Training in progress, step 72000, checkpoint
Browse files- checkpoint-72000/config.json +32 -0
- checkpoint-72000/generation_config.json +6 -0
- checkpoint-72000/model.safetensors +3 -0
- checkpoint-72000/optimizer.pt +3 -0
- checkpoint-72000/rng_state.pth +3 -0
- checkpoint-72000/scheduler.pt +3 -0
- checkpoint-72000/special_tokens_map.json +34 -0
- checkpoint-72000/tokenizer.json +0 -0
- checkpoint-72000/tokenizer_config.json +63 -0
- checkpoint-72000/trainer_state.json +447 -0
- checkpoint-72000/training_args.bin +3 -0
checkpoint-72000/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 1,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_ctx": 512,
|
| 14 |
+
"n_embd": 256,
|
| 15 |
+
"n_head": 8,
|
| 16 |
+
"n_inner": 2048,
|
| 17 |
+
"n_layer": 8,
|
| 18 |
+
"n_positions": 512,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.45.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 8192
|
| 32 |
+
}
|
checkpoint-72000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"transformers_version": "4.45.2"
|
| 6 |
+
}
|
checkpoint-72000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da495f87ae14beb0bb43b40adf1333fa339f93e711c187f1956a4563c6d91f09
|
| 3 |
+
size 51007160
|
checkpoint-72000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4588f3008b3aaf826bea62d6e5ad33dc0de087a52b43a1d4e4e162163ee827cd
|
| 3 |
+
size 102078202
|
checkpoint-72000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e9cca44949e1a30fbb24a96f5654955c68068e53a92cc56f36e9594bddc34c6
|
| 3 |
+
size 14244
|
checkpoint-72000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:487ad1f531bda2b080d4a44391cc890fe1de78806332bbb0af3b79ab7b4622b2
|
| 3 |
+
size 1000
|
checkpoint-72000/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-72000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-72000/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-72000/trainer_state.json
ADDED
|
@@ -0,0 +1,447 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 4.028749465942383,
|
| 3 |
+
"best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/en_clm/childes_42/checkpoint-36000",
|
| 4 |
+
"epoch": 47.792897444407565,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 72000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.3275804845668768,
|
| 13 |
+
"eval_loss": 6.811094760894775,
|
| 14 |
+
"eval_runtime": 1.2294,
|
| 15 |
+
"eval_samples_per_second": 1423.487,
|
| 16 |
+
"eval_steps_per_second": 89.476,
|
| 17 |
+
"step": 2000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.6551609691337537,
|
| 21 |
+
"grad_norm": 1.632613182067871,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 6.7052,
|
| 24 |
+
"step": 4000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.6551609691337537,
|
| 28 |
+
"eval_loss": 5.248932838439941,
|
| 29 |
+
"eval_runtime": 1.1859,
|
| 30 |
+
"eval_samples_per_second": 1475.676,
|
| 31 |
+
"eval_steps_per_second": 92.757,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.9827414537006307,
|
| 36 |
+
"eval_loss": 4.83342170715332,
|
| 37 |
+
"eval_runtime": 1.2422,
|
| 38 |
+
"eval_samples_per_second": 1408.831,
|
| 39 |
+
"eval_steps_per_second": 88.555,
|
| 40 |
+
"step": 6000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 5.310321938267507,
|
| 44 |
+
"grad_norm": 2.778367757797241,
|
| 45 |
+
"learning_rate": 2e-05,
|
| 46 |
+
"loss": 4.6011,
