Commit
•
86414a1
1
Parent(s):
a22a1df
Upload 23 files
Browse files- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- checkpoint-1000/adapter_config.json +21 -0
- checkpoint-1000/adapter_model.bin +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +656 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1200/adapter_config.json +21 -0
- checkpoint-1200/adapter_model.bin +3 -0
- checkpoint-1200/optimizer.pt +3 -0
- checkpoint-1200/rng_state.pth +3 -0
- checkpoint-1200/scheduler.pt +3 -0
- checkpoint-1200/trainer_state.json +784 -0
- checkpoint-1200/training_args.bin +3 -0
- checkpoint-400/adapter_config.json +21 -0
- checkpoint-400/adapter_model.bin +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/trainer_state.json +272 -0
- checkpoint-400/training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "yahma/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"lora_alpha": 16,
|
| 9 |
+
"lora_dropout": 0.05,
|
| 10 |
+
"merge_weights": false,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 16,
|
| 14 |
+
"target_modules": [
|
| 15 |
+
"q_proj",
|
| 16 |
+
"k_proj",
|
| 17 |
+
"v_proj",
|
| 18 |
+
"o_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44227795ebad7aa6336263a671bb5806f3b72b192d952763818634123740ab18
|
| 3 |
+
size 67201357
|
checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "yahma/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"lora_alpha": 16,
|
| 9 |
+
"lora_dropout": 0.05,
|
| 10 |
+
"merge_weights": false,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 16,
|
| 14 |
+
"target_modules": [
|
| 15 |
+
"q_proj",
|
| 16 |
+
"k_proj",
|
| 17 |
+
"v_proj",
|
| 18 |
+
"o_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-1000/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:768d39afab84a960779cf16f5482a77e1c88d29da2dd831908b17a4241556bd5
|
| 3 |
+
size 67201357
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0da6e0297addfa1565d582113ac111293bf6202cc807ea9d5db32d450bebe342
|
| 3 |
+
size 134433093
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:753f6c0769945547ada2373b7e3609dc2e5ab8c91e5819155848c6ea0fabae27
|
| 3 |
+
size 14575
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f16e3426c37be2bdadce530cd217d988bad0bd22076d42a4eb12f0edc29a7185
|
| 3 |
+
size 627
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,656 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7640588283538818,
|
| 3 |
+
"best_model_checkpoint": "./model_20230703_attempt1/checkpoint-400",
|
| 4 |
+
"epoch": 11.204481792717086,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 2.5488,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.22,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 2.3131,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.34,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 2.1798,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.45,
|
| 30 |
+
"learning_rate": 0.00011999999999999999,
|
| 31 |
+
"loss": 1.6567,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.56,
|
| 36 |
+
"learning_rate": 0.000147,
|
| 37 |
+
"loss": 1.2086,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.67,
|
| 42 |
+
"learning_rate": 0.00017699999999999997,
|
| 43 |
+
"loss": 0.8952,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.78,
|
| 48 |
+
"learning_rate": 0.00020699999999999996,
|
| 49 |
+
"loss": 1.0646,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.9,
|
| 54 |
+
"learning_rate": 0.000237,
|
| 55 |
+
"loss": 0.7725,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.01,
|
| 60 |
+
"learning_rate": 0.000267,
|
| 61 |
+
"loss": 0.8192,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.12,
|
| 66 |
+
"learning_rate": 0.00029699999999999996,
|
| 67 |
+
"loss": 0.7403,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.23,
|
| 72 |
+
"learning_rate": 0.00029764397905759156,
|
| 73 |
+
"loss": 0.6473,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.34,
|
| 78 |
+
"learning_rate": 0.0002950261780104712,
|
| 79 |
+
"loss": 0.7524,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.46,
|
| 84 |
+
"learning_rate": 0.00029240837696335075,
|
| 85 |
+
"loss": 0.6775,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.57,
|
| 90 |
+
"learning_rate": 0.00028979057591623034,
|
| 91 |
+
"loss": 0.5884,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.68,
|
| 96 |
+
"learning_rate": 0.00028717277486910994,
|
| 97 |
+
"loss": 0.7117,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.79,
|
| 102 |
+
"learning_rate": 0.00028455497382198953,
|
| 103 |
+
"loss": 0.5925,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.9,
|
| 108 |
+
"learning_rate": 0.00028193717277486907,
|
| 109 |
+
"loss": 0.6675,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.02,
|
| 114 |
+
"learning_rate": 0.00027931937172774867,
|
| 115 |
+
"loss": 0.6126,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.13,
|
| 120 |
+
"learning_rate": 0.00027670157068062826,
|
| 121 |
+
"loss": 0.557,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.24,
|
| 126 |
+
"learning_rate": 0.00027408376963350786,
|
| 127 |
+
"loss": 0.5362,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.24,
|
| 132 |
+
"eval_loss": 0.8287817239761353,
|
| 133 |
+
"eval_runtime": 34.4542,
|
| 134 |
+
"eval_samples_per_second": 11.61,
|
| 135 |
+
"eval_steps_per_second": 1.451,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.35,
|
| 140 |
+
"learning_rate": 0.0002714659685863874,
|
| 141 |
+
"loss": 0.4951,
|
| 142 |
+
"step": 210
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.46,
|
| 146 |
+
"learning_rate": 0.000268848167539267,
|
| 147 |
+
"loss": 0.4904,
|
| 148 |
+
"step": 220
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.58,
|
| 152 |
+
"learning_rate": 0.0002662303664921466,
|
| 153 |
+
"loss": 0.4544,
|
| 154 |
+
"step": 230
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.69,
|
| 158 |
+
"learning_rate": 0.0002636125654450262,
|
| 159 |
+
"loss": 0.5705,
|
| 160 |
+
"step": 240
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.8,
|
| 164 |
+
"learning_rate": 0.0002609947643979057,
|
| 165 |
+
"loss": 0.5654,
|
| 166 |
+
"step": 250
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.91,
|
| 170 |
+
"learning_rate": 0.0002583769633507853,
|
| 171 |
+
