Training in progress, step 20000, checkpoint
Browse files- checkpoint-20000/config.json +39 -0
- checkpoint-20000/generation_config.json +6 -0
- checkpoint-20000/model.safetensors +3 -0
- checkpoint-20000/optimizer.pt +3 -0
- checkpoint-20000/rng_state.pth +3 -0
- checkpoint-20000/scheduler.pt +3 -0
- checkpoint-20000/special_tokens_map.json +17 -0
- checkpoint-20000/tokenizer.json +0 -0
- checkpoint-20000/tokenizer_config.json +58 -0
- checkpoint-20000/trainer_state.json +482 -0
- checkpoint-20000/training_args.bin +3 -0
checkpoint-20000/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 5,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 4,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 128,
|
| 16 |
+
"n_head": 4,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 4,
|
| 19 |
+
"n_positions": 128,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.45.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 8192
|
| 39 |
+
}
|
checkpoint-20000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 5,
|
| 4 |
+
"eos_token_id": 4,
|
| 5 |
+
"transformers_version": "4.45.2"
|
| 6 |
+
}
|
checkpoint-20000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3786b5dc84ca0709fd77a79cd3e3c2739c964fe3ced9aa52a5d589fb3a1349f
|
| 3 |
+
size 7438256
|
checkpoint-20000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7df2391c0226c4c5c1a4a0d6006525615bf0e8d63481404e5dcd9cdc6fcc017f
|
| 3 |
+
size 14910010
|
checkpoint-20000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfcc772264c28783d526300da0e4706601be3a40cafc7e8e962d8a7454fe75a8
|
| 3 |
+
size 14244
|
checkpoint-20000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c39e8e6003ee1ce7fd365740a490e745fdbefc004d2166e31f818189d86ab0e2
|
| 3 |
+
size 1192
|
checkpoint-20000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[BOS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "[EOS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "[EOS]"
|
| 17 |
+
}
|
checkpoint-20000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-20000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[PAD]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[EOS]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "[BOS]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "[BOS]",
|
| 53 |
+
"clean_up_tokenization_spaces": true,
|
| 54 |
+
"eos_token": "[EOS]",
|
| 55 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 56 |
+
"pad_token": "[EOS]",
|
| 57 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 58 |
+
}
|
checkpoint-20000/trainer_state.json
ADDED
|
@@ -0,0 +1,482 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.385756731033325,
|
| 3 |
+
"best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/reduce_on_plateau_convergence/reverse_transcript_conv/checkpoint-20000",
|
| 4 |
+
"epoch": 0.5079107092973055,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 20000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.012697767732432638,
|
| 13 |
+
"grad_norm": 0.7031459212303162,
|
| 14 |
+
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 5.9982,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.025395535464865275,
|
| 20 |
+
"grad_norm": 0.9951984286308289,
|
| 21 |
+
"learning_rate": 0.0001,
|
| 22 |
+
"loss": 4.6781,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.025395535464865275,
|
| 27 |
+
"eval_loss": 4.492164134979248,
|
| 28 |
+
"eval_runtime": 1.8887,
|
| 29 |
+
"eval_samples_per_second": 926.554,
|
| 30 |
+
"eval_steps_per_second": 29.12,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.038093303197297916,