|
| 47 |
+
"step": 8000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 5.310321938267507,
|
| 51 |
+
"eval_loss": 4.594471454620361,
|
| 52 |
+
"eval_runtime": 1.2286,
|
| 53 |
+
"eval_samples_per_second": 1424.405,
|
| 54 |
+
"eval_steps_per_second": 89.534,
|
| 55 |
+
"step": 8000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 6.637902422834385,
|
| 59 |
+
"eval_loss": 4.447059154510498,
|
| 60 |
+
"eval_runtime": 1.212,
|
| 61 |
+
"eval_samples_per_second": 1443.928,
|
| 62 |
+
"eval_steps_per_second": 90.761,
|
| 63 |
+
"step": 10000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.965482907401261,
|
| 67 |
+
"grad_norm": 2.503838062286377,
|
| 68 |
+
"learning_rate": 2.9995e-05,
|
| 69 |
+
"loss": 4.1311,
|
| 70 |
+
"step": 12000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 7.965482907401261,
|
| 74 |
+
"eval_loss": 4.349567413330078,
|
| 75 |
+
"eval_runtime": 1.1943,
|
| 76 |
+
"eval_samples_per_second": 1465.347,
|
| 77 |
+
"eval_steps_per_second": 92.108,
|
| 78 |
+
"step": 12000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 9.293063391968138,
|
| 82 |
+
"eval_loss": 4.279144287109375,
|
| 83 |
+
"eval_runtime": 1.2744,
|
| 84 |
+
"eval_samples_per_second": 1373.229,
|
| 85 |
+
"eval_steps_per_second": 86.317,
|
| 86 |
+
"step": 14000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 10.620643876535015,
|
| 90 |
+
"grad_norm": 2.356257200241089,
|
| 91 |
+
"learning_rate": 3.999e-05,
|
| 92 |
+
"loss": 3.8551,
|
| 93 |
+
"step": 16000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 10.620643876535015,
|
| 97 |
+
"eval_loss": 4.21755838394165,
|
| 98 |
+
"eval_runtime": 1.2069,
|
| 99 |
+
"eval_samples_per_second": 1450.015,
|
| 100 |
+
"eval_steps_per_second": 91.144,
|
| 101 |
+
"step": 16000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 11.948224361101891,
|
| 105 |
+
"eval_loss": 4.180819988250732,
|
| 106 |
+
"eval_runtime": 1.2612,
|
| 107 |
+
"eval_samples_per_second": 1387.52,
|
| 108 |
+
"eval_steps_per_second": 87.216,
|
| 109 |
+
"step": 18000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 13.275804845668768,
|
| 113 |
+
"grad_norm": 2.202317237854004,
|
| 114 |
+
"learning_rate": 4.9985e-05,
|
| 115 |
+
"loss": 3.6553,
|
| 116 |
+
"step": 20000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 13.275804845668768,
|
| 120 |
+
"eval_loss": 4.148049831390381,
|
| 121 |
+
"eval_runtime": 1.1967,
|
| 122 |
+
"eval_samples_per_second": 1462.412,
|
| 123 |
+
"eval_steps_per_second": 91.923,
|
| 124 |
+
"step": 20000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 14.603385330235646,
|
| 128 |
+
"eval_loss": 4.124350070953369,
|
| 129 |
+
"eval_runtime": 1.2029,
|
| 130 |
+
"eval_samples_per_second": 1454.863,
|
| 131 |
+
"eval_steps_per_second": 91.449,
|
| 132 |
+
"step": 22000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 15.930965814802523,
|
| 136 |
+
"grad_norm": 1.9641308784484863,
|
| 137 |
+
"learning_rate": 5.9980000000000005e-05,
|
| 138 |
+
"loss": 3.4944,
|
| 139 |
+
"step": 24000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 15.930965814802523,
|
| 143 |
+
"eval_loss": 4.103585720062256,
|
| 144 |
+
"eval_runtime": 1.2371,
|
| 145 |
+
"eval_samples_per_second": 1414.56,
|
| 146 |
+
"eval_steps_per_second": 88.915,
|
| 147 |
+
"step": 24000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 17.2585462993694,
