Commit ·
16ed716
1
Parent(s): fea066b
Upload 8 files
Browse files- README.md +21 -0
- adapter_config.json +22 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +619 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.5.0.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "DopeorNope/COKAL-13b-v1",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 16,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"gate_proj",
|
| 18 |
+
"down_proj",
|
| 19 |
+
"up_proj"
|
| 20 |
+
],
|
| 21 |
+
"task_type": "CAUSAL_LM"
|
| 22 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0caecad22a42849485bea450d4363b76e52f0b543ebbb63ec17acf47cc3e410c
|
| 3 |
+
size 145576202
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33b5ae0ac06f6d91de75d4bc75c497bc52fa1368312209a90a491affa236bc02
|
| 3 |
+
size 291182202
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:122892c62c3cabc6cf8fa914201322598c0dab7ce959861f2b1127efe09d1f55
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1c15e6f8c2ff53feb785328b55555b41d928d4b307dbe488cb8acac812e17af
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,619 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1374629494394089,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 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 |
+
"learning_rate": 9.999953315763929e-06,
|
| 14 |
+
"loss": 7.3258,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.0,
|
| 19 |
+
"learning_rate": 9.999813263927483e-06,
|
| 20 |
+
"loss": 5.3323,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.0,
|
| 25 |
+
"learning_rate": 9.999579847105947e-06,
|
| 26 |
+
"loss": 4.8026,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 9.999253069658074e-06,
|
| 32 |
+
"loss": 4.693,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 9.99883293768601e-06,
|
| 38 |
+
"loss": 5.4127,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.01,
|
| 43 |
+
"learning_rate": 9.998319459035168e-06,
|
| 44 |
+
"loss": 4.9792,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01,
|
| 49 |
+
"learning_rate": 9.997712643294093e-06,
|
| 50 |
+
"loss": 5.1656,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.01,
|
| 55 |
+
"learning_rate": 9.997012501794273e-06,
|
| 56 |
+
"loss": 4.5127,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.01,
|
| 61 |
+
"learning_rate": 9.996219047609943e-06,
|
| 62 |
+
"loss": 4.9538,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.01,
|
| 67 |
+
"learning_rate": 9.995332295557818e-06,
|
| 68 |
+
"loss": 4.5908,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.02,
|
| 73 |
+
"learning_rate": 9.994352262196839e-06,
|
| 74 |
+
"loss": 5.3602,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.02,
|
| 79 |
+
"learning_rate": 9.993278965827844e-06,
|
| 80 |
+
"loss": 4.705,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.02,
|
| 85 |
+
"learning_rate": 9.992112426493247e-06,
|
| 86 |
+
"loss": 4.7682,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02,
|
| 91 |
+
"learning_rate": 9.990852665976648e-06,
|
| 92 |
+
"loss": 4.5893,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.02,
|
| 97 |
+
"learning_rate": 9.989499707802424e-06,
|
| 98 |
+
"loss": 4.9069,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.02,
|
| 103 |
+
"learning_rate": 9.988053577235306e-06,
|
| 104 |
+
"loss": 9.8812,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.02,
|
| 109 |
+
"learning_rate": 9.986514301279894e-06,
|
| 110 |
+
"loss": 4.8938,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.02,
|
| 115 |
+
"learning_rate": 9.984881908680157e-06,
|
| 116 |
+
"loss": 4.7196,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.03,
|
| 121 |
+
"learning_rate": 9.983156429918895e-06,
|
| 122 |
+
"loss": 5.1751,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.03,
|
| 127 |
+
"learning_rate": 9.981337897217171e-06,
|
| 128 |
+
"loss": 5.1721,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.03,
|
| 133 |
+
"learning_rate": 9.979426344533712e-06,
|
| 134 |
+
"loss": 5.693,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.03,
|
| 139 |
+
"learning_rate": 9.977421807564264e-06,
|
| 140 |
+
"loss": 4.7993,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.03,
|
| 145 |
+
"learning_rate": 9.97532432374094e-06,
|
| 146 |
+
"loss": 4.8612,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.03,
|
| 151 |
+
"learning_rate": 9.973133932231514e-06,
|
| 152 |
+
"loss": 4.7676,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.03,
|
| 157 |
+
"learning_rate": 9.970850673938684e-06,
|
| 158 |
+
"loss": 7.3205,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.04,
|
| 163 |
+
"learning_rate": 9.96847459149932e-06,
|
| 164 |
+
