Pierluigi Cassotti
commited on
Commit
·
79d5aa7
1
Parent(s):
b2d4951
upload model
Browse files- added_tokens.json +4 -0
- config.json +34 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +73 -0
- trainer_state.json +534 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</t>": 50266,
|
| 3 |
+
"<t>": 50265
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0"
|
| 15 |
+
},
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 4096,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"LABEL_0": 0
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-05,
|
| 22 |
+
"max_position_embeddings": 514,
|
| 23 |
+
"model_type": "roberta",
|
| 24 |
+
"num_attention_heads": 16,
|
| 25 |
+
"num_hidden_layers": 24,
|
| 26 |
+
"pad_token_id": 1,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"problem_type": "regression",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.37.0",
|
| 31 |
+
"type_vocab_size": 1,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 50267
|
| 34 |
+
}
|
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 sha256:7a4c925292df04e8252f7e364164c54f90bdaa594f3ebbe2538fe4ce6a017451
|
| 3 |
+
size 1421499508
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c11ef5bbe9de019eb343fc1167a969a6e88af4022c699ffbed56526973112ab5
|
| 3 |
+
size 2843231405
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d8e7e940f3a1d830c7f8329b13c069e84816fb0eea5bae5d8fcfb1fc3417033
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9a8f195e0e8686949ce12f6ea4ed3e8e559efdf3716c0de5bc1add6f78953c1
|
| 3 |
+
size 1064
|
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 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"50265": {
|
| 45 |
+
"content": "<t>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"50266": {
|
| 53 |
+
"content": "</t>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"bos_token": "<s>",
|
| 62 |
+
"clean_up_tokenization_spaces": true,
|
| 63 |
+
"cls_token": "<s>",
|
| 64 |
+
"eos_token": "</s>",
|
| 65 |
+
"errors": "replace",
|
| 66 |
+
"mask_token": "<mask>",
|
| 67 |
+
"model_max_length": 512,
|
| 68 |
+
"pad_token": "<pad>",
|
| 69 |
+
"sep_token": "</s>",
|
| 70 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 71 |
+
"trim_offsets": true,
|
| 72 |
+
"unk_token": "<unk>"
|
| 73 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,534 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9001113723549066,
|
| 5 |
+
"eval_steps": 4041,
|
| 6 |
+
"global_step": 36369,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 1.97525058779854e-05,
|
| 14 |
+
"loss": 0.9165,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 1.9505011755970797e-05,
|
| 20 |
+
"loss": 0.6643,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04,
|
| 25 |
+
"learning_rate": 1.9257517633956195e-05,
|
| 26 |
+
"loss": 0.6254,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 1.9010023511941593e-05,
|
| 32 |
+
"loss": 0.604,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 1.876252938992699e-05,
|
| 38 |
+
"loss": 0.5783,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.07,
|
| 43 |
+
"learning_rate": 1.8515035267912388e-05,
|
| 44 |
+
"loss": 0.5609,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.09,
|
| 49 |
+
"learning_rate": 1.8267541145897786e-05,
|
| 50 |
+
"loss": 0.5579,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"learning_rate": 1.8020047023883184e-05,
|
| 56 |
+
"loss": 0.5479,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.1,
|
| 61 |
+
"eval_loss": 0.5143907070159912,
|
| 62 |
+
"eval_rmse": 0.7172102332115173,
|
| 63 |
+
"eval_runtime": 2327.418,
|
| 64 |
+
"eval_samples_per_second": 123.451,
|
| 65 |
+
"eval_steps_per_second": 1.929,
|
| 66 |
+
"step": 4041
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.11,
|
| 70 |
+
"learning_rate": 1.777255290186858e-05,
|
| 71 |
+
"loss": 0.5383,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.12,
|
| 76 |
+
"learning_rate": 1.752505877985398e-05,
|
| 77 |
+
"loss": 0.522,
|
| 78 |
+
"step": 5000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.14,
|
| 82 |
+
"learning_rate": 1.7277564657839377e-05,
|
| 83 |
+
"loss": 0.5221,
|
| 84 |
+
"step": 5500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.15,
