Upload folder using huggingface_hub
Browse files- README.md +27 -0
- checkpoint-3462/config.json +35 -0
- checkpoint-3462/model.safetensors +3 -0
- checkpoint-3462/optimizer.pt +3 -0
- checkpoint-3462/rng_state.pth +3 -0
- checkpoint-3462/scheduler.pt +3 -0
- checkpoint-3462/trainer_state.json +1013 -0
- checkpoint-3462/training_args.bin +3 -0
- config.json +35 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Apr30_11-30-35_r-abhishek-autotrain-yu8daxhp-663a5-olct4/events.out.tfevents.1714476635.r-abhishek-autotrain-yu8daxhp-663a5-olct4.150.0 +2 -2
- runs/Apr30_11-30-35_r-abhishek-autotrain-yu8daxhp-663a5-olct4/events.out.tfevents.1714477596.r-abhishek-autotrain-yu8daxhp-663a5-olct4.150.1 +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- training_params.json +28 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-regression
|
6 |
+
widget:
|
7 |
+
- text: "I love AutoTrain"
|
8 |
+
datasets:
|
9 |
+
- autotrain-m1b56-8ger6/autotrain-data
|
10 |
+
---
|
11 |
+
|
12 |
+
# Model Trained Using AutoTrain
|
13 |
+
|
14 |
+
- Problem type: Text Regression
|
15 |
+
|
16 |
+
## Validation Metrics
|
17 |
+
loss: 0.3305796980857849
|
18 |
+
|
19 |
+
mse: 0.3305796980857849
|
20 |
+
|
21 |
+
mae: 0.44259902834892273
|
22 |
+
|
23 |
+
r2: 0.7003744220771353
|
24 |
+
|
25 |
+
rmse: 0.5749605894088745
|
26 |
+
|
27 |
+
explained_variance: 0.700911283493042
|
checkpoint-3462/config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/roberta-base",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "target"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"target": 0
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-05,
|
23 |
+
"max_position_embeddings": 514,
|
24 |
+
"model_type": "roberta",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"pad_token_id": 1,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"problem_type": "regression",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.40.1",
|
32 |
+
"type_vocab_size": 1,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 50265
|
35 |
+
}
|
checkpoint-3462/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:775d65fd7488be3a614de8f7c06ab4e48f197ada2653a63cc0fbc5b2c12d4db5
|
3 |
+
size 498609748
|
checkpoint-3462/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8618b735e09b52d75a226b518f028976605ce57b2bfaf6f1516f5c6fa50fad06
|
3 |
+
size 997339386
|
checkpoint-3462/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:378fff54753e0b270452883b1f2e7eac45752acd9d0ee301b67ff6ed7b4d8a67
|
3 |
+
size 14244
|
checkpoint-3462/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3799d2969b06463edfb0d77525690e6c403209eb7f7d6bcc2471e87a5296959
|
3 |
+
size 1064
|
checkpoint-3462/trainer_state.json
ADDED
@@ -0,0 +1,1013 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3305796980857849,
|
3 |
+
"best_model_checkpoint": "autotrain-m1b56-8ger6/checkpoint-3462",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3462,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.014442518775274409,
|
13 |
+
"grad_norm": 52.66768264770508,
|
14 |
+
"learning_rate": 2.0192307692307692e-06,
|
15 |
+
"loss": 8.6614,
|
16 |
+
"step": 25
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.028885037550548817,
|
20 |
+
"grad_norm": 70.3343276977539,
|
21 |
+
"learning_rate": 4.423076923076924e-06,
|
22 |
+
"loss": 7.3266,
|
23 |
+
"step": 50
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.043327556325823226,
|
27 |
+
"grad_norm": 64.09215545654297,
|
28 |
+
"learning_rate": 6.730769230769231e-06,
|
29 |
+
"loss": 1.6514,
|
30 |
+
"step": 75
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.057770075101097634,
|
34 |
+
"grad_norm": 29.524045944213867,
|
35 |
+
"learning_rate": 9.134615384615384e-06,
|
36 |
+
"loss": 1.0548,
|
37 |
+
"step": 100
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.07221259387637204,
|
41 |
+
"grad_norm": 14.635738372802734,
|
42 |
+
"learning_rate": 1.153846153846154e-05,
|
43 |
+
"loss": 0.9082,
|
44 |
+
"step": 125
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.08665511265164645,
|
48 |
+
"grad_norm": 19.21646499633789,
|
49 |
+
"learning_rate": 1.3942307692307693e-05,
|
50 |
+
"loss": 0.5165,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.10109763142692085,
|
55 |
+
"grad_norm": 34.39830017089844,
|
56 |
+
"learning_rate": 1.6346153846153847e-05,
|
57 |
+
"loss": 0.5166,
|
58 |
+
"step": 175
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.11554015020219527,
|
62 |
+
"grad_norm": 12.46200180053711,
|
63 |
+
