Initial Upload
Browse files- all_results.json +14 -0
- config.json +83 -0
- eval_results.json +9 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +535 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.12109375,
|
| 4 |
+
"eval_runtime": 1.9531,
|
| 5 |
+
"eval_samples": 2,
|
| 6 |
+
"eval_samples_per_second": 1.024,
|
| 7 |
+
"eval_steps_per_second": 0.512,
|
| 8 |
+
"perplexity": 8.340254654356475,
|
| 9 |
+
"train_loss": 2.3266365131578945,
|
| 10 |
+
"train_runtime": 29836.7817,
|
| 11 |
+
"train_samples": 7602,
|
| 12 |
+
"train_samples_per_second": 0.255,
|
| 13 |
+
"train_steps_per_second": 0.032
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "EleutherAI/gpt-neo-2.7B",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPTNeoForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0,
|
| 8 |
+
"attention_layers": [
|
| 9 |
+
"global",
|
| 10 |
+
"local",
|
| 11 |
+
"global",
|
| 12 |
+
"local",
|
| 13 |
+
"global",
|
| 14 |
+
"local",
|
| 15 |
+
"global",
|
| 16 |
+
"local",
|
| 17 |
+
"global",
|
| 18 |
+
"local",
|
| 19 |
+
"global",
|
| 20 |
+
"local",
|
| 21 |
+
"global",
|
| 22 |
+
"local",
|
| 23 |
+
"global",
|
| 24 |
+
"local",
|
| 25 |
+
"global",
|
| 26 |
+
"local",
|
| 27 |
+
"global",
|
| 28 |
+
"local",
|
| 29 |
+
"global",
|
| 30 |
+
"local",
|
| 31 |
+
"global",
|
| 32 |
+
"local",
|
| 33 |
+
"global",
|
| 34 |
+
"local",
|
| 35 |
+
"global",
|
| 36 |
+
"local",
|
| 37 |
+
"global",
|
| 38 |
+
"local",
|
| 39 |
+
"global",
|
| 40 |
+
"local"
|
| 41 |
+
],
|
| 42 |
+
"attention_types": [
|
| 43 |
+
[
|
| 44 |
+
[
|
| 45 |
+
"global",
|
| 46 |
+
"local"
|
| 47 |
+
],
|
| 48 |
+
16
|
| 49 |
+
]
|
| 50 |
+
],
|
| 51 |
+
"bos_token_id": 50256,
|
| 52 |
+
"embed_dropout": 0,
|
| 53 |
+
"eos_token_id": 50256,
|
| 54 |
+
"gradient_checkpointing": true,
|
| 55 |
+
"hidden_size": 2560,
|
| 56 |
+
"initializer_range": 0.02,
|
| 57 |
+
"intermediate_size": null,
|
| 58 |
+
"layer_norm_epsilon": 1e-05,
|
| 59 |
+
"max_position_embeddings": 2048,
|
| 60 |
+
"model_type": "gpt_neo",
|
| 61 |
+
"num_heads": 20,
|
| 62 |
+
"num_layers": 32,
|
| 63 |
+
"resid_dropout": 0,
|
| 64 |
+
"summary_activation": null,
|
| 65 |
+
"summary_first_dropout": 0.1,
|
| 66 |
+
"summary_proj_to_labels": true,
|
| 67 |
+
"summary_type": "cls_index",
|
| 68 |
+
"summary_use_proj": true,
|
| 69 |
+
"task_specific_params": {
|
| 70 |
+
"text-generation": {
|
| 71 |
+
"do_sample": true,
|
| 72 |
+
"max_length": 50,
|
| 73 |
+
"temperature": 0.9
|
| 74 |
+
}
|
| 75 |
+
},
|
| 76 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 77 |
+
"transformers_version": "4.7.0.dev0",
|
| 78 |
+
"use_cache": false,
|
| 79 |
+
"vocab_size": 50257,
|
| 80 |
+
"window_size": 256,
|
| 81 |
+
"adventure": true,
|
| 82 |
+
"rep_pen": 2.0
|
| 83 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.12109375,
|
| 4 |
+
"eval_runtime": 1.9531,
|
| 5 |
+
"eval_samples": 2,
|
| 6 |
+
"eval_samples_per_second": 1.024,
|
| 7 |
+
"eval_steps_per_second": 0.512,
|
| 8 |
+
"perplexity": 8.340254654356475
|
| 9 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcffa1bea41968022432acf4cc772444c359ea531f7bec401c71f106566186ee
|
| 3 |
+
size 5369805480
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-2.7B", "tokenizer_file": null}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 2.3266365131578945,
