uploaded model files
Browse filesuploaded config.json, generation_config.json, rng_state.pth, scheduler.pt, trainer_state.json and training_args.bin
- config.json +61 -0
- generation_config.json +7 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +963 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.41.2",
|
| 59 |
+
"use_cache": true,
|
| 60 |
+
"vocab_size": 32100
|
| 61 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.41.2"
|
| 7 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35a8d8eacf283889da0874aadff8220ee2f87113f49e1832b59c6111a6658025
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:039014ba91243e54a67d23dc434e106504fb8f22fd4e48a9733489fc322c1a89
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,963 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5654382109642029,
|
| 3 |
+
"best_model_checkpoint": "./results_t5_base/checkpoint-1100",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18181818181818182,
|
| 13 |
+
"grad_norm": 34.49951934814453,
|
| 14 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 15 |
+
"loss": 15.0621,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.36363636363636365,
|
| 20 |
+
"grad_norm": 34.444114685058594,
|
| 21 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 22 |
+
"loss": 14.3473,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5454545454545454,
|
| 27 |
+
"grad_norm": 27.946786880493164,
|
| 28 |
+
"learning_rate": 3e-06,
|
| 29 |
+
"loss": 13.5965,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7272727272727273,
|
| 34 |
+
"grad_norm": 26.316389083862305,
|
| 35 |
+
"learning_rate": 4.000000000000001e-06,
|
| 36 |
+
"loss": 12.6354,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9090909090909091,
|
| 41 |
+
"grad_norm": 31.084760665893555,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 11.446,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_loss": 9.390619277954102,
|
| 49 |
+
"eval_runtime": 1.9144,
|
| 50 |
+
"eval_samples_per_second": 50.67,
|
| 51 |
+
"eval_steps_per_second": 3.657,
|
| 52 |
+
"step": 55
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.0909090909090908,
|
| 56 |
+
"grad_norm": 27.938682556152344,
|
| 57 |
+
"learning_rate": 6e-06,
|
| 58 |
+
"loss": 9.6083,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.2727272727272727,
|
| 63 |
+
"grad_norm": 24.73709487915039,
|
| 64 |
+
"learning_rate": 7.000000000000001e-06,
|
| 65 |
+
"loss": 7.8641,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.4545454545454546,
|
| 70 |
+
"grad_norm": 20.69359588623047,
|
| 71 |
+
"learning_rate": 8.000000000000001e-06,
|
| 72 |
+
"loss": 5.7202,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.6363636363636362,
|
| 77 |
+
"grad_norm": 9.500884056091309,
|
| 78 |
+
"learning_rate": 9e-06,
|
| 79 |
+
"loss": 4.0409,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.8181818181818183,
|
| 84 |
+
"grad_norm": 3.8369476795196533,
|
| 85 |
+
"learning_rate": 1e-05,
|
| 86 |
+
"loss": 3.3363,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.0,
|
| 91 |
+
"grad_norm": 2.6282877922058105,
|
| 92 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 93 |
+
"loss": 2.4721,
|
| 94 |
+
"step": 110
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 2.0,
|
| 98 |
+
"eval_loss": 1.9182844161987305,
|
| 99 |
+
"eval_runtime": 1.9094,
|
| 100 |
+
"eval_samples_per_second": 50.801,
|
| 101 |
+
"eval_steps_per_second": 3.666,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.1818181818181817,
|
| 106 |
+
"grad_norm": 1.8732331991195679,
|
| 107 |
+
"learning_rate": 1.2e-05,
|
| 108 |
+
"loss": 2.2906,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.3636363636363638,
|
| 113 |
+
"grad_norm": 1.2134524583816528,
