manual upload with upload_folder.py
Browse files- checkpoint-1332/config.json +28 -0
- checkpoint-1332/generation_config.json +7 -0
- checkpoint-1332/model.safetensors +3 -0
- checkpoint-1332/trainer_state.json +907 -0
- checkpoint-1332/training_args.bin +3 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
checkpoint-1332/config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "BEE-spoke-data/smol_llama-220M-GQA",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 10,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.36.2",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 32128
|
| 28 |
+
}
|
checkpoint-1332/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.36.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
checkpoint-1332/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:001f96db3db5fef52d8d4f32549dab7821146f27a4a9c557e162ec543c63ef99
|
| 3 |
+
size 435736840
|
checkpoint-1332/trainer_state.json
ADDED
|
@@ -0,0 +1,907 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.7867298578199051,
|
| 5 |
+
"eval_steps": 123,
|
| 6 |
+
"global_step": 1332,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"eval_loss": 2.6729655265808105,
|
| 14 |
+
"eval_runtime": 1.2923,
|
| 15 |
+
"eval_samples_per_second": 1104.214,
|
| 16 |
+
"eval_steps_per_second": 138.51,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01,
|
| 21 |
+
"learning_rate": 1.0344827586206898e-05,
|
| 22 |
+
"loss": 2.4503,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"learning_rate": 2.0689655172413797e-05,
|
| 28 |
+
"loss": 2.1075,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.04,
|
| 33 |
+
"learning_rate": 3.103448275862069e-05,
|
| 34 |
+
"loss": 1.846,
|
| 35 |
+
"step": 30
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.05,
|
| 39 |
+
"learning_rate": 4.137931034482759e-05,
|
| 40 |
+
"loss": 1.7096,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.07,
|
| 45 |
+
"learning_rate": 5.172413793103448e-05,
|
| 46 |
+
"loss": 1.62,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.08,
|
| 51 |
+
"learning_rate": 5.9999705491506956e-05,
|
| 52 |
+
"loss": 1.5077,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.09,
|
| 57 |
+
"learning_rate": 5.998939830138442e-05,
|
| 58 |
+
"loss": 1.5523,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.11,
|
| 63 |
+
"learning_rate": 5.996437146844947e-05,
|
| 64 |
+
"loss": 1.497,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.12,
|
| 69 |
+
"learning_rate": 5.9924637276577847e-05,
|
| 70 |
+
"loss": 1.4915,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.14,
|
| 75 |
+
"learning_rate": 5.987021522843196e-05,
|
| 76 |
+
"loss": 1.4696,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.15,
|
| 81 |
+
"learning_rate": 5.9801132035888535e-05,
|
| 82 |
+
"loss": 1.4571,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.16,
|
| 87 |
+
"learning_rate": 5.971742160692758e-05,
|
| 88 |
+
"loss": 1.467,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.17,
|
| 93 |
+
"eval_loss": 1.0446314811706543,
|
| 94 |
+
"eval_runtime": 1.2693,
|
| 95 |
+
"eval_samples_per_second": 1124.217,
|
| 96 |
+
"eval_steps_per_second": 141.019,
|
| 97 |
+
"step": 123
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.18,
|
| 101 |
+
"learning_rate": 5.9619125028989474e-05,
|
| 102 |
+
"loss": 1.4675,
|
| 103 |
+
"step": 130
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.19,
|
| 107 |
+
"learning_rate": 5.9506290548808e-05,
|
| 108 |
+
"loss": 1.4741,
|
| 109 |
+
"step": 140
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.2,
|
| 113 |
+
"learning_rate": 5.937897354872957e-05,
|
| 114 |
+
"loss": 1.4539,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.22,
|
