learning_rate": 3.3000000000000006e-06,
|
| 732 |
+
"loss": 0.6691,
|
| 733 |
+
"step": 2850
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 3.83,
|
| 737 |
+
"learning_rate": 3.2285714285714288e-06,
|
| 738 |
+
"loss": 0.5512,
|
| 739 |
+
"step": 2875
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 3.87,
|
| 743 |
+
"learning_rate": 3.1571428571428573e-06,
|
| 744 |
+
"loss": 0.5573,
|
| 745 |
+
"step": 2900
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 3.9,
|
| 749 |
+
"learning_rate": 3.085714285714286e-06,
|
| 750 |
+
"loss": 0.5772,
|
| 751 |
+
"step": 2925
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 3.93,
|
| 755 |
+
"learning_rate": 3.0142857142857145e-06,
|
| 756 |
+
"loss": 0.6307,
|
| 757 |
+
"step": 2950
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 3.97,
|
| 761 |
+
"learning_rate": 2.9428571428571427e-06,
|
| 762 |
+
"loss": 0.5967,
|
| 763 |
+
"step": 2975
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 4.0,
|
| 767 |
+
"learning_rate": 2.8714285714285717e-06,
|
| 768 |
+
"loss": 0.6273,
|
| 769 |
+
"step": 3000
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 4.0,
|
| 773 |
+
"eval_loss": 0.6194672584533691,
|
| 774 |
+
"eval_runtime": 222.9187,
|
| 775 |
+
"eval_samples_per_second": 22.205,
|
| 776 |
+
"eval_steps_per_second": 5.554,
|
| 777 |
+
"step": 3000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 4.03,
|
| 781 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 782 |
+
"loss": 0.5915,
|
| 783 |
+
"step": 3025
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 4.07,
|
| 787 |
+
"learning_rate": 2.728571428571429e-06,
|
| 788 |
+
"loss": 0.6411,
|
| 789 |
+
"step": 3050
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 4.1,
|
| 793 |
+
"learning_rate": 2.6571428571428575e-06,
|
| 794 |
+
"loss": 0.6522,
|
| 795 |
+
"step": 3075
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 4.13,
|
| 799 |
+
"learning_rate": 2.5857142857142856e-06,
|
| 800 |
+
"loss": 0.5862,
|
| 801 |
+
"step": 3100
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 4.17,
|
| 805 |
+
"learning_rate": 2.5142857142857147e-06,
|
| 806 |
+
"loss": 0.5907,
|
| 807 |
+
"step": 3125
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 4.2,
|
| 811 |
+
"learning_rate": 2.442857142857143e-06,
|
| 812 |
+
"loss": 0.6228,
|
| 813 |
+
"step": 3150
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 4.23,
|
| 817 |
+
"learning_rate": 2.371428571428572e-06,
|
| 818 |
+
"loss": 0.639,
|
| 819 |
+
"step": 3175
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 4.27,
|
| 823 |
+
"learning_rate": 2.3000000000000004e-06,
|
| 824 |
+
"loss": 0.6105,
|
| 825 |
+
"step": 3200
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 4.3,
|
| 829 |
+
"learning_rate": 2.228571428571429e-06,
|
| 830 |
+
"loss": 0.6154,
|
| 831 |
+
"step": 3225
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 4.33,
|
| 835 |
+
"learning_rate": 2.157142857142857e-06,
|
| 836 |
+
"loss": 0.6179,
|
| 837 |
+
"step": 3250
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 4.37,
|
| 841 |
+
"learning_rate": 2.0857142857142858e-06,
|
| 842 |
+
"loss": 0.5826,
|
| 843 |
+
"step": 3275
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 4.4,
|
| 847 |
+
"learning_rate": 2.0142857142857144e-06,
|
| 848 |
+
"loss": 0.6063,
|
| 849 |
+
"step": 3300
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.43,
|
| 853 |
+
"learning_rate": 1.942857142857143e-06,
|
| 854 |
+
"loss": 0.6412,
|
| 855 |
+
"step": 3325
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 4.47,
|
| 859 |
+
"learning_rate": 1.8714285714285715e-06,
|
| 860 |
+
"loss": 0.5746,
|
| 861 |
+
"step": 3350
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 4.5,
|
| 865 |
+
"learning_rate": 1.8000000000000001e-06,
|
| 866 |
+
"loss": 0.6644,
|
| 867 |
+
"step": 3375
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 4.53,
|
| 871 |
+
"learning_rate": 1.7285714285714287e-06,
|
| 872 |
+
"loss": 0.5814,
|
| 873 |
+
"step": 3400
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 4.57,
|
| 877 |
+
"learning_rate": 1.657142857142857e-06,
|
| 878 |
+
"loss": 0.6841,
|
| 879 |
+
"step": 3425
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 4.6,
|
| 883 |
+
"learning_rate": 1.5857142857142857e-06,
|
| 884 |
+
"loss": 0.6066,
|
| 885 |
+
"step": 3450
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 4.63,
|
| 889 |
+
"learning_rate": 1.5142857142857145e-06,
|
| 890 |
+
"loss": 0.5992,
|
| 891 |
+
"step": 3475
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 4.67,
|
| 895 |
+
"learning_rate": 1.442857142857143e-06,
|
| 896 |
+
"loss": 0.6001,
|
| 897 |
+