|
| 114 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 115 |
+
"loss": 2.012,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.5454545454545454,
|
| 120 |
+
"grad_norm": 1.0808675289154053,
|
| 121 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 122 |
+
"loss": 1.9923,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.7272727272727275,
|
| 127 |
+
"grad_norm": 0.7511759996414185,
|
| 128 |
+
"learning_rate": 1.5e-05,
|
| 129 |
+
"loss": 1.7195,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.909090909090909,
|
| 134 |
+
"grad_norm": 0.7951436638832092,
|
| 135 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 136 |
+
"loss": 1.7114,
|
| 137 |
+
"step": 160
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.0,
|
| 141 |
+
"eval_loss": 1.3082835674285889,
|
| 142 |
+
"eval_runtime": 1.9145,
|
| 143 |
+
"eval_samples_per_second": 50.666,
|
| 144 |
+
"eval_steps_per_second": 3.656,
|
| 145 |
+
"step": 165
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.090909090909091,
|
| 149 |
+
"grad_norm": 1.0560592412948608,
|
| 150 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 151 |
+
"loss": 1.4839,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.2727272727272725,
|
| 156 |
+
"grad_norm": 0.8097766041755676,
|
| 157 |
+
"learning_rate": 1.8e-05,
|
| 158 |
+
"loss": 1.4752,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.4545454545454546,
|
| 163 |
+
"grad_norm": 0.7408425211906433,
|
| 164 |
+
"learning_rate": 1.9e-05,
|
| 165 |
+
"loss": 1.4855,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.6363636363636362,
|
| 170 |
+
"grad_norm": 0.902044415473938,
|
| 171 |
+
"learning_rate": 2e-05,
|
| 172 |
+
"loss": 1.439,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.8181818181818183,
|
| 177 |
+
"grad_norm": 0.8487627506256104,
|
| 178 |
+
"learning_rate": 2.1e-05,
|
| 179 |
+
"loss": 1.3827,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 4.0,
|
| 184 |
+
"grad_norm": 1.330592393875122,
|
| 185 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 186 |
+
"loss": 1.3552,
|
| 187 |
+
"step": 220
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 4.0,
|
| 191 |
+
"eval_loss": 1.0556784868240356,
|
| 192 |
+
"eval_runtime": 1.9095,
|
| 193 |
+
"eval_samples_per_second": 50.8,
|
| 194 |
+
"eval_steps_per_second": 3.666,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.181818181818182,
|
| 199 |
+
"grad_norm": 0.8066139221191406,
|
| 200 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 201 |
+
"loss": 1.2733,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.363636363636363,
|
| 206 |
+
"grad_norm": 0.6790980696678162,
|
| 207 |
+
"learning_rate": 2.4e-05,
|
| 208 |
+
"loss": 1.2248,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.545454545454545,
|
| 213 |
+
"grad_norm": 0.8204854726791382,
|
| 214 |
+
"learning_rate": 2.5e-05,
|
| 215 |
+
"loss": 1.2713,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.7272727272727275,
|
| 220 |
+
"grad_norm": 0.7819919586181641,
|
| 221 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 222 |
+
"loss": 1.2195,
|
| 223 |
+
"step": 260
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 4.909090909090909,
|
| 227 |
+
"grad_norm": 0.5966542363166809,
|
| 228 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 229 |
+
"loss": 1.1837,
|
| 230 |
+
"step": 270
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.0,
|
| 234 |
+
"eval_loss": 0.9253256916999817,
|
| 235 |
+
"eval_runtime": 1.9159,
|
| 236 |
+
"eval_samples_per_second": 50.628,
|
| 237 |
+
"eval_steps_per_second": 3.654,
|
| 238 |
+
"step": 275
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 5.090909090909091,
|
| 242 |
+
"grad_norm": 0.772972583770752,
|