|
| 151 |
+
"eval_loss": 4.083707809448242,
|
| 152 |
+
"eval_runtime": 1.193,
|
| 153 |
+
"eval_samples_per_second": 1466.868,
|
| 154 |
+
"eval_steps_per_second": 92.203,
|
| 155 |
+
"step": 26000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 18.586126783936276,
|
| 159 |
+
"grad_norm": 1.8919872045516968,
|
| 160 |
+
"learning_rate": 6.997500000000001e-05,
|
| 161 |
+
"loss": 3.3589,
|
| 162 |
+
"step": 28000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 18.586126783936276,
|
| 166 |
+
"eval_loss": 4.0663957595825195,
|
| 167 |
+
"eval_runtime": 1.2019,
|
| 168 |
+
"eval_samples_per_second": 1456.061,
|
| 169 |
+
"eval_steps_per_second": 91.524,
|
| 170 |
+
"step": 28000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 19.913707268503153,
|
| 174 |
+
"eval_loss": 4.049406051635742,
|
| 175 |
+
"eval_runtime": 1.258,
|
| 176 |
+
"eval_samples_per_second": 1391.058,
|
| 177 |
+
"eval_steps_per_second": 87.438,
|
| 178 |
+
"step": 30000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 21.24128775307003,
|
| 182 |
+
"grad_norm": 1.8024287223815918,
|
| 183 |
+
"learning_rate": 7.997e-05,
|
| 184 |
+
"loss": 3.2511,
|
| 185 |
+
"step": 32000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 21.24128775307003,
|
| 189 |
+
"eval_loss": 4.053829669952393,
|
| 190 |
+
"eval_runtime": 1.2009,
|
| 191 |
+
"eval_samples_per_second": 1457.199,
|
| 192 |
+
"eval_steps_per_second": 91.595,
|
| 193 |
+
"step": 32000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 22.568868237636906,
|
| 197 |
+
"eval_loss": 4.051271915435791,
|
| 198 |
+
"eval_runtime": 1.2605,
|
| 199 |
+
"eval_samples_per_second": 1388.36,
|
| 200 |
+
"eval_steps_per_second": 87.268,
|
| 201 |
+
"step": 34000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 23.896448722203782,
|
| 205 |
+
"grad_norm": 1.6429823637008667,
|
| 206 |
+
"learning_rate": 8.9965e-05,
|
| 207 |
+
"loss": 3.1592,
|
| 208 |
+
"step": 36000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 23.896448722203782,
|
| 212 |
+
"eval_loss": 4.028749465942383,
|
| 213 |
+
"eval_runtime": 1.3249,
|
| 214 |
+
"eval_samples_per_second": 1320.851,
|
| 215 |
+
"eval_steps_per_second": 83.025,
|
| 216 |
+
"step": 36000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 25.22402920677066,
|
| 220 |
+
"eval_loss": 4.039541721343994,
|
| 221 |
+
"eval_runtime": 1.2593,
|
| 222 |
+
"eval_samples_per_second": 1389.67,
|
| 223 |
+
"eval_steps_per_second": 87.351,
|
| 224 |
+
"step": 38000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 26.551609691337536,
|
| 228 |
+
"grad_norm": 1.6173956394195557,
|
| 229 |
+
"learning_rate": 9.996000000000001e-05,
|
| 230 |
+
"loss": 3.0779,
|
| 231 |
+
"step": 40000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 26.551609691337536,
|
| 235 |
+
"eval_loss": 4.046719551086426,
|
| 236 |
+
"eval_runtime": 1.278,
|
| 237 |
+
"eval_samples_per_second": 1369.312,
|
| 238 |
+
"eval_steps_per_second": 86.071,
|
| 239 |
+
"step": 40000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 27.879190175904416,
|
| 243 |
+
"eval_loss": 4.04121208190918,
|
| 244 |
+
"eval_runtime": 1.1867,
|
| 245 |
+
"eval_samples_per_second": 1474.648,
|
| 246 |
+
"eval_steps_per_second": 92.692,
|
| 247 |
+
"step": 42000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 29.206770660471292,