"learning_rate": 1.8750000000000002e-05,
|
64 |
+
"loss": 0.6898,
|
65 |
+
"step": 200
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.12998266897746968,
|
69 |
+
"grad_norm": 44.481101989746094,
|
70 |
+
"learning_rate": 2.1153846153846154e-05,
|
71 |
+
"loss": 0.5929,
|
72 |
+
"step": 225
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.14442518775274407,
|
76 |
+
"grad_norm": 14.731172561645508,
|
77 |
+
"learning_rate": 2.355769230769231e-05,
|
78 |
+
"loss": 0.5474,
|
79 |
+
"step": 250
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.1588677065280185,
|
83 |
+
"grad_norm": 27.139829635620117,
|
84 |
+
"learning_rate": 2.586538461538462e-05,
|
85 |
+
"loss": 0.7523,
|
86 |
+
"step": 275
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1733102253032929,
|
90 |
+
"grad_norm": 13.601739883422852,
|
91 |
+
"learning_rate": 2.826923076923077e-05,
|
92 |
+
"loss": 0.6244,
|
93 |
+
"step": 300
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.1877527440785673,
|
97 |
+
"grad_norm": 18.18332862854004,
|
98 |
+
"learning_rate": 3.0673076923076926e-05,
|
99 |
+
"loss": 0.618,
|
100 |
+
"step": 325
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.2021952628538417,
|
104 |
+
"grad_norm": 6.123499870300293,
|
105 |
+
"learning_rate": 3.307692307692308e-05,
|
106 |
+
"loss": 0.7482,
|
107 |
+
"step": 350
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.21663778162911612,
|
111 |
+
"grad_norm": 10.999884605407715,
|
112 |
+
"learning_rate": 3.548076923076924e-05,
|
113 |
+
"loss": 0.5383,
|
114 |
+
"step": 375
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.23108030040439054,
|
118 |
+
"grad_norm": 22.577754974365234,
|
119 |
+
"learning_rate": 3.788461538461538e-05,
|
120 |
+
"loss": 0.5854,
|
121 |
+
"step": 400
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.24552281917966493,
|
125 |
+
"grad_norm": 31.469331741333008,
|
126 |
+
"learning_rate": 4.028846153846154e-05,
|
127 |
+
"loss": 0.5403,
|
128 |
+
"step": 425
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.25996533795493937,
|
132 |
+
"grad_norm": 8.64493465423584,
|
133 |
+
"learning_rate": 4.269230769230769e-05,
|
134 |
+
"loss": 0.6795,
|
135 |
+
"step": 450
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.27440785673021373,
|
139 |
+
"grad_norm": 7.3773393630981445,
|
140 |
+
"learning_rate": 4.509615384615385e-05,
|
141 |
+
"loss": 0.5801,
|
142 |
+
"step": 475
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.28885037550548814,
|
146 |
+
"grad_norm": 11.987143516540527,
|
147 |
+
"learning_rate": 4.75e-05,
|
148 |
+
"loss": 0.508,
|
149 |
+
"step": 500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.30329289428076256,
|
153 |
+
"grad_norm": 7.039488792419434,
|
154 |
+
"learning_rate": 4.9903846153846154e-05,
|
155 |
+
"loss": 0.5415,
|
156 |
+
"step": 525
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.317735413056037,
|
160 |
+
"grad_norm": 13.371904373168945,
|
161 |
+
"learning_rate": 4.9743205649475715e-05,
|
162 |
+
"loss": 0.5646,
|
163 |
+
"step": 550
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.3321779318313114,
|
167 |
+
"grad_norm": 32.50100326538086,
|
168 |
+
"learning_rate": 4.947571153434625e-05,
|
169 |
+
"loss": 0.7043,
|
170 |
+
"step": 575
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.3466204506065858,
|
174 |
+
"grad_norm": 25.765533447265625,
|
175 |
+
"learning_rate": 4.920821741921678e-05,
|
176 |
+
"loss": 0.5854,
|
177 |
+
"step": 600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.3610629693818602,
|
181 |
+
"grad_norm": 33.29277420043945,
|
182 |
+
"learning_rate": 4.894072330408731e-05,
|
183 |
+
"loss": 0.7418,
|
184 |
+
"step": 625
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.3755054881571346,
|
188 |
+
"grad_norm": 23.995582580566406,
|
189 |
+
"learning_rate": 4.8673229188957844e-05,
|
190 |
+
"loss": 0.7084,
|
191 |
+
"step": 650
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.389948006932409,
|
195 |
+
"grad_norm": 24.641578674316406,
|
196 |
+
"learning_rate": 4.840573507382838e-05,
|
197 |
+
"loss": 0.6657,
|
198 |
+
"step": 675
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.4043905257076834,
|
202 |
+
"grad_norm": 16.46844482421875,
|
203 |
+
"learning_rate": 4.813824095869891e-05,
|
204 |
+
"loss": 0.4334,
|
205 |
+
"step": 700
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.41883304448295783,
|
209 |
+
"grad_norm": 15.955053329467773,
|
210 |
+
"learning_rate": 4.7870746843569445e-05,
|
211 |
+
"loss": 0.4989,
|