"loss": 0.445,
|
| 172 |
+
"step": 260
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 3.03,
|
| 176 |
+
"learning_rate": 0.0002557591623036649,
|
| 177 |
+
"loss": 0.3859,
|
| 178 |
+
"step": 270
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 3.14,
|
| 182 |
+
"learning_rate": 0.0002531413612565445,
|
| 183 |
+
"loss": 0.5015,
|
| 184 |
+
"step": 280
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.25,
|
| 188 |
+
"learning_rate": 0.00025052356020942404,
|
| 189 |
+
"loss": 0.4177,
|
| 190 |
+
"step": 290
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.36,
|
| 194 |
+
"learning_rate": 0.00024790575916230364,
|
| 195 |
+
"loss": 0.4322,
|
| 196 |
+
"step": 300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.47,
|
| 200 |
+
"learning_rate": 0.00024528795811518323,
|
| 201 |
+
"loss": 0.3028,
|
| 202 |
+
"step": 310
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 3.59,
|
| 206 |
+
"learning_rate": 0.00024267015706806283,
|
| 207 |
+
"loss": 0.3839,
|
| 208 |
+
"step": 320
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 3.7,
|
| 212 |
+
"learning_rate": 0.0002400523560209424,
|
| 213 |
+
"loss": 0.3121,
|
| 214 |
+
"step": 330
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 3.81,
|
| 218 |
+
"learning_rate": 0.00023743455497382196,
|
| 219 |
+
"loss": 0.5043,
|
| 220 |
+
"step": 340
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.92,
|
| 224 |
+
"learning_rate": 0.00023481675392670153,
|
| 225 |
+
"loss": 0.3569,
|
| 226 |
+
"step": 350
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 4.03,
|
| 230 |
+
"learning_rate": 0.00023219895287958115,
|
| 231 |
+
"loss": 0.2791,
|
| 232 |
+
"step": 360
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.15,
|
| 236 |
+
"learning_rate": 0.00022958115183246072,
|
| 237 |
+
"loss": 0.2648,
|
| 238 |
+
"step": 370
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 4.26,
|
| 242 |
+
"learning_rate": 0.00022696335078534028,
|
| 243 |
+
"loss": 0.2998,
|
| 244 |
+
"step": 380
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 4.37,
|
| 248 |
+
"learning_rate": 0.00022434554973821985,
|
| 249 |
+
"loss": 0.3416,
|
| 250 |
+
"step": 390
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 4.48,
|
| 254 |
+
"learning_rate": 0.00022172774869109947,
|
| 255 |
+
"loss": 0.3044,
|
| 256 |
+
"step": 400
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.48,
|
| 260 |
+
"eval_loss": 0.7640588283538818,
|
| 261 |
+
"eval_runtime": 34.4837,
|
| 262 |
+
"eval_samples_per_second": 11.6,
|
| 263 |
+
"eval_steps_per_second": 1.45,
|
| 264 |
+
"step": 400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.59,
|
| 268 |
+
"learning_rate": 0.00021910994764397904,
|
| 269 |
+
"loss": 0.4006,
|
| 270 |
+
"step": 410
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.71,
|
| 274 |
+
"learning_rate": 0.0002164921465968586,
|
| 275 |
+
"loss": 0.2957,
|
| 276 |
+
"step": 420
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.82,
|
| 280 |
+
"learning_rate": 0.0002138743455497382,
|
| 281 |
+
"loss": 0.3241,
|
| 282 |
+
"step": 430
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.93,
|
| 286 |
+
"learning_rate": 0.0002112565445026178,
|
| 287 |
+
"loss": 0.2763,
|
| 288 |
+
"step": 440
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 5.04,
|
| 292 |
+
"learning_rate": 0.00020863874345549736,
|
| 293 |
+
"loss": 0.2206,
|
| 294 |
+
"step": 450
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.15,
|
| 298 |
+
"learning_rate": 0.00020602094240837693,
|
| 299 |
+
"loss": 0.2224,
|
| 300 |
+
"step": 460
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 5.27,
|
| 304 |
+
"learning_rate": 0.00020340314136125653,
|
| 305 |
+
"loss": 0.1844,
|
| 306 |
+
"step": 470
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 5.38,
|
| 310 |
+
"learning_rate": 0.00020078534031413612,
|
| 311 |
+
"loss": 0.2651,
|
| 312 |
+
"step": 480
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 5.49,
|
| 316 |
+
"learning_rate": 0.0001981675392670157,
|
| 317 |
+
"loss": 0.2708,
|
| 318 |
+
"step": 490
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 5.6,
|
| 322 |
+
"learning_rate": 0.00019554973821989528,
|
| 323 |
+
"loss": 0.2604,
|
| 324 |
+
"step": 500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 5.71,
|
| 328 |
+
"learning_rate": 0.00019293193717277485,
|
| 329 |
+
"loss": 0.2326,
|
| 330 |
+
"step": 510
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 5.83,
|
| 334 |
+
"learning_rate": 0.00019031413612565444,
|
| 335 |
+
"loss": 0.2328,
|
| 336 |
+
"step": 520
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 5.94,
|
| 340 |
+
"learning_rate": 0.000187696335078534,
|
| 341 |
+
"loss": 0.2052,
|
| 342 |
+
"step": 530
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 6.05,
|
| 346 |
+
"learning_rate": 0.0001850785340314136,
|
| 347 |
+
"loss": 0.3427,
|
| 348 |
+
"step": 540
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 6.16,
|
| 352 |
+
"learning_rate": 0.00018246073298429317,
|
| 353 |
+
"loss": 0.164,
|
| 354 |
+
"step": 550
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 6.27,
|
| 358 |
+
"learning_rate": 0.00017984293193717277,
|
| 359 |
+
"loss": 0.172,
|
| 360 |
+
"step": 560
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 6.39,
|
| 364 |
+
"learning_rate": 0.00017722513089005233,
|
| 365 |
+
"loss": 0.2155,
|
| 366 |
+
"step": 570
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 6.5,
|
| 370 |
+
"learning_rate": 0.00017460732984293193,
|
| 371 |
+
"loss": 0.1079,
|
| 372 |
+
"step": 580
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 6.61,
|
| 376 |
+
"learning_rate": 0.0001719895287958115,
|
| 377 |
+
"loss": 0.1656,
|
| 378 |
+
"step": 590
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 6.72,
|
| 382 |
+
"learning_rate": 0.0001693717277486911,
|
| 383 |
+
"loss": 0.1915,
|
| 384 |
+
"step": 600
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 6.72,
|
| 388 |
+
"eval_loss": 0.8178408145904541,
|
| 389 |
+
"eval_runtime": 34.3695,
|
| 390 |
+
"eval_samples_per_second": 11.638,
|
| 391 |
+
"eval_steps_per_second": 1.455,
|
| 392 |
+
"step": 600
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 6.83,
|
| 396 |
+
"learning_rate": 0.00016675392670157069,
|
| 397 |
+
