Training in progress, step 68000, checkpoint
Browse files- checkpoint-68000/config.json +32 -0
- checkpoint-68000/generation_config.json +6 -0
- checkpoint-68000/model.safetensors +3 -0
- checkpoint-68000/optimizer.pt +3 -0
- checkpoint-68000/rng_state.pth +3 -0
- checkpoint-68000/scheduler.pt +3 -0
- checkpoint-68000/special_tokens_map.json +34 -0
- checkpoint-68000/tokenizer.json +0 -0
- checkpoint-68000/tokenizer_config.json +63 -0
- checkpoint-68000/trainer_state.json +424 -0
- checkpoint-68000/training_args.bin +3 -0
checkpoint-68000/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-68000/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-68000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7280f85993dd010b21de53e47e8a3d02b5c1a4e4b35d4ad53485329a5dbaf9b
|
| 3 |
+
size 51007160
|
checkpoint-68000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aef6a2928019dabc5e40a83636e4f6872009f28bf36141ba6f9c11f5a75c6a57
|
| 3 |
+
size 102078202
|
checkpoint-68000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:515d4cdb68d3cad87c85057cf8625b7cfa7044b43f2784154506ffa5a1a21be4
|
| 3 |
+
size 14308
|
checkpoint-68000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9104f8454b0213557695d6ff59096df15107752b926c4f20c1e7c073203e326
|
| 3 |
+
size 1000
|
checkpoint-68000/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-68000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-68000/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-68000/trainer_state.json
ADDED
|
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 4.032560348510742,
|
| 3 |
+
"best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/en_clm/childes_30/checkpoint-36000",
|
| 4 |
+
"epoch": 45.13773647527381,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 68000,
|
| 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": 6.8483405113220215,
|
| 14 |
+
"eval_runtime": 1.2535,
|
| 15 |
+
"eval_samples_per_second": 1396.096,
|
| 16 |
+
"eval_steps_per_second": 87.755,
|
| 17 |
+
"step": 2000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.6551609691337537,
|
| 21 |
+
"grad_norm": 1.5963196754455566,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 6.7292,
|
| 24 |
+
"step": 4000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.6551609691337537,
|
| 28 |
+
"eval_loss": 5.239430904388428,
|
| 29 |
+
"eval_runtime": 1.2364,
|
| 30 |
+
"eval_samples_per_second": 1415.409,
|
| 31 |
+
"eval_steps_per_second": 88.969,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.9827414537006307,
|
| 36 |
+
"eval_loss": 4.829074859619141,
|
| 37 |
+
"eval_runtime": 1.2415,
|
| 38 |
+
"eval_samples_per_second": 1409.56,
|
| 39 |
+
"eval_steps_per_second": 88.601,
|
| 40 |
+
"step": 6000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 5.310321938267507,
|
| 44 |
+
"grad_norm": 2.6859147548675537,
|
| 45 |
+
"learning_rate": 1.9997500000000003e-05,
|
| 46 |
+
"loss": 4.5966,
|
| 47 |
+
"step": 8000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 5.310321938267507,
|
| 51 |
+
"eval_loss": 4.593608856201172,
|
| 52 |
+
"eval_runtime": 1.2358,
|
| 53 |
+
"eval_samples_per_second": 1416.133,
|
| 54 |
+
"eval_steps_per_second": 89.014,
|
| 55 |
+
"step": 8000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 6.637902422834385,
|
| 59 |
+
"eval_loss": 4.449240684509277,
|
| 60 |
+
"eval_runtime": 1.3247,
|
| 61 |
+
"eval_samples_per_second": 1321.089,
|
| 62 |
+
"eval_steps_per_second": 83.04,
|
| 63 |
+
"step": 10000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.965482907401261,
|
| 67 |
+
"grad_norm": 2.4272868633270264,
|
| 68 |
+
"learning_rate": 2.9995e-05,
|
| 69 |
+
"loss": 4.1336,
|
| 70 |
+
"step": 12000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 7.965482907401261,
|
| 74 |
+
"eval_loss": 4.348520278930664,
|
| 75 |
+
"eval_runtime": 1.2394,
|
| 76 |
+
"eval_samples_per_second": 1411.988,
