Upload folder using huggingface_hub
Browse files- README.md +67 -0
- all_results.json +13 -0
- config.json +105 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
- runs/Mar16_18-04-43_megamax-spl-vm01/events.out.tfevents.1742128491.megamax-spl-vm01.3229474.0 +3 -0
- runs/Mar16_18-07-16_megamax-spl-vm01/events.out.tfevents.1742128639.megamax-spl-vm01.3236623.0 +3 -0
- runs/Mar16_18-07-16_megamax-spl-vm01/events.out.tfevents.1742130492.megamax-spl-vm01.3236623.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +1263 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
+
tags:
|
| 6 |
+
- image-classification
|
| 7 |
+
- vision
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: beans_outputs
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# beans_outputs
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the /home/ubuntu/sdb/astitva/segmentation/classification_ds dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.8746
|
| 24 |
+
- Accuracy: 0.9515
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 2e-05
|
| 44 |
+
- train_batch_size: 8
|
| 45 |
+
- eval_batch_size: 8
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 5.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 55 |
+
| 2.1775 | 1.0 | 336 | 2.1821 | 0.7616 |
|
| 56 |
+
| 1.4653 | 2.0 | 672 | 1.4698 | 0.8840 |
|
| 57 |
+
| 1.1052 | 3.0 | 1008 | 1.0802 | 0.9304 |
|
| 58 |
+
| 1.0055 | 4.0 | 1344 | 0.9248 | 0.9494 |
|
| 59 |
+
| 0.7847 | 5.0 | 1680 | 0.8746 | 0.9515 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.50.0.dev0
|
| 65 |
+
- Pytorch 2.6.0+cu124
|
| 66 |
+
- Datasets 3.3.2
|
| 67 |
+
- Tokenizers 0.21.0
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9514767932489452,
|
| 4 |
+
"eval_loss": 0.8745647668838501,
|
| 5 |
+
"eval_runtime": 51.5176,
|
| 6 |
+
"eval_samples_per_second": 9.201,
|
| 7 |
+
"eval_steps_per_second": 1.165,
|
| 8 |
+
"total_flos": 1.0410532148820787e+18,
|
| 9 |
+
"train_loss": 1.5688391100792658,
|
| 10 |
+
"train_runtime": 1801.1044,
|
| 11 |
+
"train_samples_per_second": 7.457,
|
| 12 |
+
"train_steps_per_second": 0.933
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"finetuning_task": "image-classification",
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "aloevera",
|
| 14 |
+
"1": "arjun",
|
| 15 |
+
"10": "coffee",
|
| 16 |
+
"11": "coriander",
|
| 17 |
+
"12": "curry",
|
| 18 |
+
"13": "giloy",
|
| 19 |
+
"14": "ginger",
|
| 20 |
+
"15": "glochidion",
|
| 21 |
+
"16": "gotu kola",
|
| 22 |
+
"17": "hibiscus",
|
| 23 |
+
"18": "jasmine",
|
| 24 |
+
"19": "lemon",
|
| 25 |
+
"2": "ashwagandha",
|
| 26 |
+
"20": "madar",
|
| 27 |
+
"21": "mango",
|
| 28 |
+
"22": "marigold",
|
| 29 |
+
"23": "mint",
|
| 30 |
+
"24": "moringa",
|
| 31 |
+
"25": "naruneendi",
|
| 32 |
+
"26": "neem",
|
| 33 |
+
"27": "onion",
|
| 34 |
+
"28": "papaya",
|
| 35 |
+
"29": "ricinus",
|
| 36 |
+
"3": "babool",
|
| 37 |
+
"30": "rose",
|
| 38 |
+
"31": "sarpagandha",
|
| 39 |
+
"32": "shatavari",
|
| 40 |
+
"33": "stereoserpum",
|
| 41 |
+
"34": "tomato",
|
| 42 |
+
"35": "tulsi",
|
| 43 |
+
"36": "turmeric",
|
| 44 |
+
"37": "wedelia",
|
| 45 |
+
"4": "bael",
|
| 46 |
+
"5": "bakuchi",
|
| 47 |
+
"6": "barberry",
|
| 48 |
+
"7": "bhilawa",
|
| 49 |
+
"8": "bhringraj",
|
| 50 |
+
"9": "chilly"
|
| 51 |
+
},
|
| 52 |
+
"image_size": 224,
|
| 53 |
+
"initializer_range": 0.02,
|
| 54 |
+
"intermediate_size": 3072,
|
| 55 |
+
"label2id": {
|
| 56 |
+
"aloevera": "0",
|
| 57 |
+
"arjun": "1",
|
| 58 |
+
"ashwagandha": "2",
|
| 59 |
+
"babool": "3",
|
| 60 |
+
"bael": "4",
|
| 61 |
+
"bakuchi": "5",
|
| 62 |
+
"barberry": "6",
|
| 63 |
+
"bhilawa": "7",
|
| 64 |
+
"bhringraj": "8",
|
| 65 |
+
"chilly": "9",
|
| 66 |
+
"coffee": "10",
|
| 67 |
+
"coriander": "11",
|
| 68 |
+
"curry": "12",
|
| 69 |
+
"giloy": "13",
|
| 70 |
+
"ginger": "14",
|
| 71 |
+
"glochidion": "15",
|
| 72 |
+
"gotu kola": "16",
|
| 73 |
+
"hibiscus": "17",
|
| 74 |
+
"jasmine": "18",
|
| 75 |
+
"lemon": "19",
|
| 76 |
+
"madar": "20",
|
| 77 |
+
"mango": "21",
|
| 78 |
+
"marigold": "22",
|
| 79 |
+
"mint": "23",
|
| 80 |
+
"moringa": "24",
|
| 81 |
+
"naruneendi": "25",
|
| 82 |
+
"neem": "26",
|
| 83 |
+
"onion": "27",
|
| 84 |
+
"papaya": "28",
|
| 85 |
+
"ricinus": "29",
|
| 86 |
+
"rose": "30",
|
| 87 |
+
"sarpagandha": "31",
|
| 88 |
+
"shatavari": "32",
|
| 89 |
+
"stereoserpum": "33",
|
| 90 |
+
"tomato": "34",
|
| 91 |
+
"tulsi": "35",
|
| 92 |
+
"turmeric": "36",
|
| 93 |
+
"wedelia": "37"
|
| 94 |
+
},
|
| 95 |
+
"layer_norm_eps": 1e-12,
|
| 96 |
+
"model_type": "vit",
|
| 97 |
+
"num_attention_heads": 12,
|
| 98 |
+
"num_channels": 3,
|
| 99 |
+
"num_hidden_layers": 12,
|
| 100 |
+
"patch_size": 16,
|
| 101 |
+
"problem_type": "single_label_classification",
|
| 102 |
+
"qkv_bias": true,
|
| 103 |
+
"torch_dtype": "float32",
|
| 104 |
+
"transformers_version": "4.50.0.dev0"
|
| 105 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9514767932489452,
|
| 4 |
+
"eval_loss": 0.8745647668838501,
|
| 5 |
+
"eval_runtime": 51.5176,
|
| 6 |
+
"eval_samples_per_second": 9.201,
|
| 7 |
+
"eval_steps_per_second": 1.165
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:405aae6925ebb7690e4fc69bb192018b73635b0d76ba5fef4ea3dba7998a9b01
|
| 3 |
+
size 343334720
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
runs/Mar16_18-04-43_megamax-spl-vm01/events.out.tfevents.1742128491.megamax-spl-vm01.3229474.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc49302704f3016139389073f1fd079d7f7097dcc4196b717235d4943c8adf22
|
| 3 |
+
size 7663
|
runs/Mar16_18-07-16_megamax-spl-vm01/events.out.tfevents.1742128639.megamax-spl-vm01.3236623.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8a4193d1d23f9ead30fac7487299d057dceeb75b5f0548eb3f7aeaa15c2b795
