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:bfbbd6df2ab163fbdf89d19979c49fcb95be2b536fb82d1baa2827c72cb28b79
|
| 3 |
+
size 51007160
|
checkpoint-72000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7d868887533934ddb3bfa0f0c7686fc23a65b802ecfba6c5ba238f3113016d9
|
| 3 |
+
size 102078202
|
checkpoint-72000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93d1c762c930131c91ccc0335344afb21f1f7c2dd3c1304e5fcdca3de37584eb
|
| 3 |
+
size 14308
|
checkpoint-72000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:292474c5f96e51c44229e044bdf41a1a062d1d60891d459babe8d8fb38e57ea7
|
| 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": 4.224654674530029,
|
| 3 |
+
"best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/en_clm/wikipedia_30/checkpoint-72000",
|
| 4 |
+
"epoch": 37.86484354457008,
|
| 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": 1.0518012095713911,
|
| 13 |
+
"eval_loss": 7.518920421600342,
|
| 14 |
+
"eval_runtime": 2.2399,
|
| 15 |
+
"eval_samples_per_second": 1422.808,
|
| 16 |
+
"eval_steps_per_second": 89.288,
|
| 17 |
+
"step": 2000
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.1036024191427822,
|
| 21 |
+
"grad_norm": 1.2947496175765991,
|
| 22 |
+
"learning_rate": 1e-05,
|
| 23 |
+
"loss": 7.6141,
|
| 24 |
+
"step": 4000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.1036024191427822,
|
| 28 |
+
"eval_loss": 6.568221092224121,
|
| 29 |
+
"eval_runtime": 2.1236,
|
| 30 |
+
"eval_samples_per_second": 1500.783,
|
| 31 |
+
"eval_steps_per_second": 94.182,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.155403628714173,
|
| 36 |
+
"eval_loss": 6.16925573348999,
|
| 37 |
+
"eval_runtime": 2.1624,
|
| 38 |
+
"eval_samples_per_second": 1473.825,
|
| 39 |
+
"eval_steps_per_second": 92.49,
|
| 40 |
+
"step": 6000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 4.2072048382855645,
|
| 44 |
+
"grad_norm": 2.330080270767212,
|
| 45 |
+
"learning_rate": 2e-05,
|
| 46 |
+
"loss": 6.2396,
|
| 47 |
+
"step": 8000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 4.2072048382855645,
|
| 51 |
+
"eval_loss": 5.901575088500977,
|
| 52 |
+
"eval_runtime": 2.1326,
|
| 53 |
+
"eval_samples_per_second": 1494.388,
|
| 54 |
+
"eval_steps_per_second": 93.78,
|
| 55 |
+
"step": 8000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 5.259006047856955,
|
| 59 |
+
"eval_loss": 5.67369270324707,
|
| 60 |
+
"eval_runtime": 2.1364,
|
| 61 |
+
"eval_samples_per_second": 1491.788,
|
| 62 |
+
"eval_steps_per_second": 93.617,
|
| 63 |
+
"step": 10000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 6.310807257428346,
|
| 67 |
+
"grad_norm": 2.565220594406128,
|
| 68 |
+
"learning_rate": 2.99925e-05,
|
| 69 |
+
"loss": 5.7217,
|
| 70 |
+
"step": 12000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 6.310807257428346,
|
| 74 |
+
"eval_loss": 5.460005760192871,
|
| 75 |
+
"eval_runtime": 2.1835,
|
| 76 |
+
"eval_samples_per_second": 1459.563,
|
| 77 |
+
"eval_steps_per_second": 91.595,
|
| 78 |
+
"step": 12000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 7.362608466999737,
|
| 82 |
+
"eval_loss": 5.272489547729492,
|
| 83 |
+
"eval_runtime": 2.1833,
|
| 84 |
+
"eval_samples_per_second": 1459.691,
|
| 85 |
+
"eval_steps_per_second": 91.603,
|
| 86 |
+
"step": 14000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.414409676571129,
|
| 90 |
+
"grad_norm": 2.7334115505218506,
|
| 91 |
+
"learning_rate": 3.99875e-05,
|
| 92 |
+
"loss": 5.3064,
|
| 93 |
+
"step": 16000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.414409676571129,
|
| 97 |
+
"eval_loss": 5.1074652671813965,
|
| 98 |
+
"eval_runtime": 2.2402,
|
| 99 |
+
"eval_samples_per_second": 1422.652,
|
| 100 |
+