"loss": 0.2569,
|
| 398 |
+
"step": 610
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.95,
|
| 402 |
+
"learning_rate": 0.00016413612565445025,
|
| 403 |
+
"loss": 0.2147,
|
| 404 |
+
"step": 620
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 7.06,
|
| 408 |
+
"learning_rate": 0.00016151832460732982,
|
| 409 |
+
"loss": 0.2239,
|
| 410 |
+
"step": 630
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 7.17,
|
| 414 |
+
"learning_rate": 0.00015890052356020941,
|
| 415 |
+
"loss": 0.1435,
|
| 416 |
+
"step": 640
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 7.28,
|
| 420 |
+
"learning_rate": 0.000156282722513089,
|
| 421 |
+
"loss": 0.201,
|
| 422 |
+
"step": 650
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 7.39,
|
| 426 |
+
"learning_rate": 0.00015366492146596858,
|
| 427 |
+
"loss": 0.1336,
|
| 428 |
+
"step": 660
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 7.51,
|
| 432 |
+
"learning_rate": 0.00015104712041884814,
|
| 433 |
+
"loss": 0.1271,
|
| 434 |
+
"step": 670
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 7.62,
|
| 438 |
+
"learning_rate": 0.00014842931937172774,
|
| 439 |
+
"loss": 0.1659,
|
| 440 |
+
"step": 680
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 7.73,
|
| 444 |
+
"learning_rate": 0.00014581151832460733,
|
| 445 |
+
"loss": 0.141,
|
| 446 |
+
"step": 690
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 7.84,
|
| 450 |
+
"learning_rate": 0.0001431937172774869,
|
| 451 |
+
"loss": 0.1463,
|
| 452 |
+
"step": 700
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 7.96,
|
| 456 |
+
"learning_rate": 0.0001405759162303665,
|
| 457 |
+
"loss": 0.1573,
|
| 458 |
+
"step": 710
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 8.07,
|
| 462 |
+
"learning_rate": 0.00013795811518324606,
|
| 463 |
+
"loss": 0.1132,
|
| 464 |
+
"step": 720
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 8.18,
|
| 468 |
+
"learning_rate": 0.00013534031413612566,
|
| 469 |
+
"loss": 0.0951,
|
| 470 |
+
"step": 730
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 8.29,
|
| 474 |
+
"learning_rate": 0.00013272251308900522,
|
| 475 |
+
"loss": 0.1343,
|
| 476 |
+
"step": 740
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 8.4,
|
| 480 |
+
"learning_rate": 0.00013010471204188482,
|
| 481 |
+
"loss": 0.1275,
|
| 482 |
+
"step": 750
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 8.52,
|
| 486 |
+
"learning_rate": 0.00012748691099476439,
|
| 487 |
+
"loss": 0.1846,
|
| 488 |
+
"step": 760
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 8.63,
|
| 492 |
+
"learning_rate": 0.00012486910994764398,
|
| 493 |
+
"loss": 0.1475,
|
| 494 |
+
"step": 770
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 8.74,
|
| 498 |
+
"learning_rate": 0.00012225130890052355,
|
| 499 |
+
"loss": 0.1069,
|
| 500 |
+
"step": 780
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 8.85,
|
| 504 |
+
"learning_rate": 0.00011963350785340314,
|
| 505 |
+
"loss": 0.1219,
|
| 506 |
+
"step": 790
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 8.96,
|
| 510 |
+
"learning_rate": 0.00011701570680628271,
|
| 511 |
+
"loss": 0.1004,
|
| 512 |
+
"step": 800
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 8.96,
|
| 516 |
+
"eval_loss": 0.917429506778717,
|
| 517 |
+
"eval_runtime": 34.3427,
|
| 518 |
+
"eval_samples_per_second": 11.647,
|
| 519 |
+
"eval_steps_per_second": 1.456,
|
| 520 |
+
"step": 800
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 9.08,
|
| 524 |
+
"learning_rate": 0.0001143979057591623,
|
| 525 |
+
"loss": 0.1,
|
| 526 |
+
"step": 810
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 9.19,
|
| 530 |
+
"learning_rate": 0.00011178010471204187,
|
| 531 |
+
"loss": 0.0793,
|
| 532 |
+
"step": 820
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 9.3,
|
| 536 |
+
"learning_rate": 0.00010916230366492146,
|
| 537 |
+
"loss": 0.1194,
|
| 538 |
+
"step": 830
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 9.41,
|
| 542 |
+
"learning_rate": 0.00010654450261780103,
|
| 543 |
+
"loss": 0.0992,
|
| 544 |
+
"step": 840
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 9.52,
|
| 548 |
+
"learning_rate": 0.00010392670157068063,
|
| 549 |
+
"loss": 0.1368,
|
| 550 |
+
"step": 850
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 9.64,
|
| 554 |
+
"learning_rate": 0.0001013089005235602,
|
| 555 |
+
"loss": 0.0942,
|
| 556 |
+
"step": 860
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 9.75,
|
| 560 |
+
"learning_rate": 9.869109947643979e-05,
|
| 561 |
+
"loss": 0.0907,
|
| 562 |
+
"step": 870
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 9.86,
|
| 566 |
+
"learning_rate": 9.607329842931936e-05,
|
| 567 |
+
"loss": 0.1154,
|
| 568 |
+
"step": 880
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 9.97,
|
| 572 |
+
"learning_rate": 9.345549738219895e-05,
|
| 573 |
+
"loss": 0.1075,
|
| 574 |
+
"step": 890
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 10.08,
|
| 578 |
+
"learning_rate": 9.083769633507853e-05,
|
| 579 |
+
"loss": 0.0699,
|
| 580 |
+
"step": 900
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 10.2,
|
| 584 |
+
"learning_rate": 8.821989528795811e-05,
|
| 585 |
+
"loss": 0.0785,
|
| 586 |
+
"step": 910
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 10.31,
|
| 590 |
+
"learning_rate": 8.560209424083769e-05,
|
| 591 |
+
"loss": 0.0849,
|
| 592 |
+
"step": 920
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 10.42,
|
| 596 |
+
"learning_rate": 8.298429319371727e-05,
|
| 597 |
+
"loss": 0.1372,
|
| 598 |
+
"step": 930
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 10.53,
|
| 602 |
+
"learning_rate": 8.036649214659685e-05,
|
| 603 |
+
"loss": 0.1006,
|
| 604 |
+
"step": 940
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 10.64,
|
| 608 |
+
"learning_rate": 7.774869109947644e-05,
|
| 609 |
+
"loss": 0.0792,
|
| 610 |
+
"step": 950
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 10.76,
|
| 614 |
+
"learning_rate": 7.513089005235602e-05,
|
| 615 |
+
"loss": 0.0723,
|
| 616 |
+
"step": 960
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 10.87,
|
| 620 |
+
"learning_rate": 7.25130890052356e-05,
|
| 621 |
+
"loss": 0.071,
|
| 622 |
+
"step": 970
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 10.98,