|
| 3 |
+
size 43996
|
runs/Mar16_18-07-16_megamax-spl-vm01/events.out.tfevents.1742130492.megamax-spl-vm01.3236623.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40a8bff43120b59a5c0964a06324ad8fabed2569bbce79d2ddd4215bc8308dce
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 1.0410532148820787e+18,
|
| 4 |
+
"train_loss": 1.5688391100792658,
|
| 5 |
+
"train_runtime": 1801.1044,
|
| 6 |
+
"train_samples_per_second": 7.457,
|
| 7 |
+
"train_steps_per_second": 0.933
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1263 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8745647668838501,
|
| 3 |
+
"best_model_checkpoint": "./beans_outputs/checkpoint-1680",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1680,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02976190476190476,
|
| 13 |
+
"grad_norm": 3.170905113220215,
|
| 14 |
+
"learning_rate": 1.9880952380952384e-05,
|
| 15 |
+
"loss": 3.6048,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05952380952380952,
|
| 20 |
+
"grad_norm": 2.51796555519104,
|
| 21 |
+
"learning_rate": 1.9761904761904763e-05,
|
| 22 |
+
"loss": 3.5551,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08928571428571429,
|
| 27 |
+
"grad_norm": 2.868872880935669,
|
| 28 |
+
"learning_rate": 1.9642857142857145e-05,
|
| 29 |
+
"loss": 3.4868,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11904761904761904,
|
| 34 |
+
"grad_norm": 3.2086801528930664,
|
| 35 |
+
"learning_rate": 1.9523809523809524e-05,
|
| 36 |
+
"loss": 3.4105,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1488095238095238,
|
| 41 |
+
"grad_norm": 2.825397253036499,
|
| 42 |
+
"learning_rate": 1.9404761904761906e-05,
|
| 43 |
+
"loss": 3.3538,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17857142857142858,
|
| 48 |
+
"grad_norm": 3.486938238143921,
|
| 49 |
+
"learning_rate": 1.928571428571429e-05,
|
| 50 |
+
"loss": 3.3201,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.20833333333333334,
|
| 55 |
+
"grad_norm": 2.802475929260254,
|
| 56 |
+
"learning_rate": 1.916666666666667e-05,
|
| 57 |
+
"loss": 3.2432,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.23809523809523808,
|
| 62 |
+
"grad_norm": 2.789459228515625,
|
| 63 |
+
"learning_rate": 1.904761904761905e-05,
|
| 64 |
+
"loss": 3.2041,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.26785714285714285,
|
| 69 |
+
"grad_norm": 3.008307933807373,
|
| 70 |
+
"learning_rate": 1.892857142857143e-05,
|
| 71 |
+
"loss": 3.1679,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2976190476190476,
|
| 76 |
+
"grad_norm": 2.6487619876861572,
|
| 77 |
+
"learning_rate": 1.880952380952381e-05,
|
| 78 |
+
"loss": 3.1249,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3273809523809524,
|
| 83 |
+
"grad_norm": 2.947179079055786,
|
| 84 |
+
"learning_rate": 1.8690476190476193e-05,
|
| 85 |
+
"loss": 3.0909,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.35714285714285715,
|
| 90 |
+
"grad_norm": 3.1243131160736084,
|
| 91 |
+
"learning_rate": 1.8571428571428575e-05,
|
| 92 |
+
"loss": 3.0953,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3869047619047619,
|
| 97 |
+
"grad_norm": 2.9400837421417236,
|
| 98 |
+
"learning_rate": 1.8452380952380954e-05,
|
| 99 |
+
"loss": 2.9629,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.4166666666666667,
|
| 104 |
+
"grad_norm": 2.7061338424682617,
|
| 105 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 106 |
+
"loss": 2.9307,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.44642857142857145,
|
| 111 |
+
"grad_norm": 2.6359243392944336,
|
| 112 |
+
"learning_rate": 1.8214285714285715e-05,
|
| 113 |
+
"loss": 2.8238,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.47619047619047616,
|
| 118 |
+
"grad_norm": 2.740408420562744,
|
| 119 |
+
"learning_rate": 1.8095238095238097e-05,
|
| 120 |
+
"loss": 2.8961,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5059523809523809,
|
| 125 |
+
"grad_norm": 2.858968496322632,
|
| 126 |
+
"learning_rate": 1.797619047619048e-05,
|
| 127 |
+
"loss": 2.7505,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5357142857142857,
|
| 132 |
+
"grad_norm": 2.7578256130218506,
|
| 133 |
+
"learning_rate": 1.785714285714286e-05,
|
| 134 |
+
"loss": 2.7989,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5654761904761905,
|
| 139 |
+
"grad_norm": 2.9766931533813477,
|
| 140 |
+
"learning_rate": 1.7738095238095237e-05,
|
| 141 |
+
"loss": 2.6722,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5952380952380952,
|
| 146 |
+
"grad_norm": 2.7900352478027344,
|
| 147 |
+
"learning_rate": 1.761904761904762e-05,
|
| 148 |
+
"loss": 2.7213,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.625,
|
| 153 |
+
"grad_norm": 3.004939556121826,
|
| 154 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 155 |
+
"loss": 2.7287,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6547619047619048,
|
| 160 |
+
"grad_norm": 2.7375917434692383,
|
| 161 |
+
"learning_rate": 1.7380952380952384e-05,
|
| 162 |
+
"loss": 2.6691,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6845238095238095,
|
| 167 |
+
"grad_norm": 3.2530713081359863,
|
| 168 |
+
"learning_rate": 1.7261904761904763e-05,
|
| 169 |
+
"loss": 2.5742,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7142857142857143,
|
| 174 |
+
"grad_norm": 3.0463545322418213,
|
| 175 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 176 |
+
"loss": 2.4523,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7440476190476191,
|
| 181 |
+
"grad_norm": 3.0471720695495605,
|
| 182 |
+