| 243 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 244 |
+
"loss": 1.151,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.2727272727272725,
|
| 249 |
+
"grad_norm": 0.6945077180862427,
|
| 250 |
+
"learning_rate": 2.9e-05,
|
| 251 |
+
"loss": 1.0236,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.454545454545454,
|
| 256 |
+
"grad_norm": 0.6860663294792175,
|
| 257 |
+
"learning_rate": 3e-05,
|
| 258 |
+
"loss": 1.123,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.636363636363637,
|
| 263 |
+
"grad_norm": 0.640788197517395,
|
| 264 |
+
"learning_rate": 3.1e-05,
|
| 265 |
+
"loss": 1.1041,
|
| 266 |
+
"step": 310
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.818181818181818,
|
| 270 |
+
"grad_norm": 0.6724874377250671,
|
| 271 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 272 |
+
"loss": 1.0774,
|
| 273 |
+
"step": 320
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.0,
|
| 277 |
+
"grad_norm": 1.2789943218231201,
|
| 278 |
+
"learning_rate": 3.3e-05,
|
| 279 |
+
"loss": 1.0695,
|
| 280 |
+
"step": 330
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 6.0,
|
| 284 |
+
"eval_loss": 0.8376194834709167,
|
| 285 |
+
"eval_runtime": 1.9165,
|
| 286 |
+
"eval_samples_per_second": 50.613,
|
| 287 |
+
"eval_steps_per_second": 3.652,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 6.181818181818182,
|
| 292 |
+
"grad_norm": 0.6990534067153931,
|
| 293 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 294 |
+
"loss": 1.0048,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.363636363636363,
|
| 299 |
+
"grad_norm": 0.8184038400650024,
|
| 300 |
+
"learning_rate": 3.5e-05,
|
| 301 |
+
"loss": 0.9969,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.545454545454545,
|
| 306 |
+
"grad_norm": 0.6995009183883667,
|
| 307 |
+
"learning_rate": 3.6e-05,
|
| 308 |
+
"loss": 0.949,
|
| 309 |
+
"step": 360
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.7272727272727275,
|
| 313 |
+
"grad_norm": 0.784795343875885,
|
| 314 |
+
"learning_rate": 3.7e-05,
|
| 315 |
+
"loss": 1.0163,
|
| 316 |
+
"step": 370
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 6.909090909090909,
|
| 320 |
+
"grad_norm": 0.6257941126823425,
|
| 321 |
+
"learning_rate": 3.8e-05,
|
| 322 |
+
"loss": 1.0053,
|
| 323 |
+
"step": 380
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 7.0,
|
| 327 |
+
"eval_loss": 0.7738495469093323,
|
| 328 |
+
"eval_runtime": 1.9131,
|
| 329 |
+
"eval_samples_per_second": 50.703,
|
| 330 |
+
"eval_steps_per_second": 3.659,
|
| 331 |
+
"step": 385
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.090909090909091,
|
| 335 |
+
"grad_norm": 0.6166519522666931,
|
| 336 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 337 |
+
"loss": 0.929,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.2727272727272725,
|
| 342 |
+
"grad_norm": 0.6807654500007629,
|
| 343 |
+
"learning_rate": 4e-05,
|
| 344 |
+
"loss": 0.8915,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.454545454545454,
|
| 349 |
+
"grad_norm": 0.6417834162712097,
|
| 350 |
+
"learning_rate": 4.1e-05,
|
| 351 |
+
"loss": 0.9398,
|
| 352 |
+
"step": 410
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.636363636363637,
|
| 356 |
+
"grad_norm": 0.7357299327850342,
|
| 357 |
+
"learning_rate": 4.2e-05,
|
| 358 |
+
"loss": 0.9189,
|
| 359 |
+
"step": 420
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.818181818181818,
|
| 363 |
+
"grad_norm": 0.6846190094947815,
|
| 364 |
+
"learning_rate": 4.3e-05,
|
| 365 |
+
"loss": 0.9205,
|
| 366 |
+
"step": 430
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.0,
|
| 370 |
+
"grad_norm": 0.9817469120025635,
|
| 371 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 372 |