|
| 626 |
+
"learning_rate": 6.989528795811518e-05,
|
| 627 |
+
"loss": 0.0798,
|
| 628 |
+
"step": 980
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 11.09,
|
| 632 |
+
"learning_rate": 6.727748691099476e-05,
|
| 633 |
+
"loss": 0.0936,
|
| 634 |
+
"step": 990
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 11.2,
|
| 638 |
+
"learning_rate": 6.465968586387434e-05,
|
| 639 |
+
"loss": 0.0676,
|
| 640 |
+
"step": 1000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 11.2,
|
| 644 |
+
"eval_loss": 1.1027586460113525,
|
| 645 |
+
"eval_runtime": 34.3596,
|
| 646 |
+
"eval_samples_per_second": 11.642,
|
| 647 |
+
"eval_steps_per_second": 1.455,
|
| 648 |
+
"step": 1000
|
| 649 |
+
}
|
| 650 |
+
],
|
| 651 |
+
"max_steps": 1246,
|
| 652 |
+
"num_train_epochs": 14,
|
| 653 |
+
"total_flos": 3.310417634033664e+16,
|
| 654 |
+
"trial_name": null,
|
| 655 |
+
"trial_params": null
|
| 656 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f8fa89aba362c561a5d10dcf50a4d3de02ce3a4f30cbbddad543a4b8d2c0015
|
| 3 |
+
size 3963
|
checkpoint-1200/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "yahma/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"lora_alpha": 16,
|
| 9 |
+
"lora_dropout": 0.05,
|
| 10 |
+
"merge_weights": false,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 16,
|
| 14 |
+
"target_modules": [
|
| 15 |
+
"q_proj",
|
| 16 |
+
"k_proj",
|
| 17 |
+
"v_proj",
|
| 18 |
+
"o_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-1200/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:195501712e1c5313b13f8bf0634e0bfd09d7d1b83869fe1e550562f705ba2905
|
| 3 |
+
size 67201357
|
checkpoint-1200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56d840c45d1485c54b4cd54ba735023335388905a22933946f7055b51d0db9ea
|
| 3 |
+
size 134433093
|
checkpoint-1200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ea5c8c0e9ebd21e01cf2dc5e1bfbd2ced34d973ca03872447374c7c970c6de1
|
| 3 |
+
size 14575
|
checkpoint-1200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9bd8878ff8f2c87036575bc7d47a3c5d16d0bb81927b31744d1ffb9d17ea674
|
| 3 |
+
size 627
|
checkpoint-1200/trainer_state.json
ADDED
|
@@ -0,0 +1,784 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7640588283538818,
|
| 3 |
+
"best_model_checkpoint": "./model_20230703_attempt1/checkpoint-400",
|
| 4 |
+
"epoch": 13.445378151260504,
|
| 5 |
+
"global_step": 1200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 2.5488,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.22,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 2.3131,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.34,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 2.1798,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.45,
|
| 30 |
+
"learning_rate": 0.00011999999999999999,
|
| 31 |
+
"loss": 1.6567,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.56,
|
| 36 |
+
"learning_rate": 0.000147,
|
| 37 |
+
"loss": 1.2086,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.67,
|
| 42 |
+
"learning_rate": 0.00017699999999999997,
|
| 43 |
+
"loss": 0.8952,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.78,
|
| 48 |
+
"learning_rate": 0.00020699999999999996,
|
| 49 |
+
"loss": 1.0646,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.9,
|
| 54 |
+
"learning_rate": 0.000237,
|
| 55 |
+
"loss": 0.7725,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.01,
|
| 60 |
+
"learning_rate": 0.000267,
|
| 61 |
+
"loss": 0.8192,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.12,
|
| 66 |
+
"learning_rate": 0.00029699999999999996,
|
| 67 |
+
"loss": 0.7403,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.23,
|
| 72 |
+
"learning_rate": 0.00029764397905759156,
|
| 73 |
+
"loss": 0.6473,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.34,
|
| 78 |
+
"learning_rate": 0.0002950261780104712,
|
| 79 |
+
"loss": 0.7524,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.46,
|
| 84 |
+
"learning_rate": 0.00029240837696335075,
|
| 85 |
+
"loss": 0.6775,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.57,
|
| 90 |
+
"learning_rate": 0.00028979057591623034,
|
| 91 |
+
"loss": 0.5884,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.68,
|
| 96 |
+
"learning_rate": 0.00028717277486910994,
|
| 97 |
+
"loss": 0.7117,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.79,
|
| 102 |
+
"learning_rate": 0.00028455497382198953,
|
| 103 |
+
"loss": 0.5925,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.9,
|
| 108 |
+
"learning_rate": 0.00028193717277486907,
|
| 109 |
+
"loss": 0.6675,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.02,
|
| 114 |
+
"learning_rate": 0.00027931937172774867,
|
| 115 |
+
"loss": 0.6126,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.13,
|
| 120 |
+
"learning_rate": 0.00027670157068062826,
|
| 121 |
+
"loss": 0.557,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.24,
|
| 126 |
+
"learning_rate": 0.00027408376963350786,
|
| 127 |
+
"loss": 0.5362,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.24,
|
| 132 |
+
"eval_loss": 0.8287817239761353,
|
| 133 |
+
"eval_runtime": 34.4542,
|
| 134 |
+
"eval_samples_per_second": 11.61,
|
| 135 |
+
"eval_steps_per_second": 1.451,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.35,
|
| 140 |
+
"learning_rate": 0.0002714659685863874,
|
| 141 |
+
"loss": 0.4951,
|
| 142 |
+
"step": 210
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.46,
|
| 146 |
+
"learning_rate": 0.000268848167539267,
|
| 147 |
+
"loss": 0.4904,
|
| 148 |
+
"step": 220
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.58,
|
| 152 |
+
"learning_rate": 0.0002662303664921466,
|
| 153 |
+
"loss": 0.4544,
|
| 154 |
+
"step": 230
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.69,
|
| 158 |
+
"learning_rate": 0.0002636125654450262,
|
| 159 |
+
"loss": 0.5705,
|
| 160 |
+
"step": 240
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.8,
|
| 164 |
+
"learning_rate": 0.0002609947643979057,
|
| 165 |
+
"loss": 0.5654,
|
| 166 |
+
"step": 250
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.91,
|
| 170 |
+
"learning_rate": 0.0002583769633507853,
|
| 171 |
+
"loss": 0.445,
|
| 172 |
+
"step": 260
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 3.03,
|
| 176 |
+