"eval_steps_per_second": 89.278,
|
| 101 |
+
"step": 16000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 9.46621088614252,
|
| 105 |
+
"eval_loss": 4.9716596603393555,
|
| 106 |
+
"eval_runtime": 2.1736,
|
| 107 |
+
"eval_samples_per_second": 1466.258,
|
| 108 |
+
"eval_steps_per_second": 92.015,
|
| 109 |
+
"step": 18000
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 10.51801209571391,
|
| 113 |
+
"grad_norm": 2.6722376346588135,
|
| 114 |
+
"learning_rate": 4.9985e-05,
|
| 115 |
+
"loss": 4.9744,
|
| 116 |
+
"step": 20000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 10.51801209571391,
|
| 120 |
+
"eval_loss": 4.864916801452637,
|
| 121 |
+
"eval_runtime": 2.2031,
|
| 122 |
+
"eval_samples_per_second": 1446.585,
|
| 123 |
+
"eval_steps_per_second": 90.78,
|
| 124 |
+
"step": 20000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 11.569813305285301,
|
| 128 |
+
"eval_loss": 4.763542652130127,
|
| 129 |
+
"eval_runtime": 2.4382,
|
| 130 |
+
"eval_samples_per_second": 1307.131,
|
| 131 |
+
"eval_steps_per_second": 82.029,
|
| 132 |
+
"step": 22000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 12.621614514856692,
|
| 136 |
+
"grad_norm": 2.4539408683776855,
|
| 137 |
+
"learning_rate": 5.9985e-05,
|
| 138 |
+
"loss": 4.7273,
|
| 139 |
+
"step": 24000
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 12.621614514856692,
|
| 143 |
+
"eval_loss": 4.683297634124756,
|
| 144 |
+
"eval_runtime": 2.452,
|
| 145 |
+
"eval_samples_per_second": 1299.733,
|
| 146 |
+
"eval_steps_per_second": 81.565,
|
| 147 |
+
"step": 24000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 13.673415724428082,
|
| 151 |
+
"eval_loss": 4.621574401855469,
|
| 152 |
+
"eval_runtime": 2.1825,
|
| 153 |
+
"eval_samples_per_second": 1460.226,
|
| 154 |
+
"eval_steps_per_second": 91.636,
|
| 155 |
+
"step": 26000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 14.725216933999475,
|
| 159 |
+
"grad_norm": 2.4913346767425537,
|
| 160 |
+
"learning_rate": 6.998e-05,
|
| 161 |
+
"loss": 4.5397,
|
| 162 |
+
"step": 28000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 14.725216933999475,
|
| 166 |
+
"eval_loss": 4.562623977661133,
|
| 167 |
+
"eval_runtime": 2.201,
|
| 168 |
+
"eval_samples_per_second": 1447.965,
|
| 169 |
+
"eval_steps_per_second": 90.867,
|
| 170 |
+
"step": 28000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 15.777018143570865,
|
| 174 |
+
"eval_loss": 4.506168842315674,
|
| 175 |
+
"eval_runtime": 2.2491,
|
| 176 |
+
"eval_samples_per_second": 1416.988,
|
| 177 |
+
"eval_steps_per_second": 88.923,
|
| 178 |
+
"step": 30000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 16.828819353142258,
|
| 182 |
+
"grad_norm": 2.2661523818969727,
|
| 183 |
+
"learning_rate": 7.99775e-05,
|
| 184 |
+
"loss": 4.3839,
|
| 185 |
+
"step": 32000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 16.828819353142258,
|
| 189 |
+
"eval_loss": 4.464449882507324,
|
| 190 |
+
"eval_runtime": 2.253,
|
| 191 |
+
"eval_samples_per_second": 1414.55,
|
| 192 |
+
"eval_steps_per_second": 88.77,
|
| 193 |
+
"step": 32000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 17.88062056271365,
|
| 197 |
+
"eval_loss": 4.426318168640137,
|
| 198 |
+
"eval_runtime": 2.2688,
|
| 199 |
+
"eval_samples_per_second": 1404.709,
|
| 200 |
+
"eval_steps_per_second": 88.152,
|
| 201 |
+
"step": 34000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 18.93242177228504,
|
| 205 |
+
"grad_norm": 2.226025104522705,
|
| 206 |
+
"learning_rate": 8.9975e-05,
|
| 207 |
+
"loss": 4.2529,
|
| 208 |
+
"step": 36000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 18.93242177228504,
|
| 212 |
+
"eval_loss": 4.3944478034973145,
|
| 213 |
+