"learning_rate": 1.7023809523809524e-05,
|
| 183 |
+
"loss": 2.4592,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7738095238095238,
|
| 188 |
+
"grad_norm": 3.4415907859802246,
|
| 189 |
+
"learning_rate": 1.6904761904761906e-05,
|
| 190 |
+
"loss": 2.4316,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8035714285714286,
|
| 195 |
+
"grad_norm": 2.830673933029175,
|
| 196 |
+
"learning_rate": 1.678571428571429e-05,
|
| 197 |
+
"loss": 2.3903,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8333333333333334,
|
| 202 |
+
"grad_norm": 3.584303617477417,
|
| 203 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 204 |
+
"loss": 2.4643,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8630952380952381,
|
| 209 |
+
"grad_norm": 3.9748589992523193,
|
| 210 |
+
"learning_rate": 1.6547619047619046e-05,
|
| 211 |
+
"loss": 2.3237,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.8928571428571429,
|
| 216 |
+
"grad_norm": 2.929922103881836,
|
| 217 |
+
"learning_rate": 1.642857142857143e-05,
|
| 218 |
+
"loss": 2.2639,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9226190476190477,
|
| 223 |
+
"grad_norm": 4.647745132446289,
|
| 224 |
+
"learning_rate": 1.630952380952381e-05,
|
| 225 |
+
"loss": 2.4637,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9523809523809523,
|
| 230 |
+
"grad_norm": 3.6543118953704834,
|
| 231 |
+
"learning_rate": 1.6190476190476193e-05,
|
| 232 |
+
"loss": 2.2519,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9821428571428571,
|
| 237 |
+
"grad_norm": 3.3143322467803955,
|
| 238 |
+
"learning_rate": 1.6071428571428572e-05,
|
| 239 |
+
"loss": 2.1775,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.0,
|
| 244 |
+
"eval_accuracy": 0.7616033755274262,
|
| 245 |
+
"eval_loss": 2.1820600032806396,
|
| 246 |
+
"eval_runtime": 50.7645,
|
| 247 |
+
"eval_samples_per_second": 9.337,
|
| 248 |
+
"eval_steps_per_second": 1.182,
|
| 249 |
+
"step": 336
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.0119047619047619,
|
| 253 |
+
"grad_norm": 3.666236639022827,
|
| 254 |
+
"learning_rate": 1.5952380952380954e-05,
|
| 255 |
+
"loss": 2.1187,
|
| 256 |
+
"step": 340
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.0416666666666667,
|
| 260 |
+
"grad_norm": 3.736830472946167,
|
| 261 |
+
"learning_rate": 1.5833333333333333e-05,
|
| 262 |
+
"loss": 2.1312,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.0714285714285714,
|
| 267 |
+
"grad_norm": 3.002455711364746,
|
| 268 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 269 |
+
"loss": 2.2274,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.1011904761904763,
|
| 274 |
+
"grad_norm": 3.2685108184814453,
|
| 275 |
+
"learning_rate": 1.5595238095238098e-05,
|
| 276 |
+
"loss": 2.1347,
|
| 277 |
+
"step": 370
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.130952380952381,
|
| 281 |
+
"grad_norm": 3.4998621940612793,
|
| 282 |
+
"learning_rate": 1.5476190476190476e-05,
|
| 283 |
+
"loss": 2.0757,
|
| 284 |
+
"step": 380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.1607142857142858,
|
| 288 |
+
"grad_norm": 3.306267738342285,
|
| 289 |
+
"learning_rate": 1.535714285714286e-05,
|
| 290 |
+
"loss": 2.0177,
|
| 291 |
+
"step": 390
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.1904761904761905,
|
| 295 |
+
"grad_norm": 3.8774032592773438,
|
| 296 |
+
"learning_rate": 1.523809523809524e-05,
|
| 297 |
+
"loss": 1.9748,
|
| 298 |
+
"step": 400
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.2202380952380953,
|
| 302 |
+
"grad_norm": 2.662797212600708,
|
| 303 |
+
"learning_rate": 1.511904761904762e-05,
|
| 304 |
+
"loss": 1.9628,
|
| 305 |
+
"step": 410
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.25,
|
| 309 |
+
"grad_norm": 3.9353742599487305,
|
| 310 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 311 |
+
"loss": 2.0104,
|
| 312 |
+
"step": 420
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.2797619047619047,
|
| 316 |
+
"grad_norm": 3.3460521697998047,
|
| 317 |
+
"learning_rate": 1.4880952380952383e-05,
|
| 318 |
+
"loss": 2.0678,
|
| 319 |
+
"step": 430
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.3095238095238095,
|
| 323 |
+
"grad_norm": 3.0211353302001953,
|
| 324 |
+
"learning_rate": 1.4761904761904763e-05,
|
| 325 |
+
"loss": 2.0294,
|
| 326 |
+
"step": 440
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.3392857142857144,
|
| 330 |
+
"grad_norm": 2.827756404876709,
|
| 331 |
+
"learning_rate": 1.4642857142857144e-05,
|
| 332 |
+
"loss": 1.9104,
|
| 333 |
+
"step": 450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.369047619047619,
|
| 337 |
+
"grad_norm": 2.606844663619995,
|
| 338 |
+
"learning_rate": 1.4523809523809524e-05,
|
| 339 |
+
"loss": 1.933,
|
| 340 |
+
"step": 460
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.3988095238095237,
|
| 344 |
+
"grad_norm": 3.994950294494629,
|
| 345 |
+
"learning_rate": 1.4404761904761907e-05,
|
| 346 |
+
"loss": 1.9977,
|
| 347 |
+
"step": 470
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.4285714285714286,
|
| 351 |
+
"grad_norm": 3.6433207988739014,
|
| 352 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 353 |
+
"loss": 1.897,
|
| 354 |
+
"step": 480
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.4583333333333333,
|
| 358 |
+
"grad_norm": 3.1899826526641846,
|
| 359 |
+
"learning_rate": 1.416666666666667e-05,
|
| 360 |
+
"loss": 1.9046,
|
| 361 |
+
"step": 490
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.4880952380952381,
|
| 365 |
+
"grad_norm": 3.352928638458252,
|
| 366 |
+
"learning_rate": 1.4047619047619048e-05,
|
| 367 |
+
