Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: mistral_poe_nores
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# mistral_poe_nores
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: nan
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 4
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- total_eval_batch_size: 4
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 1
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 58 |
+
| 0.0 | 1.0 | 325 | nan |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- PEFT 0.7.1
|
| 64 |
+
- Transformers 4.39.0.dev0
|
| 65 |
+
- Pytorch 2.2.2+cu121
|
| 66 |
+
- Datasets 2.14.6
|
| 67 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 31516744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0001e67d047d86fe35c689a579716cb7edb2fb7b38e206ea3bc29c3c09cea2a6
|
| 3 |
size 31516744
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.0818373912579521,
|
| 4 |
+
"train_runtime": 5942.6057,
|
| 5 |
+
"train_samples": 10393,
|
| 6 |
+
"train_samples_per_second": 1.749,
|
| 7 |
+
"train_steps_per_second": 0.055
|
| 8 |
+
}
|
runs/May14_13-09-14_ip-172-31-69-60.ec2.internal/events.out.tfevents.1715692171.ip-172-31-69-60.ec2.internal.17971.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb2dabfc886276cc7d7f6ed86391f23f4c6637e5652341641afc5d98dc131dd7
|
| 3 |
+
size 19128
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.0818373912579521,
|
| 4 |
+
"train_runtime": 5942.6057,
|
| 5 |
+
"train_samples": 10393,
|
| 6 |
+
"train_samples_per_second": 1.749,
|
| 7 |
+
"train_steps_per_second": 0.055
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,500 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 325,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 5.4355961871184695,
|
| 14 |
+
"learning_rate": 6.060606060606061e-06,
|
| 15 |
+
"loss": 3.2405,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 4.909094332293041,
|
| 21 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 22 |
+
"loss": 3.0858,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 5.112464378906454,
|
| 28 |
+
"learning_rate": 6.060606060606061e-05,
|
| 29 |
+
"loss": 1.9599,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05,
|
| 34 |
+
"grad_norm": 0.3661963814900562,
|
| 35 |
+
"learning_rate": 9.090909090909092e-05,
|
| 36 |
+
"loss": 0.1188,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06,
|
| 41 |
+
"grad_norm": 0.06921527944926209,
|
| 42 |
+
"learning_rate": 0.00012121212121212122,
|
| 43 |
+
"loss": 0.0046,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08,
|
| 48 |
+
"grad_norm": 0.040536599266940046,
|
| 49 |
+
"learning_rate": 0.00015151515151515152,
|
| 50 |
+
"loss": 0.0005,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09,
|
| 55 |
+
"grad_norm": 0.009045738723501581,
|
| 56 |
+
"learning_rate": 0.00018181818181818183,
|
| 57 |
+
"loss": 0.0002,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.11,
|
| 62 |
+
"grad_norm": 0.005949166769229894,
|
| 63 |
+
"learning_rate": 0.00019997685019798912,
|
| 64 |
+
"loss": 0.0001,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.12,
|
| 69 |
+
"grad_norm": 0.2264354893455914,
|
| 70 |
+
"learning_rate": 0.0001997165380022878,
|
| 71 |
+
"loss": 0.0001,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.14,
|
| 76 |
+
"grad_norm": 0.0016974513785695078,
|
| 77 |
+
"learning_rate": 0.000199167731989929,
|
| 78 |
+
"loss": 0.0,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.15,
|
| 83 |
+
"grad_norm": 0.001311791625613364,
|
| 84 |
+
"learning_rate": 0.0001983320199330545,
|
| 85 |
+
"loss": 0.0,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.17,