|
| 77 |
+
"eval_steps_per_second": 88.754,
|
| 78 |
+
"step": 12000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 9.293063391968138,
|
| 82 |
+
"eval_loss": 4.277740955352783,
|
| 83 |
+
"eval_runtime": 1.2759,
|
| 84 |
+
"eval_samples_per_second": 1371.628,
|
| 85 |
+
"eval_steps_per_second": 86.217,
|
| 86 |
+
"step": 14000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 10.620643876535015,
|
| 90 |
+
"grad_norm": 2.4516773223876953,
|
| 91 |
+
"learning_rate": 3.999e-05,
|
| 92 |
+
"loss": 3.8576,
|
| 93 |
+
"step": 16000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 10.620643876535015,
|
| 97 |
+
"eval_loss": 4.223555564880371,
|
| 98 |
+
"eval_runtime": 1.2226,
|
| 99 |
+
"eval_samples_per_second": 1431.375,
|
| 100 |
+
"eval_steps_per_second": 89.972,
|
| 101 |
+
"step": 16000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 11.948224361101891,
|
| 105 |
+
"eval_loss": 4.18381929397583,
|
| 106 |
+
"eval_runtime": 1.2371,
|
| 107 |
+
"eval_samples_per_second": 1414.6,
|
| 108 |
+
"eval_steps_per_second": 88.918,
|
| 109 |
+
"step": 18000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 13.275804845668768,
|
| 113 |
+
"grad_norm": 2.2412021160125732,
|
| 114 |
+
"learning_rate": 4.9985e-05,
|
| 115 |
+
"loss": 3.6557,
|
| 116 |
+
"step": 20000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 13.275804845668768,
|
| 120 |
+
"eval_loss": 4.157003879547119,
|
| 121 |
+
"eval_runtime": 1.238,
|
| 122 |
+
"eval_samples_per_second": 1413.601,
|
| 123 |
+
"eval_steps_per_second": 88.855,
|
| 124 |
+
"step": 20000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 14.603385330235646,
|
| 128 |
+
"eval_loss": 4.130462646484375,
|
| 129 |
+
"eval_runtime": 1.2695,
|
| 130 |
+
"eval_samples_per_second": 1378.51,
|
| 131 |
+
"eval_steps_per_second": 86.649,
|
| 132 |
+
"step": 22000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 15.930965814802523,
|
| 136 |
+
"grad_norm": 2.039700508117676,
|
| 137 |
+
"learning_rate": 5.9980000000000005e-05,
|
| 138 |
+
"loss": 3.4956,
|
| 139 |
+
"step": 24000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 15.930965814802523,
|
| 143 |
+
"eval_loss": 4.100128173828125,
|
| 144 |
+
"eval_runtime": 1.2566,
|
| 145 |
+
"eval_samples_per_second": 1392.686,
|
| 146 |
+
"eval_steps_per_second": 87.54,
|
| 147 |
+
"step": 24000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 17.2585462993694,
|
| 151 |
+
"eval_loss": 4.096436500549316,
|
| 152 |
+
"eval_runtime": 1.2377,
|
| 153 |
+
"eval_samples_per_second": 1413.914,
|
| 154 |
+
"eval_steps_per_second": 88.875,
|
| 155 |
+
"step": 26000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 18.586126783936276,
|
| 159 |
+
"grad_norm": 1.9197760820388794,
|
| 160 |
+
"learning_rate": 6.997500000000001e-05,
|
| 161 |
+
"loss": 3.361,
|
| 162 |
+
"step": 28000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 18.586126783936276,
|
| 166 |
+
"eval_loss": 4.0739641189575195,
|
| 167 |
+
"eval_runtime": 1.2403,
|
| 168 |
+
"eval_samples_per_second": 1410.995,
|
| 169 |
+
"eval_steps_per_second": 88.691,
|
| 170 |
+
"step": 28000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 19.913707268503153,
|
| 174 |
+
"eval_loss": 4.063148498535156,
|
| 175 |
+
"eval_runtime": 1.2518,
|
| 176 |
+
"eval_samples_per_second": 1397.962,
|
| 177 |
+
"eval_steps_per_second": 87.872,
|
| 178 |
+
"step": 30000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 21.24128775307003,
|
| 182 |
+
"grad_norm": 1.876952052116394,
|
| 183 |
+
"learning_rate": 7.997e-05,
|
| 184 |
+
"loss": 3.2519,
|
| 185 |
+
"step": 32000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 21.24128775307003,
|
| 189 |
+
"eval_loss": 4.057435989379883,
|
| 190 |
+
"eval_runtime": 1.2475,
|
| 191 |
+
"eval_samples_per_second": 1402.804,
|
| 192 |
+
"eval_steps_per_second": 88.176,
|
| 193 |
+