"loss": 1.7378,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.5178571428571428,
|
| 372 |
+
"grad_norm": 4.73577880859375,
|
| 373 |
+
"learning_rate": 1.3928571428571429e-05,
|
| 374 |
+
"loss": 1.7998,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.5476190476190477,
|
| 379 |
+
"grad_norm": 3.118739366531372,
|
| 380 |
+
"learning_rate": 1.3809523809523811e-05,
|
| 381 |
+
"loss": 1.7316,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.5773809523809523,
|
| 386 |
+
"grad_norm": 2.617877721786499,
|
| 387 |
+
"learning_rate": 1.3690476190476192e-05,
|
| 388 |
+
"loss": 1.6478,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.6071428571428572,
|
| 393 |
+
"grad_norm": 3.3894600868225098,
|
| 394 |
+
"learning_rate": 1.3571428571428574e-05,
|
| 395 |
+
"loss": 1.7311,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.6369047619047619,
|
| 400 |
+
"grad_norm": 4.088054656982422,
|
| 401 |
+
"learning_rate": 1.3452380952380954e-05,
|
| 402 |
+
"loss": 1.5008,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.6666666666666665,
|
| 407 |
+
"grad_norm": 3.2209737300872803,
|
| 408 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 409 |
+
"loss": 1.6994,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.6964285714285714,
|
| 414 |
+
"grad_norm": 3.8286681175231934,
|
| 415 |
+
"learning_rate": 1.3214285714285716e-05,
|
| 416 |
+
"loss": 1.6879,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.7261904761904763,
|
| 421 |
+
"grad_norm": 2.611720561981201,
|
| 422 |
+
"learning_rate": 1.3095238095238096e-05,
|
| 423 |
+
"loss": 1.6061,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.755952380952381,
|
| 428 |
+
"grad_norm": 2.898097276687622,
|
| 429 |
+
"learning_rate": 1.2976190476190478e-05,
|
| 430 |
+
"loss": 1.5223,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.7857142857142856,
|
| 435 |
+
"grad_norm": 2.2522895336151123,
|
| 436 |
+
"learning_rate": 1.2857142857142859e-05,
|
| 437 |
+
"loss": 1.5095,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.8154761904761905,
|
| 442 |
+
"grad_norm": 3.5610804557800293,
|
| 443 |
+
"learning_rate": 1.2738095238095238e-05,
|
| 444 |
+
"loss": 1.6524,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.8452380952380953,
|
| 449 |
+
"grad_norm": 3.532130002975464,
|
| 450 |
+
"learning_rate": 1.261904761904762e-05,
|
| 451 |
+
"loss": 1.5345,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.875,
|
| 456 |
+
"grad_norm": 3.8648953437805176,
|
| 457 |
+
"learning_rate": 1.25e-05,
|
| 458 |
+
"loss": 1.691,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.9047619047619047,
|
| 463 |
+
"grad_norm": 2.4936046600341797,
|
| 464 |
+
"learning_rate": 1.2380952380952383e-05,
|
| 465 |
+
"loss": 1.4573,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.9345238095238095,
|
| 470 |
+
"grad_norm": 3.499699592590332,
|
| 471 |
+
"learning_rate": 1.2261904761904763e-05,
|
| 472 |
+
"loss": 1.5181,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.9642857142857144,
|
| 477 |
+
"grad_norm": 2.7815959453582764,
|
| 478 |
+
"learning_rate": 1.2142857142857142e-05,
|
| 479 |
+
"loss": 1.4333,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.994047619047619,
|
| 484 |
+
"grad_norm": 3.007183790206909,
|
| 485 |
+
"learning_rate": 1.2023809523809525e-05,
|
| 486 |
+
"loss": 1.4653,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.0,
|
| 491 |
+
"eval_accuracy": 0.8839662447257384,
|
| 492 |
+
"eval_loss": 1.4698303937911987,
|
| 493 |
+
"eval_runtime": 51.4369,
|
| 494 |
+
"eval_samples_per_second": 9.215,
|
| 495 |
+
"eval_steps_per_second": 1.166,
|
| 496 |
+
"step": 672
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.0238095238095237,
|
| 500 |
+
"grad_norm": 3.4663267135620117,
|
| 501 |
+
"learning_rate": 1.1904761904761905e-05,
|
| 502 |
+
"loss": 1.4428,
|
| 503 |
+
"step": 680
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.0535714285714284,
|
| 507 |
+
"grad_norm": 2.2934768199920654,
|
| 508 |
+
"learning_rate": 1.1785714285714287e-05,
|
| 509 |
+
"loss": 1.4135,
|
| 510 |
+
"step": 690
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.0833333333333335,
|
| 514 |
+
"grad_norm": 2.601954221725464,
|
| 515 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 516 |
+
"loss": 1.456,
|
| 517 |
+
"step": 700
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 2.113095238095238,
|
| 521 |
+
"grad_norm": 3.2254600524902344,
|
| 522 |
+
"learning_rate": 1.1547619047619047e-05,
|
| 523 |
+
"loss": 1.5227,
|
| 524 |
+
"step": 710
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.142857142857143,
|
| 528 |
+
"grad_norm": 3.2958316802978516,
|
| 529 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 530 |
+
"loss": 1.4248,
|
| 531 |
+
"step": 720
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.1726190476190474,
|
| 535 |
+
"grad_norm": 4.993536472320557,
|
| 536 |
+
"learning_rate": 1.130952380952381e-05,
|
| 537 |
+
"loss": 1.4717,
|
| 538 |
+
"step": 730
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.2023809523809526,
|
| 542 |
+
"grad_norm": 3.3640084266662598,
|
| 543 |
+
"learning_rate": 1.1190476190476192e-05,
|
| 544 |
+
"loss": 1.4265,
|
| 545 |
+
"step": 740
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.232142857142857,
|
| 549 |
+
"grad_norm": 2.6835250854492188,
|
| 550 |
+
"learning_rate": 1.1071428571428572e-05,
|
| 551 |
+
"loss": 1.408,
|
| 552 |
+
"step": 750
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.261904761904762,
|
| 556 |
+
"grad_norm": 3.8518381118774414,
|
| 557 |
+
"learning_rate": 1.0952380952380955e-05,
|
| 558 |
+
"loss": 1.2666,
|
| 559 |
+
"step": 760
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 2.2916666666666665,