"loss": 4.4044,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.04,
|
| 169 |
+
"learning_rate": 9.966005729283658e-06,
|
| 170 |
+
"loss": 4.6814,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.04,
|
| 175 |
+
"learning_rate": 9.963444133394478e-06,
|
| 176 |
+
"loss": 4.999,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.04,
|
| 181 |
+
"learning_rate": 9.960789851666237e-06,
|
| 182 |
+
"loss": 4.5622,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.04,
|
| 187 |
+
"learning_rate": 9.958042933664186e-06,
|
| 188 |
+
"loss": 4.7441,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.04,
|
| 193 |
+
"learning_rate": 9.955203430683425e-06,
|
| 194 |
+
"loss": 6.912,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.04,
|
| 199 |
+
"learning_rate": 9.952271395747969e-06,
|
| 200 |
+
"loss": 5.1326,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.05,
|
| 205 |
+
"learning_rate": 9.949246883609743e-06,
|
| 206 |
+
"loss": 5.7146,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.05,
|
| 211 |
+
"learning_rate": 9.94612995074756e-06,
|
| 212 |
+
"loss": 4.6791,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.05,
|
| 217 |
+
"learning_rate": 9.942920655366075e-06,
|
| 218 |
+
"loss": 4.877,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.05,
|
| 223 |
+
"learning_rate": 9.939619057394687e-06,
|
| 224 |
+
"loss": 6.1258,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.05,
|
| 229 |
+
"learning_rate": 9.936225218486428e-06,
|
| 230 |
+
"loss": 4.5972,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.05,
|
| 235 |
+
"learning_rate": 9.93273920201681e-06,
|
| 236 |
+
"loss": 5.1205,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.05,
|
| 241 |
+
"learning_rate": 9.929161073082636e-06,
|
| 242 |
+
"loss": 4.785,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.05,
|
| 247 |
+
"learning_rate": 9.925490898500796e-06,
|
| 248 |
+
"loss": 4.2566,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.06,
|
| 253 |
+
"learning_rate": 9.921728746807008e-06,
|
| 254 |
+
"loss": 4.9092,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.06,
|
| 259 |
+
"learning_rate": 9.917874688254542e-06,
|
| 260 |
+
"loss": 4.4576,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.06,
|
| 265 |
+
"learning_rate": 9.913928794812909e-06,
|
| 266 |
+
"loss": 9.2704,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.06,
|
| 271 |
+
"learning_rate": 9.90989114016652e-06,
|
| 272 |
+
"loss": 4.8584,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.06,
|
| 277 |
+
"learning_rate": 9.905761799713302e-06,
|
| 278 |
+
"loss": 4.6457,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.06,
|
| 283 |
+
"learning_rate": 9.901540850563295e-06,
|
| 284 |
+
"loss": 4.7786,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.06,
|
| 289 |
+
"learning_rate": 9.89722837153722e-06,
|
| 290 |
+
"loss": 3.9414,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.07,
|
| 295 |
+
"learning_rate": 9.892824443164987e-06,
|
| 296 |
+
"loss": 5.1103,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.07,
|
| 301 |
+
"learning_rate": 9.88832914768421e-06,
|
| 302 |
+
"loss": 4.974,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.07,
|
| 307 |
+
"learning_rate": 9.883742569038663e-06,
|
| 308 |
+
"loss": 5.0371,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.07,
|
| 313 |
+
"learning_rate": 9.879064792876717e-06,
|
| 314 |
+
"loss": 5.6217,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.07,
|
| 319 |
+
"learning_rate": 9.874295906549728e-06,
|
| 320 |
+
"loss": 5.0545,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.07,
|
| 325 |
+
"learning_rate": 9.869435999110428e-06,
|
| 326 |
+
"loss": 4.2826,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.07,
|
| 331 |
+
"learning_rate": 9.864485161311242e-06,
|
| 332 |
+
"loss": 4.9842,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.08,
|
| 337 |
+
"learning_rate": 9.859443485602603e-06,
|
| 338 |
+
"loss": 5.1379,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.08,
|
| 343 |
+
"learning_rate": 9.85431106613122e-06,
|
| 344 |
+
"loss": 4.3783,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.08,
|
| 349 |
+
"learning_rate": 9.849087998738328e-06,
|
| 350 |
+
"loss": 5.0505,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.08,
|
| 355 |
+
"learning_rate": 9.84377438095789e-06,
|
| 356 |
+
"loss": 4.3546,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.08,
|
| 361 |
+
"learning_rate": 9.838370312014783e-06,
|
| 362 |
+
"loss": 3.8583,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.08,
|
| 367 |
+
"learning_rate": 9.832875892822937e-06,
|
| 368 |
+
"loss": 5.3064,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.08,
|
| 373 |
+
