Training in progress, step 84000, checkpoint
Browse files- checkpoint-84000/config.json +28 -0
- checkpoint-84000/model.safetensors +3 -0
- checkpoint-84000/optimizer.pt +3 -0
- checkpoint-84000/rng_state.pth +3 -0
- checkpoint-84000/scheduler.pt +3 -0
- checkpoint-84000/special_tokens_map.json +34 -0
- checkpoint-84000/tokenizer.json +0 -0
- checkpoint-84000/tokenizer_config.json +63 -0
- checkpoint-84000/trainer_state.json +516 -0
- checkpoint-84000/training_args.bin +3 -0
checkpoint-84000/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 1,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 2048,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"mask_token_id": 4,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 8,
|
| 19 |
+
"num_hidden_layers": 8,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.45.2",
|
| 25 |
+
"type_vocab_size": 2,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 8192
|
| 28 |
+
}
|
checkpoint-84000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a8d9cd1cdae46660c24afdb719d8d97f43e489a1195c3a79c07eaa2154b998c
|
| 3 |
+
size 59702184
|
checkpoint-84000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1f742162c80da3947f868c212e6a6df19318566c3f7e93b7d26be0d8a10c102
|
| 3 |
+
size 119488058
|
checkpoint-84000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92f86650e9fca75b526fd97610256eeb9a90b9075fc31964a73983ff6b94248a
|
| 3 |
+
size 14308
|
checkpoint-84000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa814c2029b55571961a2d2bb8d955eb65003fbeee7a67ac475d669cc70b4a99
|
| 3 |
+
size 1000
|
checkpoint-84000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>"
|
| 4 |
+
],
|
| 5 |
+
"bos_token": {
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"mask_token": {
|
| 20 |
+
"content": "<mask>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
+
"pad_token": "</s>",
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
checkpoint-84000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-84000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "<|endoftext|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"additional_special_tokens": [
|
| 53 |
+
"<|endoftext|>"
|
| 54 |
+
],
|
| 55 |
+
"bos_token": "<s>",
|
| 56 |
+
"clean_up_tokenization_spaces": false,
|
| 57 |
+
"eos_token": "</s>",
|
| 58 |
+
"mask_token": "<mask>",
|
| 59 |
+
"model_max_length": 128,
|
| 60 |
+
"pad_token": "</s>",
|
| 61 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 62 |
+
"unk_token": "<unk>"
|
| 63 |
+
}
|
checkpoint-84000/trainer_state.json
ADDED
|
@@ -0,0 +1,516 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.0083158016204834,
|
| 3 |
+
"best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/de_mlm/wikipedia_13/checkpoint-84000",
|
| 4 |
+
"epoch": 61.56101135947233,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 84000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.4657383657017222,
|
| 13 |
+
"eval_loss": 8.087221145629883,
|
| 14 |
+
"eval_runtime": 2.215,
|
| 15 |
+
"eval_samples_per_second": 1035.232,
|
| 16 |
+
"eval_steps_per_second": 65.012,
|
| 17 |
+
"step": 2000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.9314767314034444,
|
| 21 |
+
"grad_norm": 0.9454871416091919,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 8.1326,