| 119 |
+
"learning_rate": 5.923723651952998e-05,
|
| 120 |
+
"loss": 1.4204,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.23,
|
| 125 |
+
"learning_rate": 5.9081149029742125e-05,
|
| 126 |
+
"loss": 1.5041,
|
| 127 |
+
"step": 170
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.24,
|
| 131 |
+
"learning_rate": 5.89107876915099e-05,
|
| 132 |
+
"loss": 1.4168,
|
| 133 |
+
"step": 180
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.26,
|
| 137 |
+
"learning_rate": 5.8726236122984704e-05,
|
| 138 |
+
"loss": 1.4291,
|
| 139 |
+
"step": 190
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.27,
|
| 143 |
+
"learning_rate": 5.852758490728334e-05,
|
| 144 |
+
"loss": 1.4508,
|
| 145 |
+
"step": 200
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.28,
|
| 149 |
+
"learning_rate": 5.831493154802725e-05,
|
| 150 |
+
"loss": 1.3973,
|
| 151 |
+
"step": 210
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.3,
|
| 155 |
+
"learning_rate": 5.808838042148501e-05,
|
| 156 |
+
"loss": 1.4332,
|
| 157 |
+
"step": 220
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.31,
|
| 161 |
+
"learning_rate": 5.784804272534145e-05,
|
| 162 |
+
"loss": 1.4276,
|
| 163 |
+
"step": 230
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.32,
|
| 167 |
+
"learning_rate": 5.75940364241188e-05,
|
| 168 |
+
"loss": 1.4506,
|
| 169 |
+
"step": 240
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 0.33,
|
| 173 |
+
"eval_loss": 0.9973111748695374,
|
| 174 |
+
"eval_runtime": 1.2436,
|
| 175 |
+
"eval_samples_per_second": 1147.474,
|
| 176 |
+
"eval_steps_per_second": 143.937,
|
| 177 |
+
"step": 246
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.34,
|
| 181 |
+
"learning_rate": 5.732648619127626e-05,
|
| 182 |
+
"loss": 1.4542,
|
| 183 |
+
"step": 250
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.35,
|
| 187 |
+
"learning_rate": 5.704552334801682e-05,
|
| 188 |
+
"loss": 1.3958,
|
| 189 |
+
"step": 260
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.37,
|
| 193 |
+
"learning_rate": 5.6751285798831086e-05,
|
| 194 |
+
"loss": 1.4643,
|
| 195 |
+
"step": 270
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.38,
|
| 199 |
+
"learning_rate": 5.644391796380987e-05,
|
| 200 |
+
"loss": 1.4258,
|
| 201 |
+
"step": 280
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.39,
|
| 205 |
+
"learning_rate": 5.6123570707758725e-05,
|
| 206 |
+
"loss": 1.3974,
|
| 207 |
+
"step": 290
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.41,
|
| 211 |
+
"learning_rate": 5.579040126614927e-05,
|
| 212 |
+
"loss": 1.4072,
|
| 213 |
+
"step": 300
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.42,
|
| 217 |
+
"learning_rate": 5.544457316794353e-05,
|
| 218 |
+
"loss": 1.4257,
|
| 219 |
+
"step": 310
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.43,
|
| 223 |
+
"learning_rate": 5.508625615532936e-05,
|
| 224 |
+
"loss": 1.4207,
|
| 225 |
+
"step": 320
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.45,
|
| 229 |
+
"learning_rate": 5.471562610040617e-05,
|
| 230 |
+
"loss": 1.4272,
|
| 231 |
+
"step": 330
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.46,
|
| 235 |
+
"learning_rate": 5.433286491886194e-05,
|
| 236 |
+
"loss": 1.3961,
|
| 237 |
+
"step": 340
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.47,
|
| 241 |
+
"learning_rate": 5.393816048068387e-05,
|
| 242 |
+
"loss": 1.4054,
|
| 243 |
+
"step": 350
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.49,
|
| 247 |
+
"learning_rate": 5.353170651794646e-05,
|
| 248 |
+
"loss": 1.3896,
|
| 249 |
+
"step": 360
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.5,
|
| 253 |
+
"eval_loss": 0.9749273061752319,
|
| 254 |
+
"eval_runtime": 1.2381,