|
| 90 |
+
"grad_norm": 0.0009269384203782724,
|
| 91 |
+
"learning_rate": 0.00019721181966290613,
|
| 92 |
+
"loss": 0.0,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.18,
|
| 97 |
+
"grad_norm": 0.0005037438705437563,
|
| 98 |
+
"learning_rate": 0.00019581037207470382,
|
| 99 |
+
"loss": 0.0,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2,
|
| 104 |
+
"grad_norm": 0.00038243685210402487,
|
| 105 |
+
"learning_rate": 0.00019413173175128473,
|
| 106 |
+
"loss": 0.0,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.22,
|
| 111 |
+
"grad_norm": 0.00029852007055196047,
|
| 112 |
+
"learning_rate": 0.00019218075523263104,
|
| 113 |
+
"loss": 0.0,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.23,
|
| 118 |
+
"grad_norm": 0.00024917847674092806,
|
| 119 |
+
"learning_rate": 0.00018996308696522433,
|
| 120 |
+
"loss": 0.0411,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.25,
|
| 125 |
+
"grad_norm": 0.0005842645787073277,
|
| 126 |
+
"learning_rate": 0.00018748514297187648,
|
| 127 |
+
"loss": 0.0,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.26,
|
| 132 |
+
"grad_norm": 0.000982758385218839,
|
| 133 |
+
"learning_rate": 0.00018475409228928312,
|
| 134 |
+
"loss": 0.0,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.28,
|
| 139 |
+
"grad_norm": 0.0015145443761257185,
|
| 140 |
+
"learning_rate": 0.00018177783622700327,
|
| 141 |
+
"loss": 0.0,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.29,
|
| 146 |
+
"grad_norm": 0.0014210913401211155,
|
| 147 |
+
"learning_rate": 0.00017856498550787144,
|
| 148 |
+
"loss": 0.0,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.31,
|
| 153 |
+
"grad_norm": 0.0016652844653558673,
|
| 154 |
+
"learning_rate": 0.00017512483535597867,
|
| 155 |
+
"loss": 0.0,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.32,
|
| 160 |
+
"grad_norm": 0.0012566962692868043,
|
| 161 |
+
"learning_rate": 0.00017146733860429612,
|
| 162 |
+
"loss": 0.0,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.34,
|
| 167 |
+
"grad_norm": 0.001071493530031031,
|
| 168 |
+
"learning_rate": 0.0001676030768997445,
|
| 169 |
+
"loss": 0.0,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.35,
|
| 174 |
+
"grad_norm": 0.0008304219904860013,
|
| 175 |
+
"learning_rate": 0.00016354323008901776,
|
| 176 |
+
"loss": 0.0,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.37,
|
| 181 |
+
"grad_norm": 0.0007519983627498121,
|
| 182 |
+
"learning_rate": 0.00015929954387373103,
|
| 183 |
+
"loss": 0.0,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.38,
|
| 188 |
+
"grad_norm": 0.0008553710391757099,
|
| 189 |
+
"learning_rate": 0.00015488429582847192,
|
| 190 |
+
"loss": 0.0243,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4,
|
| 195 |
+
"grad_norm": 0.0011485573169575547,
|
| 196 |
+
"learning_rate": 0.00015031025988006936,
|
| 197 |
+
"loss": 0.0,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.42,
|
| 202 |
+
"grad_norm": 0.001488839923205427,
|
| 203 |
+
"learning_rate": 0.00014559066935084588,
|
| 204 |
+
"loss": 0.0,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.43,
|
| 209 |
+
"grad_norm": 0.001433398295827094,
|
| 210 |
+
"learning_rate": 0.00014073917867277557,
|
| 211 |
+
"loss": 0.0,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.45,
|
| 216 |
+
"grad_norm": 0.0007962292096287589,
|
| 217 |
+
"learning_rate": 0.0001357698238833126,
|
| 218 |
+
"loss": 0.0,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.46,
|
| 223 |
+
"grad_norm": 0.0009535283111172765,
|
| 224 |
+
"learning_rate": 0.000130696982017182,
|
| 225 |
+