|
| 24 |
+
"step": 4000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.9314767314034444,
|
| 28 |
+
"eval_loss": 7.397463798522949,
|
| 29 |
+
"eval_runtime": 2.2812,
|
| 30 |
+
"eval_samples_per_second": 1005.158,
|
| 31 |
+
"eval_steps_per_second": 63.124,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 4.397215097105167,
|
| 36 |
+
"eval_loss": 7.2718353271484375,
|
| 37 |
+
"eval_runtime": 2.3459,
|
| 38 |
+
"eval_samples_per_second": 977.446,
|
| 39 |
+
"eval_steps_per_second": 61.383,
|
| 40 |
+
"step": 6000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 5.862953462806889,
|
| 44 |
+
"grad_norm": 1.4085547924041748,
|
| 45 |
+
"learning_rate": 2e-05,
|
| 46 |
+
"loss": 7.2846,
|
| 47 |
+
"step": 8000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 5.862953462806889,
|
| 51 |
+
"eval_loss": 7.183506965637207,
|
| 52 |
+
"eval_runtime": 2.2787,
|
| 53 |
+
"eval_samples_per_second": 1006.271,
|
| 54 |
+
"eval_steps_per_second": 63.194,
|
| 55 |
+
"step": 8000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 7.328691828508611,
|
| 59 |
+
"eval_loss": 7.09923791885376,
|
| 60 |
+
"eval_runtime": 2.1833,
|
| 61 |
+
"eval_samples_per_second": 1050.26,
|
| 62 |
+
"eval_steps_per_second": 65.956,
|
| 63 |
+
"step": 10000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 8.794430194210333,
|
| 67 |
+
"grad_norm": 1.4775667190551758,
|
| 68 |
+
"learning_rate": 2.9995e-05,
|
| 69 |
+
"loss": 7.1078,
|
| 70 |
+
"step": 12000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 8.794430194210333,
|
| 74 |
+
"eval_loss": 7.033052444458008,
|
| 75 |
+
"eval_runtime": 2.2436,
|
| 76 |
+
"eval_samples_per_second": 1022.003,
|
| 77 |
+
"eval_steps_per_second": 64.182,
|
| 78 |
+
"step": 12000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 10.260168559912056,
|
| 82 |
+
"eval_loss": 6.949419975280762,
|
| 83 |
+
"eval_runtime": 2.3034,
|
| 84 |
+
"eval_samples_per_second": 995.501,
|
| 85 |
+
"eval_steps_per_second": 62.517,
|
| 86 |
+
"step": 14000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 11.725906925613778,
|
| 90 |
+
"grad_norm": 2.364133358001709,
|
| 91 |
+
"learning_rate": 3.999e-05,
|
| 92 |
+
"loss": 6.942,
|
| 93 |
+
"step": 16000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.725906925613778,
|
| 97 |
+
"eval_loss": 6.889880180358887,
|
| 98 |
+
"eval_runtime": 2.3275,
|
| 99 |
+
"eval_samples_per_second": 985.162,
|
| 100 |
+
"eval_steps_per_second": 61.868,
|
| 101 |
+
"step": 16000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 13.191645291315501,
|
| 105 |
+
"eval_loss": 6.782171726226807,
|
| 106 |
+
"eval_runtime": 2.2331,
|
| 107 |
+
"eval_samples_per_second": 1026.812,
|
| 108 |
+
"eval_steps_per_second": 64.484,
|
| 109 |
+
"step": 18000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 14.657383657017222,
|
| 113 |
+
"grad_norm": 2.5763492584228516,
|
| 114 |
+
"learning_rate": 4.9985e-05,
|
| 115 |
+
"loss": 6.7676,
|
| 116 |
+
"step": 20000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 14.657383657017222,
|
| 120 |
+
"eval_loss": 6.718458652496338,
|
| 121 |
+
"eval_runtime": 2.2092,
|
| 122 |
+
"eval_samples_per_second": 1037.91,
|
| 123 |
+
"eval_steps_per_second": 65.181,
|
| 124 |
+