+
"loss": 0.8928,
|
| 373 |
+
"step": 440
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 8.0,
|
| 377 |
+
"eval_loss": 0.7215824723243713,
|
| 378 |
+
"eval_runtime": 1.9094,
|
| 379 |
+
"eval_samples_per_second": 50.801,
|
| 380 |
+
"eval_steps_per_second": 3.666,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 8.181818181818182,
|
| 385 |
+
"grad_norm": 0.6967756748199463,
|
| 386 |
+
"learning_rate": 4.5e-05,
|
| 387 |
+
"loss": 0.9265,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 8.363636363636363,
|
| 392 |
+
"grad_norm": 0.6210283041000366,
|
| 393 |
+
"learning_rate": 4.600000000000001e-05,
|
| 394 |
+
"loss": 0.8445,
|
| 395 |
+
"step": 460
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 8.545454545454545,
|
| 399 |
+
"grad_norm": 0.6811444759368896,
|
| 400 |
+
"learning_rate": 4.7e-05,
|
| 401 |
+
"loss": 0.8298,
|
| 402 |
+
"step": 470
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 8.727272727272727,
|
| 406 |
+
"grad_norm": 0.5957173109054565,
|
| 407 |
+
"learning_rate": 4.8e-05,
|
| 408 |
+
"loss": 0.7891,
|
| 409 |
+
"step": 480
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 8.909090909090908,
|
| 413 |
+
"grad_norm": 0.6470558047294617,
|
| 414 |
+
"learning_rate": 4.9e-05,
|
| 415 |
+
"loss": 0.8546,
|
| 416 |
+
"step": 490
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 9.0,
|
| 420 |
+
"eval_loss": 0.6784611940383911,
|
| 421 |
+
"eval_runtime": 1.9123,
|
| 422 |
+
"eval_samples_per_second": 50.725,
|
| 423 |
+
"eval_steps_per_second": 3.661,
|
| 424 |
+
"step": 495
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 9.090909090909092,
|
| 428 |
+
"grad_norm": 0.5924862623214722,
|
| 429 |
+
"learning_rate": 5e-05,
|
| 430 |
+
"loss": 0.8455,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 9.272727272727273,
|
| 435 |
+
"grad_norm": 0.6424144506454468,
|
| 436 |
+
"learning_rate": 4.9166666666666665e-05,
|
| 437 |
+
"loss": 0.8007,
|
| 438 |
+
"step": 510
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 9.454545454545455,
|
| 442 |
+
"grad_norm": 0.6752752065658569,
|
| 443 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 444 |
+
"loss": 0.8317,
|
| 445 |
+
"step": 520
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 9.636363636363637,
|
| 449 |
+
"grad_norm": 0.5884845852851868,
|
| 450 |
+
"learning_rate": 4.75e-05,
|
| 451 |
+
"loss": 0.7812,
|
| 452 |
+
"step": 530
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 9.818181818181818,
|
| 456 |
+
"grad_norm": 0.6853846907615662,
|
| 457 |
+
"learning_rate": 4.666666666666667e-05,
|
| 458 |
+
"loss": 0.8089,
|
| 459 |
+
"step": 540
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.0,
|
| 463 |
+
"grad_norm": 1.07851243019104,
|
| 464 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 465 |
+
"loss": 0.7501,
|
| 466 |
+
"step": 550
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 10.0,
|
| 470 |
+
"eval_loss": 0.6473520994186401,
|
| 471 |
+
"eval_runtime": 1.9092,
|
| 472 |
+
"eval_samples_per_second": 50.807,
|
| 473 |
+
"eval_steps_per_second": 3.666,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.181818181818182,
|
| 478 |
+
"grad_norm": 1.17769455909729,
|
| 479 |
+
"learning_rate": 4.5e-05,
|
| 480 |
+
"loss": 0.7607,
|
| 481 |
+
"step": 560
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 10.363636363636363,
|
| 485 |
+
"grad_norm": 0.5850676894187927,
|
| 486 |
+
"learning_rate": 4.4166666666666665e-05,
|
| 487 |
+
"loss": 0.7473,
|
| 488 |
+
"step": 570
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 10.545454545454545,
|
| 492 |
+
"grad_norm": 0.5133849382400513,
|
| 493 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 494 |
+
"loss": 0.7539,
|
| 495 |