"step": 32000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 22.568868237636906,
|
| 197 |
+
"eval_loss": 4.046254634857178,
|
| 198 |
+
"eval_runtime": 1.2449,
|
| 199 |
+
"eval_samples_per_second": 1405.778,
|
| 200 |
+
"eval_steps_per_second": 88.363,
|
| 201 |
+
"step": 34000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 23.896448722203782,
|
| 205 |
+
"grad_norm": 1.6455930471420288,
|
| 206 |
+
"learning_rate": 8.9965e-05,
|
| 207 |
+
"loss": 3.161,
|
| 208 |
+
"step": 36000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 23.896448722203782,
|
| 212 |
+
"eval_loss": 4.032560348510742,
|
| 213 |
+
"eval_runtime": 1.3178,
|
| 214 |
+
"eval_samples_per_second": 1327.922,
|
| 215 |
+
"eval_steps_per_second": 83.469,
|
| 216 |
+
"step": 36000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 25.22402920677066,
|
| 220 |
+
"eval_loss": 4.040252685546875,
|
| 221 |
+
"eval_runtime": 1.2979,
|
| 222 |
+
"eval_samples_per_second": 1348.383,
|
| 223 |
+
"eval_steps_per_second": 84.756,
|
| 224 |
+
"step": 38000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 26.551609691337536,
|
| 228 |
+
"grad_norm": 1.6423633098602295,
|
| 229 |
+
"learning_rate": 9.996000000000001e-05,
|
| 230 |
+
"loss": 3.0792,
|
| 231 |
+
"step": 40000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 26.551609691337536,
|
| 235 |
+
"eval_loss": 4.043528079986572,
|
| 236 |
+
"eval_runtime": 1.2275,
|
| 237 |
+
"eval_samples_per_second": 1425.607,
|
| 238 |
+
"eval_steps_per_second": 89.61,
|
| 239 |
+
"step": 40000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 27.879190175904416,
|
| 243 |
+
"eval_loss": 4.034181594848633,
|
| 244 |
+
"eval_runtime": 1.2573,
|
| 245 |
+
"eval_samples_per_second": 1391.847,
|
| 246 |
+
"eval_steps_per_second": 87.488,
|
| 247 |
+
"step": 42000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 29.206770660471292,
|
| 251 |
+
"grad_norm": 1.733888030052185,
|
| 252 |
+
"learning_rate": 9.336333333333334e-05,
|
| 253 |
+
"loss": 3.0042,
|
| 254 |
+
"step": 44000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 29.206770660471292,
|
| 258 |
+
"eval_loss": 4.05541467666626,
|
| 259 |
+
"eval_runtime": 1.3037,
|
| 260 |
+
"eval_samples_per_second": 1342.376,
|
| 261 |
+
"eval_steps_per_second": 84.378,
|
| 262 |
+
"step": 44000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 30.53435114503817,
|
| 266 |
+
"eval_loss": 4.049606800079346,
|
| 267 |
+
"eval_runtime": 1.2277,
|
| 268 |
+
"eval_samples_per_second": 1425.421,
|
| 269 |
+
"eval_steps_per_second": 89.598,
|
| 270 |
+
"step": 46000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 31.861931629605046,
|
| 274 |
+
"grad_norm": 1.617918848991394,
|
| 275 |
+
"learning_rate": 8.67e-05,
|
| 276 |
+
"loss": 2.9291,
|
| 277 |
+
"step": 48000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 31.861931629605046,
|
| 281 |
+
"eval_loss": 4.0561981201171875,
|
| 282 |
+
"eval_runtime": 1.3017,
|
| 283 |
+
"eval_samples_per_second": 1344.376,
|
| 284 |
+
"eval_steps_per_second": 84.504,
|
| 285 |
+
"step": 48000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 33.18951211417192,
|
| 289 |
+
"eval_loss": 4.076622009277344,
|
| 290 |
+
"eval_runtime": 1.3288,
|
| 291 |
+
"eval_samples_per_second": 1317.0,
|
| 292 |
+
"eval_steps_per_second": 82.783,
|
| 293 |
+
"step": 50000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 34.5170925987388,
|
| 297 |
+
"grad_norm": 1.756861925125122,
|
| 298 |
+
"learning_rate": 8.003666666666667e-05,
|
| 299 |
+
"loss": 2.86,
|
| 300 |
+
"step": 52000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 34.5170925987388,
|
| 304 |
+
"eval_loss": 4.081105709075928,
|
| 305 |
+
"eval_runtime": 1.3275,
|
| 306 |
+
"eval_samples_per_second": 1318.234,
|
| 307 |
+
"eval_steps_per_second": 82.86,
|
| 308 |
+
"step": 52000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 35.84467308330567,