"loss": 0.0,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.48,
|
| 230 |
+
"grad_norm": 0.0007182907824322434,
|
| 231 |
+
"learning_rate": 0.0001255353295116187,
|
| 232 |
+
"loss": 0.0,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.49,
|
| 237 |
+
"grad_norm": 0.0005856905396976327,
|
| 238 |
+
"learning_rate": 0.00012029979974539234,
|
| 239 |
+
"loss": 0.0001,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.51,
|
| 244 |
+
"grad_norm": 0.0006597356088929785,
|
| 245 |
+
"learning_rate": 0.00011500553983446527,
|
| 246 |
+
"loss": 0.0,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.52,
|
| 251 |
+
"grad_norm": 0.00046921969944600897,
|
| 252 |
+
"learning_rate": 0.00010966786680927874,
|
| 253 |
+
"loss": 0.0,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.54,
|
| 258 |
+
"grad_norm": 0.0004747157984707723,
|
| 259 |
+
"learning_rate": 0.00010430222330045304,
|
| 260 |
+
"loss": 0.0,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.55,
|
| 265 |
+
"grad_norm": 0.0005057109670404985,
|
| 266 |
+
"learning_rate": 9.892413286110886e-05,
|
| 267 |
+
"loss": 0.0247,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.57,
|
| 272 |
+
"grad_norm": 0.0011112012256732618,
|
| 273 |
+
"learning_rate": 9.354915505506839e-05,
|
| 274 |
+
"loss": 0.0,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.58,
|
| 279 |
+
"grad_norm": 0.0017849176040784312,
|
| 280 |
+
"learning_rate": 8.81928404408726e-05,
|
| 281 |
+
"loss": 0.0,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6,
|
| 286 |
+
"grad_norm": 0.0018843191660111102,
|
| 287 |
+
"learning_rate": 8.287068558185225e-05,
|
| 288 |
+
"loss": 0.0,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.62,
|
| 293 |
+
"grad_norm": 0.012001828038146962,
|
| 294 |
+
"learning_rate": 7.759808821241406e-05,
|
| 295 |
+
"loss": 0.0159,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.63,
|
| 300 |
+
"grad_norm": 0.025457948501307993,
|
| 301 |
+
"learning_rate": 7.239030269025311e-05,
|
| 302 |
+
"loss": 0.0002,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.65,
|
| 307 |
+
"grad_norm": 0.006148971890773547,
|
| 308 |
+
"learning_rate": 6.726239586337408e-05,
|
| 309 |
+
"loss": 0.0001,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.66,
|
| 314 |
+
"grad_norm": 0.0012801225296810595,
|
| 315 |
+
"learning_rate": 6.22292034796035e-05,
|
| 316 |
+
"loss": 0.0,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.68,
|
| 321 |
+
"grad_norm": 0.0006558300127264007,
|
| 322 |
+
"learning_rate": 5.730528726470792e-05,
|
| 323 |
+
"loss": 0.0,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.69,
|
| 328 |
+
"grad_norm": 0.0009452296531015114,
|
| 329 |
+
"learning_rate": 5.2504892793295e-05,
|
| 330 |
+
"loss": 0.0,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.71,
|
| 335 |
+
"grad_norm": 0.0005350663526509846,
|
| 336 |
+
"learning_rate": 4.7841908274384616e-05,
|
| 337 |
+
"loss": 0.0,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.72,
|
| 342 |
+
"grad_norm": 0.0005255386736926693,
|
| 343 |
+
"learning_rate": 4.332982437088825e-05,
|
| 344 |
+
"loss": 0.0,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.74,
|
| 349 |
+
"grad_norm": 0.00047811823805356946,
|
| 350 |
+
"learning_rate": 3.898169516924398e-05,
|
| 351 |
+
"loss": 0.0,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.75,
|
| 356 |
+
"grad_norm": 0.0004586707641668245,
|
| 357 |
+
"learning_rate": 3.4810100412128747e-05,
|
| 358 |
+
"loss": 0.0,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.77,
|
| 363 |
+
"grad_norm": 0.0005340910278924554,
|
| 364 |
+
"learning_rate": 3.0827109103512643e-05,
|
| 365 |
+