|
| 88 |
+
"learning_rate": 1.7030070535824775e-05,
|
| 89 |
+
"loss": 0.5068,
|
| 90 |
+
"step": 6000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.16,
|
| 94 |
+
"learning_rate": 1.6782576413810176e-05,
|
| 95 |
+
"loss": 0.5098,
|
| 96 |
+
"step": 6500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.17,
|
| 100 |
+
"learning_rate": 1.6535082291795574e-05,
|
| 101 |
+
"loss": 0.5023,
|
| 102 |
+
"step": 7000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.19,
|
| 106 |
+
"learning_rate": 1.628758816978097e-05,
|
| 107 |
+
"loss": 0.4958,
|
| 108 |
+
"step": 7500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.2,
|
| 112 |
+
"learning_rate": 1.6040094047766366e-05,
|
| 113 |
+
"loss": 0.4928,
|
| 114 |
+
"step": 8000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2,
|
| 118 |
+
"eval_loss": 0.4747944176197052,
|
| 119 |
+
"eval_rmse": 0.689052939414978,
|
| 120 |
+
"eval_runtime": 2343.1879,
|
| 121 |
+
"eval_samples_per_second": 122.62,
|
| 122 |
+
"eval_steps_per_second": 1.916,
|
| 123 |
+
"step": 8082
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.21,
|
| 127 |
+
"learning_rate": 1.5792599925751764e-05,
|
| 128 |
+
"loss": 0.4896,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.22,
|
| 133 |
+
"learning_rate": 1.554510580373716e-05,
|
| 134 |
+
"loss": 0.4816,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.24,
|
| 139 |
+
"learning_rate": 1.529761168172256e-05,
|
| 140 |
+
"loss": 0.483,
|
| 141 |
+
"step": 9500
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.25,
|
| 145 |
+
"learning_rate": 1.5050117559707957e-05,
|
| 146 |
+
"loss": 0.4786,
|
| 147 |
+
"step": 10000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.26,
|
| 151 |
+
"learning_rate": 1.4802623437693355e-05,
|
| 152 |
+
"loss": 0.4742,
|
| 153 |
+
"step": 10500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.27,
|
| 157 |
+
"learning_rate": 1.4555129315678752e-05,
|
| 158 |
+
"loss": 0.4721,
|
| 159 |
+
"step": 11000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.28,
|
| 163 |
+
"learning_rate": 1.4307635193664152e-05,
|
| 164 |
+
"loss": 0.4665,
|
| 165 |
+
"step": 11500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.3,
|
| 169 |
+
"learning_rate": 1.406014107164955e-05,
|
| 170 |
+
"loss": 0.4632,
|
| 171 |
+
"step": 12000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.3,
|
| 175 |
+
"eval_loss": 0.44039463996887207,
|
| 176 |
+
"eval_rmse": 0.6636217832565308,
|
| 177 |
+
"eval_runtime": 2341.3935,
|
| 178 |
+
"eval_samples_per_second": 122.714,
|
| 179 |
+
"eval_steps_per_second": 1.918,
|
| 180 |
+
"step": 12123
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.31,
|
| 184 |
+
"learning_rate": 1.3812646949634947e-05,
|
| 185 |
+
"loss": 0.4624,
|
| 186 |
+
"step": 12500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.32,
|
| 190 |
+
"learning_rate": 1.3565152827620345e-05,
|
| 191 |
+
"loss": 0.4565,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.33,
|
| 196 |
+
"learning_rate": 1.3317658705605743e-05,
|
| 197 |
+
"loss": 0.4579,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.35,
|
| 202 |
+
"learning_rate": 1.307016458359114e-05,
|
| 203 |
+
"loss": 0.4612,
|
| 204 |
+
"step": 14000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.36,
|
| 208 |
+
"learning_rate": 1.2822670461576538e-05,
|
| 209 |
+
"loss": 0.4484,
|
| 210 |
+
"step": 14500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.37,
|
| 214 |
+
"learning_rate": 1.2575176339561936e-05,
|
| 215 |
+
"loss": 0.4502,
|
| 216 |
+
"step": 15000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.38,
|
| 220 |
+
"learning_rate": 1.2327682217547334e-05,
|
| 221 |
+
"loss": 0.4391,
|
| 222 |
+
"step": 15500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.4,
|
| 226 |
+
"learning_rate": 1.2080188095532732e-05,
|
| 227 |
+
"loss": 0.4475,
|
| 228 |
+
"step": 16000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.4,
|
| 232 |
+
"eval_loss": 0.4300330877304077,
|
| 233 |
+
"eval_rmse": 0.6557684540748596,
|
| 234 |
+
"eval_runtime": 2336.2101,
|
| 235 |
+
"eval_samples_per_second": 122.986,
|
| 236 |
+
"eval_steps_per_second": 1.922,
|
| 237 |
+
"step": 16164