212 |
+
"step": 725
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.43327556325823224,
|
216 |
+
"grad_norm": 20.922630310058594,
|
217 |
+
"learning_rate": 4.760325272843998e-05,
|
218 |
+
"loss": 0.5395,
|
219 |
+
"step": 750
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.44771808203350666,
|
223 |
+
"grad_norm": 33.461490631103516,
|
224 |
+
"learning_rate": 4.733575861331051e-05,
|
225 |
+
"loss": 0.7912,
|
226 |
+
"step": 775
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.4621606008087811,
|
230 |
+
"grad_norm": 28.123592376708984,
|
231 |
+
"learning_rate": 4.7068264498181045e-05,
|
232 |
+
"loss": 0.7634,
|
233 |
+
"step": 800
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.47660311958405543,
|
237 |
+
"grad_norm": 6.648211479187012,
|
238 |
+
"learning_rate": 4.6800770383051574e-05,
|
239 |
+
"loss": 0.5912,
|
240 |
+
"step": 825
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.49104563835932985,
|
244 |
+
"grad_norm": 6.500886917114258,
|
245 |
+
"learning_rate": 4.653327626792211e-05,
|
246 |
+
"loss": 0.595,
|
247 |
+
"step": 850
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.5054881571346043,
|
251 |
+
"grad_norm": 17.182079315185547,
|
252 |
+
"learning_rate": 4.626578215279264e-05,
|
253 |
+
"loss": 0.6416,
|
254 |
+
"step": 875
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.5199306759098787,
|
258 |
+
"grad_norm": 20.7849063873291,
|
259 |
+
"learning_rate": 4.5998288037663175e-05,
|
260 |
+
"loss": 0.4613,
|
261 |
+
"step": 900
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.5343731946851531,
|
265 |
+
"grad_norm": 6.231338977813721,
|
266 |
+
"learning_rate": 4.5730793922533704e-05,
|
267 |
+
"loss": 0.4601,
|
268 |
+
"step": 925
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.5488157134604275,
|
272 |
+
"grad_norm": 37.750099182128906,
|
273 |
+
"learning_rate": 4.546329980740424e-05,
|
274 |
+
"loss": 0.6588,
|
275 |
+
"step": 950
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.5632582322357019,
|
279 |
+
"grad_norm": 13.106170654296875,
|
280 |
+
"learning_rate": 4.5195805692274775e-05,
|
281 |
+
"loss": 0.6352,
|
282 |
+
"step": 975
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.5777007510109763,
|
286 |
+
"grad_norm": 12.079797744750977,
|
287 |
+
"learning_rate": 4.4928311577145304e-05,
|
288 |
+
"loss": 0.6447,
|
289 |
+
"step": 1000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.5921432697862508,
|
293 |
+
"grad_norm": 14.380491256713867,
|
294 |
+
"learning_rate": 4.466081746201583e-05,
|
295 |
+
"loss": 0.4655,
|
296 |
+
"step": 1025
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.6065857885615251,
|
300 |
+
"grad_norm": 18.562135696411133,
|
301 |
+
"learning_rate": 4.4393323346886376e-05,
|
302 |
+
"loss": 0.4547,
|
303 |
+
"step": 1050
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.6210283073367996,
|
307 |
+
"grad_norm": 22.869455337524414,
|
308 |
+
"learning_rate": 4.4125829231756905e-05,
|
309 |
+
"loss": 0.5574,
|
310 |
+
"step": 1075
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.635470826112074,
|
314 |
+
"grad_norm": 15.650333404541016,
|
315 |
+
"learning_rate": 4.3858335116627433e-05,
|
316 |
+
"loss": 0.5149,
|
317 |
+
"step": 1100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.6499133448873483,
|
321 |
+
"grad_norm": 19.41951560974121,
|
322 |
+
"learning_rate": 4.359084100149797e-05,
|
323 |
+
"loss": 0.5395,
|
324 |
+
"step": 1125
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.6643558636626228,
|
328 |
+
"grad_norm": 14.825141906738281,
|
329 |
+
"learning_rate": 4.3323346886368505e-05,
|
330 |
+
"loss": 0.3763,
|
331 |
+
"step": 1150
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.6787983824378971,
|
335 |
+
"grad_norm": 10.986475944519043,
|
336 |
+
"learning_rate": 4.3055852771239034e-05,
|
337 |
+
"loss": 0.383,
|
338 |
+
"step": 1175
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.6932409012131716,
|
342 |
+
"grad_norm": 6.805363655090332,
|
343 |
+
"learning_rate": 4.278835865610957e-05,
|
344 |
+
"loss": 0.4967,
|
345 |
+
"step": 1200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.707683419988446,
|
349 |
+
"grad_norm": 9.07087230682373,
|
350 |
+
"learning_rate": 4.25208645409801e-05,
|
351 |
+
"loss": 0.4451,
|
352 |
+
"step": 1225
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.7221259387637204,
|
356 |
+
"grad_norm": 15.876053810119629,
|
357 |
+
"learning_rate": 4.2253370425850634e-05,
|
358 |
+
"loss": 0.4178,
|
359 |
+