"loss": 0.0,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.78,
|
| 370 |
+
"grad_norm": 0.0004995001428771688,
|
| 371 |
+
"learning_rate": 2.7044244591351232e-05,
|
| 372 |
+
"loss": 0.0,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8,
|
| 377 |
+
"grad_norm": 0.0005545357128251603,
|
| 378 |
+
"learning_rate": 2.3472451228937253e-05,
|
| 379 |
+
"loss": 0.0,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.82,
|
| 384 |
+
"grad_norm": 0.0004629723700238154,
|
| 385 |
+
"learning_rate": 2.0122062711363532e-05,
|
| 386 |
+
"loss": 0.0,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.83,
|
| 391 |
+
"grad_norm": 0.0004321445477887726,
|
| 392 |
+
"learning_rate": 1.7002772178705716e-05,
|
| 393 |
+
"loss": 0.0,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.85,
|
| 398 |
+
"grad_norm": 0.00037493112860377136,
|
| 399 |
+
"learning_rate": 1.4123604172419713e-05,
|
| 400 |
+
"loss": 0.0,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.86,
|
| 405 |
+
"grad_norm": 0.00040990047440936877,
|
| 406 |
+
"learning_rate": 1.149288852608743e-05,
|
| 407 |
+
"loss": 0.0,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.88,
|
| 412 |
+
"grad_norm": 0.0004512586760278399,
|
| 413 |
+
"learning_rate": 9.118236266049707e-06,
|
| 414 |
+
"loss": 0.0,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.89,
|
| 419 |
+
"grad_norm": 0.00042807750826434474,
|
| 420 |
+
"learning_rate": 7.0065175916482095e-06,
|
| 421 |
+
"loss": 0.0,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.91,
|
| 426 |
+
"grad_norm": 0.000439904459704477,
|
| 427 |
+
"learning_rate": 5.163841998782837e-06,
|
| 428 |
+
"loss": 0.0,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.92,
|
| 433 |
+
"grad_norm": 0.0003964306028862484,
|
| 434 |
+
"learning_rate": 3.595540604290437e-06,
|
| 435 |
+
"loss": 0.0,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.94,
|
| 440 |
+
"grad_norm": 0.00041726866247303416,
|
| 441 |
+
"learning_rate": 2.30615072228183e-06,
|
| 442 |
+
"loss": 0.0,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.95,
|
| 447 |
+
"grad_norm": 0.00039289982459953004,
|
| 448 |
+
"learning_rate": 1.2994027370611173e-06,
|
| 449 |
+
"loss": 0.0,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.97,
|
| 454 |
+
"grad_norm": 0.0004343633608887479,
|
| 455 |
+
"learning_rate": 5.782093106048159e-07,
|
| 456 |
+
"loss": 0.0,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.98,
|
| 461 |
+
"grad_norm": 0.0004005418615495667,
|
| 462 |
+
"learning_rate": 1.446569558255395e-07,
|
| 463 |
+
"loss": 0.0111,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.0,
|
| 468 |
+
"grad_norm": 0.00038582080807370717,
|
| 469 |
+
"learning_rate": 0.0,
|
| 470 |
+
"loss": 0.0,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.0,
|
| 475 |
+
"eval_loss": NaN,
|
| 476 |
+
"eval_runtime": 743.4758,
|
| 477 |
+
"eval_samples_per_second": 1.555,
|
| 478 |
+
"eval_steps_per_second": 0.389,
|
| 479 |
+
"step": 325
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.0,
|
| 483 |
+
"step": 325,
|
| 484 |
+
"total_flos": 5242797101678592.0,
|
| 485 |
+
"train_loss": 0.0818373912579521,
|
| 486 |
+
"train_runtime": 5942.6057,
|
| 487 |
+
"train_samples_per_second": 1.749,
|
| 488 |
+
"train_steps_per_second": 0.055
|
| 489 |
+
}
|
| 490 |
+
],
|
| 491 |
+
"logging_steps": 5,
|
| 492 |
+
"max_steps": 325,
|
| 493 |
+
"num_input_tokens_seen": 0,
|
| 494 |
+
"num_train_epochs": 1,
|
| 495 |
+
"save_steps": 40,
|
| 496 |
+
"total_flos": 5242797101678592.0,
|
| 497 |
+
"train_batch_size": 4,
|
| 498 |
+
"trial_name": null,
|
| 499 |
+
"trial_params": null
|
| 500 |
+
}
|