|
| 255 |
+
"eval_samples_per_second": 1152.551,
|
| 256 |
+
"eval_steps_per_second": 144.574,
|
| 257 |
+
"step": 369
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.5,
|
| 261 |
+
"learning_rate": 5.3113702529722396e-05,
|
| 262 |
+
"loss": 1.3848,
|
| 263 |
+
"step": 370
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.51,
|
| 267 |
+
"learning_rate": 5.268435368416274e-05,
|
| 268 |
+
"loss": 1.4035,
|
| 269 |
+
"step": 380
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.53,
|
| 273 |
+
"learning_rate": 5.224387071779459e-05,
|
| 274 |
+
"loss": 1.3908,
|
| 275 |
+
"step": 390
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.54,
|
| 279 |
+
"learning_rate": 5.179246983208574e-05,
|
| 280 |
+
"loss": 1.4346,
|
| 281 |
+
"step": 400
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.56,
|
| 285 |
+
"learning_rate": 5.133037258732677e-05,
|
| 286 |
+
"loss": 1.3691,
|
| 287 |
+
"step": 410
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.57,
|
| 291 |
+
"learning_rate": 5.0857805793883114e-05,
|
| 292 |
+
"loss": 1.4064,
|
| 293 |
+
"step": 420
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.58,
|
| 297 |
+
"learning_rate": 5.037500140087006e-05,
|
| 298 |
+
"loss": 1.4202,
|
| 299 |
+
"step": 430
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.6,
|
| 303 |
+
"learning_rate": 4.988219638230564e-05,
|
| 304 |
+
"loss": 1.3841,
|
| 305 |
+
"step": 440
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.61,
|
| 309 |
+
"learning_rate": 4.937963262079706e-05,
|
| 310 |
+
"loss": 1.4063,
|
| 311 |
+
"step": 450
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.62,
|
| 315 |
+
"learning_rate": 4.886755678881786e-05,
|
| 316 |
+
"loss": 1.3588,
|
| 317 |
+
"step": 460
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.64,
|
| 321 |
+
"learning_rate": 4.83462202276342e-05,
|
| 322 |
+
"loss": 1.4261,
|
| 323 |
+
"step": 470
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.65,
|
| 327 |
+
"learning_rate": 4.781587882393937e-05,
|
| 328 |
+
"loss": 1.3587,
|
| 329 |
+
"step": 480
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.66,
|
| 333 |
+
"learning_rate": 4.727679288425746e-05,
|
| 334 |
+
"loss": 1.3725,
|
| 335 |
+
"step": 490
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.67,
|
| 339 |
+
"eval_loss": 0.9633959531784058,
|
| 340 |
+
"eval_runtime": 1.2455,
|
| 341 |
+
"eval_samples_per_second": 1145.725,
|
| 342 |
+
"eval_steps_per_second": 143.717,
|
| 343 |
+
"step": 492
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 0.68,
|
| 347 |
+
"learning_rate": 4.672922700717753e-05,
|
| 348 |
+
"loss": 1.387,
|
| 349 |
+
"step": 500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.69,
|
| 353 |
+
"learning_rate": 4.617344995348116e-05,
|
| 354 |
+
"loss": 1.4212,
|
| 355 |
+
"step": 510
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.7,
|
| 359 |
+
"learning_rate": 4.56097345142271e-05,
|
| 360 |
+
"loss": 1.3582,
|
| 361 |
+
"step": 520
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.72,
|
| 365 |
+
"learning_rate": 4.5038357376857706e-05,
|
| 366 |
+
"loss": 1.3673,
|
| 367 |
+
"step": 530
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.73,
|
| 371 |
+
"learning_rate": 4.445959898939291e-05,
|
| 372 |
+
"loss": 1.3926,
|
| 373 |
+
"step": 540
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.74,
|
| 377 |
+
"learning_rate": 4.38737434227785e-05,
|
| 378 |
+
"loss": 1.3984,
|
| 379 |
+
"step": 550
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 0.76,
|
| 383 |
+
"learning_rate": 4.328107823145599e-05,
|
| 384 |
+
"loss": 1.3786,
|
| 385 |
+
"step": 560
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.77,
|
| 389 |
+