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.41,
|
| 241 |
+
"learning_rate": 1.183269397351813e-05,
|
| 242 |
+
"loss": 0.4388,
|
| 243 |
+
"step": 16500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.42,
|
| 247 |
+
"learning_rate": 1.1585199851503527e-05,
|
| 248 |
+
"loss": 0.44,
|
| 249 |
+
"step": 17000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.43,
|
| 253 |
+
"learning_rate": 1.1337705729488927e-05,
|
| 254 |
+
"loss": 0.4372,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.45,
|
| 259 |
+
"learning_rate": 1.1090211607474324e-05,
|
| 260 |
+
"loss": 0.4362,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.46,
|
| 265 |
+
"learning_rate": 1.0842717485459722e-05,
|
| 266 |
+
"loss": 0.4385,
|
| 267 |
+
"step": 18500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.47,
|
| 271 |
+
"learning_rate": 1.059522336344512e-05,
|
| 272 |
+
"loss": 0.4263,
|
| 273 |
+
"step": 19000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.48,
|
| 277 |
+
"learning_rate": 1.0347729241430518e-05,
|
| 278 |
+
"loss": 0.4353,
|
| 279 |
+
"step": 19500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.49,
|
| 283 |
+
"learning_rate": 1.0100235119415916e-05,
|
| 284 |
+
"loss": 0.4295,
|
| 285 |
+
"step": 20000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.5,
|
| 289 |
+
"eval_loss": 0.40923774242401123,
|
| 290 |
+
"eval_rmse": 0.6397165060043335,
|
| 291 |
+
"eval_runtime": 2338.1242,
|
| 292 |
+
"eval_samples_per_second": 122.885,
|
| 293 |
+
"eval_steps_per_second": 1.92,
|
| 294 |
+
"step": 20205
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.51,
|
| 298 |
+
"learning_rate": 9.852740997401312e-06,
|
| 299 |
+
"loss": 0.4219,
|
| 300 |
+
"step": 20500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.52,
|
| 304 |
+
"learning_rate": 9.60524687538671e-06,
|
| 305 |
+
"loss": 0.4215,
|
| 306 |
+
"step": 21000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.53,
|
| 310 |
+
"learning_rate": 9.357752753372109e-06,
|
| 311 |
+
"loss": 0.422,
|
| 312 |
+
"step": 21500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.54,
|
| 316 |
+
"learning_rate": 9.110258631357507e-06,
|
| 317 |
+
"loss": 0.4221,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.56,
|
| 322 |
+
"learning_rate": 8.862764509342904e-06,
|
| 323 |
+
"loss": 0.4191,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.57,
|
| 328 |
+
"learning_rate": 8.615270387328302e-06,
|
| 329 |
+
"loss": 0.4178,
|
| 330 |
+
"step": 23000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.58,
|
| 334 |
+
"learning_rate": 8.3677762653137e-06,
|
| 335 |
+
"loss": 0.4154,
|
| 336 |
+
"step": 23500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.59,
|
| 340 |
+
"learning_rate": 8.120282143299098e-06,
|
| 341 |
+
"loss": 0.4087,
|
| 342 |
+
"step": 24000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.6,
|
| 346 |
+
"eval_loss": 0.39208775758743286,
|
| 347 |
+
"eval_rmse": 0.6261686086654663,
|
| 348 |
+
"eval_runtime": 2337.6873,
|
| 349 |
+
"eval_samples_per_second": 122.908,
|
| 350 |
+
"eval_steps_per_second": 1.921,
|
| 351 |
+
"step": 24246
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.61,
|
| 355 |
+
"learning_rate": 7.872788021284495e-06,
|
| 356 |
+
"loss": 0.4101,
|
| 357 |
+
"step": 24500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.62,
|
| 361 |
+
"learning_rate": 7.625293899269893e-06,
|
| 362 |
+
"loss": 0.417,
|
| 363 |
+
"step": 25000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.63,
|
| 367 |
+
"learning_rate": 7.377799777255291e-06,
|
| 368 |
+
"loss": 0.4122,
|
| 369 |
+
"step": 25500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.64,
|
| 373 |
+
"learning_rate": 7.130305655240689e-06,
|
| 374 |
+
"loss": 0.4069,
|
| 375 |
+
"step": 26000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.66,
|
| 379 |
+
"learning_rate": 6.882811533226087e-06,
|
| 380 |
+
"loss": 0.4046,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.67,
|
| 385 |
+
"learning_rate": 6.635317411211483e-06,
|
| 386 |
+
"loss": 0.4121,
|
| 387 |
+
"step": 27000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.68,
|
| 391 |
+
"learning_rate": 6.387823289196882e-06,
|
| 392 |
+
"loss": 0.402,
|
| 393 |
+