"learning_rate": 0.0002557591623036649,
|
| 177 |
+
"loss": 0.3859,
|
| 178 |
+
"step": 270
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 3.14,
|
| 182 |
+
"learning_rate": 0.0002531413612565445,
|
| 183 |
+
"loss": 0.5015,
|
| 184 |
+
"step": 280
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.25,
|
| 188 |
+
"learning_rate": 0.00025052356020942404,
|
| 189 |
+
"loss": 0.4177,
|
| 190 |
+
"step": 290
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.36,
|
| 194 |
+
"learning_rate": 0.00024790575916230364,
|
| 195 |
+
"loss": 0.4322,
|
| 196 |
+
"step": 300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.47,
|
| 200 |
+
"learning_rate": 0.00024528795811518323,
|
| 201 |
+
"loss": 0.3028,
|
| 202 |
+
"step": 310
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 3.59,
|
| 206 |
+
"learning_rate": 0.00024267015706806283,
|
| 207 |
+
"loss": 0.3839,
|
| 208 |
+
"step": 320
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 3.7,
|
| 212 |
+
"learning_rate": 0.0002400523560209424,
|
| 213 |
+
"loss": 0.3121,
|
| 214 |
+
"step": 330
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 3.81,
|
| 218 |
+
"learning_rate": 0.00023743455497382196,
|
| 219 |
+
"loss": 0.5043,
|
| 220 |
+
"step": 340
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.92,
|
| 224 |
+
"learning_rate": 0.00023481675392670153,
|
| 225 |
+
"loss": 0.3569,
|
| 226 |
+
"step": 350
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 4.03,
|
| 230 |
+
"learning_rate": 0.00023219895287958115,
|
| 231 |
+
"loss": 0.2791,
|
| 232 |
+
"step": 360
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.15,
|
| 236 |
+
"learning_rate": 0.00022958115183246072,
|
| 237 |
+
"loss": 0.2648,
|
| 238 |
+
"step": 370
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 4.26,
|
| 242 |
+
"learning_rate": 0.00022696335078534028,
|
| 243 |
+
"loss": 0.2998,
|
| 244 |
+
"step": 380
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 4.37,
|
| 248 |
+
"learning_rate": 0.00022434554973821985,
|
| 249 |
+
"loss": 0.3416,
|
| 250 |
+
"step": 390
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 4.48,
|
| 254 |
+
"learning_rate": 0.00022172774869109947,
|
| 255 |
+
"loss": 0.3044,
|
| 256 |
+
"step": 400
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.48,
|
| 260 |
+
"eval_loss": 0.7640588283538818,
|
| 261 |
+
"eval_runtime": 34.4837,
|
| 262 |
+
"eval_samples_per_second": 11.6,
|
| 263 |
+
"eval_steps_per_second": 1.45,
|
| 264 |
+
"step": 400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.59,
|
| 268 |
+
"learning_rate": 0.00021910994764397904,
|
| 269 |
+
"loss": 0.4006,
|
| 270 |
+
"step": 410
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 4.71,
|
| 274 |
+
"learning_rate": 0.0002164921465968586,
|
| 275 |
+
"loss": 0.2957,
|
| 276 |
+
"step": 420
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.82,
|
| 280 |
+
"learning_rate": 0.0002138743455497382,
|
| 281 |
+
"loss": 0.3241,
|
| 282 |
+
"step": 430
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.93,
|
| 286 |
+
"learning_rate": 0.0002112565445026178,
|
| 287 |
+
"loss": 0.2763,
|
| 288 |
+
"step": 440
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 5.04,
|
| 292 |
+
"learning_rate": 0.00020863874345549736,
|
| 293 |
+
"loss": 0.2206,
|
| 294 |
+
"step": 450
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.15,
|
| 298 |
+
"learning_rate": 0.00020602094240837693,
|
| 299 |
+
"loss": 0.2224,
|
| 300 |
+
"step": 460
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 5.27,
|
| 304 |
+
"learning_rate": 0.00020340314136125653,
|
| 305 |
+
"loss": 0.1844,
|
| 306 |
+
"step": 470
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 5.38,
|
| 310 |
+
"learning_rate": 0.00020078534031413612,
|
| 311 |
+
"loss": 0.2651,
|
| 312 |
+
"step": 480
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 5.49,
|
| 316 |
+
"learning_rate": 0.0001981675392670157,
|
| 317 |
+
"loss": 0.2708,
|
| 318 |
+
"step": 490
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 5.6,
|
| 322 |
+
"learning_rate": 0.00019554973821989528,
|
| 323 |
+
"loss": 0.2604,
|
| 324 |
+
"step": 500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 5.71,
|
| 328 |
+
"learning_rate": 0.00019293193717277485,
|
| 329 |
+
"loss": 0.2326,
|
| 330 |
+
"step": 510
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 5.83,
|
| 334 |
+
"learning_rate": 0.00019031413612565444,
|
| 335 |
+
"loss": 0.2328,
|
| 336 |
+
"step": 520
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 5.94,
|
| 340 |
+
"learning_rate": 0.000187696335078534,
|
| 341 |
+
"loss": 0.2052,
|
| 342 |
+
"step": 530
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 6.05,
|
| 346 |
+
"learning_rate": 0.0001850785340314136,
|
| 347 |
+
"loss": 0.3427,
|
| 348 |
+
"step": 540
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 6.16,
|
| 352 |
+
"learning_rate": 0.00018246073298429317,
|
| 353 |
+
"loss": 0.164,
|
| 354 |
+
"step": 550
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 6.27,
|
| 358 |
+
"learning_rate": 0.00017984293193717277,
|
| 359 |
+
"loss": 0.172,
|
| 360 |
+
"step": 560
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 6.39,
|
| 364 |
+
"learning_rate": 0.00017722513089005233,
|
| 365 |
+
"loss": 0.2155,
|
| 366 |
+
"step": 570
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 6.5,
|
| 370 |
+
"learning_rate": 0.00017460732984293193,
|
| 371 |
+
"loss": 0.1079,
|
| 372 |
+
"step": 580
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 6.61,
|
| 376 |
+
"learning_rate": 0.0001719895287958115,
|
| 377 |
+
"loss": 0.1656,
|
| 378 |
+
"step": 590
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 6.72,
|
| 382 |
+
"learning_rate": 0.0001693717277486911,
|
| 383 |
+
"loss": 0.1915,
|
| 384 |
+
"step": 600
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 6.72,
|
| 388 |
+
"eval_loss": 0.8178408145904541,
|
| 389 |
+
"eval_runtime": 34.3695,
|
| 390 |
+
"eval_samples_per_second": 11.638,
|
| 391 |
+
"eval_steps_per_second": 1.455,
|
| 392 |
+
"step": 600
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 6.83,
|
| 396 |
+
"learning_rate": 0.00016675392670157069,
|
| 397 |
+
"loss": 0.2569,
|
| 398 |
+
"step": 610
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.95,
|
| 402 |
+