+
"step": 580
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 10.727272727272727,
|
| 499 |
+
"grad_norm": 0.5890449285507202,
|
| 500 |
+
"learning_rate": 4.25e-05,
|
| 501 |
+
"loss": 0.7221,
|
| 502 |
+
"step": 590
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 10.909090909090908,
|
| 506 |
+
"grad_norm": 2.0515189170837402,
|
| 507 |
+
"learning_rate": 4.166666666666667e-05,
|
| 508 |
+
"loss": 0.7381,
|
| 509 |
+
"step": 600
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 11.0,
|
| 513 |
+
"eval_loss": 0.6253225207328796,
|
| 514 |
+
"eval_runtime": 1.9123,
|
| 515 |
+
"eval_samples_per_second": 50.724,
|
| 516 |
+
"eval_steps_per_second": 3.66,
|
| 517 |
+
"step": 605
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 11.090909090909092,
|
| 521 |
+
"grad_norm": 0.5024580955505371,
|
| 522 |
+
"learning_rate": 4.0833333333333334e-05,
|
| 523 |
+
"loss": 0.7502,
|
| 524 |
+
"step": 610
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 11.272727272727273,
|
| 528 |
+
"grad_norm": 0.5601004362106323,
|
| 529 |
+
"learning_rate": 4e-05,
|
| 530 |
+
"loss": 0.7421,
|
| 531 |
+
"step": 620
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 11.454545454545455,
|
| 535 |
+
"grad_norm": 0.5731512308120728,
|
| 536 |
+
"learning_rate": 3.9166666666666665e-05,
|
| 537 |
+
"loss": 0.7159,
|
| 538 |
+
"step": 630
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 11.636363636363637,
|
| 542 |
+
"grad_norm": 0.5588123202323914,
|
| 543 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 544 |
+
"loss": 0.6927,
|
| 545 |
+
"step": 640
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 11.818181818181818,
|
| 549 |
+
"grad_norm": 0.6156173348426819,
|
| 550 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 551 |
+
"loss": 0.6928,
|
| 552 |
+
"step": 650
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 12.0,
|
| 556 |
+
"grad_norm": 0.8520174622535706,
|
| 557 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 558 |
+
"loss": 0.7357,
|
| 559 |
+
"step": 660
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 12.0,
|
| 563 |
+
"eval_loss": 0.605716347694397,
|
| 564 |
+
"eval_runtime": 1.9125,
|
| 565 |
+
"eval_samples_per_second": 50.72,
|
| 566 |
+
"eval_steps_per_second": 3.66,
|
| 567 |
+
"step": 660
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 12.181818181818182,
|
| 571 |
+
"grad_norm": 0.702212929725647,
|
| 572 |
+
"learning_rate": 3.5833333333333335e-05,
|
| 573 |
+
"loss": 0.7132,
|
| 574 |
+
"step": 670
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 12.363636363636363,
|
| 578 |
+
"grad_norm": 0.5611622333526611,
|
| 579 |
+
"learning_rate": 3.5e-05,
|
| 580 |
+
"loss": 0.7224,
|
| 581 |
+
"step": 680
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 12.545454545454545,
|
| 585 |
+
"grad_norm": 0.5733953714370728,
|
| 586 |
+
"learning_rate": 3.4166666666666666e-05,
|
| 587 |
+
"loss": 0.7207,
|
| 588 |
+
"step": 690
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 12.727272727272727,
|
| 592 |
+
"grad_norm": 0.5382534265518188,
|
| 593 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 594 |
+
"loss": 0.6554,
|
| 595 |
+
"step": 700
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 12.909090909090908,
|
| 599 |
+
"grad_norm": 0.6537340879440308,
|
| 600 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 601 |
+
"loss": 0.6237,
|
| 602 |
+
"step": 710
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 13.0,
|
| 606 |
+
"eval_loss": 0.5956346392631531,
|
| 607 |
+
"eval_runtime": 1.9108,
|
| 608 |
+
"eval_samples_per_second": 50.765,
|
| 609 |
+
"eval_steps_per_second": 3.663,
|
| 610 |
+
"step": 715
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 13.090909090909092,