|
| 35 |
+
"grad_norm": 1.1115003824234009,
|
| 36 |
+
"learning_rate": 0.0001,
|
| 37 |
+
"loss": 4.4287,
|
| 38 |
+
"step": 1500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.05079107092973055,
|
| 42 |
+
"grad_norm": 1.2646763324737549,
|
| 43 |
+
"learning_rate": 0.0001,
|
| 44 |
+
"loss": 4.3077,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05079107092973055,
|
| 49 |
+
"eval_loss": 4.193817615509033,
|
| 50 |
+
"eval_runtime": 1.9023,
|
| 51 |
+
"eval_samples_per_second": 919.931,
|
| 52 |
+
"eval_steps_per_second": 28.912,
|
| 53 |
+
"step": 2000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.06348883866216319,
|
| 57 |
+
"grad_norm": 1.2905216217041016,
|
| 58 |
+
"learning_rate": 0.0001,
|
| 59 |
+
"loss": 4.1818,
|
| 60 |
+
"step": 2500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.07618660639459583,
|
| 64 |
+
"grad_norm": 1.5324379205703735,
|
| 65 |
+
"learning_rate": 0.0001,
|
| 66 |
+
"loss": 4.112,
|
| 67 |
+
"step": 3000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.07618660639459583,
|
| 71 |
+
"eval_loss": 4.043661117553711,
|
| 72 |
+
"eval_runtime": 1.8938,
|
| 73 |
+
"eval_samples_per_second": 924.072,
|
| 74 |
+
"eval_steps_per_second": 29.042,
|
| 75 |
+
"step": 3000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.08888437412702847,
|
| 79 |
+
"grad_norm": 1.7770308256149292,
|
| 80 |
+
"learning_rate": 0.0001,
|
| 81 |
+
"loss": 4.0753,
|
| 82 |
+
"step": 3500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.1015821418594611,
|
| 86 |
+
"grad_norm": 1.4286599159240723,
|
| 87 |
+
"learning_rate": 0.0001,
|
| 88 |
+
"loss": 4.0246,
|
| 89 |
+
"step": 4000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.1015821418594611,
|
| 93 |
+
"eval_loss": 3.935971260070801,
|
| 94 |
+
"eval_runtime": 1.8952,
|
| 95 |
+
"eval_samples_per_second": 923.363,
|
| 96 |
+
"eval_steps_per_second": 29.02,
|
| 97 |
+
"step": 4000
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.11427990959189374,
|
| 101 |
+
"grad_norm": 1.7079145908355713,
|
| 102 |
+
"learning_rate": 0.0001,
|
| 103 |
+
"loss": 3.9216,
|
| 104 |
+
"step": 4500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.12697767732432638,
|
| 108 |
+
"grad_norm": 1.6703156232833862,
|
| 109 |
+
"learning_rate": 0.0001,
|
| 110 |
+
"loss": 3.9453,
|
| 111 |
+
"step": 5000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.12697767732432638,
|
| 115 |
+
"eval_loss": 3.8490827083587646,
|
| 116 |
+
"eval_runtime": 1.907,
|
| 117 |
+
"eval_samples_per_second": 917.653,
|
| 118 |
+
"eval_steps_per_second": 28.841,
|
| 119 |
+
"step": 5000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.13967544505675902,
|
| 123 |
+
"grad_norm": 1.6159180402755737,
|
| 124 |
+
"learning_rate": 0.0001,
|
| 125 |
+
"loss": 3.8916,
|
| 126 |
+
"step": 5500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.15237321278919166,
|
| 130 |
+
"grad_norm": 1.5540586709976196,
|
| 131 |
+
"learning_rate": 0.0001,
|
| 132 |
+
"loss": 3.8408,
|
| 133 |
+
"step": 6000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.15237321278919166,
|
| 137 |
+
"eval_loss": 3.8077876567840576,
|
| 138 |
+
"eval_runtime": 1.9312,
|
| 139 |
+
"eval_samples_per_second": 906.171,
|
| 140 |
+
"eval_steps_per_second": 28.48,
|
| 141 |
+
"step": 6000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1650709805216243,
|
| 145 |
+
"grad_norm": 1.6115421056747437,
|
| 146 |
+
"learning_rate": 0.0001,
|
| 147 |
+
"loss": 3.8216,