"eval_runtime": 2.294,
|
| 214 |
+
"eval_samples_per_second": 1389.273,
|
| 215 |
+
"eval_steps_per_second": 87.184,
|
| 216 |
+
"step": 36000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 19.98422298185643,
|
| 220 |
+
"eval_loss": 4.365135669708252,
|
| 221 |
+
"eval_runtime": 2.2176,
|
| 222 |
+
"eval_samples_per_second": 1437.165,
|
| 223 |
+
"eval_steps_per_second": 90.189,
|
| 224 |
+
"step": 38000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 21.03602419142782,
|
| 228 |
+
"grad_norm": 2.1669206619262695,
|
| 229 |
+
"learning_rate": 9.997e-05,
|
| 230 |
+
"loss": 4.1409,
|
| 231 |
+
"step": 40000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 21.03602419142782,
|
| 235 |
+
"eval_loss": 4.351284503936768,
|
| 236 |
+
"eval_runtime": 2.1934,
|
| 237 |
+
"eval_samples_per_second": 1453.028,
|
| 238 |
+
"eval_steps_per_second": 91.185,
|
| 239 |
+
"step": 40000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 22.08782540099921,
|
| 243 |
+
"eval_loss": 4.321634292602539,
|
| 244 |
+
"eval_runtime": 2.2273,
|
| 245 |
+
"eval_samples_per_second": 1430.895,
|
| 246 |
+
"eval_steps_per_second": 89.796,
|
| 247 |
+
"step": 42000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 23.139626610570602,
|
| 251 |
+
"grad_norm": 2.0360896587371826,
|
| 252 |
+
"learning_rate": 9.335333333333333e-05,
|
| 253 |
+
"loss": 4.0334,
|
| 254 |
+
"step": 44000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 23.139626610570602,
|
| 258 |
+
"eval_loss": 4.300807476043701,
|
| 259 |
+
"eval_runtime": 2.3226,
|
| 260 |
+
"eval_samples_per_second": 1372.142,
|
| 261 |
+
"eval_steps_per_second": 86.109,
|
| 262 |
+
"step": 44000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 24.191427820141993,
|
| 266 |
+
"eval_loss": 4.279116153717041,
|
| 267 |
+
"eval_runtime": 2.2177,
|
| 268 |
+
"eval_samples_per_second": 1437.082,
|
| 269 |
+
"eval_steps_per_second": 90.184,
|
| 270 |
+
"step": 46000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 25.243229029713383,
|
| 274 |
+
"grad_norm": 2.137535572052002,
|
| 275 |
+
"learning_rate": 8.668833333333334e-05,
|
| 276 |
+
"loss": 3.9378,
|
| 277 |
+
"step": 48000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 25.243229029713383,
|
| 281 |
+
"eval_loss": 4.2718939781188965,
|
| 282 |
+
"eval_runtime": 2.2019,
|
| 283 |
+
"eval_samples_per_second": 1447.39,
|
| 284 |
+
"eval_steps_per_second": 90.831,
|
| 285 |
+
"step": 48000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 26.295030239284774,
|
| 289 |
+
"eval_loss": 4.26237678527832,
|
| 290 |
+
"eval_runtime": 2.2417,
|
| 291 |
+
"eval_samples_per_second": 1421.698,
|
| 292 |
+
"eval_steps_per_second": 89.219,
|
| 293 |
+
"step": 50000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 27.346831448856165,
|
| 297 |
+
"grad_norm": 2.1131036281585693,
|
| 298 |
+
"learning_rate": 8.002333333333334e-05,
|
| 299 |
+
"loss": 3.8595,
|
| 300 |
+
"step": 52000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 27.346831448856165,
|
| 304 |
+
"eval_loss": 4.253220558166504,
|
| 305 |
+
"eval_runtime": 2.2045,
|
| 306 |
+
"eval_samples_per_second": 1445.692,
|
| 307 |
+
"eval_steps_per_second": 90.724,
|
| 308 |
+
"step": 52000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 28.39863265842756,
|
| 312 |
+
"eval_loss": 4.243188381195068,
|
| 313 |
+
"eval_runtime": 2.1654,
|
| 314 |
+
"eval_samples_per_second": 1471.751,
|
| 315 |
+
"eval_steps_per_second": 92.36,
|
| 316 |
+
"step": 54000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 29.45043386799895,
|
| 320 |
+
"grad_norm": 2.1626858711242676,
|
| 321 |
+
"learning_rate": 7.335833333333335e-05,
|
| 322 |
+
"loss": 3.7927,
|
| 323 |
+