|
| 4 |
+
"train_runtime": 29836.7817,
|
| 5 |
+
"train_samples": 7602,
|
| 6 |
+
"train_samples_per_second": 0.255,
|
| 7 |
+
"train_steps_per_second": 0.032
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,535 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9994739610731194,
|
| 5 |
+
"global_step": 950,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"eval_loss": 2.40625,
|
| 13 |
+
"eval_runtime": 1.9288,
|
| 14 |
+
"eval_samples_per_second": 1.037,
|
| 15 |
+
"eval_steps_per_second": 0.518,
|
| 16 |
+
"step": 15
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03,
|
| 20 |
+
"eval_loss": 2.35546875,
|
| 21 |
+
"eval_runtime": 1.9286,
|
| 22 |
+
"eval_samples_per_second": 1.037,
|
| 23 |
+
"eval_steps_per_second": 0.519,
|
| 24 |
+
"step": 30
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05,
|
| 28 |
+
"eval_loss": 2.341796875,
|
| 29 |
+
"eval_runtime": 1.9286,
|
| 30 |
+
"eval_samples_per_second": 1.037,
|
| 31 |
+
"eval_steps_per_second": 0.519,
|
| 32 |
+
"step": 45
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.06,
|
| 36 |
+
"eval_loss": 2.33203125,
|
| 37 |
+
"eval_runtime": 1.9285,
|
| 38 |
+
"eval_samples_per_second": 1.037,
|
| 39 |
+
"eval_steps_per_second": 0.519,
|
| 40 |
+
"step": 60
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.08,
|
| 44 |
+
"eval_loss": 2.32421875,
|
| 45 |
+
"eval_runtime": 1.9288,
|
| 46 |
+
"eval_samples_per_second": 1.037,
|
| 47 |
+
"eval_steps_per_second": 0.518,
|
| 48 |
+
"step": 75
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.09,
|
| 52 |
+
"eval_loss": 2.318359375,
|
| 53 |
+
"eval_runtime": 1.9291,
|
| 54 |
+
"eval_samples_per_second": 1.037,
|
| 55 |
+
"eval_steps_per_second": 0.518,
|
| 56 |
+
"step": 90
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.11,
|
| 60 |
+
"eval_loss": 2.314453125,
|
| 61 |
+
"eval_runtime": 1.9288,
|
| 62 |
+
"eval_samples_per_second": 1.037,
|
| 63 |
+
"eval_steps_per_second": 0.518,
|
| 64 |
+
"step": 105
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.13,
|
| 68 |
+
"eval_loss": 2.3125,
|
| 69 |
+
"eval_runtime": 1.9287,
|
| 70 |
+
"eval_samples_per_second": 1.037,
|
| 71 |
+
"eval_steps_per_second": 0.518,
|
| 72 |
+
"step": 120
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.14,
|
| 76 |
+
"eval_loss": 2.3125,
|
| 77 |
+
"eval_runtime": 1.9289,
|
| 78 |
+
"eval_samples_per_second": 1.037,
|
| 79 |
+
"eval_steps_per_second": 0.518,
|
| 80 |
+
"step": 135
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.16,
|
| 84 |
+
"eval_loss": 2.306640625,
|
| 85 |
+
"eval_runtime": 1.9287,
|
| 86 |
+
"eval_samples_per_second": 1.037,
|
| 87 |
+
"eval_steps_per_second": 0.518,
|
| 88 |
+
"step": 150
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.17,
|
| 92 |
+
"eval_loss": 2.30078125,
|
| 93 |
+
"eval_runtime": 1.9284,
|
| 94 |
+
"eval_samples_per_second": 1.037,
|
| 95 |
+
"eval_steps_per_second": 0.519,
|
| 96 |
+
"step": 165
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.19,
|
| 100 |
+
"eval_loss": 2.30078125,
|
| 101 |
+
"eval_runtime": 1.9291,
|
| 102 |
+
"eval_samples_per_second": 1.037,
|
| 103 |
+
"eval_steps_per_second": 0.518,
|
| 104 |
+
"step": 180
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.21,
|
| 108 |
+
"eval_loss": 2.302734375,
|
| 109 |
+