|
| 148 |
+
"step": 6500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.17776874825405695,
|
| 152 |
+
"grad_norm": 1.6438881158828735,
|
| 153 |
+
"learning_rate": 0.0001,
|
| 154 |
+
"loss": 3.8155,
|
| 155 |
+
"step": 7000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.17776874825405695,
|
| 159 |
+
"eval_loss": 3.724748373031616,
|
| 160 |
+
"eval_runtime": 2.2357,
|
| 161 |
+
"eval_samples_per_second": 782.742,
|
| 162 |
+
"eval_steps_per_second": 24.6,
|
| 163 |
+
"step": 7000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1904665159864896,
|
| 167 |
+
"grad_norm": 1.5831265449523926,
|
| 168 |
+
"learning_rate": 0.0001,
|
| 169 |
+
"loss": 3.7525,
|
| 170 |
+
"step": 7500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2031642837189222,
|
| 174 |
+
"grad_norm": 1.6130567789077759,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 3.7213,
|
| 177 |
+
"step": 8000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2031642837189222,
|
| 181 |
+
"eval_loss": 3.696767807006836,
|
| 182 |
+
"eval_runtime": 1.8961,
|
| 183 |
+
"eval_samples_per_second": 922.949,
|
| 184 |
+
"eval_steps_per_second": 29.007,
|
| 185 |
+
"step": 8000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.21586205145135484,
|
| 189 |
+
"grad_norm": 1.789615273475647,
|
| 190 |
+
"learning_rate": 0.0001,
|
| 191 |
+
"loss": 3.7407,
|
| 192 |
+
"step": 8500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.22855981918378748,
|
| 196 |
+
"grad_norm": 1.7753719091415405,
|
| 197 |
+
"learning_rate": 0.0001,
|
| 198 |
+
"loss": 3.7151,
|
| 199 |
+
"step": 9000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.22855981918378748,
|
| 203 |
+
"eval_loss": 3.6513242721557617,
|
| 204 |
+
"eval_runtime": 1.8933,
|
| 205 |
+
"eval_samples_per_second": 924.291,
|
| 206 |
+
"eval_steps_per_second": 29.049,
|
| 207 |
+
"step": 9000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.24125758691622012,
|
| 211 |
+
"grad_norm": 1.5469183921813965,
|
| 212 |
+
"learning_rate": 0.0001,
|
| 213 |
+
"loss": 3.6057,
|
| 214 |
+
"step": 9500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.25395535464865276,
|
| 218 |
+
"grad_norm": 1.7085388898849487,
|
| 219 |
+
"learning_rate": 0.0001,
|
| 220 |
+
"loss": 3.7075,
|
| 221 |
+
"step": 10000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.25395535464865276,
|
| 225 |
+
"eval_loss": 3.600736141204834,
|
| 226 |
+
"eval_runtime": 1.8818,
|
| 227 |
+
"eval_samples_per_second": 929.961,
|
| 228 |
+
"eval_steps_per_second": 29.227,
|
| 229 |
+
"step": 10000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.2666531223810854,
|
| 233 |
+
"grad_norm": 1.5484737157821655,
|
| 234 |
+
"learning_rate": 0.0001,
|
| 235 |
+
"loss": 3.6486,
|
| 236 |
+
"step": 10500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.27935089011351805,
|
| 240 |
+
"grad_norm": 2.095698118209839,
|
| 241 |
+
"learning_rate": 0.0001,
|
| 242 |
+
"loss": 3.5585,
|
| 243 |
+
"step": 11000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.27935089011351805,
|
| 247 |
+
"eval_loss": 3.584713935852051,
|
| 248 |
+
"eval_runtime": 1.901,
|
| 249 |
+
"eval_samples_per_second": 920.585,
|
| 250 |
+
"eval_steps_per_second": 28.933,
|
| 251 |
+
"step": 11000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.2920486578459507,
|
| 255 |
+
"grad_norm": 1.822464942932129,
|
| 256 |
+
"learning_rate": 0.0001,
|
| 257 |
+
"loss": 3.6714,
|
| 258 |
+
"step": 11500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.30474642557838333,
|