"step": 27500
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.69,
|
| 397 |
+
"learning_rate": 6.14032916718228e-06,
|
| 398 |
+
"loss": 0.4029,
|
| 399 |
+
"step": 28000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.7,
|
| 403 |
+
"eval_loss": 0.39122310280799866,
|
| 404 |
+
"eval_rmse": 0.6254780888557434,
|
| 405 |
+
"eval_runtime": 2318.1699,
|
| 406 |
+
"eval_samples_per_second": 123.943,
|
| 407 |
+
"eval_steps_per_second": 1.937,
|
| 408 |
+
"step": 28287
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.71,
|
| 412 |
+
"learning_rate": 5.8928350451676775e-06,
|
| 413 |
+
"loss": 0.3937,
|
| 414 |
+
"step": 28500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.72,
|
| 418 |
+
"learning_rate": 5.645340923153075e-06,
|
| 419 |
+
"loss": 0.3978,
|
| 420 |
+
"step": 29000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.73,
|
| 424 |
+
"learning_rate": 5.397846801138473e-06,
|
| 425 |
+
"loss": 0.3929,
|
| 426 |
+
"step": 29500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.74,
|
| 430 |
+
"learning_rate": 5.150352679123871e-06,
|
| 431 |
+
"loss": 0.3855,
|
| 432 |
+
"step": 30000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.75,
|
| 436 |
+
"learning_rate": 4.902858557109269e-06,
|
| 437 |
+
"loss": 0.3977,
|
| 438 |
+
"step": 30500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.77,
|
| 442 |
+
"learning_rate": 4.655364435094667e-06,
|
| 443 |
+
"loss": 0.387,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.78,
|
| 448 |
+
"learning_rate": 4.407870313080065e-06,
|
| 449 |
+
"loss": 0.3907,
|
| 450 |
+
"step": 31500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.79,
|
| 454 |
+
"learning_rate": 4.160376191065463e-06,
|
| 455 |
+
"loss": 0.392,
|
| 456 |
+
"step": 32000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.8,
|
| 460 |
+
"eval_loss": 0.3795255720615387,
|
| 461 |
+
"eval_rmse": 0.6160560250282288,
|
| 462 |
+
"eval_runtime": 2318.679,
|
| 463 |
+
"eval_samples_per_second": 123.916,
|
| 464 |
+
"eval_steps_per_second": 1.936,
|
| 465 |
+
"step": 32328
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.8,
|
| 469 |
+
"learning_rate": 3.9128820690508604e-06,
|
| 470 |
+
"loss": 0.387,
|
| 471 |
+
"step": 32500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.82,
|
| 475 |
+
"learning_rate": 3.665387947036258e-06,
|
| 476 |
+
"loss": 0.389,
|
| 477 |
+
"step": 33000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.83,
|
| 481 |
+
"learning_rate": 3.417893825021656e-06,
|
| 482 |
+
"loss": 0.3844,
|
| 483 |
+
"step": 33500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.84,
|
| 487 |
+
"learning_rate": 3.1703997030070537e-06,
|
| 488 |
+
"loss": 0.3882,
|
| 489 |
+
"step": 34000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.85,
|
| 493 |
+
"learning_rate": 2.922905580992452e-06,
|
| 494 |
+
"loss": 0.3833,
|
| 495 |
+
"step": 34500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.87,
|
| 499 |
+
"learning_rate": 2.6754114589778497e-06,
|
| 500 |
+
"loss": 0.3818,
|
| 501 |
+
"step": 35000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.88,
|
| 505 |
+
"learning_rate": 2.4279173369632474e-06,
|
| 506 |
+
"loss": 0.3792,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.89,
|
| 511 |
+
"learning_rate": 2.180423214948645e-06,
|
| 512 |
+
"loss": 0.3818,
|
| 513 |
+
"step": 36000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.9,
|
| 517 |
+
"eval_loss": 0.37015318870544434,
|
| 518 |
+
"eval_rmse": 0.6084016561508179,
|
| 519 |
+
"eval_runtime": 2328.1676,
|
| 520 |
+
"eval_samples_per_second": 123.411,
|
| 521 |
+
"eval_steps_per_second": 1.929,
|
| 522 |
+
"step": 36369
|
| 523 |
+
}
|
| 524 |
+
],
|
| 525 |
+
"logging_steps": 500,
|
| 526 |
+
"max_steps": 40405,
|
| 527 |
+
"num_input_tokens_seen": 0,
|
| 528 |
+
"num_train_epochs": 1,
|
| 529 |
+
"save_steps": 4041,
|
| 530 |
+
"total_flos": 1.1989753896587223e+18,
|
| 531 |
+
"train_batch_size": 64,
|
| 532 |
+
"trial_name": null,
|
| 533 |
+
"trial_params": null
|
| 534 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ed22c98895148cc86922714ecc0d66c54d8a5437907b22b0555e4f40ecc522b
|
| 3 |
+
size 4664
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|