Commit
•
58ac5f7
1
Parent(s):
9e966de
End of training
Browse files- README.md +40 -36
- all_results.json +6 -6
- config.json +30 -22
- model.safetensors +2 -2
- runs/Feb20_14-50-43_plan.cs.vt.edu/events.out.tfevents.1708469451.plan.cs.vt.edu.3543922.0 +3 -0
- runs/Feb20_14-50-43_plan.cs.vt.edu/events.out.tfevents.1708469726.plan.cs.vt.edu.3543922.1 +3 -0
- runs/Feb20_14-57-12_plan.cs.vt.edu/events.out.tfevents.1708469850.plan.cs.vt.edu.3569885.0 +3 -0
- runs/Feb20_15-18-42_plan.cs.vt.edu/events.out.tfevents.1708471132.plan.cs.vt.edu.3569885.1 +3 -0
- runs/Feb20_15-19-55_plan.cs.vt.edu/events.out.tfevents.1708471203.plan.cs.vt.edu.3569885.2 +3 -0
- runs/Feb20_15-20-55_plan.cs.vt.edu/events.out.tfevents.1708471262.plan.cs.vt.edu.3569885.3 +3 -0
- runs/Feb20_15-21-34_plan.cs.vt.edu/events.out.tfevents.1708471299.plan.cs.vt.edu.3569885.4 +3 -0
- runs/Feb20_15-49-17_plan.cs.vt.edu/events.out.tfevents.1708472959.plan.cs.vt.edu.3697382.0 +3 -0
- runs/Feb20_15-52-57_plan.cs.vt.edu/events.out.tfevents.1708473184.plan.cs.vt.edu.3697382.1 +3 -0
- runs/Feb20_15-54-37_plan.cs.vt.edu/events.out.tfevents.1708473283.plan.cs.vt.edu.3697382.2 +3 -0
- runs/Feb20_16-41-48_plan.cs.vt.edu/events.out.tfevents.1708476123.plan.cs.vt.edu.3697382.3 +3 -0
- runs/Feb20_16-42-29_plan.cs.vt.edu/events.out.tfevents.1708476167.plan.cs.vt.edu.3697382.4 +3 -0
- runs/Feb20_16-49-13_plan.cs.vt.edu/events.out.tfevents.1708476554.plan.cs.vt.edu.3697382.5 +3 -0
- runs/Feb20_16-49-46_plan.cs.vt.edu/events.out.tfevents.1708476591.plan.cs.vt.edu.3697382.6 +3 -0
- runs/Feb20_16-49-46_plan.cs.vt.edu/events.out.tfevents.1708477852.plan.cs.vt.edu.3697382.7 +3 -0
- test_results.json +6 -6
- trainer_state.json +418 -316
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
metrics:
|
|
@@ -13,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# videomae-large
|
| 15 |
|
| 16 |
-
This model
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss:
|
| 19 |
-
- Accuracy: 0.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -36,48 +38,50 @@ More information needed
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 5e-05
|
| 39 |
-
- train_batch_size:
|
| 40 |
-
- eval_batch_size:
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- lr_scheduler_warmup_ratio: 0.1
|
| 45 |
-
- training_steps:
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 51 |
-
| 2.
|
| 52 |
-
|
|
| 53 |
-
|
|
| 54 |
-
|
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
|
|
|
|
|
|
| 81 |
|
| 82 |
|
| 83 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model: MCG-NJU/videomae-large-finetuned-kinetics
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
|
|
| 15 |
|
| 16 |
# videomae-large
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [MCG-NJU/videomae-large-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-large-finetuned-kinetics) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.5042
|
| 21 |
+
- Accuracy: 0.4286
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 16
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- training_steps: 220
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 53 |
+
| 2.6619 | 0.03 | 7 | 2.7017 | 0.0 |
|
| 54 |
+
| 2.6232 | 1.03 | 14 | 2.6628 | 0.0 |
|
| 55 |
+
| 2.381 | 2.03 | 21 | 2.5798 | 0.1667 |
|
| 56 |
+
| 2.2215 | 3.03 | 28 | 2.4757 | 0.1667 |
|
| 57 |
+
| 1.7389 | 4.03 | 35 | 2.3636 | 0.2333 |
|
| 58 |
+
| 1.3366 | 5.03 | 42 | 2.2424 | 0.3 |
|
| 59 |
+
| 1.1946 | 6.03 | 49 | 2.1675 | 0.3 |
|
| 60 |
+
| 0.6809 | 7.03 | 56 | 2.0548 | 0.3667 |
|
| 61 |
+
| 0.5255 | 8.03 | 63 | 2.0410 | 0.4 |
|
| 62 |
+
| 0.3285 | 9.03 | 70 | 1.9539 | 0.4 |
|
| 63 |
+
| 0.2849 | 10.03 | 77 | 1.8536 | 0.4667 |
|
| 64 |
+
| 0.1832 | 11.03 | 84 | 1.8293 | 0.4333 |
|
| 65 |
+
| 0.1307 | 12.03 | 91 | 1.8200 | 0.4 |
|
| 66 |
+
| 0.0901 | 13.03 | 98 | 1.8355 | 0.4 |
|
| 67 |
+
| 0.0636 | 14.03 | 105 | 1.8201 | 0.4333 |
|
| 68 |
+
| 0.0413 | 15.03 | 112 | 1.7750 | 0.4667 |
|
| 69 |
+
| 0.0427 | 16.03 | 119 | 1.7460 | 0.5333 |
|
| 70 |
+
| 0.0254 | 17.03 | 126 | 1.7804 | 0.5333 |
|
| 71 |
+
| 0.0203 | 18.03 | 133 | 1.8869 | 0.4333 |
|
| 72 |
+
| 0.0174 | 19.03 | 140 | 1.7741 | 0.5667 |
|
| 73 |
+
| 0.0154 | 20.03 | 147 | 1.7401 | 0.5333 |
|
| 74 |
+
| 0.0136 | 21.03 | 154 | 1.7672 | 0.5 |
|
| 75 |
+
| 0.0116 | 22.03 | 161 | 1.7793 | 0.5333 |
|
| 76 |
+
| 0.0123 | 23.03 | 168 | 1.8018 | 0.4667 |
|
| 77 |
+
| 0.0102 | 24.03 | 175 | 1.8024 | 0.5 |
|
| 78 |
+
| 0.0103 | 25.03 | 182 | 1.8058 | 0.5 |
|
| 79 |
+
| 0.0089 | 26.03 | 189 | 1.8106 | 0.5 |
|
| 80 |
+
| 0.0088 | 27.03 | 196 | 1.8029 | 0.5 |
|
| 81 |
+
| 0.0092 | 28.03 | 203 | 1.7961 | 0.5 |
|
| 82 |
+
| 0.0083 | 29.03 | 210 | 1.7940 | 0.5 |
|
| 83 |
+
| 0.0099 | 30.03 | 217 | 1.7922 | 0.5 |
|
| 84 |
+
| 0.0085 | 31.01 | 220 | 1.7920 | 0.5 |
|
| 85 |
|
| 86 |
|
| 87 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 31.01,
|
| 3 |
+
"eval_accuracy": 0.42857142857142855,
|
| 4 |
+
"eval_loss": 1.504156231880188,
|
| 5 |
+
"eval_runtime": 2.2938,
|
| 6 |
+
"eval_samples_per_second": 6.104,
|
| 7 |
+
"eval_steps_per_second": 0.436
|