|
| 563 |
+
"grad_norm": 3.553366184234619,
|
| 564 |
+
"learning_rate": 1.0833333333333334e-05,
|
| 565 |
+
"loss": 1.4052,
|
| 566 |
+
"step": 770
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.3214285714285716,
|
| 570 |
+
"grad_norm": 2.657440423965454,
|
| 571 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 572 |
+
"loss": 1.3953,
|
| 573 |
+
"step": 780
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.3511904761904763,
|
| 577 |
+
"grad_norm": 4.050617694854736,
|
| 578 |
+
"learning_rate": 1.0595238095238096e-05,
|
| 579 |
+
"loss": 1.3073,
|
| 580 |
+
"step": 790
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 2.380952380952381,
|
| 584 |
+
"grad_norm": 3.039287567138672,
|
| 585 |
+
"learning_rate": 1.0476190476190477e-05,
|
| 586 |
+
"loss": 1.3765,
|
| 587 |
+
"step": 800
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.4107142857142856,
|
| 591 |
+
"grad_norm": 3.350076913833618,
|
| 592 |
+
"learning_rate": 1.0357142857142859e-05,
|
| 593 |
+
"loss": 1.2713,
|
| 594 |
+
"step": 810
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.4404761904761907,
|
| 598 |
+
"grad_norm": 4.112967491149902,
|
| 599 |
+
"learning_rate": 1.0238095238095238e-05,
|
| 600 |
+
"loss": 1.3557,
|
| 601 |
+
"step": 820
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 2.4702380952380953,
|
| 605 |
+
"grad_norm": 2.587895154953003,
|
| 606 |
+
"learning_rate": 1.011904761904762e-05,
|
| 607 |
+
"loss": 1.2106,
|
| 608 |
+
"step": 830
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.5,
|
| 612 |
+
"grad_norm": 2.2189221382141113,
|
| 613 |
+
"learning_rate": 1e-05,
|
| 614 |
+
"loss": 1.1529,
|
| 615 |
+
"step": 840
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.5297619047619047,
|
| 619 |
+
"grad_norm": 1.7763313055038452,
|
| 620 |
+
"learning_rate": 9.880952380952381e-06,
|
| 621 |
+
"loss": 1.2066,
|
| 622 |
+
"step": 850
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 2.5595238095238093,
|
| 626 |
+
"grad_norm": 2.5652577877044678,
|
| 627 |
+
"learning_rate": 9.761904761904762e-06,
|
| 628 |
+
"loss": 1.2206,
|
| 629 |
+
"step": 860
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 2.5892857142857144,
|
| 633 |
+
"grad_norm": 2.4081642627716064,
|
| 634 |
+
"learning_rate": 9.642857142857144e-06,
|
| 635 |
+
"loss": 1.2288,
|
| 636 |
+
"step": 870
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 2.619047619047619,
|
| 640 |
+
"grad_norm": 3.4448933601379395,
|
| 641 |
+
"learning_rate": 9.523809523809525e-06,
|
| 642 |
+
"loss": 1.2764,
|
| 643 |
+
"step": 880
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 2.6488095238095237,
|
| 647 |
+
"grad_norm": 3.65535044670105,
|
| 648 |
+
"learning_rate": 9.404761904761905e-06,
|
| 649 |
+
"loss": 1.1818,
|
| 650 |
+
"step": 890
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.678571428571429,
|
| 654 |
+
"grad_norm": 2.902886152267456,
|
| 655 |
+
"learning_rate": 9.285714285714288e-06,
|
| 656 |
+
"loss": 1.2662,
|
| 657 |
+
"step": 900
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.7083333333333335,
|
| 661 |
+
"grad_norm": 2.8251378536224365,
|
| 662 |
+
"learning_rate": 9.166666666666666e-06,
|
| 663 |
+
"loss": 1.1246,
|
| 664 |
+
"step": 910
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.738095238095238,
|
| 668 |
+
"grad_norm": 2.1443264484405518,
|
| 669 |
+
"learning_rate": 9.047619047619049e-06,
|
| 670 |
+
"loss": 1.2486,
|
| 671 |
+
"step": 920
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 2.767857142857143,
|
| 675 |
+
"grad_norm": 4.930934429168701,
|
| 676 |
+
"learning_rate": 8.92857142857143e-06,
|
| 677 |
+
"loss": 1.1865,
|
| 678 |
+
"step": 930
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.7976190476190474,
|
| 682 |
+
"grad_norm": 3.2018985748291016,
|
| 683 |
+
"learning_rate": 8.80952380952381e-06,
|
| 684 |
+
"loss": 1.1047,
|
| 685 |
+
"step": 940
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 2.8273809523809526,
|
| 689 |
+
"grad_norm": 3.2998268604278564,
|
| 690 |
+
"learning_rate": 8.690476190476192e-06,
|
| 691 |
+
"loss": 1.2098,
|
| 692 |
+
"step": 950
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.857142857142857,
|
| 696 |
+
"grad_norm": 2.1316542625427246,
|
| 697 |
+
"learning_rate": 8.571428571428571e-06,
|
| 698 |
+
"loss": 1.0918,
|
| 699 |
+
"step": 960
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.886904761904762,
|
| 703 |
+
"grad_norm": 3.8014087677001953,
|
| 704 |
+
"learning_rate": 8.452380952380953e-06,
|
| 705 |
+
"loss": 1.1139,
|
| 706 |
+
"step": 970
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.9166666666666665,
|
| 710 |
+
"grad_norm": 2.8320999145507812,
|
| 711 |
+
"learning_rate": 8.333333333333334e-06,
|
| 712 |
+
"loss": 1.213,
|
| 713 |
+
"step": 980
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.946428571428571,
|
| 717 |
+
"grad_norm": 3.016481876373291,
|
| 718 |
+
"learning_rate": 8.214285714285714e-06,
|
| 719 |
+
"loss": 1.1398,
|
| 720 |
+
"step": 990
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.9761904761904763,
|
| 724 |
+
"grad_norm": 3.9006187915802,
|
| 725 |
+
"learning_rate": 8.095238095238097e-06,
|
| 726 |
+
"loss": 1.1052,
|
| 727 |
+
"step": 1000
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 3.0,
|
| 731 |
+
"eval_accuracy": 0.930379746835443,
|
| 732 |
+
"eval_loss": 1.0801581144332886,
|
| 733 |
+
"eval_runtime": 51.0077,
|
| 734 |
+
"eval_samples_per_second": 9.293,
|
| 735 |
+
"eval_steps_per_second": 1.176,
|
| 736 |
+
"step": 1008
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 3.005952380952381,
|
| 740 |
+
"grad_norm": 2.796464204788208,