"eval_runtime": 1.9292,
|
| 110 |
+
"eval_samples_per_second": 1.037,
|
| 111 |
+
"eval_steps_per_second": 0.518,
|
| 112 |
+
"step": 195
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.22,
|
| 116 |
+
"eval_loss": 2.294921875,
|
| 117 |
+
"eval_runtime": 1.9287,
|
| 118 |
+
"eval_samples_per_second": 1.037,
|
| 119 |
+
"eval_steps_per_second": 0.518,
|
| 120 |
+
"step": 210
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.24,
|
| 124 |
+
"eval_loss": 2.287109375,
|
| 125 |
+
"eval_runtime": 1.9291,
|
| 126 |
+
"eval_samples_per_second": 1.037,
|
| 127 |
+
"eval_steps_per_second": 0.518,
|
| 128 |
+
"step": 225
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.25,
|
| 132 |
+
"eval_loss": 2.283203125,
|
| 133 |
+
"eval_runtime": 1.9283,
|
| 134 |
+
"eval_samples_per_second": 1.037,
|
| 135 |
+
"eval_steps_per_second": 0.519,
|
| 136 |
+
"step": 240
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.27,
|
| 140 |
+
"eval_loss": 2.279296875,
|
| 141 |
+
"eval_runtime": 1.9288,
|
| 142 |
+
"eval_samples_per_second": 1.037,
|
| 143 |
+
"eval_steps_per_second": 0.518,
|
| 144 |
+
"step": 255
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.28,
|
| 148 |
+
"eval_loss": 2.27734375,
|
| 149 |
+
"eval_runtime": 1.929,
|
| 150 |
+
"eval_samples_per_second": 1.037,
|
| 151 |
+
"eval_steps_per_second": 0.518,
|
| 152 |
+
"step": 270
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.3,
|
| 156 |
+
"eval_loss": 2.248046875,
|
| 157 |
+
"eval_runtime": 1.9292,
|
| 158 |
+
"eval_samples_per_second": 1.037,
|
| 159 |
+
"eval_steps_per_second": 0.518,
|
| 160 |
+
"step": 285
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.32,
|
| 164 |
+
"eval_loss": 2.2265625,
|
| 165 |
+
"eval_runtime": 1.9288,
|
| 166 |
+
"eval_samples_per_second": 1.037,
|
| 167 |
+
"eval_steps_per_second": 0.518,
|
| 168 |
+
"step": 300
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.33,
|
| 172 |
+
"eval_loss": 2.2265625,
|
| 173 |
+
"eval_runtime": 1.9288,
|
| 174 |
+
"eval_samples_per_second": 1.037,
|
| 175 |
+
"eval_steps_per_second": 0.518,
|
| 176 |
+
"step": 315
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.35,
|
| 180 |
+
"eval_loss": 2.2265625,
|
| 181 |
+
"eval_runtime": 1.9287,
|
| 182 |
+
"eval_samples_per_second": 1.037,
|
| 183 |
+
"eval_steps_per_second": 0.518,
|
| 184 |
+
"step": 330
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.36,
|
| 188 |
+
"eval_loss": 2.2265625,
|
| 189 |
+
"eval_runtime": 1.9316,
|
| 190 |
+
"eval_samples_per_second": 1.035,
|
| 191 |
+
"eval_steps_per_second": 0.518,
|
| 192 |
+
"step": 345
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.38,
|
| 196 |
+
"eval_loss": 2.228515625,
|
| 197 |
+
"eval_runtime": 1.9288,
|
| 198 |
+
"eval_samples_per_second": 1.037,
|
| 199 |
+
"eval_steps_per_second": 0.518,
|
| 200 |
+
"step": 360
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.39,
|
| 204 |
+
"eval_loss": 2.2265625,
|
| 205 |
+
"eval_runtime": 1.9286,
|
| 206 |
+
"eval_samples_per_second": 1.037,
|
| 207 |
+
"eval_steps_per_second": 0.519,
|
| 208 |
+
"step": 375
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.41,
|
| 212 |
+
"eval_loss": 2.224609375,
|
| 213 |
+
"eval_runtime": 1.9289,
|
| 214 |
+
"eval_samples_per_second": 1.037,
|
| 215 |
+
"eval_steps_per_second": 0.518,
|
| 216 |
+