| 8 |
}
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "MCG-NJU/videomae-large",
|
| 3 |
"architectures": [
|
| 4 |
"VideoMAEForVideoClassification"
|
| 5 |
],
|
|
@@ -12,31 +12,39 @@
|
|
| 12 |
"hidden_dropout_prob": 0.0,
|
| 13 |
"hidden_size": 1024,
|
| 14 |
"id2label": {
|
| 15 |
-
"0": "
|
| 16 |
-
"1": "
|
| 17 |
-
"2": "
|
| 18 |
-
"3": "
|
| 19 |
-
"4": "
|
| 20 |
-
"5": "
|
| 21 |
-
"6": "
|
| 22 |
-
"7": "
|
| 23 |
-
"8": "
|
| 24 |
-
"9": "
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
},
|
| 26 |
"image_size": 224,
|
| 27 |
"initializer_range": 0.02,
|
| 28 |
"intermediate_size": 4096,
|
| 29 |
"label2id": {
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
},
|
| 41 |
"layer_norm_eps": 1e-12,
|
| 42 |
"model_type": "videomae",
|
|
@@ -51,5 +59,5 @@
|
|
| 51 |
"torch_dtype": "float32",
|
| 52 |
"transformers_version": "4.37.2",
|
| 53 |
"tubelet_size": 2,
|
| 54 |
-
"use_mean_pooling":
|
| 55 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "MCG-NJU/videomae-large-finetuned-kinetics",
|
| 3 |
"architectures": [
|
| 4 |
"VideoMAEForVideoClassification"
|
| 5 |
],
|
|
|
|
| 12 |
"hidden_dropout_prob": 0.0,
|
| 13 |
"hidden_size": 1024,
|
| 14 |
"id2label": {
|
| 15 |
+
"0": "climb",
|
| 16 |
+
"1": "crawl",
|
| 17 |
+
"2": "grasp",
|
| 18 |
+
"3": "hiding",
|
| 19 |
+
"4": "jump",
|
| 20 |
+
"5": "pick up",
|
| 21 |
+
"6": "pull",
|
| 22 |
+
"7": "push",
|
| 23 |
+
"8": "put down",
|
| 24 |
+
"9": "roll",
|
| 25 |
+
"10": "running",
|
| 26 |
+
"11": "slide",
|
| 27 |
+
"12": "walking",
|
| 28 |
+
"13": "zibaroon"
|
| 29 |
},
|
| 30 |
"image_size": 224,
|
| 31 |
"initializer_range": 0.02,
|
| 32 |
"intermediate_size": 4096,
|
| 33 |
"label2id": {
|
| 34 |
+
"climb": 0,
|
| 35 |
+
"crawl": 1,
|
| 36 |
+
"grasp": 2,
|
| 37 |
+
"hiding": 3,
|
| 38 |
+
"jump": 4,
|
| 39 |
+
"pick up": 5,
|
| 40 |
+
"pull": 6,
|
| 41 |
+
"push": 7,
|
| 42 |
+
"put down": 8,
|
| 43 |
+
"roll": 9,
|
| 44 |
+
"running": 10,
|
| 45 |
+
"slide": 11,
|
| 46 |
+
"walking": 12,
|
| 47 |
+
"zibaroon": 13
|
| 48 |
},
|
| 49 |
"layer_norm_eps": 1e-12,
|
| 50 |
"model_type": "videomae",
|
|
|
|
| 59 |
"torch_dtype": "float32",
|
| 60 |
"transformers_version": "4.37.2",
|
| 61 |
"tubelet_size": 2,
|
| 62 |
+
"use_mean_pooling": true
|
| 63 |
}
|
model.safetensors
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 sha256:6699c065fd187ca3510c6f854530949fe1a0fb8ca23b46262e967099572e5b07
|
| 3 |
+
size 1215545408
|
runs/Feb20_14-50-43_plan.cs.vt.edu/events.out.tfevents.1708469451.plan.cs.vt.edu.3543922.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43c0590daa12c802f4fbd7a642eff30ad07498cf04a73e68ad0e4cdc43b9b090
|
| 3 |
+
size 7974
|
runs/Feb20_14-50-43_plan.cs.vt.edu/events.out.tfevents.1708469726.plan.cs.vt.edu.3543922.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:640213db4fe4008ca9a6d4c1d31af408cabc120fa3ebfbf3c4a76e8c5d1dd81e
|
| 3 |
+
size 405
|
runs/Feb20_14-57-12_plan.cs.vt.edu/events.out.tfevents.1708469850.plan.cs.vt.edu.3569885.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1913e300bd7725c4aee313c4e56326cb9d4a41615ec5efbe09b0da162d18b2f1
|
| 3 |
+
size 17240
|
runs/Feb20_15-18-42_plan.cs.vt.edu/events.out.tfevents.1708471132.plan.cs.vt.edu.3569885.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc38f52209a4f52c900bd7c44160fcbff23ddbff1e26b0ed556fc2d5fddf1677
|
| 3 |
+
size 5098
|
runs/Feb20_15-19-55_plan.cs.vt.edu/events.out.tfevents.1708471203.plan.cs.vt.edu.3569885.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca35aa06a66c9f289a90569ddff96b03dad1b6b22a6420d6f240b3b1d611fd1c
|
| 3 |
+
size 5098
|
runs/Feb20_15-20-55_plan.cs.vt.edu/events.out.tfevents.1708471262.plan.cs.vt.edu.3569885.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dcc59d8afec032a73bdb632bc6e6f9c61d89c3a486377592935e9fe4883539d
|
| 3 |
+
size 5038
|
runs/Feb20_15-21-34_plan.cs.vt.edu/events.out.tfevents.1708471299.plan.cs.vt.edu.3569885.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e05a10eb291cc84cc4f4f52a7416f14c55b419548fcaa661a215f09e5eef7812
|
| 3 |
+
size 20198
|
runs/Feb20_15-49-17_plan.cs.vt.edu/events.out.tfevents.1708472959.plan.cs.vt.edu.3697382.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10957846cb7f2c0af0a8d18d5d4ab869cbf591c8ffdf139c94245aedd7c9890e
|
| 3 |
+
size 5067
|
runs/Feb20_15-52-57_plan.cs.vt.edu/events.out.tfevents.1708473184.plan.cs.vt.edu.3697382.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81f27ba231d80a65a24706a979eb5aa9d852449ce9f2006225e11f27555e1a08
|
| 3 |
+
size 5116
|
runs/Feb20_15-54-37_plan.cs.vt.edu/events.out.tfevents.1708473283.plan.cs.vt.edu.3697382.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d56fd9a2804f59e4f63066b24e75f61b1fe8357335f9676c8c70844feab690a4
|
| 3 |
+
size 22531
|
runs/Feb20_16-41-48_plan.cs.vt.edu/events.out.tfevents.1708476123.plan.cs.vt.edu.3697382.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d56bfc0cf7cf6a99eeb5ad550b898600384890e08744f468c2f7bc6b7f16236d
|
| 3 |
+
size 346
|