"step": 56000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 29.45043386799895,
|
| 327 |
+
"eval_loss": 4.237761974334717,
|
| 328 |
+
"eval_runtime": 2.3384,
|
| 329 |
+
"eval_samples_per_second": 1362.919,
|
| 330 |
+
"eval_steps_per_second": 85.53,
|
| 331 |
+
"step": 56000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 30.50223507757034,
|
| 335 |
+
"eval_loss": 4.237727165222168,
|
| 336 |
+
"eval_runtime": 2.2527,
|
| 337 |
+
"eval_samples_per_second": 1414.746,
|
| 338 |
+
"eval_steps_per_second": 88.782,
|
| 339 |
+
"step": 58000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 31.55403628714173,
|
| 343 |
+
"grad_norm": 2.1217854022979736,
|
| 344 |
+
"learning_rate": 6.669333333333334e-05,
|
| 345 |
+
"loss": 3.7367,
|
| 346 |
+
"step": 60000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 31.55403628714173,
|
| 350 |
+
"eval_loss": 4.233393669128418,
|
| 351 |
+
"eval_runtime": 2.2874,
|
| 352 |
+
"eval_samples_per_second": 1393.302,
|
| 353 |
+
"eval_steps_per_second": 87.437,
|
| 354 |
+
"step": 60000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 32.60583749671312,
|
| 358 |
+
"eval_loss": 4.229984283447266,
|
| 359 |
+
"eval_runtime": 2.3158,
|
| 360 |
+
"eval_samples_per_second": 1376.171,
|
| 361 |
+
"eval_steps_per_second": 86.362,
|
| 362 |
+
"step": 62000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 33.657638706284516,
|
| 366 |
+
"grad_norm": 2.3173110485076904,
|
| 367 |
+
"learning_rate": 6.003e-05,
|
| 368 |
+
"loss": 3.6869,
|
| 369 |
+
"step": 64000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 33.657638706284516,
|
| 373 |
+
"eval_loss": 4.226880073547363,
|
| 374 |
+
"eval_runtime": 2.3034,
|
| 375 |
+
"eval_samples_per_second": 1383.631,
|
| 376 |
+
"eval_steps_per_second": 86.83,
|
| 377 |
+
"step": 64000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 34.7094399158559,
|
| 381 |
+
"eval_loss": 4.224526405334473,
|
| 382 |
+
"eval_runtime": 2.2795,
|
| 383 |
+
"eval_samples_per_second": 1398.138,
|
| 384 |
+
"eval_steps_per_second": 87.74,
|
| 385 |
+
"step": 66000
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 35.7612411254273,
|
| 389 |
+
"grad_norm": 2.3296120166778564,
|
| 390 |
+
"learning_rate": 5.336333333333333e-05,
|
| 391 |
+
"loss": 3.6416,
|
| 392 |
+
"step": 68000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 35.7612411254273,
|
| 396 |
+
"eval_loss": 4.225712299346924,
|
| 397 |
+
"eval_runtime": 2.2719,
|
| 398 |
+
"eval_samples_per_second": 1402.762,
|
| 399 |
+
"eval_steps_per_second": 88.03,
|
| 400 |
+
"step": 68000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 36.813042334998684,
|
| 404 |
+
"eval_loss": 4.220585346221924,
|
| 405 |
+
"eval_runtime": 2.2631,
|
| 406 |
+
"eval_samples_per_second": 1408.243,
|
| 407 |
+
"eval_steps_per_second": 88.374,
|
| 408 |
+
"step": 70000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 37.86484354457008,
|
| 412 |
+
"grad_norm": 2.309408187866211,
|
| 413 |
+
"learning_rate": 4.669833333333333e-05,
|
| 414 |
+
"loss": 3.6032,
|
| 415 |
+
"step": 72000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 37.86484354457008,
|
| 419 |
+
"eval_loss": 4.224654674530029,
|
| 420 |
+
"eval_runtime": 2.272,
|
| 421 |
+
"eval_samples_per_second": 1402.745,
|
| 422 |
+
"eval_steps_per_second": 88.029,
|
| 423 |
+
"step": 72000
|
| 424 |
+
}
|
| 425 |
+
],
|
| 426 |
+
"logging_steps": 4000,
|
| 427 |
+
"max_steps": 100000,
|
| 428 |
+
"num_input_tokens_seen": 0,
|
| 429 |
+
"num_train_epochs": 53,
|
| 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": 1.861227910994227e+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:ab68434ec7156d3a63e4783f824871a48d62c7c2fdcc831fdd5471c5f4aec7fe
|
| 3 |
+
size 5368
|