"learning_rate": 0.00016413612565445025,
|
| 403 |
+
"loss": 0.2147,
|
| 404 |
+
"step": 620
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 7.06,
|
| 408 |
+
"learning_rate": 0.00016151832460732982,
|
| 409 |
+
"loss": 0.2239,
|
| 410 |
+
"step": 630
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 7.17,
|
| 414 |
+
"learning_rate": 0.00015890052356020941,
|
| 415 |
+
"loss": 0.1435,
|
| 416 |
+
"step": 640
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 7.28,
|
| 420 |
+
"learning_rate": 0.000156282722513089,
|
| 421 |
+
"loss": 0.201,
|
| 422 |
+
"step": 650
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 7.39,
|
| 426 |
+
"learning_rate": 0.00015366492146596858,
|
| 427 |
+
"loss": 0.1336,
|
| 428 |
+
"step": 660
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 7.51,
|
| 432 |
+
"learning_rate": 0.00015104712041884814,
|
| 433 |
+
"loss": 0.1271,
|
| 434 |
+
"step": 670
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 7.62,
|
| 438 |
+
"learning_rate": 0.00014842931937172774,
|
| 439 |
+
"loss": 0.1659,
|
| 440 |
+
"step": 680
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 7.73,
|
| 444 |
+
"learning_rate": 0.00014581151832460733,
|
| 445 |
+
"loss": 0.141,
|
| 446 |
+
"step": 690
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 7.84,
|
| 450 |
+
"learning_rate": 0.0001431937172774869,
|
| 451 |
+
"loss": 0.1463,
|
| 452 |
+
"step": 700
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 7.96,
|
| 456 |
+
"learning_rate": 0.0001405759162303665,
|
| 457 |
+
"loss": 0.1573,
|
| 458 |
+
"step": 710
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 8.07,
|
| 462 |
+
"learning_rate": 0.00013795811518324606,
|
| 463 |
+
"loss": 0.1132,
|
| 464 |
+
"step": 720
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 8.18,
|
| 468 |
+
"learning_rate": 0.00013534031413612566,
|
| 469 |
+
"loss": 0.0951,
|
| 470 |
+
"step": 730
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 8.29,
|
| 474 |
+
"learning_rate": 0.00013272251308900522,
|
| 475 |
+
"loss": 0.1343,
|
| 476 |
+
"step": 740
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 8.4,
|
| 480 |
+
"learning_rate": 0.00013010471204188482,
|
| 481 |
+
"loss": 0.1275,
|
| 482 |
+
"step": 750
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 8.52,
|
| 486 |
+
"learning_rate": 0.00012748691099476439,
|
| 487 |
+
"loss": 0.1846,
|
| 488 |
+
"step": 760
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 8.63,
|
| 492 |
+
"learning_rate": 0.00012486910994764398,
|
| 493 |
+
"loss": 0.1475,
|
| 494 |
+
"step": 770
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 8.74,
|
| 498 |
+
"learning_rate": 0.00012225130890052355,
|
| 499 |
+
"loss": 0.1069,
|
| 500 |
+
"step": 780
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 8.85,
|
| 504 |
+
"learning_rate": 0.00011963350785340314,
|
| 505 |
+
"loss": 0.1219,
|
| 506 |
+
"step": 790
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 8.96,
|
| 510 |
+
"learning_rate": 0.00011701570680628271,
|
| 511 |
+
"loss": 0.1004,
|
| 512 |
+
"step": 800
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 8.96,
|
| 516 |
+
"eval_loss": 0.917429506778717,
|
| 517 |
+
"eval_runtime": 34.3427,
|
| 518 |
+
"eval_samples_per_second": 11.647,
|
| 519 |
+
"eval_steps_per_second": 1.456,
|
| 520 |
+
"step": 800
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 9.08,
|
| 524 |
+
"learning_rate": 0.0001143979057591623,
|
| 525 |
+
"loss": 0.1,
|
| 526 |
+
"step": 810
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 9.19,
|
| 530 |
+
"learning_rate": 0.00011178010471204187,
|
| 531 |
+
"loss": 0.0793,
|
| 532 |
+
"step": 820
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 9.3,
|
| 536 |
+
"learning_rate": 0.00010916230366492146,
|
| 537 |
+
"loss": 0.1194,
|
| 538 |
+
"step": 830
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 9.41,
|
| 542 |
+
"learning_rate": 0.00010654450261780103,
|
| 543 |
+
"loss": 0.0992,
|
| 544 |
+
"step": 840
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 9.52,
|
| 548 |
+
"learning_rate": 0.00010392670157068063,
|
| 549 |
+
"loss": 0.1368,
|
| 550 |
+
"step": 850
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 9.64,
|
| 554 |
+
"learning_rate": 0.0001013089005235602,
|
| 555 |
+
"loss": 0.0942,
|
| 556 |
+
"step": 860
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 9.75,
|
| 560 |
+
"learning_rate": 9.869109947643979e-05,
|
| 561 |
+
"loss": 0.0907,
|
| 562 |
+
"step": 870
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 9.86,
|
| 566 |
+
"learning_rate": 9.607329842931936e-05,
|
| 567 |
+
"loss": 0.1154,
|
| 568 |
+
"step": 880
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 9.97,
|
| 572 |
+
"learning_rate": 9.345549738219895e-05,
|
| 573 |
+
"loss": 0.1075,
|
| 574 |
+
"step": 890
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 10.08,
|
| 578 |
+
"learning_rate": 9.083769633507853e-05,
|
| 579 |
+
"loss": 0.0699,
|
| 580 |
+
"step": 900
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 10.2,
|
| 584 |
+
"learning_rate": 8.821989528795811e-05,
|
| 585 |
+
"loss": 0.0785,
|
| 586 |
+
"step": 910
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 10.31,
|
| 590 |
+
"learning_rate": 8.560209424083769e-05,
|
| 591 |
+
"loss": 0.0849,
|
| 592 |
+
"step": 920
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 10.42,
|
| 596 |
+
"learning_rate": 8.298429319371727e-05,
|
| 597 |
+
"loss": 0.1372,
|
| 598 |
+
"step": 930
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 10.53,
|
| 602 |
+
"learning_rate": 8.036649214659685e-05,
|
| 603 |
+
"loss": 0.1006,
|
| 604 |
+
"step": 940
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 10.64,
|
| 608 |
+
"learning_rate": 7.774869109947644e-05,
|
| 609 |
+
"loss": 0.0792,
|
| 610 |
+
"step": 950
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 10.76,
|
| 614 |
+
"learning_rate": 7.513089005235602e-05,
|
| 615 |
+
"loss": 0.0723,
|
| 616 |
+
"step": 960
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 10.87,
|
| 620 |
+
"learning_rate": 7.25130890052356e-05,
|
| 621 |
+
"loss": 0.071,
|
| 622 |
+
"step": 970
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 10.98,
|
| 626 |
+
"learning_rate": 6.989528795811518e-05,
|
| 627 |
+
"loss": 0.0798,
|
| 628 |