|
| 312 |
+
"eval_loss": 4.090775489807129,
|
| 313 |
+
"eval_runtime": 1.2283,
|
| 314 |
+
"eval_samples_per_second": 1424.695,
|
| 315 |
+
"eval_steps_per_second": 89.552,
|
| 316 |
+
"step": 54000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 37.17225356787255,
|
| 320 |
+
"grad_norm": 1.795430302619934,
|
| 321 |
+
"learning_rate": 7.337333333333334e-05,
|
| 322 |
+
"loss": 2.8053,
|
| 323 |
+
"step": 56000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 37.17225356787255,
|
| 327 |
+
"eval_loss": 4.113212585449219,
|
| 328 |
+
"eval_runtime": 1.2612,
|
| 329 |
+
"eval_samples_per_second": 1387.586,
|
| 330 |
+
"eval_steps_per_second": 87.22,
|
| 331 |
+
"step": 56000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 38.49983405243943,
|
| 335 |
+
"eval_loss": 4.122709274291992,
|
| 336 |
+
"eval_runtime": 1.2628,
|
| 337 |
+
"eval_samples_per_second": 1385.764,
|
| 338 |
+
"eval_steps_per_second": 87.105,
|
| 339 |
+
"step": 58000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 39.827414537006305,
|
| 343 |
+
"grad_norm": 1.8639148473739624,
|
| 344 |
+
"learning_rate": 6.671e-05,
|
| 345 |
+
"loss": 2.7515,
|
| 346 |
+
"step": 60000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 39.827414537006305,
|
| 350 |
+
"eval_loss": 4.12427282333374,
|
| 351 |
+
"eval_runtime": 1.3426,
|
| 352 |
+
"eval_samples_per_second": 1303.402,
|
| 353 |
+
"eval_steps_per_second": 81.928,
|
| 354 |
+
"step": 60000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 41.154995021573185,
|
| 358 |
+
"eval_loss": 4.149072647094727,
|
| 359 |
+
"eval_runtime": 1.2735,
|
| 360 |
+
"eval_samples_per_second": 1374.132,
|
| 361 |
+
"eval_steps_per_second": 86.374,
|
| 362 |
+
"step": 62000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 42.48257550614006,
|
| 366 |
+
"grad_norm": 2.03680682182312,
|
| 367 |
+
"learning_rate": 6.0046666666666676e-05,
|
| 368 |
+
"loss": 2.7025,
|
| 369 |
+
"step": 64000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 42.48257550614006,
|
| 373 |
+
"eval_loss": 4.15885591506958,
|
| 374 |
+
"eval_runtime": 1.3238,
|
| 375 |
+
"eval_samples_per_second": 1321.989,
|
| 376 |
+
"eval_steps_per_second": 83.096,
|
| 377 |
+
"step": 64000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 43.81015599070694,
|
| 381 |
+
"eval_loss": 4.177003860473633,
|
| 382 |
+
"eval_runtime": 1.234,
|
| 383 |
+
"eval_samples_per_second": 1418.12,
|
| 384 |
+
"eval_steps_per_second": 89.139,
|
| 385 |
+
"step": 66000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 45.13773647527381,
|
| 389 |
+
"grad_norm": 1.9955369234085083,
|
| 390 |
+
"learning_rate": 5.338166666666668e-05,
|
| 391 |
+
"loss": 2.6629,
|
| 392 |
+
"step": 68000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 45.13773647527381,
|
| 396 |
+
"eval_loss": 4.193336486816406,
|
| 397 |
+
"eval_runtime": 1.264,
|
| 398 |
+
"eval_samples_per_second": 1384.509,
|
| 399 |
+
"eval_steps_per_second": 87.026,
|
| 400 |
+
"step": 68000
|
| 401 |
+
}
|
| 402 |
+
],
|
| 403 |
+
"logging_steps": 4000,
|
| 404 |
+
"max_steps": 100000,
|
| 405 |
+
"num_input_tokens_seen": 0,
|
| 406 |
+
"num_train_epochs": 67,
|
| 407 |
+
"save_steps": 4000,
|
| 408 |
+
"stateful_callbacks": {
|
| 409 |
+
"TrainerControl": {
|
| 410 |
+
"args": {
|
| 411 |
+
"should_epoch_stop": false,
|
| 412 |
+
"should_evaluate": false,
|
| 413 |
+
"should_log": false,
|
| 414 |
+
"should_save": true,
|
| 415 |
+
"should_training_stop": false
|
| 416 |
+
},
|
| 417 |
+
"attributes": {}
|
| 418 |
+
}
|
| 419 |
+
},
|
| 420 |
+
"total_flos": 1.7580317877829632e+16,
|
| 421 |
+
"train_batch_size": 16,
|
| 422 |
+
"trial_name": null,
|
| 423 |
+
"trial_params": null
|
| 424 |
+
}
|
checkpoint-68000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85a361fa7873534a4ba4b592e19d32a6f23bc55630c1df486f010c443c87a5fa
|
| 3 |
+
size 5368
|