"step": 1250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.7365684575389948,
|
363 |
+
"grad_norm": 10.015765190124512,
|
364 |
+
"learning_rate": 4.198587631072117e-05,
|
365 |
+
"loss": 0.5196,
|
366 |
+
"step": 1275
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.7510109763142692,
|
370 |
+
"grad_norm": 14.343164443969727,
|
371 |
+
"learning_rate": 4.17183821955917e-05,
|
372 |
+
"loss": 0.3987,
|
373 |
+
"step": 1300
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.7654534950895436,
|
377 |
+
"grad_norm": 7.555254936218262,
|
378 |
+
"learning_rate": 4.145088808046223e-05,
|
379 |
+
"loss": 0.4268,
|
380 |
+
"step": 1325
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.779896013864818,
|
384 |
+
"grad_norm": 19.02402114868164,
|
385 |
+
"learning_rate": 4.1183393965332764e-05,
|
386 |
+
"loss": 0.5197,
|
387 |
+
"step": 1350
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.7943385326400925,
|
391 |
+
"grad_norm": 17.702478408813477,
|
392 |
+
"learning_rate": 4.09158998502033e-05,
|
393 |
+
"loss": 0.3667,
|
394 |
+
"step": 1375
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.8087810514153668,
|
398 |
+
"grad_norm": 14.175180435180664,
|
399 |
+
"learning_rate": 4.064840573507383e-05,
|
400 |
+
"loss": 0.4353,
|
401 |
+
"step": 1400
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.8232235701906413,
|
405 |
+
"grad_norm": 11.903855323791504,
|
406 |
+
"learning_rate": 4.0380911619944364e-05,
|
407 |
+
"loss": 0.5338,
|
408 |
+
"step": 1425
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.8376660889659157,
|
412 |
+
"grad_norm": 13.651313781738281,
|
413 |
+
"learning_rate": 4.01134175048149e-05,
|
414 |
+
"loss": 0.4009,
|
415 |
+
"step": 1450
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.85210860774119,
|
419 |
+
"grad_norm": 5.367980480194092,
|
420 |
+
"learning_rate": 3.984592338968543e-05,
|
421 |
+
"loss": 0.5129,
|
422 |
+
"step": 1475
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.8665511265164645,
|
426 |
+
"grad_norm": 18.119848251342773,
|
427 |
+
"learning_rate": 3.957842927455596e-05,
|
428 |
+
"loss": 0.4251,
|
429 |
+
"step": 1500
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.8809936452917388,
|
433 |
+
"grad_norm": 8.821969032287598,
|
434 |
+
"learning_rate": 3.9310935159426494e-05,
|
435 |
+
"loss": 0.3965,
|
436 |
+
"step": 1525
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.8954361640670133,
|
440 |
+
"grad_norm": 5.4203782081604,
|
441 |
+
"learning_rate": 3.904344104429703e-05,
|
442 |
+
"loss": 0.427,
|
443 |
+
"step": 1550
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.9098786828422877,
|
447 |
+
"grad_norm": 10.101963996887207,
|
448 |
+
"learning_rate": 3.877594692916756e-05,
|
449 |
+
"loss": 0.3891,
|
450 |
+
"step": 1575
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.9243212016175621,
|
454 |
+
"grad_norm": 5.893563747406006,
|
455 |
+
"learning_rate": 3.8508452814038094e-05,
|
456 |
+
"loss": 0.4165,
|
457 |
+
"step": 1600
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.9387637203928365,
|
461 |
+
"grad_norm": 6.127294540405273,
|
462 |
+
"learning_rate": 3.8240958698908623e-05,
|
463 |
+
"loss": 0.5194,
|
464 |
+
"step": 1625
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.9532062391681109,
|
468 |
+
"grad_norm": 13.313063621520996,
|
469 |
+
"learning_rate": 3.797346458377916e-05,
|
470 |
+
"loss": 0.4108,
|
471 |
+
"step": 1650
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.9676487579433853,
|
475 |
+
"grad_norm": 14.13697624206543,
|
476 |
+
"learning_rate": 3.7705970468649695e-05,
|
477 |
+
"loss": 0.4612,
|
478 |
+
"step": 1675
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.9820912767186597,
|
482 |
+
"grad_norm": 8.540029525756836,
|
483 |
+
"learning_rate": 3.7438476353520224e-05,
|
484 |
+
"loss": 0.4081,
|
485 |
+
"step": 1700
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.9965337954939342,
|
489 |
+
"grad_norm": 15.01349925994873,
|
490 |
+
"learning_rate": 3.717098223839075e-05,
|
491 |
+
"loss": 0.4559,
|
492 |
+
"step": 1725
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 1.0,
|
496 |
+
"eval_explained_variance": 0.6565504670143127,
|
497 |
+
"eval_loss": 0.5362390279769897,
|
498 |
+
"eval_mae": 0.5734534859657288,
|
499 |
+
"eval_mse": 0.5362390279769897,
|
500 |
+
"eval_r2": 0.5139721769346014,
|
501 |
+
"eval_rmse": 0.7322834134101868,
|
502 |
+
"eval_runtime": 21.5346,
|
503 |
+
"eval_samples_per_second": 160.765,
|
504 |
+
"eval_steps_per_second": 10.077,
|
505 |