|
| 614 |
+
"grad_norm": 0.5932813882827759,
|
| 615 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 616 |
+
"loss": 0.7095,
|
| 617 |
+
"step": 720
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 13.272727272727273,
|
| 621 |
+
"grad_norm": 0.5455180406570435,
|
| 622 |
+
"learning_rate": 3.0833333333333335e-05,
|
| 623 |
+
"loss": 0.6415,
|
| 624 |
+
"step": 730
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 13.454545454545455,
|
| 628 |
+
"grad_norm": 0.548633337020874,
|
| 629 |
+
"learning_rate": 3e-05,
|
| 630 |
+
"loss": 0.6528,
|
| 631 |
+
"step": 740
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 13.636363636363637,
|
| 635 |
+
"grad_norm": 0.5608177185058594,
|
| 636 |
+
"learning_rate": 2.916666666666667e-05,
|
| 637 |
+
"loss": 0.6676,
|
| 638 |
+
"step": 750
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 13.818181818181818,
|
| 642 |
+
"grad_norm": 0.5515778660774231,
|
| 643 |
+
"learning_rate": 2.8333333333333335e-05,
|
| 644 |
+
"loss": 0.6927,
|
| 645 |
+
"step": 760
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 14.0,
|
| 649 |
+
"grad_norm": 1.0543361902236938,
|
| 650 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 651 |
+
"loss": 0.6932,
|
| 652 |
+
"step": 770
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 14.0,
|
| 656 |
+
"eval_loss": 0.5847615599632263,
|
| 657 |
+
"eval_runtime": 1.9117,
|
| 658 |
+
"eval_samples_per_second": 50.741,
|
| 659 |
+
"eval_steps_per_second": 3.662,
|
| 660 |
+
"step": 770
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 14.181818181818182,
|
| 664 |
+
"grad_norm": 0.5957939624786377,
|
| 665 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 666 |
+
"loss": 0.6294,
|
| 667 |
+
"step": 780
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 14.363636363636363,
|
| 671 |
+
"grad_norm": 0.495108962059021,
|
| 672 |
+
"learning_rate": 2.5833333333333336e-05,
|
| 673 |
+
"loss": 0.6384,
|
| 674 |
+
"step": 790
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 14.545454545454545,
|
| 678 |
+
"grad_norm": 0.45685040950775146,
|
| 679 |
+
"learning_rate": 2.5e-05,
|
| 680 |
+
"loss": 0.6492,
|
| 681 |
+
"step": 800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 14.727272727272727,
|
| 685 |
+
"grad_norm": 0.5110467672348022,
|
| 686 |
+
"learning_rate": 2.4166666666666667e-05,
|
| 687 |
+
"loss": 0.6384,
|
| 688 |
+
"step": 810
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 14.909090909090908,
|
| 692 |
+
"grad_norm": 0.48996323347091675,
|
| 693 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 694 |
+
"loss": 0.6802,
|
| 695 |
+
"step": 820
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 15.0,
|
| 699 |
+
"eval_loss": 0.5759454965591431,
|
| 700 |
+
"eval_runtime": 1.9161,
|
| 701 |
+
"eval_samples_per_second": 50.624,
|
| 702 |
+
"eval_steps_per_second": 3.653,
|
| 703 |
+
"step": 825
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 15.090909090909092,
|
| 707 |
+
"grad_norm": 0.5354136228561401,
|
| 708 |
+
"learning_rate": 2.25e-05,
|
| 709 |
+
"loss": 0.6623,
|
| 710 |
+
"step": 830
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 15.272727272727273,
|
| 714 |
+
"grad_norm": 0.5101513266563416,
|
| 715 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 716 |
+
"loss": 0.664,
|
| 717 |
+
"step": 840
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 15.454545454545455,
|
| 721 |
+
"grad_norm": 0.593004047870636,
|
| 722 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 723 |
+
"loss": 0.6559,
|
| 724 |
+
"step": 850
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 15.636363636363637,
|
| 728 |
+
"grad_norm": 0.5267238020896912,
|
| 729 |
+
"learning_rate": 2e-05,