runs/Feb20_16-42-29_plan.cs.vt.edu/events.out.tfevents.1708476167.plan.cs.vt.edu.3697382.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0634219e6e9c583cb9b2d9ba2dab584bb8ab664f632d8c3d77360468e86b8f07
|
| 3 |
+
size 15172
|
runs/Feb20_16-49-13_plan.cs.vt.edu/events.out.tfevents.1708476554.plan.cs.vt.edu.3697382.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d2268931e4164e0e77e63e1c142777578c78de76043e1a2b93ba2742272cb3a
|
| 3 |
+
size 5068
|
runs/Feb20_16-49-46_plan.cs.vt.edu/events.out.tfevents.1708476591.plan.cs.vt.edu.3697382.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f046b4a37f5f59784fd5f956981984eb5c3f9442da4a05ba47ea603f6be6f774
|
| 3 |
+
size 22532
|
runs/Feb20_16-49-46_plan.cs.vt.edu/events.out.tfevents.1708477852.plan.cs.vt.edu.3697382.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58f713a0ad5eb7c555067fef62196245e31bb4a68d52309b425b41bddbf23130
|
| 3 |
+
size 734
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 31.01,
|
| 3 |
+
"eval_accuracy": 0.42857142857142855,
|
| 4 |
+
"eval_loss": 1.504156231880188,
|
| 5 |
+
"eval_runtime": 2.2938,
|
| 6 |
+
"eval_samples_per_second": 6.104,
|
| 7 |
+
"eval_steps_per_second": 0.436
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,498 +1,600 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "MCG-NJU/videomae-large/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"learning_rate": 1.
|
| 14 |
-
"loss": 2.
|
| 15 |
-
"step":
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.03,
|
| 19 |
-
"eval_accuracy": 0.
|
| 20 |
-
"eval_loss": 2.
|
| 21 |
-
"eval_runtime": 5.
|
| 22 |
-
"eval_samples_per_second":
|
| 23 |
-
"eval_steps_per_second": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 1.03,
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
"
|
|
|
|
|
|
|
|
|
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch":
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"eval_samples_per_second": 11.18,
|
| 38 |
-
"eval_steps_per_second": 0.479,
|
| 39 |
-
"step": 20
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 2.03,
|
| 43 |
-
"learning_rate":
|
| 44 |
-
"loss":
|
| 45 |
-
"step":
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 2.03,
|
| 49 |
-
"eval_accuracy": 0.
|
| 50 |
-
"eval_loss":
|
| 51 |
-
"eval_runtime":
|
| 52 |
-
"eval_samples_per_second":
|
| 53 |
-
"eval_steps_per_second": 0.
|
| 54 |
-
"step":
|
| 55 |
},
|
| 56 |
{
|
| 57 |
-
"epoch": 3.
|
| 58 |
-
"learning_rate": 4.
|
| 59 |
-
"loss":
|
| 60 |
-
"step":
|
| 61 |
},
|
| 62 |
{
|
| 63 |
"epoch": 3.03,
|
| 64 |
-
"eval_accuracy": 0.
|
| 65 |
-
"eval_loss":
|
| 66 |
-
"eval_runtime": 5.
|
| 67 |
-
"eval_samples_per_second":
|
| 68 |
-
"eval_steps_per_second": 0.
|
| 69 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 4.03,
|
| 73 |
-
"learning_rate": 4.
|
| 74 |
-
"loss":
|
| 75 |
-
"step":
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 4.03,
|
| 79 |
-
"eval_accuracy": 0.
|
| 80 |
-
"eval_loss":
|
| 81 |
-
"eval_runtime": 6.
|
| 82 |
-
"eval_samples_per_second":
|
| 83 |
-
"eval_steps_per_second": 0.
|
| 84 |
-
"step":
|
| 85 |
},
|
| 86 |
{
|
| 87 |
-
"epoch": 5.
|
| 88 |
-
"learning_rate": 4.
|
| 89 |
-
"loss":
|
| 90 |
-
"step":
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 5.03,
|
| 94 |
-
"eval_accuracy": 0.
|
| 95 |
-
"eval_loss":
|
| 96 |
-
"eval_runtime":
|
| 97 |
-
"eval_samples_per_second":
|
| 98 |
-
"eval_steps_per_second": 0.
|
| 99 |
-
"step":
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch": 6.
|
| 103 |
-
"learning_rate": 4.
|
| 104 |
-
"loss":
|
| 105 |
-
"step":
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 6.03,
|
| 109 |
-
"eval_accuracy": 0.
|
| 110 |
-
"eval_loss":
|
| 111 |
-
"eval_runtime": 5.
|
| 112 |
-
"eval_samples_per_second":
|
| 113 |
-
"eval_steps_per_second": 0.
|
| 114 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 7.03,
|
| 118 |
-
"learning_rate": 4.
|
| 119 |
-
"loss": 0.
|
| 120 |
-
"step":
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 7.03,
|
| 124 |
-
"eval_accuracy": 0.
|
| 125 |
-
"eval_loss":
|
| 126 |
-
"eval_runtime": 5.
|
| 127 |
-
"eval_samples_per_second":
|
| 128 |
-
"eval_steps_per_second": 0.
|
| 129 |
-
"step":
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 8.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
-
"step":
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 8.03,
|
| 139 |
-
"eval_accuracy": 0.
|
| 140 |
-
"eval_loss":
|
| 141 |
-
"eval_runtime":
|
| 142 |
-
"eval_samples_per_second":
|
| 143 |
-
"eval_steps_per_second": 0.
|
| 144 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 9.03,
|
| 148 |
-
"learning_rate": 3.
|
| 149 |
-
"loss": 0.
|
| 150 |
-
"step":
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 9.03,
|
| 154 |
-
"eval_accuracy": 0.
|
| 155 |
-
"eval_loss":
|
| 156 |
-
"eval_runtime": 6.
|
| 157 |
-
"eval_samples_per_second":
|
| 158 |
-
"eval_steps_per_second": 0.
|
| 159 |
-
"step":
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 10.
|
| 163 |
-
"learning_rate": 3.
|
| 164 |
-
"loss": 0.
|
| 165 |
-
"step":
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 10.03,
|
| 169 |
-
"eval_accuracy": 0.