+
"step": 1731
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 1.0109763142692085,
|
509 |
+
"grad_norm": 21.412073135375977,
|
510 |
+
"learning_rate": 3.6903488123261295e-05,
|
511 |
+
"loss": 0.4508,
|
512 |
+
"step": 1750
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 1.025418833044483,
|
516 |
+
"grad_norm": 8.56926155090332,
|
517 |
+
"learning_rate": 3.6635994008131824e-05,
|
518 |
+
"loss": 0.4829,
|
519 |
+
"step": 1775
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 1.0398613518197575,
|
523 |
+
"grad_norm": 9.545137405395508,
|
524 |
+
"learning_rate": 3.6368499893002353e-05,
|
525 |
+
"loss": 0.4499,
|
526 |
+
"step": 1800
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 1.0543038705950318,
|
530 |
+
"grad_norm": 27.51245880126953,
|
531 |
+
"learning_rate": 3.610100577787289e-05,
|
532 |
+
"loss": 0.4109,
|
533 |
+
"step": 1825
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 1.0687463893703062,
|
537 |
+
"grad_norm": 12.80823802947998,
|
538 |
+
"learning_rate": 3.583351166274342e-05,
|
539 |
+
"loss": 0.3662,
|
540 |
+
"step": 1850
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 1.0831889081455806,
|
544 |
+
"grad_norm": 7.883637428283691,
|
545 |
+
"learning_rate": 3.5566017547613954e-05,
|
546 |
+
"loss": 0.4184,
|
547 |
+
"step": 1875
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 1.097631426920855,
|
551 |
+
"grad_norm": 7.406681537628174,
|
552 |
+
"learning_rate": 3.529852343248449e-05,
|
553 |
+
"loss": 0.3439,
|
554 |
+
"step": 1900
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 1.1120739456961295,
|
558 |
+
"grad_norm": 19.036779403686523,
|
559 |
+
"learning_rate": 3.503102931735502e-05,
|
560 |
+
"loss": 0.4009,
|
561 |
+
"step": 1925
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 1.1265164644714039,
|
565 |
+
"grad_norm": 8.52979850769043,
|
566 |
+
"learning_rate": 3.476353520222555e-05,
|
567 |
+
"loss": 0.4397,
|
568 |
+
"step": 1950
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 1.1409589832466782,
|
572 |
+
"grad_norm": 16.250051498413086,
|
573 |
+
"learning_rate": 3.449604108709609e-05,
|
574 |
+
"loss": 0.4651,
|
575 |
+
"step": 1975
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 1.1554015020219526,
|
579 |
+
"grad_norm": 5.9189300537109375,
|
580 |
+
"learning_rate": 3.422854697196662e-05,
|
581 |
+
"loss": 0.4419,
|
582 |
+
"step": 2000
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 1.169844020797227,
|
586 |
+
"grad_norm": 11.332290649414062,
|
587 |
+
"learning_rate": 3.396105285683715e-05,
|
588 |
+
"loss": 0.3755,
|
589 |
+
"step": 2025
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 1.1842865395725015,
|
593 |
+
"grad_norm": 9.792673110961914,
|
594 |
+
"learning_rate": 3.3693558741707684e-05,
|
595 |
+
"loss": 0.358,
|
596 |
+
"step": 2050
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 1.1987290583477759,
|
600 |
+
"grad_norm": 14.335423469543457,
|
601 |
+
"learning_rate": 3.342606462657822e-05,
|
602 |
+
"loss": 0.3512,
|
603 |
+
"step": 2075
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 1.2131715771230502,
|
607 |
+
"grad_norm": 9.749696731567383,
|
608 |
+
"learning_rate": 3.315857051144875e-05,
|
609 |
+
"loss": 0.4072,
|
610 |
+
"step": 2100
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 1.2276140958983246,
|
614 |
+
"grad_norm": 9.317971229553223,
|
615 |
+
"learning_rate": 3.2891076396319284e-05,
|
616 |
+
"loss": 0.4359,
|
617 |
+
"step": 2125
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 1.242056614673599,
|
621 |
+
"grad_norm": 14.866842269897461,
|
622 |
+
"learning_rate": 3.262358228118981e-05,
|
623 |
+
"loss": 0.4314,
|
624 |
+
"step": 2150
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 1.2564991334488735,
|
628 |
+
"grad_norm": 6.312429428100586,
|
629 |
+
"learning_rate": 3.235608816606035e-05,
|
630 |
+
"loss": 0.3819,
|
631 |
+
"step": 2175
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 1.270941652224148,
|
635 |
+
"grad_norm": 5.175512313842773,
|
636 |
+
"learning_rate": 3.208859405093088e-05,
|
637 |
+
"loss": 0.4469,
|
638 |
+
"step": 2200
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 1.2853841709994223,
|
642 |
+
"grad_norm": 16.6768856048584,
|
643 |
+
"learning_rate": 3.1821099935801414e-05,
|
644 |
+
"loss": 0.4156,
|
645 |
+
"step": 2225
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 1.2998266897746968,
|
649 |
+
"grad_norm": 5.419372081756592,
|
650 |
+
"learning_rate": 3.155360582067194e-05,
|
651 |
+