|
| 741 |
+
"learning_rate": 7.976190476190477e-06,
|
| 742 |
+
"loss": 1.1341,
|
| 743 |
+
"step": 1010
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 3.0357142857142856,
|
| 747 |
+
"grad_norm": 2.1846368312835693,
|
| 748 |
+
"learning_rate": 7.857142857142858e-06,
|
| 749 |
+
"loss": 1.173,
|
| 750 |
+
"step": 1020
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 3.0654761904761907,
|
| 754 |
+
"grad_norm": 3.3909096717834473,
|
| 755 |
+
"learning_rate": 7.738095238095238e-06,
|
| 756 |
+
"loss": 1.0198,
|
| 757 |
+
"step": 1030
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 3.0952380952380953,
|
| 761 |
+
"grad_norm": 3.5887138843536377,
|
| 762 |
+
"learning_rate": 7.61904761904762e-06,
|
| 763 |
+
"loss": 1.0729,
|
| 764 |
+
"step": 1040
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 3.125,
|
| 768 |
+
"grad_norm": 2.7871737480163574,
|
| 769 |
+
"learning_rate": 7.500000000000001e-06,
|
| 770 |
+
"loss": 0.9676,
|
| 771 |
+
"step": 1050
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 3.1547619047619047,
|
| 775 |
+
"grad_norm": 3.3368754386901855,
|
| 776 |
+
"learning_rate": 7.380952380952382e-06,
|
| 777 |
+
"loss": 0.9599,
|
| 778 |
+
"step": 1060
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 3.1845238095238093,
|
| 782 |
+
"grad_norm": 3.748992919921875,
|
| 783 |
+
"learning_rate": 7.261904761904762e-06,
|
| 784 |
+
"loss": 1.1599,
|
| 785 |
+
"step": 1070
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 3.2142857142857144,
|
| 789 |
+
"grad_norm": 4.470694065093994,
|
| 790 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 791 |
+
"loss": 1.155,
|
| 792 |
+
"step": 1080
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 3.244047619047619,
|
| 796 |
+
"grad_norm": 1.8315823078155518,
|
| 797 |
+
"learning_rate": 7.023809523809524e-06,
|
| 798 |
+
"loss": 0.979,
|
| 799 |
+
"step": 1090
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 3.2738095238095237,
|
| 803 |
+
"grad_norm": 2.505209445953369,
|
| 804 |
+
"learning_rate": 6.9047619047619055e-06,
|
| 805 |
+
"loss": 1.142,
|
| 806 |
+
"step": 1100
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.3035714285714284,
|
| 810 |
+
"grad_norm": 3.056353807449341,
|
| 811 |
+
"learning_rate": 6.785714285714287e-06,
|
| 812 |
+
"loss": 1.0072,
|
| 813 |
+
"step": 1110
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.3333333333333335,
|
| 817 |
+
"grad_norm": 3.9302310943603516,
|
| 818 |
+
"learning_rate": 6.666666666666667e-06,
|
| 819 |
+
"loss": 1.0705,
|
| 820 |
+
"step": 1120
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 3.363095238095238,
|
| 824 |
+
"grad_norm": 4.6520490646362305,
|
| 825 |
+
"learning_rate": 6.547619047619048e-06,
|
| 826 |
+
"loss": 1.0325,
|
| 827 |
+
"step": 1130
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.392857142857143,
|
| 831 |
+
"grad_norm": 3.9381701946258545,
|
| 832 |
+
"learning_rate": 6.4285714285714295e-06,
|
| 833 |
+
"loss": 0.9674,
|
| 834 |
+
"step": 1140
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.4226190476190474,
|
| 838 |
+
"grad_norm": 5.080965042114258,
|
| 839 |
+
"learning_rate": 6.30952380952381e-06,
|
| 840 |
+
"loss": 0.9812,
|
| 841 |
+
"step": 1150
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.4523809523809526,
|
| 845 |
+
"grad_norm": 4.649317264556885,
|
| 846 |
+
"learning_rate": 6.1904761904761914e-06,
|
| 847 |
+
"loss": 1.1093,
|
| 848 |
+
"step": 1160
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.482142857142857,
|
| 852 |
+
"grad_norm": 5.5956315994262695,
|
| 853 |
+
"learning_rate": 6.071428571428571e-06,
|
| 854 |
+
"loss": 1.0133,
|
| 855 |
+
"step": 1170
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 3.511904761904762,
|
| 859 |
+
"grad_norm": 4.99602746963501,
|
| 860 |
+
"learning_rate": 5.9523809523809525e-06,
|
| 861 |
+
"loss": 1.075,
|
| 862 |
+
"step": 1180
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 3.5416666666666665,
|
| 866 |
+
"grad_norm": 3.875300407409668,
|
| 867 |
+
"learning_rate": 5.833333333333334e-06,
|
| 868 |
+
"loss": 1.1469,
|
| 869 |
+
"step": 1190
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 3.571428571428571,
|
| 873 |
+
"grad_norm": 2.9351279735565186,
|
| 874 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 875 |
+
"loss": 1.1746,
|
| 876 |
+
"step": 1200
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 3.6011904761904763,
|
| 880 |
+
"grad_norm": 3.581909418106079,
|
| 881 |
+
"learning_rate": 5.595238095238096e-06,
|
| 882 |
+
"loss": 1.0452,
|
| 883 |
+
"step": 1210
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 3.630952380952381,
|
| 887 |
+
"grad_norm": 2.4383697509765625,
|
| 888 |
+
"learning_rate": 5.476190476190477e-06,
|
| 889 |
+
"loss": 0.884,
|
| 890 |
+
"step": 1220
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.6607142857142856,
|
| 894 |
+
"grad_norm": 3.386600971221924,
|
| 895 |
+
"learning_rate": 5.357142857142857e-06,
|
| 896 |
+
"loss": 0.9479,
|
| 897 |
+
"step": 1230
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 3.6904761904761907,
|
| 901 |
+
"grad_norm": 1.5890535116195679,
|
| 902 |
+
"learning_rate": 5.2380952380952384e-06,
|
| 903 |
+
"loss": 0.8953,
|
| 904 |
+
"step": 1240
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 3.7202380952380953,
|
| 908 |
+
"grad_norm": 2.729491710662842,
|
| 909 |
+
"learning_rate": 5.119047619047619e-06,
|
| 910 |
+
"loss": 0.9071,
|
| 911 |
+
"step": 1250
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.75,
|
| 915 |
+
"grad_norm": 4.265748977661133,
|
| 916 |
+
"learning_rate": 5e-06,
|
| 917 |
+
"loss": 1.0496,
|
| 918 |
+