|
| 730 |
+
"loss": 0.6319,
|
| 731 |
+
"step": 860
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 15.818181818181818,
|
| 735 |
+
"grad_norm": 0.5737471580505371,
|
| 736 |
+
"learning_rate": 1.9166666666666667e-05,
|
| 737 |
+
"loss": 0.5883,
|
| 738 |
+
"step": 870
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 16.0,
|
| 742 |
+
"grad_norm": 0.805059015750885,
|
| 743 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 744 |
+
"loss": 0.654,
|
| 745 |
+
"step": 880
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 16.0,
|
| 749 |
+
"eval_loss": 0.5736147165298462,
|
| 750 |
+
"eval_runtime": 1.9086,
|
| 751 |
+
"eval_samples_per_second": 50.824,
|
| 752 |
+
"eval_steps_per_second": 3.668,
|
| 753 |
+
"step": 880
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 16.181818181818183,
|
| 757 |
+
"grad_norm": 0.5428951978683472,
|
| 758 |
+
"learning_rate": 1.75e-05,
|
| 759 |
+
"loss": 0.613,
|
| 760 |
+
"step": 890
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 16.363636363636363,
|
| 764 |
+
"grad_norm": 0.538959264755249,
|
| 765 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 766 |
+
"loss": 0.6214,
|
| 767 |
+
"step": 900
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 16.545454545454547,
|
| 771 |
+
"grad_norm": 0.6322575211524963,
|
| 772 |
+
"learning_rate": 1.5833333333333333e-05,
|
| 773 |
+
"loss": 0.6162,
|
| 774 |
+
"step": 910
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 16.727272727272727,
|
| 778 |
+
"grad_norm": 0.6376714110374451,
|
| 779 |
+
"learning_rate": 1.5e-05,
|
| 780 |
+
"loss": 0.6161,
|
| 781 |
+
"step": 920
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 16.90909090909091,
|
| 785 |
+
"grad_norm": 0.5397374033927917,
|
| 786 |
+
"learning_rate": 1.4166666666666668e-05,
|
| 787 |
+
"loss": 0.6439,
|
| 788 |
+
"step": 930
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 17.0,
|
| 792 |
+
"eval_loss": 0.5707854628562927,
|
| 793 |
+
"eval_runtime": 1.9113,
|
| 794 |
+
"eval_samples_per_second": 50.752,
|
| 795 |
+
"eval_steps_per_second": 3.663,
|
| 796 |
+
"step": 935
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 17.09090909090909,
|
| 800 |
+
"grad_norm": 0.43974068760871887,
|
| 801 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 802 |
+
"loss": 0.6028,
|
| 803 |
+
"step": 940
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 17.272727272727273,
|
| 807 |
+
"grad_norm": 0.5189619660377502,
|
| 808 |
+
"learning_rate": 1.25e-05,
|
| 809 |
+
"loss": 0.5696,
|
| 810 |
+
"step": 950
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 17.454545454545453,
|
| 814 |
+
"grad_norm": 0.5635692477226257,
|
| 815 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 816 |
+
"loss": 0.63,
|
| 817 |
+
"step": 960
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 17.636363636363637,
|
| 821 |
+
"grad_norm": 0.5299723744392395,
|
| 822 |
+
"learning_rate": 1.0833333333333334e-05,
|
| 823 |
+
"loss": 0.6387,
|
| 824 |
+
"step": 970
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 17.818181818181817,
|
| 828 |
+
"grad_norm": 0.6093310117721558,
|
| 829 |
+
"learning_rate": 1e-05,
|
| 830 |
+
"loss": 0.6522,
|
| 831 |
+
"step": 980
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 18.0,
|
| 835 |
+
"grad_norm": 0.7209185361862183,
|
| 836 |
+
"learning_rate": 9.166666666666666e-06,
|
| 837 |
+
"loss": 0.6005,
|
| 838 |
+
"step": 990
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 18.0,
|
| 842 |
+
"eval_loss": 0.5690126419067383,
|
| 843 |
+
"eval_runtime": 1.9113,
|
| 844 |
+
"eval_samples_per_second": 50.75,
|
| 845 |
+
"eval_steps_per_second": 3.662,
|
| 846 |
+
"step": 990
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 18.181818181818183,