"loss": 0.3966,
|
652 |
+
"step": 2250
|
653 |
+
},
|
654 |
+
{
|
655 |
+
"epoch": 1.314269208549971,
|
656 |
+
"grad_norm": 9.6641263961792,
|
657 |
+
"learning_rate": 3.128611170554248e-05,
|
658 |
+
"loss": 0.3622,
|
659 |
+
"step": 2275
|
660 |
+
},
|
661 |
+
{
|
662 |
+
"epoch": 1.3287117273252456,
|
663 |
+
"grad_norm": 11.433446884155273,
|
664 |
+
"learning_rate": 3.1018617590413014e-05,
|
665 |
+
"loss": 0.5056,
|
666 |
+
"step": 2300
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 1.34315424610052,
|
670 |
+
"grad_norm": 8.54787540435791,
|
671 |
+
"learning_rate": 3.075112347528354e-05,
|
672 |
+
"loss": 0.3228,
|
673 |
+
"step": 2325
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 1.3575967648757943,
|
677 |
+
"grad_norm": 24.707653045654297,
|
678 |
+
"learning_rate": 3.0483629360154076e-05,
|
679 |
+
"loss": 0.3755,
|
680 |
+
"step": 2350
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 1.3720392836510689,
|
684 |
+
"grad_norm": 13.02287483215332,
|
685 |
+
"learning_rate": 3.021613524502461e-05,
|
686 |
+
"loss": 0.313,
|
687 |
+
"step": 2375
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 1.3864818024263432,
|
691 |
+
"grad_norm": 7.0347771644592285,
|
692 |
+
"learning_rate": 2.9948641129895144e-05,
|
693 |
+
"loss": 0.3618,
|
694 |
+
"step": 2400
|
695 |
+
},
|
696 |
+
{
|
697 |
+
"epoch": 1.4009243212016176,
|
698 |
+
"grad_norm": 3.799116611480713,
|
699 |
+
"learning_rate": 2.9681147014765676e-05,
|
700 |
+
"loss": 0.3338,
|
701 |
+
"step": 2425
|
702 |
+
},
|
703 |
+
{
|
704 |
+
"epoch": 1.415366839976892,
|
705 |
+
"grad_norm": 10.154156684875488,
|
706 |
+
"learning_rate": 2.941365289963621e-05,
|
707 |
+
"loss": 0.3184,
|
708 |
+
"step": 2450
|
709 |
+
},
|
710 |
+
{
|
711 |
+
"epoch": 1.4298093587521663,
|
712 |
+
"grad_norm": 22.4088191986084,
|
713 |
+
"learning_rate": 2.9146158784506744e-05,
|
714 |
+
"loss": 0.3218,
|
715 |
+
"step": 2475
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 1.4442518775274409,
|
719 |
+
"grad_norm": 5.571261405944824,
|
720 |
+
"learning_rate": 2.8878664669377277e-05,
|
721 |
+
"loss": 0.4167,
|
722 |
+
"step": 2500
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 1.4586943963027152,
|
726 |
+
"grad_norm": 10.851147651672363,
|
727 |
+
"learning_rate": 2.8611170554247806e-05,
|
728 |
+
"loss": 0.3881,
|
729 |
+
"step": 2525
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 1.4731369150779896,
|
733 |
+
"grad_norm": 30.00836181640625,
|
734 |
+
"learning_rate": 2.8343676439118338e-05,
|
735 |
+
"loss": 0.3706,
|
736 |
+
"step": 2550
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 1.487579433853264,
|
740 |
+
"grad_norm": 12.909472465515137,
|
741 |
+
"learning_rate": 2.8076182323988874e-05,
|
742 |
+
"loss": 0.4325,
|
743 |
+
"step": 2575
|
744 |
+
},
|
745 |
+
{
|
746 |
+
"epoch": 1.5020219526285383,
|
747 |
+
"grad_norm": 10.231127738952637,
|
748 |
+
"learning_rate": 2.7808688208859406e-05,
|
749 |
+
"loss": 0.3357,
|
750 |
+
"step": 2600
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"epoch": 1.516464471403813,
|
754 |
+
"grad_norm": 7.157652378082275,
|
755 |
+
"learning_rate": 2.754119409372994e-05,
|
756 |
+
"loss": 0.3927,
|
757 |
+
"step": 2625
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 1.5309069901790873,
|
761 |
+
"grad_norm": 13.10181999206543,
|
762 |
+
"learning_rate": 2.727369997860047e-05,
|
763 |
+
"loss": 0.3189,
|
764 |
+
"step": 2650
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 1.5453495089543616,
|
768 |
+
"grad_norm": 12.194095611572266,
|
769 |
+
"learning_rate": 2.7006205863471007e-05,
|
770 |
+
"loss": 0.4226,
|
771 |
+
"step": 2675
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 1.5597920277296362,
|
775 |
+
"grad_norm": 18.289899826049805,
|
776 |
+
"learning_rate": 2.673871174834154e-05,
|
777 |
+
"loss": 0.2865,
|
778 |
+
"step": 2700
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 1.5742345465049103,
|
782 |
+
"grad_norm": 4.3070068359375,
|
783 |
+
"learning_rate": 2.647121763321207e-05,
|
784 |
+
"loss": 0.3107,
|
785 |
+
"step": 2725
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 1.588677065280185,
|
789 |
+
"grad_norm": 26.21879768371582,
|
790 |
+
"learning_rate": 2.62037235180826e-05,
|
791 |
+
"loss": 0.3243,
|
792 |
+
"step": 2750
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 1.6031195840554593,
|
796 |
+
"grad_norm": 8.495038986206055,
|
797 |
+
"learning_rate": 2.593622940295314e-05,
|
798 |
+
"loss": 0.3285,
|
799 |
+
"step": 2775