"learning_rate": 4.2681894312222835e-05,
|
| 390 |
+
"loss": 1.3879,
|
| 391 |
+
"step": 570
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 0.79,
|
| 395 |
+
"learning_rate": 4.2076485761452074e-05,
|
| 396 |
+
"loss": 1.3952,
|
| 397 |
+
"step": 580
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.8,
|
| 401 |
+
"learning_rate": 4.146514973074152e-05,
|
| 402 |
+
"loss": 1.3746,
|
| 403 |
+
"step": 590
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.81,
|
| 407 |
+
"learning_rate": 4.084818628106341e-05,
|
| 408 |
+
"loss": 1.3788,
|
| 409 |
+
"step": 600
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.83,
|
| 413 |
+
"learning_rate": 4.022589823548594e-05,
|
| 414 |
+
"loss": 1.3901,
|
| 415 |
+
"step": 610
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.83,
|
| 419 |
+
"eval_loss": 0.9544292688369751,
|
| 420 |
+
"eval_runtime": 1.2361,
|
| 421 |
+
"eval_samples_per_second": 1154.443,
|
| 422 |
+
"eval_steps_per_second": 144.811,
|
| 423 |
+
"step": 615
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.84,
|
| 427 |
+
"learning_rate": 3.959859103053922e-05,
|
| 428 |
+
"loss": 1.3985,
|
| 429 |
+
"step": 620
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.85,
|
| 433 |
+
"learning_rate": 3.8966572566298416e-05,
|
| 434 |
+
"loss": 1.3521,
|
| 435 |
+
"step": 630
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.87,
|
| 439 |
+
"learning_rate": 3.833015305525763e-05,
|
| 440 |
+
"loss": 1.3964,
|
| 441 |
+
"step": 640
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.88,
|
| 445 |
+
"learning_rate": 3.7689644870068936e-05,
|
| 446 |
+
"loss": 1.353,
|
| 447 |
+
"step": 650
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.89,
|
| 451 |
+
"learning_rate": 3.704536239022104e-05,
|
| 452 |
+
"loss": 1.374,
|
| 453 |
+
"step": 660
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.91,
|
| 457 |
+
"learning_rate": 3.639762184773295e-05,
|
| 458 |
+
"loss": 1.3879,
|
| 459 |
+
"step": 670
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.92,
|
| 463 |
+
"learning_rate": 3.5746741171938384e-05,
|
| 464 |
+
"loss": 1.3619,
|
| 465 |
+
"step": 680
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.93,
|
| 469 |
+
"learning_rate": 3.509303983343707e-05,
|
| 470 |
+
"loss": 1.3933,
|
| 471 |
+
"step": 690
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.95,
|
| 475 |
+
"learning_rate": 3.4436838687289594e-05,
|
| 476 |
+
"loss": 1.4074,
|
| 477 |
+
"step": 700
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.96,
|
| 481 |
+
"learning_rate": 3.3778459815532676e-05,
|
| 482 |
+
"loss": 1.3754,
|
| 483 |
+
"step": 710
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.97,
|
| 487 |
+
"learning_rate": 3.3118226369092156e-05,
|
| 488 |
+
"loss": 1.3612,
|
| 489 |
+
"step": 720
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.99,
|
| 493 |
+
"learning_rate": 3.2456462409171516e-05,
|
| 494 |
+
"loss": 1.3759,
|
| 495 |
+
"step": 730
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.0,
|
| 499 |
+
"eval_loss": 0.9486423134803772,
|
| 500 |
+
"eval_runtime": 1.2367,
|
| 501 |
+
"eval_samples_per_second": 1153.891,
|
| 502 |
+
"eval_steps_per_second": 144.742,
|
| 503 |
+
"step": 738
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.0,
|
| 507 |
+
"learning_rate": 3.1793492748193396e-05,
|
| 508 |
+
"loss": 1.3409,
|
| 509 |
+
"step": 740
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.02,
|
| 513 |
+
"learning_rate": 3.1129642790372544e-05,
|
| 514 |
+
"loss": 1.3312,
|
| 515 |
+
"step": 750
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.01,
|
| 519 |
+
"learning_rate": 3.0465238371998244e-05,
|
| 520 |
+
"loss": 1.3471,
|
| 521 |
+
"step": 760