"step": 20000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 16.123122022718945,
|
| 128 |
+
"eval_loss": 6.653624057769775,
|
| 129 |
+
"eval_runtime": 2.33,
|
| 130 |
+
"eval_samples_per_second": 984.135,
|
| 131 |
+
"eval_steps_per_second": 61.804,
|
| 132 |
+
"step": 22000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 17.588860388420667,
|
| 136 |
+
"grad_norm": 4.001818656921387,
|
| 137 |
+
"learning_rate": 5.9980000000000005e-05,
|
| 138 |
+
"loss": 6.5959,
|
| 139 |
+
"step": 24000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 17.588860388420667,
|
| 143 |
+
"eval_loss": 6.543092727661133,
|
| 144 |
+
"eval_runtime": 2.3092,
|
| 145 |
+
"eval_samples_per_second": 992.981,
|
| 146 |
+
"eval_steps_per_second": 62.359,
|
| 147 |
+
"step": 24000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 19.054598754122388,
|
| 151 |
+
"eval_loss": 6.392500400543213,
|
| 152 |
+
"eval_runtime": 2.4925,
|
| 153 |
+
"eval_samples_per_second": 919.956,
|
| 154 |
+
"eval_steps_per_second": 57.773,
|
| 155 |
+
"step": 26000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 20.520337119824113,
|
| 159 |
+
"grad_norm": 4.359928607940674,
|
| 160 |
+
"learning_rate": 6.99775e-05,
|
| 161 |
+
"loss": 6.3624,
|
| 162 |
+
"step": 28000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 20.520337119824113,
|
| 166 |
+
"eval_loss": 6.211884021759033,
|
| 167 |
+
"eval_runtime": 2.3499,
|
| 168 |
+
"eval_samples_per_second": 975.797,
|
| 169 |
+
"eval_steps_per_second": 61.28,
|
| 170 |
+
"step": 28000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 21.986075485525834,
|
| 174 |
+
"eval_loss": 5.952591896057129,
|
| 175 |
+
"eval_runtime": 2.3365,
|
| 176 |
+
"eval_samples_per_second": 981.37,
|
| 177 |
+
"eval_steps_per_second": 61.63,
|
| 178 |
+
"step": 30000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 23.451813851227556,
|
| 182 |
+
"grad_norm": 5.47481632232666,
|
| 183 |
+
"learning_rate": 7.997250000000001e-05,
|
| 184 |
+
"loss": 5.9309,
|
| 185 |
+
"step": 32000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 23.451813851227556,
|
| 189 |
+
"eval_loss": 5.4161834716796875,
|
| 190 |
+
"eval_runtime": 2.2165,
|
| 191 |
+
"eval_samples_per_second": 1034.515,
|
| 192 |
+
"eval_steps_per_second": 64.967,
|
| 193 |
+
"step": 32000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 24.917552216929277,
|
| 197 |
+
"eval_loss": 5.0255045890808105,
|
| 198 |
+
"eval_runtime": 2.3492,
|
| 199 |
+
"eval_samples_per_second": 976.095,
|
| 200 |
+
"eval_steps_per_second": 61.299,
|
| 201 |
+
"step": 34000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 26.383290582631002,
|
| 205 |
+
"grad_norm": 5.85042667388916,
|
| 206 |
+
"learning_rate": 8.996750000000001e-05,
|
| 207 |
+
"loss": 5.0575,
|
| 208 |
+
"step": 36000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 26.383290582631002,
|
| 212 |
+
"eval_loss": 4.76804256439209,
|
| 213 |
+
"eval_runtime": 2.2482,
|
| 214 |
+
"eval_samples_per_second": 1019.914,
|
| 215 |
+
"eval_steps_per_second": 64.05,
|
| 216 |
+
"step": 36000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 27.849028948332723,
|
| 220 |
+
"eval_loss": 4.502030372619629,
|
| 221 |
+
"eval_runtime": 2.3066,
|
| 222 |
+
"eval_samples_per_second": 994.084,
|
| 223 |
+
"eval_steps_per_second": 62.428,