|
| 251 |
+
"grad_norm": 1.6253678798675537,
|
| 252 |
+
"learning_rate": 9.336333333333334e-05,
|
| 253 |
+
"loss": 3.0034,
|
| 254 |
+
"step": 44000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 29.206770660471292,
|
| 258 |
+
"eval_loss": 4.051359176635742,
|
| 259 |
+
"eval_runtime": 1.196,
|
| 260 |
+
"eval_samples_per_second": 1463.173,
|
| 261 |
+
"eval_steps_per_second": 91.971,
|
| 262 |
+
"step": 44000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 30.53435114503817,
|
| 266 |
+
"eval_loss": 4.058103084564209,
|
| 267 |
+
"eval_runtime": 1.2111,
|
| 268 |
+
"eval_samples_per_second": 1444.932,
|
| 269 |
+
"eval_steps_per_second": 90.824,
|
| 270 |
+
"step": 46000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 31.861931629605046,
|
| 274 |
+
"grad_norm": 1.605022668838501,
|
| 275 |
+
"learning_rate": 8.67e-05,
|
| 276 |
+
"loss": 2.9282,
|
| 277 |
+
"step": 48000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 31.861931629605046,
|
| 281 |
+
"eval_loss": 4.061252117156982,
|
| 282 |
+
"eval_runtime": 1.2378,
|
| 283 |
+
"eval_samples_per_second": 1413.846,
|
| 284 |
+
"eval_steps_per_second": 88.87,
|
| 285 |
+
"step": 48000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 33.18951211417192,
|
| 289 |
+
"eval_loss": 4.073904991149902,
|
| 290 |
+
"eval_runtime": 1.1783,
|
| 291 |
+
"eval_samples_per_second": 1485.184,
|
| 292 |
+
"eval_steps_per_second": 93.354,
|
| 293 |
+
"step": 50000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 34.5170925987388,
|
| 297 |
+
"grad_norm": 1.6729241609573364,
|
| 298 |
+
"learning_rate": 8.003666666666667e-05,
|
| 299 |
+
"loss": 2.8601,
|
| 300 |
+
"step": 52000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 34.5170925987388,
|
| 304 |
+
"eval_loss": 4.086970329284668,
|
| 305 |
+
"eval_runtime": 1.1925,
|
| 306 |
+
"eval_samples_per_second": 1467.453,
|
| 307 |
+
"eval_steps_per_second": 92.24,
|
| 308 |
+
"step": 52000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 35.84467308330567,
|
| 312 |
+
"eval_loss": 4.089752197265625,
|
| 313 |
+
"eval_runtime": 1.3022,
|
| 314 |
+
"eval_samples_per_second": 1343.925,
|
| 315 |
+
"eval_steps_per_second": 84.475,
|
| 316 |
+
"step": 54000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 37.17225356787255,
|
| 320 |
+
"grad_norm": 1.7726185321807861,
|
| 321 |
+
"learning_rate": 7.337166666666667e-05,
|
| 322 |
+
"loss": 2.8037,
|
| 323 |
+
"step": 56000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 37.17225356787255,
|
| 327 |
+
"eval_loss": 4.120365619659424,
|
| 328 |
+
"eval_runtime": 1.2009,
|
| 329 |
+
"eval_samples_per_second": 1457.256,
|
| 330 |
+
"eval_steps_per_second": 91.599,
|
| 331 |
+
"step": 56000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 38.49983405243943,
|
| 335 |
+
"eval_loss": 4.132432460784912,
|
| 336 |
+
"eval_runtime": 1.2255,
|
| 337 |
+
"eval_samples_per_second": 1427.982,
|
| 338 |
+
"eval_steps_per_second": 89.759,
|
| 339 |
+
"step": 58000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 39.827414537006305,
|
| 343 |
+
"grad_norm": 1.9301064014434814,
|
| 344 |
+
"learning_rate": 6.670833333333333e-05,
|
| 345 |
+
"loss": 2.751,
|
| 346 |
+
"step": 60000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 39.827414537006305,
|
| 350 |
+
"eval_loss": 4.133945941925049,