"step": 390
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.43,
|
| 220 |
+
"eval_loss": 2.22265625,
|
| 221 |
+
"eval_runtime": 1.9294,
|
| 222 |
+
"eval_samples_per_second": 1.037,
|
| 223 |
+
"eval_steps_per_second": 0.518,
|
| 224 |
+
"step": 405
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.44,
|
| 228 |
+
"eval_loss": 2.220703125,
|
| 229 |
+
"eval_runtime": 1.9284,
|
| 230 |
+
"eval_samples_per_second": 1.037,
|
| 231 |
+
"eval_steps_per_second": 0.519,
|
| 232 |
+
"step": 420
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.46,
|
| 236 |
+
"eval_loss": 2.22265625,
|
| 237 |
+
"eval_runtime": 1.9289,
|
| 238 |
+
"eval_samples_per_second": 1.037,
|
| 239 |
+
"eval_steps_per_second": 0.518,
|
| 240 |
+
"step": 435
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.47,
|
| 244 |
+
"eval_loss": 2.22265625,
|
| 245 |
+
"eval_runtime": 1.9295,
|
| 246 |
+
"eval_samples_per_second": 1.037,
|
| 247 |
+
"eval_steps_per_second": 0.518,
|
| 248 |
+
"step": 450
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.49,
|
| 252 |
+
"eval_loss": 2.220703125,
|
| 253 |
+
"eval_runtime": 1.9284,
|
| 254 |
+
"eval_samples_per_second": 1.037,
|
| 255 |
+
"eval_steps_per_second": 0.519,
|
| 256 |
+
"step": 465
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.5,
|
| 260 |
+
"eval_loss": 2.220703125,
|
| 261 |
+
"eval_runtime": 1.9291,
|
| 262 |
+
"eval_samples_per_second": 1.037,
|
| 263 |
+
"eval_steps_per_second": 0.518,
|
| 264 |
+
"step": 480
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.52,
|
| 268 |
+
"eval_loss": 2.21875,
|
| 269 |
+
"eval_runtime": 1.9289,
|
| 270 |
+
"eval_samples_per_second": 1.037,
|
| 271 |
+
"eval_steps_per_second": 0.518,
|
| 272 |
+
"step": 495
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.53,
|
| 276 |
+
"learning_rate": 5e-06,
|
| 277 |
+
"loss": 2.374,
|
| 278 |
+
"step": 500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.54,
|
| 282 |
+
"eval_loss": 2.203125,
|
| 283 |
+
"eval_runtime": 1.937,
|
| 284 |
+
"eval_samples_per_second": 1.033,
|
| 285 |
+
"eval_steps_per_second": 0.516,
|
| 286 |
+
"step": 510
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.55,
|
| 290 |
+
"eval_loss": 2.1875,
|
| 291 |
+
"eval_runtime": 1.9291,
|
| 292 |
+
"eval_samples_per_second": 1.037,
|
| 293 |
+
"eval_steps_per_second": 0.518,
|
| 294 |
+
"step": 525
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.57,
|
| 298 |
+
"eval_loss": 2.185546875,
|
| 299 |
+
"eval_runtime": 1.9291,
|
| 300 |
+
"eval_samples_per_second": 1.037,
|
| 301 |
+
"eval_steps_per_second": 0.518,
|
| 302 |
+
"step": 540
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.58,
|
| 306 |
+
"eval_loss": 2.140625,
|
| 307 |
+
"eval_runtime": 1.9294,
|
| 308 |
+
"eval_samples_per_second": 1.037,
|
| 309 |
+
"eval_steps_per_second": 0.518,
|
| 310 |
+
"step": 555
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6,
|
| 314 |
+
"eval_loss": 2.134765625,
|
| 315 |
+
"eval_runtime": 1.9289,
|
| 316 |
+
"eval_samples_per_second": 1.037,
|
| 317 |
+
"eval_steps_per_second": 0.518,
|
| 318 |
+
"step": 570
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.62,
|
| 322 |
+
"eval_loss": 2.134765625,
|
| 323 |
+
"eval_runtime": 1.9285,
|
| 324 |
+
"eval_samples_per_second": 1.037,
|
| 325 |
+
"eval_steps_per_second": 0.519,
|