|
| 170 |
-
"eval_loss":
|
| 171 |
-
"eval_runtime":
|
| 172 |
-
"eval_samples_per_second":
|
| 173 |
-
"eval_steps_per_second": 0.
|
| 174 |
-
"step":
|
| 175 |
},
|
| 176 |
{
|
| 177 |
-
"epoch": 11.
|
| 178 |
-
"learning_rate": 3.
|
| 179 |
-
"loss": 0.
|
| 180 |
-
"step":
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 11.03,
|
| 184 |
-
"eval_accuracy": 0.
|
| 185 |
-
"eval_loss":
|
| 186 |
-
"eval_runtime": 5.
|
| 187 |
-
"eval_samples_per_second":
|
| 188 |
-
"eval_steps_per_second": 0.
|
| 189 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 12.03,
|
| 193 |
-
"learning_rate": 3.
|
| 194 |
-
"loss": 0.
|
| 195 |
-
"step":
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 12.03,
|
| 199 |
-
"eval_accuracy":
|
| 200 |
-
"eval_loss":
|
| 201 |
-
"eval_runtime": 5.
|
| 202 |
-
"eval_samples_per_second":
|
| 203 |
-
"eval_steps_per_second": 0.
|
| 204 |
-
"step":
|
| 205 |
},
|
| 206 |
{
|
| 207 |
-
"epoch": 13.
|
| 208 |
-
"learning_rate":
|
| 209 |
-
"loss": 0.
|
| 210 |
-
"step":
|
| 211 |
},
|
| 212 |
{
|
| 213 |
"epoch": 13.03,
|
| 214 |
-
"eval_accuracy": 0.
|
| 215 |
-
"eval_loss":
|
| 216 |
-
"eval_runtime":
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second": 0.
|
| 219 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 14.03,
|
| 223 |
-
"learning_rate": 2.
|
| 224 |
-
"loss": 0.
|
| 225 |
-
"step":
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 14.03,
|
| 229 |
-
"eval_accuracy":
|
| 230 |
-
"eval_loss":
|
| 231 |
-
"eval_runtime":
|
| 232 |
-
"eval_samples_per_second":
|
| 233 |
-
"eval_steps_per_second": 0.
|
| 234 |
-
"step":
|
| 235 |
},
|
| 236 |
{
|
| 237 |
-
"epoch": 15.
|
| 238 |
-
"learning_rate": 2.
|
| 239 |
-
"loss": 0.
|
| 240 |
-
"step":
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 15.03,
|
| 244 |
-
"eval_accuracy":
|
| 245 |
-
"eval_loss":
|
| 246 |
-
"eval_runtime": 5.
|
| 247 |
-
"eval_samples_per_second":
|
| 248 |
-
"eval_steps_per_second": 0.
|
| 249 |
-
"step":
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch": 16.
|
| 253 |
-
"learning_rate": 2.
|
| 254 |
-
"loss": 0.
|
| 255 |
-
"step":
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 16.03,
|
| 259 |
-
"eval_accuracy":
|
| 260 |
-
"eval_loss":
|
| 261 |
-
"eval_runtime": 5.
|
| 262 |
-
"eval_samples_per_second":
|
| 263 |
-
"eval_steps_per_second": 0.
|
| 264 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 17.03,
|
| 268 |
-
"learning_rate": 2.
|
| 269 |
-
"loss": 0.
|
| 270 |
-
"step":
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 17.03,
|
| 274 |
-
"eval_accuracy":
|
| 275 |
-
"eval_loss":
|
| 276 |
-
"eval_runtime":
|
| 277 |
-
"eval_samples_per_second":
|
| 278 |
-
"eval_steps_per_second": 0.
|
| 279 |
-
"step":
|
| 280 |
},
|
| 281 |
{
|
| 282 |
-
"epoch": 18.
|
| 283 |
-
"learning_rate": 2.
|
| 284 |
-
"loss": 0.
|
| 285 |
-
"step":
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 18.03,
|
| 289 |
-
"eval_accuracy": 0.
|
| 290 |
-
"eval_loss":
|
| 291 |
-
"eval_runtime": 5.
|
| 292 |
-
"eval_samples_per_second":
|
| 293 |
-
"eval_steps_per_second": 0.
|
| 294 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 19.03,
|
| 298 |
-
"learning_rate":
|
| 299 |
-
"loss": 0.
|
| 300 |
-
"step":
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 19.03,
|
| 304 |
-
"eval_accuracy": 0.
|
| 305 |
-
"eval_loss":
|
| 306 |
-
"eval_runtime": 5.
|
| 307 |
-
"eval_samples_per_second":
|
| 308 |
-
"eval_steps_per_second": 0.
|
| 309 |
-
"step":
|
| 310 |
},
|
| 311 |
{
|
| 312 |
-
"epoch": 20.
|
| 313 |
-
"learning_rate": 1.
|
| 314 |
-
"loss": 0.
|
| 315 |
-
"step":
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 20.03,
|
| 319 |
-
"eval_accuracy":
|
| 320 |
-
"eval_loss":
|
| 321 |
-
"eval_runtime": 5.
|
| 322 |
-
"eval_samples_per_second":
|
| 323 |
-
"eval_steps_per_second": 0.
|
| 324 |
-
"step":
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch": 21.
|
| 328 |
-
"learning_rate": 1.
|
| 329 |
-
"loss": 0.
|
| 330 |
-
"step":
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 21.03,
|
| 334 |
-
"eval_accuracy":
|
| 335 |
-
"eval_loss":
|
| 336 |
-
"eval_runtime":
|
| 337 |
-
"eval_samples_per_second":
|
| 338 |
-
"eval_steps_per_second": 0.
|
| 339 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 22.03,
|
| 343 |
-
"learning_rate": 1.
|
| 344 |
-
"loss": 0.
|
| 345 |
-
"step":
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 22.03,
|
| 349 |
-
"eval_accuracy":
|
| 350 |
-
"eval_loss":
|
| 351 |
-
"eval_runtime": 5.
|
| 352 |
-
"eval_samples_per_second":
|
| 353 |
-
"eval_steps_per_second": 0.
|
| 354 |
-
"step":
|
| 355 |
},
|
| 356 |
{
|
| 357 |
-
"epoch": 23.
|
| 358 |
-
"learning_rate": 1.
|
| 359 |
-
"loss": 0.
|
| 360 |
-
"step":
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 23.03,
|
| 364 |
-
"eval_accuracy":
|
| 365 |
-
"eval_loss":
|
| 366 |
-
"eval_runtime":
|
| 367 |
-
"eval_samples_per_second":
|
| 368 |
-
"eval_steps_per_second": 0.
|
| 369 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 24.03,
|
| 373 |
-
"learning_rate":
|
| 374 |
-
"loss": 0.
|
| 375 |
-
"step":
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 24.03,
|
| 379 |
-
"eval_accuracy":
|
| 380 |
-
"eval_loss":
|
| 381 |
-
"eval_runtime":
|
| 382 |
-
"eval_samples_per_second":
|
| 383 |
-
"eval_steps_per_second": 0.