|
| 224 |
+
"step": 38000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 29.314767314034444,
|
| 228 |
+
"grad_norm": 4.6283698081970215,
|
| 229 |
+
"learning_rate": 9.99625e-05,
|
| 230 |
+
"loss": 4.5282,
|
| 231 |
+
"step": 40000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 29.314767314034444,
|
| 235 |
+
"eval_loss": 4.321413993835449,
|
| 236 |
+
"eval_runtime": 2.2564,
|
| 237 |
+
"eval_samples_per_second": 1016.223,
|
| 238 |
+
"eval_steps_per_second": 63.819,
|
| 239 |
+
"step": 40000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 30.780505679736166,
|
| 243 |
+
"eval_loss": 4.131194114685059,
|
| 244 |
+
"eval_runtime": 2.27,
|
| 245 |
+
"eval_samples_per_second": 1010.131,
|
| 246 |
+
"eval_steps_per_second": 63.436,
|
| 247 |
+
"step": 42000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 32.24624404543789,
|
| 251 |
+
"grad_norm": 4.427154064178467,
|
| 252 |
+
"learning_rate": 9.336166666666667e-05,
|
| 253 |
+
"loss": 4.1335,
|
| 254 |
+
"step": 44000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 32.24624404543789,
|
| 258 |
+
"eval_loss": 3.9708411693573,
|
| 259 |
+
"eval_runtime": 2.1314,
|
| 260 |
+
"eval_samples_per_second": 1075.829,
|
| 261 |
+
"eval_steps_per_second": 67.562,
|
| 262 |
+
"step": 44000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 33.71198241113961,
|
| 266 |
+
"eval_loss": 3.861647605895996,
|
| 267 |
+
"eval_runtime": 2.2216,
|
| 268 |
+
"eval_samples_per_second": 1032.141,
|
| 269 |
+
"eval_steps_per_second": 64.818,
|
| 270 |
+
"step": 46000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 35.17772077684133,
|
| 274 |
+
"grad_norm": 4.964674949645996,
|
| 275 |
+
"learning_rate": 8.669666666666667e-05,
|
| 276 |
+
"loss": 3.8339,
|
| 277 |
+
"step": 48000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 35.17772077684133,
|
| 281 |
+
"eval_loss": 3.763975143432617,
|
| 282 |
+
"eval_runtime": 2.2678,
|
| 283 |
+
"eval_samples_per_second": 1011.117,
|
| 284 |
+
"eval_steps_per_second": 63.498,
|
| 285 |
+
"step": 48000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 36.64345914254306,
|
| 289 |
+
"eval_loss": 3.707411527633667,
|
| 290 |
+
"eval_runtime": 2.1845,
|
| 291 |
+
"eval_samples_per_second": 1049.673,
|
| 292 |
+
"eval_steps_per_second": 65.919,
|
| 293 |
+
"step": 50000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 38.109197508244776,
|
| 297 |
+
"grad_norm": 5.166478633880615,
|
| 298 |
+
"learning_rate": 8.003333333333333e-05,
|
| 299 |
+
"loss": 3.6042,
|
| 300 |
+
"step": 52000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 38.109197508244776,
|
| 304 |
+
"eval_loss": 3.636035680770874,
|
| 305 |
+
"eval_runtime": 2.279,
|
| 306 |
+
"eval_samples_per_second": 1006.125,
|
| 307 |
+
"eval_steps_per_second": 63.184,
|
| 308 |
+
"step": 52000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 39.5749358739465,
|
| 312 |
+
"eval_loss": 3.520251750946045,
|
| 313 |
+
"eval_runtime": 2.3313,
|
| 314 |
+
"eval_samples_per_second": 983.562,
|
| 315 |
+
"eval_steps_per_second": 61.768,
|
| 316 |
+
"step": 54000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 41.040674239648226,
|
| 320 |
+
"grad_norm": 5.001477241516113,
|
| 321 |
+
"learning_rate": 7.337000000000001e-05,
|
| 322 |
+