|
| 850 |
+
"grad_norm": 0.523536205291748,
|
| 851 |
+
"learning_rate": 8.333333333333334e-06,
|
| 852 |
+
"loss": 0.6112,
|
| 853 |
+
"step": 1000
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 18.363636363636363,
|
| 857 |
+
"grad_norm": 0.5092321634292603,
|
| 858 |
+
"learning_rate": 7.5e-06,
|
| 859 |
+
"loss": 0.6261,
|
| 860 |
+
"step": 1010
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 18.545454545454547,
|
| 864 |
+
"grad_norm": 0.5760687589645386,
|
| 865 |
+
"learning_rate": 6.666666666666667e-06,
|
| 866 |
+
"loss": 0.591,
|
| 867 |
+
"step": 1020
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 18.727272727272727,
|
| 871 |
+
"grad_norm": 0.5239204168319702,
|
| 872 |
+
"learning_rate": 5.833333333333334e-06,
|
| 873 |
+
"loss": 0.6091,
|
| 874 |
+
"step": 1030
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 18.90909090909091,
|
| 878 |
+
"grad_norm": 0.5258241891860962,
|
| 879 |
+
"learning_rate": 5e-06,
|
| 880 |
+
"loss": 0.6392,
|
| 881 |
+
"step": 1040
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 19.0,
|
| 885 |
+
"eval_loss": 0.5662071108818054,
|
| 886 |
+
"eval_runtime": 1.9107,
|
| 887 |
+
"eval_samples_per_second": 50.767,
|
| 888 |
+
"eval_steps_per_second": 3.664,
|
| 889 |
+
"step": 1045
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 19.09090909090909,
|
| 893 |
+
"grad_norm": 0.5691114664077759,
|
| 894 |
+
"learning_rate": 4.166666666666667e-06,
|
| 895 |
+
"loss": 0.5851,
|
| 896 |
+
"step": 1050
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 19.272727272727273,
|
| 900 |
+
"grad_norm": 0.5294829607009888,
|
| 901 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 902 |
+
"loss": 0.5744,
|
| 903 |
+
"step": 1060
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 19.454545454545453,
|
| 907 |
+
"grad_norm": 0.5142855644226074,
|
| 908 |
+
"learning_rate": 2.5e-06,
|
| 909 |
+
"loss": 0.6367,
|
| 910 |
+
"step": 1070
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 19.636363636363637,
|
| 914 |
+
"grad_norm": 0.6378938555717468,
|
| 915 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 916 |
+
"loss": 0.5809,
|
| 917 |
+
"step": 1080
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 19.818181818181817,
|
| 921 |
+
"grad_norm": 0.5766515731811523,
|
| 922 |
+
"learning_rate": 8.333333333333333e-07,
|
| 923 |
+
"loss": 0.6091,
|
| 924 |
+
"step": 1090
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 20.0,
|
| 928 |
+
"grad_norm": 0.8583983778953552,
|
| 929 |
+
"learning_rate": 0.0,
|
| 930 |
+
"loss": 0.6453,
|
| 931 |
+
"step": 1100
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 20.0,
|
| 935 |
+
"eval_loss": 0.5654382109642029,
|
| 936 |
+
"eval_runtime": 1.9129,
|
| 937 |
+
"eval_samples_per_second": 50.709,
|
| 938 |
+
"eval_steps_per_second": 3.659,
|
| 939 |
+
"step": 1100
|
| 940 |
+
}
|
| 941 |
+
],
|
| 942 |
+
"logging_steps": 10,
|
| 943 |
+
"max_steps": 1100,
|
| 944 |
+
"num_input_tokens_seen": 0,
|
| 945 |
+
"num_train_epochs": 20,
|
| 946 |
+
"save_steps": 500,
|
| 947 |
+
"stateful_callbacks": {
|
| 948 |
+
"TrainerControl": {
|
| 949 |
+
"args": {
|
| 950 |
+
"should_epoch_stop": false,
|
| 951 |
+
"should_evaluate": false,
|
| 952 |
+
"should_log": false,
|
| 953 |
+
"should_save": true,
|
| 954 |
+
"should_training_stop": true
|
| 955 |
+
},
|
| 956 |
+
"attributes": {}
|
| 957 |
+
}
|
| 958 |
+
},
|
| 959 |
+
"total_flos": 1.0595867295744e+16,
|
| 960 |
+
"train_batch_size": 16,
|
| 961 |
+
"trial_name": null,
|
| 962 |
+
"trial_params": null
|
| 963 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66728a66637bc08b9510c8914f8b81394f4205c8cd579f4a73859ac888dcb9a1
|
| 3 |
+
size 5048
|