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 1.6175621028307337,
|
803 |
+
"grad_norm": 17.74176788330078,
|
804 |
+
"learning_rate": 2.566873528782367e-05,
|
805 |
+
"loss": 0.3819,
|
806 |
+
"step": 2800
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 1.6320046216060082,
|
810 |
+
"grad_norm": 8.67226505279541,
|
811 |
+
"learning_rate": 2.54012411726942e-05,
|
812 |
+
"loss": 0.4388,
|
813 |
+
"step": 2825
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 1.6464471403812824,
|
817 |
+
"grad_norm": 9.305310249328613,
|
818 |
+
"learning_rate": 2.5133747057564733e-05,
|
819 |
+
"loss": 0.3801,
|
820 |
+
"step": 2850
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 1.660889659156557,
|
824 |
+
"grad_norm": 16.156944274902344,
|
825 |
+
"learning_rate": 2.4866252942435266e-05,
|
826 |
+
"loss": 0.337,
|
827 |
+
"step": 2875
|
828 |
+
},
|
829 |
+
{
|
830 |
+
"epoch": 1.6753321779318313,
|
831 |
+
"grad_norm": 18.950183868408203,
|
832 |
+
"learning_rate": 2.45987588273058e-05,
|
833 |
+
"loss": 0.3913,
|
834 |
+
"step": 2900
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 1.6897746967071057,
|
838 |
+
"grad_norm": 4.8534321784973145,
|
839 |
+
"learning_rate": 2.4331264712176334e-05,
|
840 |
+
"loss": 0.3677,
|
841 |
+
"step": 2925
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 1.7042172154823803,
|
845 |
+
"grad_norm": 7.860241413116455,
|
846 |
+
"learning_rate": 2.4063770597046866e-05,
|
847 |
+
"loss": 0.3495,
|
848 |
+
"step": 2950
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 1.7186597342576544,
|
852 |
+
"grad_norm": 10.027009010314941,
|
853 |
+
"learning_rate": 2.37962764819174e-05,
|
854 |
+
"loss": 0.3787,
|
855 |
+
"step": 2975
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 1.733102253032929,
|
859 |
+
"grad_norm": 13.39957046508789,
|
860 |
+
"learning_rate": 2.352878236678793e-05,
|
861 |
+
"loss": 0.3064,
|
862 |
+
"step": 3000
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 1.7475447718082033,
|
866 |
+
"grad_norm": 8.104743957519531,
|
867 |
+
"learning_rate": 2.3261288251658463e-05,
|
868 |
+
"loss": 0.3703,
|
869 |
+
"step": 3025
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 1.7619872905834777,
|
873 |
+
"grad_norm": 7.085102558135986,
|
874 |
+
"learning_rate": 2.2993794136529e-05,
|
875 |
+
"loss": 0.3488,
|
876 |
+
"step": 3050
|
877 |
+
},
|
878 |
+
{
|
879 |
+
"epoch": 1.7764298093587523,
|
880 |
+
"grad_norm": 8.273953437805176,
|
881 |
+
"learning_rate": 2.272630002139953e-05,
|
882 |
+
"loss": 0.3574,
|
883 |
+
"step": 3075
|
884 |
+
},
|
885 |
+
{
|
886 |
+
"epoch": 1.7908723281340264,
|
887 |
+
"grad_norm": 5.399058818817139,
|
888 |
+
"learning_rate": 2.2458805906270064e-05,
|
889 |
+
"loss": 0.3699,
|
890 |
+
"step": 3100
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 1.805314846909301,
|
894 |
+
"grad_norm": 25.818262100219727,
|
895 |
+
"learning_rate": 2.2191311791140596e-05,
|
896 |
+
"loss": 0.2714,
|
897 |
+
"step": 3125
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 1.8197573656845754,
|
901 |
+
"grad_norm": 8.441669464111328,
|
902 |
+
"learning_rate": 2.192381767601113e-05,
|
903 |
+
"loss": 0.3225,
|
904 |
+
"step": 3150
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 1.8341998844598497,
|
908 |
+
"grad_norm": 3.318145751953125,
|
909 |
+
"learning_rate": 2.165632356088166e-05,
|
910 |
+
"loss": 0.3359,
|
911 |
+
"step": 3175
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 1.8486424032351243,
|
915 |
+
"grad_norm": 3.700218439102173,
|
916 |
+
"learning_rate": 2.1388829445752197e-05,
|
917 |
+
"loss": 0.3138,
|
918 |
+
"step": 3200
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"epoch": 1.8630849220103987,
|
922 |
+
"grad_norm": 4.9609246253967285,
|
923 |
+
"learning_rate": 2.1121335330622726e-05,
|
924 |
+
"loss": 0.3429,
|
925 |
+
"step": 3225
|
926 |
+
},
|
927 |
+
{
|
928 |
+
"epoch": 1.877527440785673,
|
929 |
+
"grad_norm": 11.287262916564941,
|
930 |
+
"learning_rate": 2.085384121549326e-05,
|
931 |
+
"loss": 0.3926,
|
932 |
+
"step": 3250
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 1.8919699595609474,
|
936 |
+
"grad_norm": 13.642833709716797,
|
937 |
+
"learning_rate": 2.0586347100363794e-05,
|
938 |
+
"loss": 0.3484,
|
939 |
+
"step": 3275
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 1.9064124783362217,
|
943 |
+
"grad_norm": 5.669510364532471,
|
944 |
+
"learning_rate": 2.0318852985234326e-05,
|
945 |
+
"loss": 0.3307,
|
946 |
+
"step": 3300