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.03,
|
| 525 |
+
"learning_rate": 2.9800605601504653e-05,
|
| 526 |
+
"loss": 1.3114,
|
| 527 |
+
"step": 770
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.04,
|
| 531 |
+
"learning_rate": 2.913607069940759e-05,
|
| 532 |
+
"loss": 1.3057,
|
| 533 |
+
"step": 780
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.05,
|
| 537 |
+
"learning_rate": 2.8471959838186304e-05,
|
| 538 |
+
"loss": 1.3084,
|
| 539 |
+
"step": 790
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.07,
|
| 543 |
+
"learning_rate": 2.7808598982188836e-05,
|
| 544 |
+
"loss": 1.3462,
|
| 545 |
+
"step": 800
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 1.08,
|
| 549 |
+
"learning_rate": 2.7146313727639476e-05,
|
| 550 |
+
"loss": 1.3102,
|
| 551 |
+
"step": 810
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.09,
|
| 555 |
+
"learning_rate": 2.6485429142826975e-05,
|
| 556 |
+
"loss": 1.3643,
|
| 557 |
+
"step": 820
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.11,
|
| 561 |
+
"learning_rate": 2.582626960855189e-05,
|
| 562 |
+
"loss": 1.289,
|
| 563 |
+
"step": 830
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.12,
|
| 567 |
+
"learning_rate": 2.5169158658911295e-05,
|
| 568 |
+
"loss": 1.3365,
|
| 569 |
+
"step": 840
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.13,
|
| 573 |
+
"learning_rate": 2.4514418822499098e-05,
|
| 574 |
+
"loss": 1.321,
|
| 575 |
+
"step": 850
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.15,
|
| 579 |
+
"learning_rate": 2.386237146409995e-05,
|
| 580 |
+
"loss": 1.2995,
|
| 581 |
+
"step": 860
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.15,
|
| 585 |
+
"eval_loss": 0.9462347030639648,
|
| 586 |
+
"eval_runtime": 1.2314,
|
| 587 |
+
"eval_samples_per_second": 1158.882,
|
| 588 |
+
"eval_steps_per_second": 145.368,
|
| 589 |
+
"step": 861
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 1.16,
|
| 593 |
+
"learning_rate": 2.3213336626954345e-05,
|
| 594 |
+
"loss": 1.2977,
|
| 595 |
+
"step": 870
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 1.17,
|
| 599 |
+
"learning_rate": 2.256763287567233e-05,
|
| 600 |
+
"loss": 1.3168,
|
| 601 |
+
"step": 880
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.19,
|
| 605 |
+
"learning_rate": 2.1925577139873016e-05,
|
| 606 |
+
"loss": 1.3419,
|
| 607 |
+
"step": 890
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 1.2,
|
| 611 |
+
"learning_rate": 2.1287484558626633e-05,
|
| 612 |
+
"loss": 1.3265,
|
| 613 |
+
"step": 900
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 1.22,
|
| 617 |
+
"learning_rate": 2.0653668325775296e-05,
|
| 618 |
+
"loss": 1.3237,
|
| 619 |
+
"step": 910
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.23,
|
| 623 |
+
"learning_rate": 2.0024439536208675e-05,
|
| 624 |
+
"loss": 1.3329,
|
| 625 |
+
"step": 920
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.24,
|
| 629 |
+
"learning_rate": 1.9400107033169888e-05,
|
| 630 |
+
"loss": 1.3135,
|
| 631 |
+
"step": 930
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 1.26,
|
| 635 |
+
"learning_rate": 1.8780977256666445e-05,
|
| 636 |
+
"loss": 1.3386,
|
| 637 |
+
"step": 940
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.27,
|
| 641 |
+
"learning_rate": 1.816735409306088e-05,
|
| 642 |
+
"loss": 1.3674,
|
| 643 |
+
"step": 950
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.28,
|
| 647 |
+
"learning_rate": 1.7559538725914758e-05,
|
| 648 |
+
"loss": 1.3275,
|
| 649 |
+
"step": 960
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 1.3,
|
| 653 |
+
"learning_rate": 1.6957829488159292e-05,
|
| 654 |
+
"loss": 1.3255,
|
| 655 |
+
"step": 970
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.31,