|
| 384 |
-
"step":
|
| 385 |
},
|
| 386 |
{
|
| 387 |
-
"epoch": 25.
|
| 388 |
-
"learning_rate":
|
| 389 |
-
"loss": 0.
|
| 390 |
-
"step":
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 25.03,
|
| 394 |
-
"eval_accuracy":
|
| 395 |
-
"eval_loss":
|
| 396 |
-
"eval_runtime": 5.
|
| 397 |
-
"eval_samples_per_second":
|
| 398 |
-
"eval_steps_per_second": 0.
|
| 399 |
-
"step":
|
| 400 |
},
|
| 401 |
{
|
| 402 |
-
"epoch": 26.
|
| 403 |
-
"learning_rate":
|
| 404 |
-
"loss": 0.
|
| 405 |
-
"step":
|
| 406 |
},
|
| 407 |
{
|
| 408 |
"epoch": 26.03,
|
| 409 |
-
"eval_accuracy":
|
| 410 |
-
"eval_loss":
|
| 411 |
-
"eval_runtime": 5.
|
| 412 |
-
"eval_samples_per_second":
|
| 413 |
-
"eval_steps_per_second": 0.
|
| 414 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 27.03,
|
| 418 |
-
"learning_rate":
|
| 419 |
-
"loss": 0.
|
| 420 |
-
"step":
|
| 421 |
},
|
| 422 |
{
|
| 423 |
"epoch": 27.03,
|
| 424 |
-
"eval_accuracy":
|
| 425 |
-
"eval_loss":
|
| 426 |
-
"eval_runtime": 5.
|
| 427 |
-
"eval_samples_per_second":
|
| 428 |
-
"eval_steps_per_second": 0.
|
| 429 |
-
"step":
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 28.
|
| 433 |
-
"learning_rate":
|
| 434 |
-
"loss": 0.
|
| 435 |
-
"step":
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 28.03,
|
| 439 |
-
"eval_accuracy":
|
| 440 |
-
"eval_loss":
|
| 441 |
-
"eval_runtime": 5.
|
| 442 |
-
"eval_samples_per_second":
|
| 443 |
-
"eval_steps_per_second": 0.
|
| 444 |
-
"step":
|
| 445 |
},
|
| 446 |
{
|
| 447 |
-
"epoch": 29.
|
| 448 |
-
"learning_rate":
|
| 449 |
-
"loss": 0.
|
| 450 |
-
"step":
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"epoch": 29.03,
|
| 454 |
-
"
|
| 455 |
-
"
|
| 456 |
-
"
|
| 457 |
-
"eval_samples_per_second": 11.447,
|
| 458 |
-
"eval_steps_per_second": 0.491,
|
| 459 |
-
"step": 300
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 29.03,
|
| 463 |
-
"
|
| 464 |
-
"
|
| 465 |
-
"
|
| 466 |
-
"
|
| 467 |
-
"
|
| 468 |
-
"
|
| 469 |
},
|
| 470 |
{
|
| 471 |
-
"epoch":
|
| 472 |
-
"
|
| 473 |
-
"
|
| 474 |
-
"
|
| 475 |
-
"eval_samples_per_second": 9.208,
|
| 476 |
-
"eval_steps_per_second": 0.297,
|
| 477 |
-
"step": 300
|
| 478 |
},
|
| 479 |
{
|
| 480 |
-
"epoch":
|
| 481 |
-
"eval_accuracy": 0.
|
| 482 |
-
"eval_loss":
|
| 483 |
-
"eval_runtime":
|
| 484 |
-
"eval_samples_per_second":
|
| 485 |
-
"eval_steps_per_second": 0.
|
| 486 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 487 |
}
|
| 488 |
],
|
| 489 |
-
"logging_steps":
|
| 490 |
-
"max_steps":
|
| 491 |
"num_input_tokens_seen": 0,
|
| 492 |
"num_train_epochs": 9223372036854775807,
|
| 493 |
"save_steps": 500,
|
| 494 |
-
"total_flos":
|
| 495 |
-
"train_batch_size":
|
| 496 |
"trial_name": null,
|
| 497 |
"trial_params": null
|
| 498 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5666666666666667,
|
| 3 |
+
"best_model_checkpoint": "MCG-NJU/videomae-large/checkpoint-140",
|
| 4 |
+
"epoch": 31.013636363636362,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 220,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 14 |
+
"loss": 2.6619,
|
| 15 |
+
"step": 5
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.03,
|
| 19 |
+
"eval_accuracy": 0.0,
|
| 20 |
+
"eval_loss": 2.7016749382019043,
|
| 21 |
+
"eval_runtime": 5.569,
|
| 22 |
+
"eval_samples_per_second": 5.387,
|
| 23 |
+
"eval_steps_per_second": 0.359,
|
| 24 |
+
"step": 7
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.01,
|
| 28 |
+
"learning_rate": 2.272727272727273e-05,
|
| 29 |
+
"loss": 2.6232,
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 1.03,
|
| 34 |
+
"eval_accuracy": 0.0,
|
| 35 |
+
"eval_loss": 2.6628258228302,
|
| 36 |
+
"eval_runtime": 5.363,
|
| 37 |
+
"eval_samples_per_second": 5.594,
|
| 38 |
+
"eval_steps_per_second": 0.373,
|
| 39 |
+
"step": 14
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"learning_rate": 3.409090909090909e-05,
|
| 44 |
+
"loss": 2.5419,
|
| 45 |
+
"step": 15
|
|
|
|
|
|
|
|
|
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 2.03,
|
| 49 |
+
"learning_rate": 4.545454545454546e-05,
|
| 50 |
+
"loss": 2.381,
|
| 51 |
+
"step": 20
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 2.03,
|
| 55 |
+
"eval_accuracy": 0.16666666666666666,
|
| 56 |
+
"eval_loss": 2.5797576904296875,
|
| 57 |
+
"eval_runtime": 5.6099,
|
| 58 |
+
"eval_samples_per_second": 5.348,
|
| 59 |
+
"eval_steps_per_second": 0.357,
|
| 60 |
+
"step": 21
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"epoch": 3.02,
|
| 64 |
+
"learning_rate": 4.9242424242424245e-05,
|
| 65 |
+
"loss": 2.2215,
|
| 66 |
+
"step": 25
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 3.03,
|
| 70 |
+
"eval_accuracy": 0.16666666666666666,
|
| 71 |
+
"eval_loss": 2.4757392406463623,
|
| 72 |
+
"eval_runtime": 5.5008,
|
| 73 |
+
"eval_samples_per_second": 5.454,
|
| 74 |
+
"eval_steps_per_second": 0.364,
|
| 75 |
+
"step": 28
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 4.01,
|
| 79 |
+
"learning_rate": 4.797979797979798e-05,
|
| 80 |
+
"loss": 1.8738,
|
| 81 |
+
"step": 30
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 4.03,
|
| 85 |
+
"learning_rate": 4.671717171717172e-05,
|
| 86 |
+
"loss": 1.7389,
|
| 87 |
+
"step": 35
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 4.03,