| 262 |
+
"grad_norm": 1.756412148475647,
|
| 263 |
+
"learning_rate": 0.0001,
|
| 264 |
+
"loss": 3.6149,
|
| 265 |
+
"step": 12000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.30474642557838333,
|
| 269 |
+
"eval_loss": 3.5466842651367188,
|
| 270 |
+
"eval_runtime": 1.8965,
|
| 271 |
+
"eval_samples_per_second": 922.772,
|
| 272 |
+
"eval_steps_per_second": 29.001,
|
| 273 |
+
"step": 12000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.31744419331081597,
|
| 277 |
+
"grad_norm": 1.7527214288711548,
|
| 278 |
+
"learning_rate": 0.0001,
|
| 279 |
+
"loss": 3.4993,
|
| 280 |
+
"step": 12500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.3301419610432486,
|
| 284 |
+
"grad_norm": 1.4713279008865356,
|
| 285 |
+
"learning_rate": 0.0001,
|
| 286 |
+
"loss": 3.5912,
|
| 287 |
+
"step": 13000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.3301419610432486,
|
| 291 |
+
"eval_loss": 3.5182790756225586,
|
| 292 |
+
"eval_runtime": 1.8952,
|
| 293 |
+
"eval_samples_per_second": 923.389,
|
| 294 |
+
"eval_steps_per_second": 29.021,
|
| 295 |
+
"step": 13000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.34283972877568125,
|
| 299 |
+
"grad_norm": 1.8965306282043457,
|
| 300 |
+
"learning_rate": 0.0001,
|
| 301 |
+
"loss": 3.5699,
|
| 302 |
+
"step": 13500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3555374965081139,
|
| 306 |
+
"grad_norm": 1.6826404333114624,
|
| 307 |
+
"learning_rate": 0.0001,
|
| 308 |
+
"loss": 3.4807,
|
| 309 |
+
"step": 14000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.3555374965081139,
|
| 313 |
+
"eval_loss": 3.499809980392456,
|
| 314 |
+
"eval_runtime": 1.922,
|
| 315 |
+
"eval_samples_per_second": 910.515,
|
| 316 |
+
"eval_steps_per_second": 28.616,
|
| 317 |
+
"step": 14000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.36823526424054653,
|
| 321 |
+
"grad_norm": 1.5509382486343384,
|
| 322 |
+
"learning_rate": 0.0001,
|
| 323 |
+
"loss": 3.552,
|
| 324 |
+
"step": 14500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.3809330319729792,
|
| 328 |
+
"grad_norm": 1.5820932388305664,
|
| 329 |
+
"learning_rate": 0.0001,
|
| 330 |
+
"loss": 3.5226,
|
| 331 |
+
"step": 15000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.3809330319729792,
|
| 335 |
+
"eval_loss": 3.4750168323516846,
|
| 336 |
+
"eval_runtime": 1.901,
|
| 337 |
+
"eval_samples_per_second": 920.552,
|
| 338 |
+
"eval_steps_per_second": 28.932,
|
| 339 |
+
"step": 15000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3936307997054118,
|
| 343 |
+
"grad_norm": 1.5643424987792969,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"loss": 3.4736,
|
| 346 |
+
"step": 15500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.4063285674378444,
|
| 350 |
+
"grad_norm": 1.6997604370117188,
|
| 351 |
+
"learning_rate": 0.0001,
|
| 352 |
+
"loss": 3.498,
|
| 353 |
+
"step": 16000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.4063285674378444,
|
| 357 |
+
"eval_loss": 3.456913948059082,
|
| 358 |
+
"eval_runtime": 1.8897,
|
| 359 |
+
"eval_samples_per_second": 926.081,
|
| 360 |
+
"eval_steps_per_second": 29.105,
|
| 361 |
+
"step": 16000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.41902633517027704,
|
| 365 |
+
"grad_norm": 1.9402141571044922,
|
| 366 |
+
"learning_rate": 0.0001,
|
| 367 |
+
"loss": 3.5182,
|
| 368 |
+
"step": 16500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.4317241029027097,
|
| 372 |
+
"grad_norm": 2.2298734188079834,
|
| 373 |
+
"learning_rate": 0.0001,
|
| 374 |