"loss": 3.4291,
|
| 323 |
+
"step": 56000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 41.040674239648226,
|
| 327 |
+
"eval_loss": 3.4423604011535645,
|
| 328 |
+
"eval_runtime": 2.4163,
|
| 329 |
+
"eval_samples_per_second": 948.983,
|
| 330 |
+
"eval_steps_per_second": 59.596,
|
| 331 |
+
"step": 56000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 42.506412605349944,
|
| 335 |
+
"eval_loss": 3.427623987197876,
|
| 336 |
+
"eval_runtime": 2.1948,
|
| 337 |
+
"eval_samples_per_second": 1044.73,
|
| 338 |
+
"eval_steps_per_second": 65.609,
|
| 339 |
+
"step": 58000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 43.97215097105167,
|
| 343 |
+
"grad_norm": 5.074405670166016,
|
| 344 |
+
"learning_rate": 6.670666666666668e-05,
|
| 345 |
+
"loss": 3.286,
|
| 346 |
+
"step": 60000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 43.97215097105167,
|
| 350 |
+
"eval_loss": 3.3796520233154297,
|
| 351 |
+
"eval_runtime": 2.2145,
|
| 352 |
+
"eval_samples_per_second": 1035.457,
|
| 353 |
+
"eval_steps_per_second": 65.027,
|
| 354 |
+
"step": 60000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 45.437889336753386,
|
| 358 |
+
"eval_loss": 3.327679395675659,
|
| 359 |
+
"eval_runtime": 2.4352,
|
| 360 |
+
"eval_samples_per_second": 941.608,
|
| 361 |
+
"eval_steps_per_second": 59.133,
|
| 362 |
+
"step": 62000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 46.90362770245511,
|
| 366 |
+
"grad_norm": 4.627829551696777,
|
| 367 |
+
"learning_rate": 6.004333333333334e-05,
|
| 368 |
+
"loss": 3.1748,
|
| 369 |
+
"step": 64000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 46.90362770245511,
|
| 373 |
+
"eval_loss": 3.292200803756714,
|
| 374 |
+
"eval_runtime": 2.358,
|
| 375 |
+
"eval_samples_per_second": 972.453,
|
| 376 |
+
"eval_steps_per_second": 61.07,
|
| 377 |
+
"step": 64000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 48.369366068156836,
|
| 381 |
+
"eval_loss": 3.2361395359039307,
|
| 382 |
+
"eval_runtime": 2.2526,
|
| 383 |
+
"eval_samples_per_second": 1017.92,
|
| 384 |
+
"eval_steps_per_second": 63.925,
|
| 385 |
+
"step": 66000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 49.835104433858554,
|
| 389 |
+
"grad_norm": 4.962168216705322,
|
| 390 |
+
"learning_rate": 5.338000000000001e-05,
|
| 391 |
+
"loss": 3.0842,
|
| 392 |
+
"step": 68000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 49.835104433858554,
|
| 396 |
+
"eval_loss": 3.204303741455078,
|
| 397 |
+
"eval_runtime": 2.2836,
|
| 398 |
+
"eval_samples_per_second": 1004.135,
|
| 399 |
+
"eval_steps_per_second": 63.059,
|
| 400 |
+
"step": 68000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 51.30084279956028,
|
| 404 |
+
"eval_loss": 3.187018871307373,
|
| 405 |
+
"eval_runtime": 2.2063,
|
| 406 |
+
"eval_samples_per_second": 1039.279,
|
| 407 |
+
"eval_steps_per_second": 65.267,
|
| 408 |
+
"step": 70000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 52.766581165262004,
|
| 412 |
+
"grad_norm": 5.1038713455200195,
|
| 413 |
+
"learning_rate": 4.671666666666667e-05,
|
| 414 |
+
"loss": 3.0082,
|
| 415 |
+
"step": 72000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 52.766581165262004,
|
| 419 |
+
"eval_loss": 3.148749589920044,
|
| 420 |
+
"eval_runtime": 2.1633,
|