|
| 659 |
+
"learning_rate": 1.6362521715665102e-05,
|
| 660 |
+
"loss": 1.2892,
|
| 661 |
+
"step": 980
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.32,
|
| 665 |
+
"eval_loss": 0.9443601369857788,
|
| 666 |
+
"eval_runtime": 1.2319,
|
| 667 |
+
"eval_samples_per_second": 1158.341,
|
| 668 |
+
"eval_steps_per_second": 145.3,
|
| 669 |
+
"step": 984
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.32,
|
| 673 |
+
"learning_rate": 1.5773907602283046e-05,
|
| 674 |
+
"loss": 1.3093,
|
| 675 |
+
"step": 990
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.34,
|
| 679 |
+
"learning_rate": 1.519227605642722e-05,
|
| 680 |
+
"loss": 1.3147,
|
| 681 |
+
"step": 1000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.35,
|
| 685 |
+
"learning_rate": 1.4617912559270592e-05,
|
| 686 |
+
"loss": 1.344,
|
| 687 |
+
"step": 1010
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 1.36,
|
| 691 |
+
"learning_rate": 1.405109902462276e-05,
|
| 692 |
+
"loss": 1.3422,
|
| 693 |
+
"step": 1020
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 1.38,
|
| 697 |
+
"learning_rate": 1.3492113660558688e-05,
|
| 698 |
+
"loss": 1.3541,
|
| 699 |
+
"step": 1030
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.39,
|
| 703 |
+
"learning_rate": 1.2941230832866392e-05,
|
| 704 |
+
"loss": 1.3398,
|
| 705 |
+
"step": 1040
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.4,
|
| 709 |
+
"learning_rate": 1.2398720930380388e-05,
|
| 710 |
+
"loss": 1.3489,
|
| 711 |
+
"step": 1050
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 1.42,
|
| 715 |
+
"learning_rate": 1.1864850232267304e-05,
|
| 716 |
+
"loss": 1.283,
|
| 717 |
+
"step": 1060
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.43,
|
| 721 |
+
"learning_rate": 1.1339880777328485e-05,
|
| 722 |
+
"loss": 1.3491,
|
| 723 |
+
"step": 1070
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 1.45,
|
| 727 |
+
"learning_rate": 1.082407023538399e-05,
|
| 728 |
+
"loss": 1.3233,
|
| 729 |
+
"step": 1080
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 1.46,
|
| 733 |
+
"learning_rate": 1.0317671780800976e-05,
|
| 734 |
+
"loss": 1.3312,
|
| 735 |
+
"step": 1090
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 1.47,
|
| 739 |
+
"learning_rate": 9.82093396822857e-06,
|
| 740 |
+
"loss": 1.3213,
|
| 741 |
+
"step": 1100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.48,
|
| 745 |
+
"eval_loss": 0.9438613653182983,
|
| 746 |
+
"eval_runtime": 1.2333,
|
| 747 |
+
"eval_samples_per_second": 1157.029,
|
| 748 |
+
"eval_steps_per_second": 145.135,
|
| 749 |
+
"step": 1107
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.49,
|
| 753 |
+
"learning_rate": 9.334100610600213e-06,
|
| 754 |
+
"loss": 1.3387,
|
| 755 |
+
"step": 1110
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.5,
|
| 759 |
+
"learning_rate": 8.857410659463456e-06,
|
| 760 |
+
"loss": 1.3257,
|
| 761 |
+
"step": 1120
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 1.51,
|
| 765 |
+
"learning_rate": 8.391098087695704e-06,
|
| 766 |
+
"loss": 1.3256,
|
| 767 |
+
"step": 1130
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 1.53,
|
| 771 |
+
"learning_rate": 7.935391774663827e-06,
|
| 772 |
+
"loss": 1.3479,
|
| 773 |
+
"step": 1140
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.54,
|
| 777 |
+
"learning_rate": 7.490515393883629e-06,
|
| 778 |
+
"loss": 1.3397,
|
| 779 |
+
"step": 1150
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.55,
|
| 783 |
+
"learning_rate": 7.0566873032346145e-06,
|
| 784 |
+
"loss": 1.3145,
|
| 785 |
+
"step": 1160
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 1.57,
|
| 789 |
+
"learning_rate": 6.634120437783775e-06,
|
| 790 |
+