+
"loss": 3.4416,
|
| 375 |
+
"step": 17000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.4317241029027097,
|
| 379 |
+
"eval_loss": 3.445345878601074,
|
| 380 |
+
"eval_runtime": 1.8985,
|
| 381 |
+
"eval_samples_per_second": 921.804,
|
| 382 |
+
"eval_steps_per_second": 28.971,
|
| 383 |
+
"step": 17000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.4444218706351423,
|
| 387 |
+
"grad_norm": 1.835460901260376,
|
| 388 |
+
"learning_rate": 0.0001,
|
| 389 |
+
"loss": 3.4224,
|
| 390 |
+
"step": 17500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.45711963836757497,
|
| 394 |
+
"grad_norm": 1.54244065284729,
|
| 395 |
+
"learning_rate": 0.0001,
|
| 396 |
+
"loss": 3.4828,
|
| 397 |
+
"step": 18000
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.45711963836757497,
|
| 401 |
+
"eval_loss": 3.414003372192383,
|
| 402 |
+
"eval_runtime": 1.9135,
|
| 403 |
+
"eval_samples_per_second": 914.54,
|
| 404 |
+
"eval_steps_per_second": 28.743,
|
| 405 |
+
"step": 18000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.4698174061000076,
|
| 409 |
+
"grad_norm": 2.3647444248199463,
|
| 410 |
+
"learning_rate": 0.0001,
|
| 411 |
+
"loss": 3.447,
|
| 412 |
+
"step": 18500
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 0.48251517383244025,
|
| 416 |
+
"grad_norm": 1.6459336280822754,
|
| 417 |
+
"learning_rate": 0.0001,
|
| 418 |
+
"loss": 3.3674,
|
| 419 |
+
"step": 19000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.48251517383244025,
|
| 423 |
+
"eval_loss": 3.4138450622558594,
|
| 424 |
+
"eval_runtime": 1.9024,
|
| 425 |
+
"eval_samples_per_second": 919.889,
|
| 426 |
+
"eval_steps_per_second": 28.911,
|
| 427 |
+
"step": 19000
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 0.4952129415648729,
|
| 431 |
+
"grad_norm": 1.6082369089126587,
|
| 432 |
+
"learning_rate": 0.0001,
|
| 433 |
+
"loss": 3.453,
|
| 434 |
+
"step": 19500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.5079107092973055,
|
| 438 |
+
"grad_norm": 1.775486946105957,
|
| 439 |
+
"learning_rate": 0.0001,
|
| 440 |
+
"loss": 3.4523,
|
| 441 |
+
"step": 20000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.5079107092973055,
|
| 445 |
+
"eval_loss": 3.385756731033325,
|
| 446 |
+
"eval_runtime": 1.9078,
|
| 447 |
+
"eval_samples_per_second": 917.285,
|
| 448 |
+
"eval_steps_per_second": 28.829,
|
| 449 |
+
"step": 20000
|
| 450 |
+
}
|
| 451 |
+
],
|
| 452 |
+
"logging_steps": 500,
|
| 453 |
+
"max_steps": 39377,
|
| 454 |
+
"num_input_tokens_seen": 0,
|
| 455 |
+
"num_train_epochs": 1,
|
| 456 |
+
"save_steps": 1000,
|
| 457 |
+
"stateful_callbacks": {
|
| 458 |
+
"EarlyStoppingCallback": {
|
| 459 |
+
"args": {
|
| 460 |
+
"early_stopping_patience": 3,
|
| 461 |
+
"early_stopping_threshold": 0.001
|
| 462 |
+
},
|
| 463 |
+
"attributes": {
|
| 464 |
+
"early_stopping_patience_counter": 0
|
| 465 |
+
}
|
| 466 |
+
},
|
| 467 |
+
"TrainerControl": {
|
| 468 |
+
"args": {
|
| 469 |
+
"should_epoch_stop": false,
|
| 470 |
+
"should_evaluate": false,
|
| 471 |
+
"should_log": false,
|
| 472 |
+
"should_save": true,
|
| 473 |
+
"should_training_stop": false
|
| 474 |
+
},
|
| 475 |
+
"attributes": {}
|
| 476 |
+
}
|
| 477 |
+
},
|
| 478 |
+
"total_flos": 389944442880000.0,
|
| 479 |
+
"train_batch_size": 32,
|
| 480 |
+
"trial_name": null,
|
| 481 |
+
"trial_params": null
|
| 482 |
+
}
|
checkpoint-20000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:539b27162b2f1812097821a7135b4ffe9aa17afeac56bc6323495680f90e1a25
|
| 3 |
+
size 5432
|