| 421 |
+
"eval_samples_per_second": 1059.95,
|
| 422 |
+
"eval_steps_per_second": 66.565,
|
| 423 |
+
"step": 72000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 54.23231953096372,
|
| 427 |
+
"eval_loss": 3.1257400512695312,
|
| 428 |
+
"eval_runtime": 2.188,
|
| 429 |
+
"eval_samples_per_second": 1048.007,
|
| 430 |
+
"eval_steps_per_second": 65.815,
|
| 431 |
+
"step": 74000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 55.698057896665446,
|
| 435 |
+
"grad_norm": 4.805927753448486,
|
| 436 |
+
"learning_rate": 4.005333333333334e-05,
|
| 437 |
+
"loss": 2.9483,
|
| 438 |
+
"step": 76000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 55.698057896665446,
|
| 442 |
+
"eval_loss": 3.1000759601593018,
|
| 443 |
+
"eval_runtime": 2.3388,
|
| 444 |
+
"eval_samples_per_second": 980.424,
|
| 445 |
+
"eval_steps_per_second": 61.57,
|
| 446 |
+
"step": 76000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 57.163796262367164,
|
| 450 |
+
"eval_loss": 3.069366216659546,
|
| 451 |
+
"eval_runtime": 2.2242,
|
| 452 |
+
"eval_samples_per_second": 1030.923,
|
| 453 |
+
"eval_steps_per_second": 64.742,
|
| 454 |
+
"step": 78000
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 58.62953462806889,
|
| 458 |
+
"grad_norm": 5.11604642868042,
|
| 459 |
+
"learning_rate": 3.339e-05,
|
| 460 |
+
"loss": 2.8885,
|
| 461 |
+
"step": 80000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 58.62953462806889,
|
| 465 |
+
"eval_loss": 3.0604772567749023,
|
| 466 |
+
"eval_runtime": 2.4526,
|
| 467 |
+
"eval_samples_per_second": 934.925,
|
| 468 |
+
"eval_steps_per_second": 58.713,
|
| 469 |
+
"step": 80000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 60.095272993770614,
|
| 473 |
+
"eval_loss": 3.0568008422851562,
|
| 474 |
+
"eval_runtime": 2.3025,
|
| 475 |
+
"eval_samples_per_second": 995.86,
|
| 476 |
+
"eval_steps_per_second": 62.54,
|
| 477 |
+
"step": 82000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 61.56101135947233,
|
| 481 |
+
"grad_norm": 5.1547369956970215,
|
| 482 |
+
"learning_rate": 2.6725e-05,
|
| 483 |
+
"loss": 2.8416,
|
| 484 |
+
"step": 84000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 61.56101135947233,
|
| 488 |
+
"eval_loss": 3.0083158016204834,
|
| 489 |
+
"eval_runtime": 2.1781,
|
| 490 |
+
"eval_samples_per_second": 1052.731,
|
| 491 |
+
"eval_steps_per_second": 66.111,
|
| 492 |
+
"step": 84000
|
| 493 |
+
}
|
| 494 |
+
],
|
| 495 |
+
"logging_steps": 4000,
|
| 496 |
+
"max_steps": 100000,
|
| 497 |
+
"num_input_tokens_seen": 0,
|
| 498 |
+
"num_train_epochs": 74,
|
| 499 |
+
"save_steps": 4000,
|
| 500 |
+
"stateful_callbacks": {
|
| 501 |
+
"TrainerControl": {
|
| 502 |
+
"args": {
|
| 503 |
+
"should_epoch_stop": false,
|
| 504 |
+
"should_evaluate": false,
|
| 505 |
+
"should_log": false,
|
| 506 |
+
"should_save": true,
|
| 507 |
+
"should_training_stop": false
|
| 508 |
+
},
|
| 509 |
+
"attributes": {}
|
| 510 |
+
}
|
| 511 |
+
},
|
| 512 |
+
"total_flos": 2.619911333884723e+16,
|
| 513 |
+
"train_batch_size": 16,
|
| 514 |
+
"trial_name": null,
|
| 515 |
+
"trial_params": null
|
| 516 |
+
}
|
checkpoint-84000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18d5335e549995a666047ad0aa350511260e15302e12c49cfc12029ab6ff3c4a
|
| 3 |
+
size 5368
|