| 326 |
+
"step": 585
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.63,
|
| 330 |
+
"eval_loss": 2.134765625,
|
| 331 |
+
"eval_runtime": 1.929,
|
| 332 |
+
"eval_samples_per_second": 1.037,
|
| 333 |
+
"eval_steps_per_second": 0.518,
|
| 334 |
+
"step": 600
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.65,
|
| 338 |
+
"eval_loss": 2.1328125,
|
| 339 |
+
"eval_runtime": 1.929,
|
| 340 |
+
"eval_samples_per_second": 1.037,
|
| 341 |
+
"eval_steps_per_second": 0.518,
|
| 342 |
+
"step": 615
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.66,
|
| 346 |
+
"eval_loss": 2.1328125,
|
| 347 |
+
"eval_runtime": 1.9284,
|
| 348 |
+
"eval_samples_per_second": 1.037,
|
| 349 |
+
"eval_steps_per_second": 0.519,
|
| 350 |
+
"step": 630
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.68,
|
| 354 |
+
"eval_loss": 2.130859375,
|
| 355 |
+
"eval_runtime": 1.929,
|
| 356 |
+
"eval_samples_per_second": 1.037,
|
| 357 |
+
"eval_steps_per_second": 0.518,
|
| 358 |
+
"step": 645
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.69,
|
| 362 |
+
"eval_loss": 2.12890625,
|
| 363 |
+
"eval_runtime": 1.9293,
|
| 364 |
+
"eval_samples_per_second": 1.037,
|
| 365 |
+
"eval_steps_per_second": 0.518,
|
| 366 |
+
"step": 660
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.71,
|
| 370 |
+
"eval_loss": 2.12890625,
|
| 371 |
+
"eval_runtime": 1.9283,
|
| 372 |
+
"eval_samples_per_second": 1.037,
|
| 373 |
+
"eval_steps_per_second": 0.519,
|
| 374 |
+
"step": 675
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.73,
|
| 378 |
+
"eval_loss": 2.1328125,
|
| 379 |
+
"eval_runtime": 1.9291,
|
| 380 |
+
"eval_samples_per_second": 1.037,
|
| 381 |
+
"eval_steps_per_second": 0.518,
|
| 382 |
+
"step": 690
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.74,
|
| 386 |
+
"eval_loss": 2.1328125,
|
| 387 |
+
"eval_runtime": 1.9288,
|
| 388 |
+
"eval_samples_per_second": 1.037,
|
| 389 |
+
"eval_steps_per_second": 0.518,
|
| 390 |
+
"step": 705
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.76,
|
| 394 |
+
"eval_loss": 2.130859375,
|
| 395 |
+
"eval_runtime": 1.9294,
|
| 396 |
+
"eval_samples_per_second": 1.037,
|
| 397 |
+
"eval_steps_per_second": 0.518,
|
| 398 |
+
"step": 720
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.77,
|
| 402 |
+
"eval_loss": 2.134765625,
|
| 403 |
+
"eval_runtime": 1.929,
|
| 404 |
+
"eval_samples_per_second": 1.037,
|
| 405 |
+
"eval_steps_per_second": 0.518,
|
| 406 |
+
"step": 735
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.79,
|
| 410 |
+
"eval_loss": 2.1328125,
|
| 411 |
+
"eval_runtime": 1.9295,
|
| 412 |
+
"eval_samples_per_second": 1.037,
|
| 413 |
+
"eval_steps_per_second": 0.518,
|
| 414 |
+
"step": 750
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.8,
|
| 418 |
+
"eval_loss": 2.134765625,
|
| 419 |
+
"eval_runtime": 1.9289,
|
| 420 |
+
"eval_samples_per_second": 1.037,
|
| 421 |
+
"eval_steps_per_second": 0.518,
|
| 422 |
+
"step": 765
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.82,
|
| 426 |
+
"eval_loss": 2.134765625,
|
| 427 |
+
"eval_runtime": 1.9291,
|
| 428 |
+
"eval_samples_per_second": 1.037,
|
| 429 |
+
"eval_steps_per_second": 0.518,
|
| 430 |
+
"step": 780
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.84,
|
| 434 |
+
"eval_loss": 2.134765625,
|
| 435 |