|
| 351 |
+
"eval_runtime": 1.183,
|
| 352 |
+
"eval_samples_per_second": 1479.285,
|
| 353 |
+
"eval_steps_per_second": 92.984,
|
| 354 |
+
"step": 60000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 41.154995021573185,
|
| 358 |
+
"eval_loss": 4.15323543548584,
|
| 359 |
+
"eval_runtime": 1.192,
|
| 360 |
+
"eval_samples_per_second": 1468.091,
|
| 361 |
+
"eval_steps_per_second": 92.28,
|
| 362 |
+
"step": 62000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 42.48257550614006,
|
| 366 |
+
"grad_norm": 1.9594330787658691,
|
| 367 |
+
"learning_rate": 6.0045000000000005e-05,
|
| 368 |
+
"loss": 2.7015,
|
| 369 |
+
"step": 64000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 42.48257550614006,
|
| 373 |
+
"eval_loss": 4.174168586730957,
|
| 374 |
+
"eval_runtime": 1.2323,
|
| 375 |
+
"eval_samples_per_second": 1420.062,
|
| 376 |
+
"eval_steps_per_second": 89.261,
|
| 377 |
+
"step": 64000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 43.81015599070694,
|
| 381 |
+
"eval_loss": 4.171698570251465,
|
| 382 |
+
"eval_runtime": 1.1928,
|
| 383 |
+
"eval_samples_per_second": 1467.17,
|
| 384 |
+
"eval_steps_per_second": 92.222,
|
| 385 |
+
"step": 66000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 45.13773647527381,
|
| 389 |
+
"grad_norm": 2.075021505355835,
|
| 390 |
+
"learning_rate": 5.338166666666668e-05,
|
| 391 |
+
"loss": 2.6626,
|
| 392 |
+
"step": 68000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 45.13773647527381,
|
| 396 |
+
"eval_loss": 4.188798904418945,
|
| 397 |
+
"eval_runtime": 1.2242,
|
| 398 |
+
"eval_samples_per_second": 1429.478,
|
| 399 |
+
"eval_steps_per_second": 89.853,
|
| 400 |
+
"step": 68000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 46.46531695984069,
|
| 404 |
+
"eval_loss": 4.200418949127197,
|
| 405 |
+
"eval_runtime": 1.2,
|
| 406 |
+
"eval_samples_per_second": 1458.315,
|
| 407 |
+
"eval_steps_per_second": 91.666,
|
| 408 |
+
"step": 70000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 47.792897444407565,
|
| 412 |
+
"grad_norm": 2.2053654193878174,
|
| 413 |
+
"learning_rate": 4.6718333333333336e-05,
|
| 414 |
+
"loss": 2.6203,
|
| 415 |
+
"step": 72000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 47.792897444407565,
|
| 419 |
+
"eval_loss": 4.213426113128662,
|
| 420 |
+
"eval_runtime": 1.1844,
|
| 421 |
+
"eval_samples_per_second": 1477.507,
|
| 422 |
+
"eval_steps_per_second": 92.872,
|
| 423 |
+
"step": 72000
|
| 424 |
+
}
|
| 425 |
+
],
|
| 426 |
+
"logging_steps": 4000,
|
| 427 |
+
"max_steps": 100000,
|
| 428 |
+
"num_input_tokens_seen": 0,
|
| 429 |
+
"num_train_epochs": 67,
|
| 430 |
+
"save_steps": 4000,
|
| 431 |
+
"stateful_callbacks": {
|
| 432 |
+
"TrainerControl": {
|
| 433 |
+
"args": {
|
| 434 |
+
"should_epoch_stop": false,
|
| 435 |
+
"should_evaluate": false,
|
| 436 |
+
"should_log": false,
|
| 437 |
+
"should_save": true,
|
| 438 |
+
"should_training_stop": false
|
| 439 |
+
},
|
| 440 |
+
"attributes": {}
|
| 441 |
+
}
|
| 442 |
+
},
|
| 443 |
+
"total_flos": 1.8614484940210176e+16,
|
| 444 |
+
"train_batch_size": 16,
|
| 445 |
+
"trial_name": null,
|
| 446 |
+
"trial_params": null
|
| 447 |
+
}
|
checkpoint-72000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b14000269a14dc69f619038c3611edf21a043ef764a94b5e099aa54cf929ad1d
|
| 3 |
+
size 5368
|