|
| 91 |
+
"eval_accuracy": 0.23333333333333334,
|
| 92 |
+
"eval_loss": 2.363579511642456,
|
| 93 |
+
"eval_runtime": 6.4613,
|
| 94 |
+
"eval_samples_per_second": 4.643,
|
| 95 |
+
"eval_steps_per_second": 0.31,
|
| 96 |
+
"step": 35
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"epoch": 5.02,
|
| 100 |
+
"learning_rate": 4.545454545454546e-05,
|
| 101 |
+
"loss": 1.3366,
|
| 102 |
+
"step": 40
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 5.03,
|
| 106 |
+
"eval_accuracy": 0.3,
|
| 107 |
+
"eval_loss": 2.2424137592315674,
|
| 108 |
+
"eval_runtime": 5.7626,
|
| 109 |
+
"eval_samples_per_second": 5.206,
|
| 110 |
+
"eval_steps_per_second": 0.347,
|
| 111 |
+
"step": 42
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 6.01,
|
| 115 |
+
"learning_rate": 4.41919191919192e-05,
|
| 116 |
+
"loss": 1.1946,
|
| 117 |
+
"step": 45
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 6.03,
|
| 121 |
+
"eval_accuracy": 0.3,
|
| 122 |
+
"eval_loss": 2.167524814605713,
|
| 123 |
+
"eval_runtime": 5.8137,
|
| 124 |
+
"eval_samples_per_second": 5.16,
|
| 125 |
+
"eval_steps_per_second": 0.344,
|
| 126 |
+
"step": 49
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 7.0,
|
| 130 |
+
"learning_rate": 4.292929292929293e-05,
|
| 131 |
+
"loss": 0.8832,
|
| 132 |
+
"step": 50
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 7.03,
|
| 136 |
+
"learning_rate": 4.166666666666667e-05,
|
| 137 |
+
"loss": 0.6809,
|
| 138 |
+
"step": 55
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 7.03,
|
| 142 |
+
"eval_accuracy": 0.36666666666666664,
|
| 143 |
+
"eval_loss": 2.0548174381256104,
|
| 144 |
+
"eval_runtime": 5.6032,
|
| 145 |
+
"eval_samples_per_second": 5.354,
|
| 146 |
+
"eval_steps_per_second": 0.357,
|
| 147 |
+
"step": 56
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 8.02,
|
| 151 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 152 |
+
"loss": 0.5255,
|
| 153 |
+
"step": 60
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 8.03,
|
| 157 |
+
"eval_accuracy": 0.4,
|
| 158 |
+
"eval_loss": 2.0410492420196533,
|
| 159 |
+
"eval_runtime": 5.8803,
|
| 160 |
+
"eval_samples_per_second": 5.102,
|
| 161 |
+
"eval_steps_per_second": 0.34,
|
| 162 |
+
"step": 63
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 9.01,
|
| 166 |
+
"learning_rate": 3.9141414141414145e-05,
|
| 167 |
+
"loss": 0.4759,
|
| 168 |
+
"step": 65
|
| 169 |
},
|
| 170 |
{
|
| 171 |
"epoch": 9.03,
|
| 172 |
+
"learning_rate": 3.787878787878788e-05,
|
| 173 |
+
"loss": 0.3285,
|
| 174 |
+
"step": 70
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 9.03,
|
| 178 |
+
"eval_accuracy": 0.4,
|
| 179 |
+
"eval_loss": 1.9539462327957153,
|
| 180 |
+
"eval_runtime": 6.0204,
|
| 181 |
+
"eval_samples_per_second": 4.983,
|
| 182 |
+
"eval_steps_per_second": 0.332,
|
| 183 |
+
"step": 70
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 10.02,
|
| 187 |
+
"learning_rate": 3.661616161616162e-05,
|
| 188 |
+
"loss": 0.2849,
|
| 189 |
+
"step": 75
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 10.03,
|
| 193 |
+
"eval_accuracy": 0.4666666666666667,
|
| 194 |
+
"eval_loss": 1.8536347150802612,
|
| 195 |
+
"eval_runtime": 5.2379,
|
| 196 |
+
"eval_samples_per_second": 5.727,
|
| 197 |
+
"eval_steps_per_second": 0.382,
|
| 198 |
+
"step": 77
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 11.01,
|
| 202 |
+
"learning_rate": 3.535353535353535e-05,
|
| 203 |
+
"loss": 0.1832,
|
| 204 |
+
"step": 80
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 11.03,
|
| 208 |
+
"eval_accuracy": 0.43333333333333335,
|
| 209 |
+
"eval_loss": 1.8293204307556152,
|
| 210 |
+
"eval_runtime": 5.7575,
|
| 211 |
+
"eval_samples_per_second": 5.211,
|
| 212 |
+
"eval_steps_per_second": 0.347,
|
| 213 |
+
"step": 84
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 12.0,
|
| 217 |
+
"learning_rate": 3.409090909090909e-05,
|
| 218 |
+
"loss": 0.1485,
|
| 219 |
+
"step": 85
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 12.03,
|
| 223 |
+
"learning_rate": 3.282828282828283e-05,
|
| 224 |
+
"loss": 0.1307,
|
| 225 |
+
"step": 90
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 12.03,
|
| 229 |
+
"eval_accuracy": 0.4,
|
| 230 |
+
"eval_loss": 1.8200174570083618,
|
| 231 |
+
"eval_runtime": 5.6546,
|
| 232 |
+
"eval_samples_per_second": 5.305,
|
| 233 |
+
"eval_steps_per_second": 0.354,
|
| 234 |
+
"step": 91
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 13.02,
|
| 238 |
+
"learning_rate": 3.1565656565656566e-05,
|
| 239 |
+
"loss": 0.0901,
|
| 240 |
+
"step": 95
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 13.03,
|
| 244 |
+
"eval_accuracy": 0.4,
|
| 245 |
+
"eval_loss": 1.8354666233062744,
|
| 246 |
+
"eval_runtime": 5.7638,
|
| 247 |
+
"eval_samples_per_second": 5.205,
|
| 248 |
+
"eval_steps_per_second": 0.347,
|
| 249 |
+
"step": 98
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 14.01,
|
| 253 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 254 |
+
"loss": 0.0757,
|
| 255 |
+
"step": 100
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 14.03,
|
| 259 |
+
"learning_rate": 2.904040404040404e-05,
|
| 260 |
+
"loss": 0.0636,
|
| 261 |
+
"step": 105
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 14.03,