+
"step": 980
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 11.09,
|
| 632 |
+
"learning_rate": 6.727748691099476e-05,
|
| 633 |
+
"loss": 0.0936,
|
| 634 |
+
"step": 990
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 11.2,
|
| 638 |
+
"learning_rate": 6.465968586387434e-05,
|
| 639 |
+
"loss": 0.0676,
|
| 640 |
+
"step": 1000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 11.2,
|
| 644 |
+
"eval_loss": 1.1027586460113525,
|
| 645 |
+
"eval_runtime": 34.3596,
|
| 646 |
+
"eval_samples_per_second": 11.642,
|
| 647 |
+
"eval_steps_per_second": 1.455,
|
| 648 |
+
"step": 1000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 11.32,
|
| 652 |
+
"learning_rate": 6.204188481675392e-05,
|
| 653 |
+
"loss": 0.0702,
|
| 654 |
+
"step": 1010
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 11.43,
|
| 658 |
+
"learning_rate": 5.94240837696335e-05,
|
| 659 |
+
"loss": 0.0761,
|
| 660 |
+
"step": 1020
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 11.54,
|
| 664 |
+
"learning_rate": 5.680628272251308e-05,
|
| 665 |
+
"loss": 0.0727,
|
| 666 |
+
"step": 1030
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 11.65,
|
| 670 |
+
"learning_rate": 5.4188481675392663e-05,
|
| 671 |
+
"loss": 0.0688,
|
| 672 |
+
"step": 1040
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 11.76,
|
| 676 |
+
"learning_rate": 5.1570680628272244e-05,
|
| 677 |
+
"loss": 0.0781,
|
| 678 |
+
"step": 1050
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 11.88,
|
| 682 |
+
"learning_rate": 4.8952879581151825e-05,
|
| 683 |
+
"loss": 0.068,
|
| 684 |
+
"step": 1060
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 11.99,
|
| 688 |
+
"learning_rate": 4.6335078534031406e-05,
|
| 689 |
+
"loss": 0.0682,
|
| 690 |
+
"step": 1070
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 12.1,
|
| 694 |
+
"learning_rate": 4.371727748691099e-05,
|
| 695 |
+
"loss": 0.0591,
|
| 696 |
+
"step": 1080
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 12.21,
|
| 700 |
+
"learning_rate": 4.109947643979057e-05,
|
| 701 |
+
"loss": 0.0579,
|
| 702 |
+
"step": 1090
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 12.32,
|
| 706 |
+
"learning_rate": 3.8481675392670156e-05,
|
| 707 |
+
"loss": 0.0632,
|
| 708 |
+
"step": 1100
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 12.44,
|
| 712 |
+
"learning_rate": 3.5863874345549736e-05,
|
| 713 |
+
"loss": 0.0635,
|
| 714 |
+
"step": 1110
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 12.55,
|
| 718 |
+
"learning_rate": 3.324607329842932e-05,
|
| 719 |
+
"loss": 0.0857,
|
| 720 |
+
"step": 1120
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 12.66,
|
| 724 |
+
"learning_rate": 3.06282722513089e-05,
|
| 725 |
+
"loss": 0.0656,
|
| 726 |
+
"step": 1130
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 12.77,
|
| 730 |
+
"learning_rate": 2.801047120418848e-05,
|
| 731 |
+
"loss": 0.0649,
|
| 732 |
+
"step": 1140
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 12.89,
|
| 736 |
+
"learning_rate": 2.539267015706806e-05,
|
| 737 |
+
"loss": 0.0572,
|
| 738 |
+
"step": 1150
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 13.0,
|
| 742 |
+
"learning_rate": 2.277486910994764e-05,
|
| 743 |
+
"loss": 0.0638,
|
| 744 |
+
"step": 1160
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 13.11,
|
| 748 |
+
"learning_rate": 2.0157068062827222e-05,
|
| 749 |
+
"loss": 0.0556,
|
| 750 |
+
"step": 1170
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 13.22,
|
| 754 |
+
"learning_rate": 1.7539267015706803e-05,
|
| 755 |
+
"loss": 0.0529,
|
| 756 |
+
"step": 1180
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 13.33,
|
| 760 |
+
"learning_rate": 1.4921465968586385e-05,
|
| 761 |
+
"loss": 0.0513,
|
| 762 |
+
"step": 1190
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 13.45,
|
| 766 |
+
"learning_rate": 1.2303664921465966e-05,
|
| 767 |
+
"loss": 0.0845,
|
| 768 |
+
"step": 1200
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 13.45,
|
| 772 |
+
"eval_loss": 1.133836030960083,
|
| 773 |
+
"eval_runtime": 34.4155,
|
| 774 |
+
"eval_samples_per_second": 11.623,
|
| 775 |
+
"eval_steps_per_second": 1.453,
|
| 776 |
+
"step": 1200
|
| 777 |
+
}
|
| 778 |
+
],
|
| 779 |
+
"max_steps": 1246,
|
| 780 |
+
"num_train_epochs": 14,
|
| 781 |
+
"total_flos": 3.984965106597888e+16,
|
| 782 |
+
"trial_name": null,
|
| 783 |
+
"trial_params": null
|
| 784 |
+
}
|
checkpoint-1200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f8fa89aba362c561a5d10dcf50a4d3de02ce3a4f30cbbddad543a4b8d2c0015
|
| 3 |
+
size 3963
|
checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "yahma/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"lora_alpha": 16,
|
| 9 |
+
"lora_dropout": 0.05,
|
| 10 |
+
"merge_weights": false,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 16,
|
| 14 |
+
"target_modules": [
|
| 15 |
+
"q_proj",
|
| 16 |
+
"k_proj",
|
| 17 |
+
"v_proj",
|
| 18 |
+
"o_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-400/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56cbdb2dbc3bf6157b8abf87e4f1ddb75f603ad285eed04445c87f577cdac777
|
| 3 |
+
size 67201357
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb78158bd75b006f42e16d1605d7d73c644f806e48e7030be3ed981ae7061a61
|
| 3 |
+
size 134433093
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0e8d1ed74d4143d417972d29cddfdc8dcddc446eddb2598f30921438a996c10
|
| 3 |
+
size 14575
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:548308e36f5e947ba8c40b03bcea8d90a68c16bdbac16560a5af44c6119de423
|
| 3 |
+
size 627
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,272 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7640588283538818,
|
| 3 |
+
"best_model_checkpoint": "./model_20230703_attempt1/checkpoint-400",
|
| 4 |
+
"epoch": 4.481792717086835,
|
| 5 |
+
"global_step": 400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 2.5488,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.22,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 2.3131,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.34,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 2.1798,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.45,
|
| 30 |
+
"learning_rate": 0.00011999999999999999,
|
| 31 |
+