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 1.9208549971114963,
|
950 |
+
"grad_norm": 11.987211227416992,
|
951 |
+
"learning_rate": 2.005135887010486e-05,
|
952 |
+
"loss": 0.2979,
|
953 |
+
"step": 3325
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 1.9352975158867707,
|
957 |
+
"grad_norm": 8.090258598327637,
|
958 |
+
"learning_rate": 1.978386475497539e-05,
|
959 |
+
"loss": 0.2786,
|
960 |
+
"step": 3350
|
961 |
+
},
|
962 |
+
{
|
963 |
+
"epoch": 1.949740034662045,
|
964 |
+
"grad_norm": 5.356060028076172,
|
965 |
+
"learning_rate": 1.9516370639845923e-05,
|
966 |
+
"loss": 0.281,
|
967 |
+
"step": 3375
|
968 |
+
},
|
969 |
+
{
|
970 |
+
"epoch": 1.9641825534373196,
|
971 |
+
"grad_norm": 9.354238510131836,
|
972 |
+
"learning_rate": 1.924887652471646e-05,
|
973 |
+
"loss": 0.2761,
|
974 |
+
"step": 3400
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 1.9786250722125938,
|
978 |
+
"grad_norm": 12.076613426208496,
|
979 |
+
"learning_rate": 1.8981382409586988e-05,
|
980 |
+
"loss": 0.3394,
|
981 |
+
"step": 3425
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 1.9930675909878683,
|
985 |
+
"grad_norm": 6.9947428703308105,
|
986 |
+
"learning_rate": 1.8713888294457524e-05,
|
987 |
+
"loss": 0.3652,
|
988 |
+
"step": 3450
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 2.0,
|
992 |
+
"eval_explained_variance": 0.700911283493042,
|
993 |
+
"eval_loss": 0.3305796980857849,
|
994 |
+
"eval_mae": 0.44259902834892273,
|
995 |
+
"eval_mse": 0.3305796980857849,
|
996 |
+
"eval_r2": 0.7003744220771353,
|
997 |
+
"eval_rmse": 0.5749605894088745,
|
998 |
+
"eval_runtime": 21.4982,
|
999 |
+
"eval_samples_per_second": 161.037,
|
1000 |
+
"eval_steps_per_second": 10.094,
|
1001 |
+
"step": 3462
|
1002 |
+
}
|
1003 |
+
],
|
1004 |
+
"logging_steps": 25,
|
1005 |
+
"max_steps": 5193,
|
1006 |
+
"num_input_tokens_seen": 0,
|
1007 |
+
"num_train_epochs": 3,
|
1008 |
+
"save_steps": 500,
|
1009 |
+
"total_flos": 7285479708948480.0,
|
1010 |
+
"train_batch_size": 8,
|
1011 |
+
"trial_name": null,
|
1012 |
+
"trial_params": null
|
1013 |
+
}
|
checkpoint-3462/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:686af3a4982678cc23b8424229c94be57bb84a776c74836677e7bde5ad5ee125
|
3 |
+
size 5048
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FacebookAI/roberta-base",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"architectures": [
|
5 |
+
"RobertaForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "target"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"target": 0
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-05,
|
23 |
+
"max_position_embeddings": 514,
|
24 |
+
"model_type": "roberta",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"pad_token_id": 1,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"problem_type": "regression",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.40.1",
|
32 |
+
"type_vocab_size": 1,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 50265
|
35 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:775d65fd7488be3a614de8f7c06ab4e48f197ada2653a63cc0fbc5b2c12d4db5
|
3 |
+
size 498609748
|
runs/Apr30_11-30-35_r-abhishek-autotrain-yu8daxhp-663a5-olct4/events.out.tfevents.1714476635.r-abhishek-autotrain-yu8daxhp-663a5-olct4.150.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a31300fc20d14b92f93e9a777afc30b148928b2e6aa0d674f559742e7d37972
|
3 |
+
size 50393
|
runs/Apr30_11-30-35_r-abhishek-autotrain-yu8daxhp-663a5-olct4/events.out.tfevents.1714477596.r-abhishek-autotrain-yu8daxhp-663a5-olct4.150.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6557043cd9acc094a0619bbcbee73518e42823ca5c682a7f6f8de09621c7ec0d
|
3 |
+
size 609
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50264": {
|
37 |
+
"content": "<mask>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 512,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "RobertaTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:686af3a4982678cc23b8424229c94be57bb84a776c74836677e7bde5ad5ee125
|
3 |
+
size 5048
|
training_params.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "autotrain-m1b56-8ger6/autotrain-data",
|
3 |
+
"model": "FacebookAI/roberta-base",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 512,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "autotrain-m1b56-8ger6",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"evaluation_strategy": "epoch",
|
26 |
+
"username": "abhishek",
|
27 |
+
"log": "tensorboard"
|
28 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|