|
| 265 |
+
"eval_accuracy": 0.43333333333333335,
|
| 266 |
+
"eval_loss": 1.8200985193252563,
|
| 267 |
+
"eval_runtime": 5.0989,
|
| 268 |
+
"eval_samples_per_second": 5.884,
|
| 269 |
+
"eval_steps_per_second": 0.392,
|
| 270 |
+
"step": 105
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"epoch": 15.02,
|
| 274 |
+
"learning_rate": 2.777777777777778e-05,
|
| 275 |
+
"loss": 0.0413,
|
| 276 |
+
"step": 110
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 15.03,
|
| 280 |
+
"eval_accuracy": 0.4666666666666667,
|
| 281 |
+
"eval_loss": 1.7749541997909546,
|
| 282 |
+
"eval_runtime": 5.2291,
|
| 283 |
+
"eval_samples_per_second": 5.737,
|
| 284 |
+
"eval_steps_per_second": 0.382,
|
| 285 |
+
"step": 112
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 16.01,
|
| 289 |
+
"learning_rate": 2.6515151515151516e-05,
|
| 290 |
+
"loss": 0.0427,
|
| 291 |
+
"step": 115
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 16.03,
|
| 295 |
+
"eval_accuracy": 0.5333333333333333,
|
| 296 |
+
"eval_loss": 1.745997667312622,
|
| 297 |
+
"eval_runtime": 5.2765,
|
| 298 |
+
"eval_samples_per_second": 5.686,
|
| 299 |
+
"eval_steps_per_second": 0.379,
|
| 300 |
+
"step": 119
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 17.0,
|
| 304 |
+
"learning_rate": 2.5252525252525256e-05,
|
| 305 |
+
"loss": 0.0369,
|
| 306 |
+
"step": 120
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 17.03,
|
| 310 |
+
"learning_rate": 2.398989898989899e-05,
|
| 311 |
+
"loss": 0.0254,
|
| 312 |
+
"step": 125
|
| 313 |
},
|
| 314 |
{
|
| 315 |
"epoch": 17.03,
|
| 316 |
+
"eval_accuracy": 0.5333333333333333,
|
| 317 |
+
"eval_loss": 1.7804018259048462,
|
| 318 |
+
"eval_runtime": 5.5848,
|
| 319 |
+
"eval_samples_per_second": 5.372,
|
| 320 |
+
"eval_steps_per_second": 0.358,
|
| 321 |
+
"step": 126
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 18.02,
|
| 325 |
+
"learning_rate": 2.272727272727273e-05,
|
| 326 |
+
"loss": 0.0203,
|
| 327 |
+
"step": 130
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 18.03,
|
| 331 |
+
"eval_accuracy": 0.43333333333333335,
|
| 332 |
+
"eval_loss": 1.8868685960769653,
|
| 333 |
+
"eval_runtime": 5.6579,
|
| 334 |
+
"eval_samples_per_second": 5.302,
|
| 335 |
+
"eval_steps_per_second": 0.353,
|
| 336 |
+
"step": 133
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 19.01,
|
| 340 |
+
"learning_rate": 2.1464646464646466e-05,
|
| 341 |
+
"loss": 0.0231,
|
| 342 |
+
"step": 135
|
| 343 |
},
|
| 344 |
{
|
| 345 |
"epoch": 19.03,
|
| 346 |
+
"learning_rate": 2.0202020202020203e-05,
|
| 347 |
+
"loss": 0.0174,
|
| 348 |
+
"step": 140
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 19.03,
|
| 352 |
+
"eval_accuracy": 0.5666666666666667,
|
| 353 |
+
"eval_loss": 1.7740839719772339,
|
| 354 |
+
"eval_runtime": 5.4112,
|
| 355 |
+
"eval_samples_per_second": 5.544,
|
| 356 |
+
"eval_steps_per_second": 0.37,
|
| 357 |
+
"step": 140
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 20.02,
|
| 361 |
+
"learning_rate": 1.893939393939394e-05,
|
| 362 |
+
"loss": 0.0154,
|
| 363 |
+
"step": 145
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 20.03,
|
| 367 |
+
"eval_accuracy": 0.5333333333333333,
|
| 368 |
+
"eval_loss": 1.7400553226470947,
|
| 369 |
+
"eval_runtime": 5.673,
|
| 370 |
+
"eval_samples_per_second": 5.288,
|
| 371 |
+
"eval_steps_per_second": 0.353,
|
| 372 |
+
"step": 147
|
| 373 |
},
|
| 374 |
{
|
| 375 |
+
"epoch": 21.01,
|
| 376 |
+
"learning_rate": 1.7676767676767676e-05,
|
| 377 |
+
"loss": 0.0136,
|
| 378 |
+
"step": 150
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 21.03,
|
| 382 |
+
"eval_accuracy": 0.5,
|
| 383 |
+
"eval_loss": 1.7672396898269653,
|
| 384 |
+
"eval_runtime": 5.5489,
|
| 385 |
+
"eval_samples_per_second": 5.406,
|
| 386 |
+
"eval_steps_per_second": 0.36,
|
| 387 |
+
"step": 154
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 22.0,
|
| 391 |
+
"learning_rate": 1.6414141414141416e-05,
|
| 392 |
+
"loss": 0.0123,
|
| 393 |
+
"step": 155
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 22.03,
|
| 397 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 398 |
+
"loss": 0.0116,
|
| 399 |
+
"step": 160
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 22.03,
|
| 403 |
+
"eval_accuracy": 0.5333333333333333,
|
| 404 |
+
"eval_loss": 1.7792834043502808,
|
| 405 |
+
"eval_runtime": 5.7051,
|
| 406 |
+
"eval_samples_per_second": 5.258,
|
| 407 |
+
"eval_steps_per_second": 0.351,
|
| 408 |
+
"step": 161
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 23.02,
|
| 412 |
+
"learning_rate": 1.388888888888889e-05,
|
| 413 |
+
"loss": 0.0123,
|
| 414 |
+
"step": 165
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 23.03,
|
| 418 |
+
"eval_accuracy": 0.4666666666666667,
|
| 419 |
+
"eval_loss": 1.8018161058425903,
|
| 420 |
+
"eval_runtime": 5.5773,
|
| 421 |
+
"eval_samples_per_second": 5.379,
|
| 422 |
+
"eval_steps_per_second": 0.359,
|
| 423 |
+
"step": 168
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 24.01,
|
| 427 |
+
"learning_rate": 1.2626262626262628e-05,
|
| 428 |
+
"loss": 0.0093,
|
| 429 |
+
"step": 170
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 24.03,
|
| 433 |
+
"learning_rate": 1.1363636363636365e-05,