"step": 1260
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 3.7797619047619047,
|
| 922 |
+
"grad_norm": 3.6234512329101562,
|
| 923 |
+
"learning_rate": 4.880952380952381e-06,
|
| 924 |
+
"loss": 0.9945,
|
| 925 |
+
"step": 1270
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 3.8095238095238093,
|
| 929 |
+
"grad_norm": 3.0296449661254883,
|
| 930 |
+
"learning_rate": 4.761904761904762e-06,
|
| 931 |
+
"loss": 1.0592,
|
| 932 |
+
"step": 1280
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.8392857142857144,
|
| 936 |
+
"grad_norm": 3.7550673484802246,
|
| 937 |
+
"learning_rate": 4.642857142857144e-06,
|
| 938 |
+
"loss": 0.9102,
|
| 939 |
+
"step": 1290
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 3.869047619047619,
|
| 943 |
+
"grad_norm": 2.3732712268829346,
|
| 944 |
+
"learning_rate": 4.523809523809524e-06,
|
| 945 |
+
"loss": 0.9721,
|
| 946 |
+
"step": 1300
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.8988095238095237,
|
| 950 |
+
"grad_norm": 4.049142360687256,
|
| 951 |
+
"learning_rate": 4.404761904761905e-06,
|
| 952 |
+
"loss": 0.9409,
|
| 953 |
+
"step": 1310
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 3.928571428571429,
|
| 957 |
+
"grad_norm": 2.1877949237823486,
|
| 958 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 959 |
+
"loss": 1.0235,
|
| 960 |
+
"step": 1320
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.9583333333333335,
|
| 964 |
+
"grad_norm": 1.8449411392211914,
|
| 965 |
+
"learning_rate": 4.166666666666667e-06,
|
| 966 |
+
"loss": 0.978,
|
| 967 |
+
"step": 1330
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 3.988095238095238,
|
| 971 |
+
"grad_norm": 2.8841190338134766,
|
| 972 |
+
"learning_rate": 4.047619047619048e-06,
|
| 973 |
+
"loss": 1.0055,
|
| 974 |
+
"step": 1340
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 4.0,
|
| 978 |
+
"eval_accuracy": 0.9493670886075949,
|
| 979 |
+
"eval_loss": 0.9248189926147461,
|
| 980 |
+
"eval_runtime": 51.0423,
|
| 981 |
+
"eval_samples_per_second": 9.286,
|
| 982 |
+
"eval_steps_per_second": 1.175,
|
| 983 |
+
"step": 1344
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 4.017857142857143,
|
| 987 |
+
"grad_norm": 2.242076873779297,
|
| 988 |
+
"learning_rate": 3.928571428571429e-06,
|
| 989 |
+
"loss": 0.9244,
|
| 990 |
+
"step": 1350
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 4.0476190476190474,
|
| 994 |
+
"grad_norm": 1.98090660572052,
|
| 995 |
+
"learning_rate": 3.80952380952381e-06,
|
| 996 |
+
"loss": 0.8568,
|
| 997 |
+
"step": 1360
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 4.0773809523809526,
|
| 1001 |
+
"grad_norm": 3.927706718444824,
|
| 1002 |
+
"learning_rate": 3.690476190476191e-06,
|
| 1003 |
+
"loss": 0.9644,
|
| 1004 |
+
"step": 1370
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 4.107142857142857,
|
| 1008 |
+
"grad_norm": 2.3780994415283203,
|
| 1009 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 1010 |
+
"loss": 0.97,
|
| 1011 |
+
"step": 1380
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 4.136904761904762,
|
| 1015 |
+
"grad_norm": 2.21608304977417,
|
| 1016 |
+
"learning_rate": 3.4523809523809528e-06,
|
| 1017 |
+
"loss": 0.9728,
|
| 1018 |
+
"step": 1390
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 4.166666666666667,
|
| 1022 |
+
"grad_norm": 6.764073848724365,
|
| 1023 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 1024 |
+
"loss": 0.8729,
|
| 1025 |
+
"step": 1400
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 4.196428571428571,
|
| 1029 |
+
"grad_norm": 1.5746071338653564,
|
| 1030 |
+
"learning_rate": 3.2142857142857147e-06,
|
| 1031 |
+
"loss": 0.7702,
|
| 1032 |
+
"step": 1410
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 4.226190476190476,
|
| 1036 |
+
"grad_norm": 1.8241825103759766,
|
| 1037 |
+
"learning_rate": 3.0952380952380957e-06,
|
| 1038 |
+
"loss": 0.9121,
|
| 1039 |
+
"step": 1420
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 4.255952380952381,
|
| 1043 |
+
"grad_norm": 3.9683926105499268,
|
| 1044 |
+
"learning_rate": 2.9761904761904763e-06,
|
| 1045 |
+
"loss": 0.8749,
|
| 1046 |
+
"step": 1430
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 4.285714285714286,
|
| 1050 |
+
"grad_norm": 1.5732113122940063,
|
| 1051 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 1052 |
+
"loss": 0.9421,
|
| 1053 |
+
"step": 1440
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 4.315476190476191,
|
| 1057 |
+
"grad_norm": 2.5848405361175537,
|
| 1058 |
+
"learning_rate": 2.7380952380952387e-06,
|
| 1059 |
+
"loss": 0.9617,
|
| 1060 |
+
"step": 1450
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 4.345238095238095,
|
| 1064 |
+
"grad_norm": 3.7017910480499268,
|
| 1065 |
+
"learning_rate": 2.6190476190476192e-06,
|
| 1066 |
+
"loss": 0.905,
|
| 1067 |
+
"step": 1460
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 4.375,
|
| 1071 |
+
"grad_norm": 5.973739147186279,
|
| 1072 |
+
"learning_rate": 2.5e-06,
|
| 1073 |
+
"loss": 0.89,
|
| 1074 |
+
"step": 1470
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 4.404761904761905,
|
| 1078 |
+
"grad_norm": 1.8716737031936646,
|
| 1079 |
+
"learning_rate": 2.380952380952381e-06,
|
| 1080 |
+
"loss": 0.9635,
|
| 1081 |
+
"step": 1480
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 4.434523809523809,
|
| 1085 |
+
"grad_norm": 3.3029792308807373,
|
| 1086 |
+
"learning_rate": 2.261904761904762e-06,
|
| 1087 |
+
"loss": 0.933,
|
| 1088 |
+
"step": 1490
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.464285714285714,
|
| 1092 |
+
"grad_norm": 2.5819740295410156,
|
| 1093 |
+