"loss": 1.6567,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.56,
|
| 36 |
+
"learning_rate": 0.000147,
|
| 37 |
+
"loss": 1.2086,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.67,
|
| 42 |
+
"learning_rate": 0.00017699999999999997,
|
| 43 |
+
"loss": 0.8952,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.78,
|
| 48 |
+
"learning_rate": 0.00020699999999999996,
|
| 49 |
+
"loss": 1.0646,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.9,
|
| 54 |
+
"learning_rate": 0.000237,
|
| 55 |
+
"loss": 0.7725,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.01,
|
| 60 |
+
"learning_rate": 0.000267,
|
| 61 |
+
"loss": 0.8192,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.12,
|
| 66 |
+
"learning_rate": 0.00029699999999999996,
|
| 67 |
+
"loss": 0.7403,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.23,
|
| 72 |
+
"learning_rate": 0.00029764397905759156,
|
| 73 |
+
"loss": 0.6473,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.34,
|
| 78 |
+
"learning_rate": 0.0002950261780104712,
|
| 79 |
+
"loss": 0.7524,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.46,
|
| 84 |
+
"learning_rate": 0.00029240837696335075,
|
| 85 |
+
"loss": 0.6775,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.57,
|
| 90 |
+
"learning_rate": 0.00028979057591623034,
|
| 91 |
+
"loss": 0.5884,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.68,
|
| 96 |
+
"learning_rate": 0.00028717277486910994,
|
| 97 |
+
"loss": 0.7117,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.79,
|
| 102 |
+
"learning_rate": 0.00028455497382198953,
|
| 103 |
+
"loss": 0.5925,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.9,
|
| 108 |
+
"learning_rate": 0.00028193717277486907,
|
| 109 |
+
"loss": 0.6675,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.02,
|
| 114 |
+
"learning_rate": 0.00027931937172774867,
|
| 115 |
+
"loss": 0.6126,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.13,
|
| 120 |
+
"learning_rate": 0.00027670157068062826,
|
| 121 |
+
"loss": 0.557,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.24,
|
| 126 |
+
"learning_rate": 0.00027408376963350786,
|
| 127 |
+
"loss": 0.5362,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.24,
|
| 132 |
+
"eval_loss": 0.8287817239761353,
|
| 133 |
+
"eval_runtime": 34.4542,
|
| 134 |
+
"eval_samples_per_second": 11.61,
|
| 135 |
+
"eval_steps_per_second": 1.451,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.35,
|
| 140 |
+
"learning_rate": 0.0002714659685863874,
|
| 141 |
+
"loss": 0.4951,
|
| 142 |
+
"step": 210
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.46,
|
| 146 |
+
"learning_rate": 0.000268848167539267,
|
| 147 |
+
"loss": 0.4904,
|
| 148 |
+
"step": 220
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.58,
|
| 152 |
+
"learning_rate": 0.0002662303664921466,
|
| 153 |
+
"loss": 0.4544,
|
| 154 |
+
"step": 230
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.69,
|
| 158 |
+
"learning_rate": 0.0002636125654450262,
|
| 159 |
+
"loss": 0.5705,
|
| 160 |
+
"step": 240
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.8,
|
| 164 |
+
"learning_rate": 0.0002609947643979057,
|
| 165 |
+
"loss": 0.5654,
|
| 166 |
+
"step": 250
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.91,
|
| 170 |
+
"learning_rate": 0.0002583769633507853,
|
| 171 |
+
"loss": 0.445,
|
| 172 |
+
"step": 260
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 3.03,
|
| 176 |
+
"learning_rate": 0.0002557591623036649,
|
| 177 |
+
"loss": 0.3859,
|
| 178 |
+
"step": 270
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 3.14,
|
| 182 |
+
"learning_rate": 0.0002531413612565445,
|
| 183 |
+
"loss": 0.5015,
|
| 184 |
+
"step": 280
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.25,
|
| 188 |
+
"learning_rate": 0.00025052356020942404,
|
| 189 |
+
"loss": 0.4177,
|
| 190 |
+
"step": 290
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.36,
|
| 194 |
+
"learning_rate": 0.00024790575916230364,
|
| 195 |
+
"loss": 0.4322,
|
| 196 |
+
"step": 300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.47,
|
| 200 |
+
"learning_rate": 0.00024528795811518323,
|
| 201 |
+
"loss": 0.3028,
|
| 202 |
+
"step": 310
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 3.59,
|
| 206 |
+
"learning_rate": 0.00024267015706806283,
|
| 207 |
+
"loss": 0.3839,
|
| 208 |
+
"step": 320
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 3.7,
|
| 212 |
+
"learning_rate": 0.0002400523560209424,
|
| 213 |
+
"loss": 0.3121,
|
| 214 |
+
"step": 330
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 3.81,
|
| 218 |
+
"learning_rate": 0.00023743455497382196,
|
| 219 |
+
"loss": 0.5043,
|
| 220 |
+
"step": 340
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.92,
|
| 224 |
+
"learning_rate": 0.00023481675392670153,
|
| 225 |
+
"loss": 0.3569,
|
| 226 |
+
"step": 350
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 4.03,
|
| 230 |
+
"learning_rate": 0.00023219895287958115,
|
| 231 |
+
"loss": 0.2791,
|
| 232 |
+
"step": 360
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.15,
|
| 236 |
+
"learning_rate": 0.00022958115183246072,
|
| 237 |
+
"loss": 0.2648,
|
| 238 |
+
"step": 370
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 4.26,
|
| 242 |
+
"learning_rate": 0.00022696335078534028,
|
| 243 |
+
"loss": 0.2998,
|
| 244 |
+
"step": 380
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 4.37,
|
| 248 |
+
"learning_rate": 0.00022434554973821985,
|
| 249 |
+
"loss": 0.3416,
|
| 250 |
+
"step": 390
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 4.48,
|
| 254 |
+
"learning_rate": 0.00022172774869109947,
|
| 255 |
+
"loss": 0.3044,
|
| 256 |
+
"step": 400
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.48,
|
| 260 |
+
"eval_loss": 0.7640588283538818,
|
| 261 |
+
"eval_runtime": 34.4837,
|
| 262 |
+
"eval_samples_per_second": 11.6,
|
| 263 |
+
"eval_steps_per_second": 1.45,
|
| 264 |
+
"step": 400
|
| 265 |
+
}
|
| 266 |
+
],
|
| 267 |
+
"max_steps": 1246,
|
| 268 |
+
"num_train_epochs": 14,
|
| 269 |
+
"total_flos": 1.32826870923264e+16,
|
| 270 |
+
"trial_name": null,
|
| 271 |
+
"trial_params": null
|
| 272 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f8fa89aba362c561a5d10dcf50a4d3de02ce3a4f30cbbddad543a4b8d2c0015
|
| 3 |
+
size 3963
|