|
| 434 |
+
"loss": 0.0102,
|
| 435 |
+
"step": 175
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 24.03,
|
| 439 |
+
"eval_accuracy": 0.5,
|
| 440 |
+
"eval_loss": 1.8023875951766968,
|
| 441 |
+
"eval_runtime": 5.4661,
|
| 442 |
+
"eval_samples_per_second": 5.488,
|
| 443 |
+
"eval_steps_per_second": 0.366,
|
| 444 |
+
"step": 175
|
| 445 |
},
|
| 446 |
{
|
| 447 |
+
"epoch": 25.02,
|
| 448 |
+
"learning_rate": 1.0101010101010101e-05,
|
| 449 |
+
"loss": 0.0103,
|
| 450 |
+
"step": 180
|
| 451 |
},
|
| 452 |
{
|
| 453 |
"epoch": 25.03,
|
| 454 |
+
"eval_accuracy": 0.5,
|
| 455 |
+
"eval_loss": 1.8057912588119507,
|
| 456 |
+
"eval_runtime": 5.5758,
|
| 457 |
+
"eval_samples_per_second": 5.38,
|
| 458 |
+
"eval_steps_per_second": 0.359,
|
| 459 |
+
"step": 182
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 26.01,
|
| 463 |
+
"learning_rate": 8.838383838383838e-06,
|
| 464 |
+
"loss": 0.0089,
|
| 465 |
+
"step": 185
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 26.03,
|
| 469 |
+
"eval_accuracy": 0.5,
|
| 470 |
+
"eval_loss": 1.810552954673767,
|
| 471 |
+
"eval_runtime": 5.6149,
|
| 472 |
+
"eval_samples_per_second": 5.343,
|
| 473 |
+
"eval_steps_per_second": 0.356,
|
| 474 |
+
"step": 189
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 27.0,
|
| 478 |
+
"learning_rate": 7.5757575757575764e-06,
|
| 479 |
+
"loss": 0.009,
|
| 480 |
+
"step": 190
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 27.03,
|
| 484 |
+
"learning_rate": 6.313131313131314e-06,
|
| 485 |
+
"loss": 0.0088,
|
| 486 |
+
"step": 195
|
| 487 |
},
|
| 488 |
{
|
| 489 |
"epoch": 27.03,
|
| 490 |
+
"eval_accuracy": 0.5,
|
| 491 |
+
"eval_loss": 1.8028618097305298,
|
| 492 |
+
"eval_runtime": 5.3559,
|
| 493 |
+
"eval_samples_per_second": 5.601,
|
| 494 |
+
"eval_steps_per_second": 0.373,
|
| 495 |
+
"step": 196
|
| 496 |
},
|
| 497 |
{
|
| 498 |
+
"epoch": 28.02,
|
| 499 |
+
"learning_rate": 5.050505050505051e-06,
|
| 500 |
+
"loss": 0.0092,
|
| 501 |
+
"step": 200
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 28.03,
|
| 505 |
+
"eval_accuracy": 0.5,
|
| 506 |
+
"eval_loss": 1.7960565090179443,
|
| 507 |
+
"eval_runtime": 5.2538,
|
| 508 |
+
"eval_samples_per_second": 5.71,
|
| 509 |
+
"eval_steps_per_second": 0.381,
|
| 510 |
+
"step": 203
|
| 511 |
},
|
| 512 |
{
|
| 513 |
+
"epoch": 29.01,
|
| 514 |
+
"learning_rate": 3.7878787878787882e-06,
|
| 515 |
+
"loss": 0.0082,
|
| 516 |
+
"step": 205
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 29.03,
|
| 520 |
+
"learning_rate": 2.5252525252525253e-06,
|
| 521 |
+
"loss": 0.0083,
|
| 522 |
+
"step": 210
|
|
|
|
|
|
|
|
|
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 29.03,
|
| 526 |
+
"eval_accuracy": 0.5,
|
| 527 |
+
"eval_loss": 1.7939893007278442,
|
| 528 |
+
"eval_runtime": 5.0992,
|
| 529 |
+
"eval_samples_per_second": 5.883,
|
| 530 |
+
"eval_steps_per_second": 0.392,
|
| 531 |
+
"step": 210
|
| 532 |
},
|
| 533 |
{
|
| 534 |
+
"epoch": 30.02,
|
| 535 |
+
"learning_rate": 1.2626262626262627e-06,
|
| 536 |
+
"loss": 0.0099,
|
| 537 |
+
"step": 215
|
|
|
|
|
|
|
|
|
|
| 538 |
},
|
| 539 |
{
|
| 540 |
+
"epoch": 30.03,
|
| 541 |
+
"eval_accuracy": 0.5,
|
| 542 |
+
"eval_loss": 1.7922049760818481,
|
| 543 |
+
"eval_runtime": 5.3556,
|
| 544 |
+
"eval_samples_per_second": 5.602,
|
| 545 |
+
"eval_steps_per_second": 0.373,
|
| 546 |
+
"step": 217
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 31.01,
|
| 550 |
+
"learning_rate": 0.0,
|
| 551 |
+
"loss": 0.0085,
|
| 552 |
+
"step": 220
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 31.01,
|
| 556 |
+
"eval_accuracy": 0.5,
|
| 557 |
+
"eval_loss": 1.7919764518737793,
|
| 558 |
+
"eval_runtime": 5.1737,
|
| 559 |
+
"eval_samples_per_second": 5.799,
|
| 560 |
+
"eval_steps_per_second": 0.387,
|
| 561 |
+
"step": 220
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 31.01,
|
| 565 |
+
"step": 220,
|
| 566 |
+
"total_flos": 1.5320910961010737e+19,
|
| 567 |
+
"train_loss": 0.5185655888847329,
|
| 568 |
+
"train_runtime": 1238.2272,
|
| 569 |
+
"train_samples_per_second": 2.843,
|
| 570 |
+
"train_steps_per_second": 0.178
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 31.01,
|
| 574 |
+
"eval_accuracy": 0.42857142857142855,
|
| 575 |
+
"eval_loss": 1.504156231880188,
|
| 576 |
+
"eval_runtime": 2.3481,
|
| 577 |
+
"eval_samples_per_second": 5.962,
|
| 578 |
+
"eval_steps_per_second": 0.426,
|
| 579 |
+
"step": 220
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 31.01,
|
| 583 |
+
"eval_accuracy": 0.42857142857142855,
|
| 584 |
+
"eval_loss": 1.504156231880188,
|
| 585 |
+
"eval_runtime": 2.2938,
|
| 586 |
+
"eval_samples_per_second": 6.104,
|
| 587 |
+
"eval_steps_per_second": 0.436,
|
| 588 |
+
"step": 220
|
| 589 |
}
|
| 590 |
],
|
| 591 |
+
"logging_steps": 5,
|
| 592 |
+
"max_steps": 220,
|
| 593 |
"num_input_tokens_seen": 0,
|
| 594 |
"num_train_epochs": 9223372036854775807,
|
| 595 |
"save_steps": 500,
|
| 596 |
+
"total_flos": 1.5320910961010737e+19,
|
| 597 |
+
"train_batch_size": 16,
|
| 598 |
"trial_name": null,
|
| 599 |
"trial_params": null
|
| 600 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c4ef8e9fe8d9207ef60f4ef95e43a78337eeb8ead430b1b5a800c027fd54c2d
|
| 3 |
size 4728
|