"learning_rate": 2.1428571428571427e-06,
|
| 1094 |
+
"loss": 0.8899,
|
| 1095 |
+
"step": 1500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 4.494047619047619,
|
| 1099 |
+
"grad_norm": 3.5635058879852295,
|
| 1100 |
+
"learning_rate": 2.023809523809524e-06,
|
| 1101 |
+
"loss": 0.8539,
|
| 1102 |
+
"step": 1510
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 4.523809523809524,
|
| 1106 |
+
"grad_norm": 2.5672874450683594,
|
| 1107 |
+
"learning_rate": 1.904761904761905e-06,
|
| 1108 |
+
"loss": 1.0972,
|
| 1109 |
+
"step": 1520
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 4.553571428571429,
|
| 1113 |
+
"grad_norm": 5.11098051071167,
|
| 1114 |
+
"learning_rate": 1.7857142857142859e-06,
|
| 1115 |
+
"loss": 0.9862,
|
| 1116 |
+
"step": 1530
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 4.583333333333333,
|
| 1120 |
+
"grad_norm": 2.5244972705841064,
|
| 1121 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 1122 |
+
"loss": 1.0213,
|
| 1123 |
+
"step": 1540
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 4.613095238095238,
|
| 1127 |
+
"grad_norm": 3.5044398307800293,
|
| 1128 |
+
"learning_rate": 1.5476190476190479e-06,
|
| 1129 |
+
"loss": 0.9144,
|
| 1130 |
+
"step": 1550
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.642857142857143,
|
| 1134 |
+
"grad_norm": 2.4903435707092285,
|
| 1135 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 1136 |
+
"loss": 0.9331,
|
| 1137 |
+
"step": 1560
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 4.6726190476190474,
|
| 1141 |
+
"grad_norm": 3.208696126937866,
|
| 1142 |
+
"learning_rate": 1.3095238095238096e-06,
|
| 1143 |
+
"loss": 1.013,
|
| 1144 |
+
"step": 1570
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 4.7023809523809526,
|
| 1148 |
+
"grad_norm": 2.255563735961914,
|
| 1149 |
+
"learning_rate": 1.1904761904761906e-06,
|
| 1150 |
+
"loss": 0.7625,
|
| 1151 |
+
"step": 1580
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 4.732142857142857,
|
| 1155 |
+
"grad_norm": 2.1157748699188232,
|
| 1156 |
+
"learning_rate": 1.0714285714285714e-06,
|
| 1157 |
+
"loss": 0.8885,
|
| 1158 |
+
"step": 1590
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 4.761904761904762,
|
| 1162 |
+
"grad_norm": 3.0076255798339844,
|
| 1163 |
+
"learning_rate": 9.523809523809525e-07,
|
| 1164 |
+
"loss": 1.0166,
|
| 1165 |
+
"step": 1600
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 4.791666666666667,
|
| 1169 |
+
"grad_norm": 2.899481773376465,
|
| 1170 |
+
"learning_rate": 8.333333333333333e-07,
|
| 1171 |
+
"loss": 0.9983,
|
| 1172 |
+
"step": 1610
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 4.821428571428571,
|
| 1176 |
+
"grad_norm": 6.084941387176514,
|
| 1177 |
+
"learning_rate": 7.142857142857143e-07,
|
| 1178 |
+
"loss": 1.1526,
|
| 1179 |
+
"step": 1620
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 4.851190476190476,
|
| 1183 |
+
"grad_norm": 3.8710179328918457,
|
| 1184 |
+
"learning_rate": 5.952380952380953e-07,
|
| 1185 |
+
"loss": 0.8589,
|
| 1186 |
+
"step": 1630
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 4.880952380952381,
|
| 1190 |
+
"grad_norm": 2.1053106784820557,
|
| 1191 |
+
"learning_rate": 4.7619047619047623e-07,
|
| 1192 |
+
"loss": 0.8788,
|
| 1193 |
+
"step": 1640
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 4.910714285714286,
|
| 1197 |
+
"grad_norm": 2.2121217250823975,
|
| 1198 |
+
"learning_rate": 3.5714285714285716e-07,
|
| 1199 |
+
"loss": 0.8718,
|
| 1200 |
+
"step": 1650
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 4.940476190476191,
|
| 1204 |
+
"grad_norm": 2.3137481212615967,
|
| 1205 |
+
"learning_rate": 2.3809523809523811e-07,
|
| 1206 |
+
"loss": 0.7878,
|
| 1207 |
+
"step": 1660
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 4.970238095238095,
|
| 1211 |
+
"grad_norm": 2.676529884338379,
|
| 1212 |
+
"learning_rate": 1.1904761904761906e-07,
|
| 1213 |
+
"loss": 0.7782,
|
| 1214 |
+
"step": 1670
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 5.0,
|
| 1218 |
+
"grad_norm": 7.775545597076416,
|
| 1219 |
+
"learning_rate": 0.0,
|
| 1220 |
+
"loss": 0.7847,
|
| 1221 |
+
"step": 1680
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 5.0,
|
| 1225 |
+
"eval_accuracy": 0.9514767932489452,
|
| 1226 |
+
"eval_loss": 0.8745647668838501,
|
| 1227 |
+
"eval_runtime": 50.8678,
|
| 1228 |
+
"eval_samples_per_second": 9.318,
|
| 1229 |
+
"eval_steps_per_second": 1.18,
|
| 1230 |
+
"step": 1680
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 5.0,
|
| 1234 |
+
"step": 1680,
|
| 1235 |
+
"total_flos": 1.0410532148820787e+18,
|
| 1236 |
+
"train_loss": 1.5688391100792658,
|
| 1237 |
+
"train_runtime": 1801.1044,
|
| 1238 |
+
"train_samples_per_second": 7.457,
|
| 1239 |
+
"train_steps_per_second": 0.933
|
| 1240 |
+
}
|
| 1241 |
+
],
|
| 1242 |
+
"logging_steps": 10,
|
| 1243 |
+
"max_steps": 1680,
|
| 1244 |
+
"num_input_tokens_seen": 0,
|
| 1245 |
+
"num_train_epochs": 5,
|
| 1246 |
+
"save_steps": 500,
|
| 1247 |
+
"stateful_callbacks": {
|
| 1248 |
+
"TrainerControl": {
|
| 1249 |
+
"args": {
|
| 1250 |
+
"should_epoch_stop": false,
|
| 1251 |
+
"should_evaluate": false,
|
| 1252 |
+
"should_log": false,
|
| 1253 |
+
"should_save": true,
|
| 1254 |
+
"should_training_stop": true
|
| 1255 |
+
},
|
| 1256 |
+
"attributes": {}
|
| 1257 |
+
}
|
| 1258 |
+
},
|
| 1259 |
+
"total_flos": 1.0410532148820787e+18,
|
| 1260 |
+
"train_batch_size": 8,
|
| 1261 |
+
"trial_name": null,
|
| 1262 |
+
"trial_params": null
|
| 1263 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31662c38d27298aa5f2cd538b8973a3eb6908906cc3a005f04bcb4fc904d82b6
|
| 3 |
+
size 5368
|