"loss": 1.3372,
|
| 791 |
+
"step": 1170
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.58,
|
| 795 |
+
"learning_rate": 6.22302220527104e-06,
|
| 796 |
+
"loss": 1.3226,
|
| 797 |
+
"step": 1180
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 1.59,
|
| 801 |
+
"learning_rate": 5.823594384307744e-06,
|
| 802 |
+
"loss": 1.3637,
|
| 803 |
+
"step": 1190
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.61,
|
| 807 |
+
"learning_rate": 5.436033025337929e-06,
|
| 808 |
+
"loss": 1.3552,
|
| 809 |
+
"step": 1200
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.62,
|
| 813 |
+
"learning_rate": 5.060528354411302e-06,
|
| 814 |
+
"loss": 1.3379,
|
| 815 |
+
"step": 1210
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.64,
|
| 819 |
+
"learning_rate": 4.697264679814908e-06,
|
| 820 |
+
"loss": 1.3679,
|
| 821 |
+
"step": 1220
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 1.65,
|
| 825 |
+
"learning_rate": 4.346420301609418e-06,
|
| 826 |
+
"loss": 1.3233,
|
| 827 |
+
"step": 1230
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 1.65,
|
| 831 |
+
"eval_loss": 0.9434655904769897,
|
| 832 |
+
"eval_runtime": 1.2359,
|
| 833 |
+
"eval_samples_per_second": 1154.599,
|
| 834 |
+
"eval_steps_per_second": 144.831,
|
| 835 |
+
"step": 1230
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.66,
|
| 839 |
+
"learning_rate": 4.008167424114447e-06,
|
| 840 |
+
"loss": 1.3575,
|
| 841 |
+
"step": 1240
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.68,
|
| 845 |
+
"learning_rate": 3.682672071385791e-06,
|
| 846 |
+
"loss": 1.3296,
|
| 847 |
+
"step": 1250
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.69,
|
| 851 |
+
"learning_rate": 3.3700940057261587e-06,
|
| 852 |
+
"loss": 1.3691,
|
| 853 |
+
"step": 1260
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 1.7,
|
| 857 |
+
"learning_rate": 3.070586649269298e-06,
|
| 858 |
+
"loss": 1.3525,
|
| 859 |
+
"step": 1270
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 1.72,
|
| 863 |
+
"learning_rate": 2.78429700867612e-06,
|
| 864 |
+
"loss": 1.3283,
|
| 865 |
+
"step": 1280
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 1.73,
|
| 869 |
+
"learning_rate": 2.5113656029796437e-06,
|
| 870 |
+
"loss": 1.3397,
|
| 871 |
+
"step": 1290
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.74,
|
| 875 |
+
"learning_rate": 2.251926394614322e-06,
|
| 876 |
+
"loss": 1.3354,
|
| 877 |
+
"step": 1300
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 1.76,
|
| 881 |
+
"learning_rate": 2.0061067236634823e-06,
|
| 882 |
+
"loss": 1.3426,
|
| 883 |
+
"step": 1310
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 1.77,
|
| 887 |
+
"learning_rate": 1.7740272453572314e-06,
|
| 888 |
+
"loss": 1.364,
|
| 889 |
+
"step": 1320
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 1.78,
|
| 893 |
+
"learning_rate": 1.5558018708514477e-06,
|
| 894 |
+
"loss": 1.3184,
|
| 895 |
+
"step": 1330
|
| 896 |
+
}
|
| 897 |
+
],
|
| 898 |
+
"logging_steps": 10,
|
| 899 |
+
"max_steps": 1476,
|
| 900 |
+
"num_input_tokens_seen": 0,
|
| 901 |
+
"num_train_epochs": 2,
|
| 902 |
+
"save_steps": 148,
|
| 903 |
+
"total_flos": 4.787173841489101e+16,
|
| 904 |
+
"train_batch_size": 4,
|
| 905 |
+
"trial_name": null,
|
| 906 |
+
"trial_params": null
|
| 907 |
+
}
|
checkpoint-1332/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f54d8a906435914ee535a2296ab2ef41450bd0c8f54cf4b7c8bdee39996977b
|
| 3 |
+
size 5304
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.36.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 435736840
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abe96487e317580862d6d466598183789a4837af487f2984876841774b885e4b
|
| 3 |
size 435736840
|