+
"eval_runtime": 1.9289,
|
| 436 |
+
"eval_samples_per_second": 1.037,
|
| 437 |
+
"eval_steps_per_second": 0.518,
|
| 438 |
+
"step": 795
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.85,
|
| 442 |
+
"eval_loss": 2.1328125,
|
| 443 |
+
"eval_runtime": 1.9291,
|
| 444 |
+
"eval_samples_per_second": 1.037,
|
| 445 |
+
"eval_steps_per_second": 0.518,
|
| 446 |
+
"step": 810
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.87,
|
| 450 |
+
"eval_loss": 2.12890625,
|
| 451 |
+
"eval_runtime": 1.9286,
|
| 452 |
+
"eval_samples_per_second": 1.037,
|
| 453 |
+
"eval_steps_per_second": 0.519,
|
| 454 |
+
"step": 825
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.88,
|
| 458 |
+
"eval_loss": 2.119140625,
|
| 459 |
+
"eval_runtime": 1.9289,
|
| 460 |
+
"eval_samples_per_second": 1.037,
|
| 461 |
+
"eval_steps_per_second": 0.518,
|
| 462 |
+
"step": 840
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.9,
|
| 466 |
+
"eval_loss": 2.12109375,
|
| 467 |
+
"eval_runtime": 1.9287,
|
| 468 |
+
"eval_samples_per_second": 1.037,
|
| 469 |
+
"eval_steps_per_second": 0.518,
|
| 470 |
+
"step": 855
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.92,
|
| 474 |
+
"eval_loss": 2.1171875,
|
| 475 |
+
"eval_runtime": 1.9289,
|
| 476 |
+
"eval_samples_per_second": 1.037,
|
| 477 |
+
"eval_steps_per_second": 0.518,
|
| 478 |
+
"step": 870
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.93,
|
| 482 |
+
"eval_loss": 2.119140625,
|
| 483 |
+
"eval_runtime": 1.9291,
|
| 484 |
+
"eval_samples_per_second": 1.037,
|
| 485 |
+
"eval_steps_per_second": 0.518,
|
| 486 |
+
"step": 885
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.95,
|
| 490 |
+
"eval_loss": 2.123046875,
|
| 491 |
+
"eval_runtime": 1.9294,
|
| 492 |
+
"eval_samples_per_second": 1.037,
|
| 493 |
+
"eval_steps_per_second": 0.518,
|
| 494 |
+
"step": 900
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.96,
|
| 498 |
+
"eval_loss": 2.12109375,
|
| 499 |
+
"eval_runtime": 1.9292,
|
| 500 |
+
"eval_samples_per_second": 1.037,
|
| 501 |
+
"eval_steps_per_second": 0.518,
|
| 502 |
+
"step": 915
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.98,
|
| 506 |
+
"eval_loss": 2.119140625,
|
| 507 |
+
"eval_runtime": 1.9287,
|
| 508 |
+
"eval_samples_per_second": 1.037,
|
| 509 |
+
"eval_steps_per_second": 0.518,
|
| 510 |
+
"step": 930
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.99,
|
| 514 |
+
"eval_loss": 2.12109375,
|
| 515 |
+
"eval_runtime": 1.9291,
|
| 516 |
+
"eval_samples_per_second": 1.037,
|
| 517 |
+
"eval_steps_per_second": 0.518,
|
| 518 |
+
"step": 945
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.0,
|
| 522 |
+
"step": 950,
|
| 523 |
+
"total_flos": 1.2380121253648794e+17,
|
| 524 |
+
"train_loss": 2.3266365131578945,
|
| 525 |
+
"train_runtime": 29836.7817,
|
| 526 |
+
"train_samples_per_second": 0.255,
|
| 527 |
+
"train_steps_per_second": 0.032
|
| 528 |
+
}
|
| 529 |
+
],
|
| 530 |
+
"max_steps": 950,
|
| 531 |
+
"num_train_epochs": 1,
|
| 532 |
+
"total_flos": 1.2380121253648794e+17,
|
| 533 |
+
"trial_name": null,
|
| 534 |
+
"trial_params": null
|
| 535 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17859c13656d6e2916f5d2d72677e9246a7b8f5b5d522de646decacc275735cf
|
| 3 |
+
size 3439
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|