"step": 3500
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 4.67,
|
| 901 |
+
"eval_loss": 0.6105530858039856,
|
| 902 |
+
"eval_runtime": 216.5509,
|
| 903 |
+
"eval_samples_per_second": 22.858,
|
| 904 |
+
"eval_steps_per_second": 5.717,
|
| 905 |
+
"step": 3500
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 4.7,
|
| 909 |
+
"learning_rate": 1.3714285714285717e-06,
|
| 910 |
+
"loss": 0.6524,
|
| 911 |
+
"step": 3525
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 4.73,
|
| 915 |
+
"learning_rate": 1.3e-06,
|
| 916 |
+
"loss": 0.5826,
|
| 917 |
+
"step": 3550
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 4.77,
|
| 921 |
+
"learning_rate": 1.2285714285714286e-06,
|
| 922 |
+
"loss": 0.5674,
|
| 923 |
+
"step": 3575
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 4.8,
|
| 927 |
+
"learning_rate": 1.1571428571428572e-06,
|
| 928 |
+
"loss": 0.5817,
|
| 929 |
+
"step": 3600
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.83,
|
| 933 |
+
"learning_rate": 1.0857142857142858e-06,
|
| 934 |
+
"loss": 0.6095,
|
| 935 |
+
"step": 3625
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 4.87,
|
| 939 |
+
"learning_rate": 1.0142857142857144e-06,
|
| 940 |
+
"loss": 0.6374,
|
| 941 |
+
"step": 3650
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.9,
|
| 945 |
+
"learning_rate": 9.42857142857143e-07,
|
| 946 |
+
"loss": 0.6038,
|
| 947 |
+
"step": 3675
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 4.93,
|
| 951 |
+
"learning_rate": 8.714285714285716e-07,
|
| 952 |
+
"loss": 0.6349,
|
| 953 |
+
"step": 3700
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.97,
|
| 957 |
+
"learning_rate": 8.000000000000001e-07,
|
| 958 |
+
"loss": 0.6017,
|
| 959 |
+
"step": 3725
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 5.0,
|
| 963 |
+
"learning_rate": 7.285714285714287e-07,
|
| 964 |
+
"loss": 0.6295,
|
| 965 |
+
"step": 3750
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 5.03,
|
| 969 |
+
"learning_rate": 6.571428571428571e-07,
|
| 970 |
+
"loss": 0.631,
|
| 971 |
+
"step": 3775
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 5.07,
|
| 975 |
+
"learning_rate": 5.857142857142857e-07,
|
| 976 |
+
"loss": 0.5753,
|
| 977 |
+
"step": 3800
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 5.1,
|
| 981 |
+
"learning_rate": 5.142857142857143e-07,
|
| 982 |
+
"loss": 0.5888,
|
| 983 |
+
"step": 3825
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 5.13,
|
| 987 |
+
"learning_rate": 4.4285714285714286e-07,
|
| 988 |
+
"loss": 0.6269,
|
| 989 |
+
"step": 3850
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 5.17,
|
| 993 |
+
"learning_rate": 3.7142857142857145e-07,
|
| 994 |
+
"loss": 0.5584,
|
| 995 |
+
"step": 3875
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 5.2,
|
| 999 |
+
"learning_rate": 3.0000000000000004e-07,
|
| 1000 |
+
"loss": 0.642,
|
| 1001 |
+
"step": 3900
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 5.23,
|
| 1005 |
+
"learning_rate": 2.285714285714286e-07,
|
| 1006 |
+
"loss": 0.561,
|
| 1007 |
+
"step": 3925
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 5.27,
|
| 1011 |
+
"learning_rate": 1.5714285714285717e-07,
|
| 1012 |
+
"loss": 0.6469,
|
| 1013 |
+
"step": 3950
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 5.3,
|
| 1017 |
+
"learning_rate": 8.571428571428573e-08,
|
| 1018 |
+
"loss": 0.6164,
|
| 1019 |
+
"step": 3975
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 5.33,
|
| 1023 |
+
"learning_rate": 1.4285714285714288e-08,
|
| 1024 |
+
"loss": 0.6082,
|
| 1025 |
+
"step": 4000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 5.33,
|
| 1029 |
+
"eval_loss": 0.6078237891197205,
|
| 1030 |
+
"eval_runtime": 220.2328,
|
| 1031 |
+
"eval_samples_per_second": 22.476,
|
| 1032 |
+
"eval_steps_per_second": 5.621,
|
| 1033 |
+
"step": 4000
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 5.33,
|
| 1037 |
+
"step": 4000,
|
| 1038 |
+
"total_flos": 1.6501699427328e+18,
|
| 1039 |
+
"train_loss": 1.4726774854660034,
|
| 1040 |
+
"train_runtime": 5301.1107,
|
| 1041 |
+
"train_samples_per_second": 12.073,
|
| 1042 |
+
"train_steps_per_second": 0.755
|
| 1043 |
+
}
|
| 1044 |
+
],
|
| 1045 |
+
"logging_steps": 25,
|
| 1046 |
+
"max_steps": 4000,
|
| 1047 |
+
"num_input_tokens_seen": 0,
|
| 1048 |
+
"num_train_epochs": 6,
|
| 1049 |
+
"save_steps": 500,
|
| 1050 |
+
"total_flos": 1.6501699427328e+18,
|
| 1051 |
+
"train_batch_size": 4,
|
| 1052 |
+
"trial_name": null,
|
| 1053 |
+
"trial_params": null
|
| 1054 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:775d3f66b05e1f0b0a241c7939bfe039c39404da0b0ccec1f12b1d2afec24a2c
|
| 3 |
size 4856
|