"learning_rate": 9.827291225983458e-06,
|
| 374 |
+
"loss": 4.9614,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.09,
|
| 379 |
+
"learning_rate": 9.821616415782708e-06,
|
| 380 |
+
"loss": 4.6139,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.09,
|
| 385 |
+
"learning_rate": 9.815851568190358e-06,
|
| 386 |
+
"loss": 4.377,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.09,
|
| 391 |
+
"learning_rate": 9.80999679085741e-06,
|
| 392 |
+
"loss": 4.7139,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.09,
|
| 397 |
+
"learning_rate": 9.80405219311419e-06,
|
| 398 |
+
"loss": 4.6675,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.09,
|
| 403 |
+
"learning_rate": 9.798017885968295e-06,
|
| 404 |
+
"loss": 4.9449,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.09,
|
| 409 |
+
"learning_rate": 9.791893982102537e-06,
|
| 410 |
+
"loss": 4.0762,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.09,
|
| 415 |
+
"learning_rate": 9.785680595872824e-06,
|
| 416 |
+
"loss": 4.7968,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.09,
|
| 421 |
+
"learning_rate": 9.77937784330603e-06,
|
| 422 |
+
"loss": 4.8185,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.1,
|
| 427 |
+
"learning_rate": 9.772985842097832e-06,
|
| 428 |
+
"loss": 4.2703,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.1,
|
| 433 |
+
"learning_rate": 9.766504711610507e-06,
|
| 434 |
+
"loss": 4.9194,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.1,
|
| 439 |
+
"learning_rate": 9.759934572870706e-06,
|
| 440 |
+
"loss": 4.1361,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.1,
|
| 445 |
+
"learning_rate": 9.753275548567192e-06,
|
| 446 |
+
"loss": 4.1172,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.1,
|
| 451 |
+
"learning_rate": 9.74652776304855e-06,
|
| 452 |
+
"loss": 3.9886,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.1,
|
| 457 |
+
"learning_rate": 9.739691342320866e-06,
|
| 458 |
+
"loss": 4.671,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.1,
|
| 463 |
+
"learning_rate": 9.732766414045368e-06,
|
| 464 |
+
"loss": 4.0636,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.11,
|
| 469 |
+
"learning_rate": 9.725753107536053e-06,
|
| 470 |
+
"loss": 4.1989,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.11,
|
| 475 |
+
"learning_rate": 9.718651553757266e-06,
|
| 476 |
+
"loss": 8.7987,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.11,
|
| 481 |
+
"learning_rate": 9.711461885321247e-06,
|
| 482 |
+
"loss": 4.2278,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.11,
|
| 487 |
+
"learning_rate": 9.704184236485672e-06,
|
| 488 |
+
"loss": 4.8235,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.11,
|
| 493 |
+
"learning_rate": 9.696818743151128e-06,
|
| 494 |
+
"loss": 4.5301,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.11,
|
| 499 |
+
"learning_rate": 9.68936554285859e-06,
|
| 500 |
+
"loss": 4.3466,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.11,
|
| 505 |
+
"learning_rate": 9.68182477478684e-06,
|
| 506 |
+
"loss": 4.0524,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.12,
|
| 511 |
+
"learning_rate": 9.67419657974988e-06,
|
| 512 |
+
"loss": 4.7024,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.12,
|
| 517 |
+
"learning_rate": 9.66648110019429e-06,
|
| 518 |
+
"loss": 4.9533,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.12,
|
| 523 |
+
"learning_rate": 9.658678480196579e-06,
|
| 524 |
+
"loss": 4.568,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.12,
|
| 529 |
+
"learning_rate": 9.650788865460487e-06,
|
| 530 |
+
"loss": 4.8176,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.12,
|
| 535 |
+
"learning_rate": 9.642812403314272e-06,
|
| 536 |
+
"loss": 5.1862,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.12,
|
| 541 |
+
"learning_rate": 9.634749242707948e-06,
|
| 542 |
+
"loss": 6.4518,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.12,
|
| 547 |
+
"learning_rate": 9.626599534210514e-06,
|
| 548 |
+
"loss": 4.2189,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.13,
|
| 553 |
+
"learning_rate": 9.618363430007134e-06,
|
| 554 |
+
"loss": 4.8472,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.13,
|
| 559 |
+
"learning_rate": 9.610041083896304e-06,
|
| 560 |
+
"loss": 3.8581,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.13,
|
| 565 |
+
"learning_rate": 9.60163265128697e-06,
|
| 566 |
+
"loss": 4.1841,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.13,
|
| 571 |
+
"learning_rate": 9.593138289195634e-06,
|
| 572 |
+
"loss": 4.8045,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.13,
|
| 577 |
+
"learning_rate": 9.584558156243418e-06,
|
| 578 |
+
"loss": 4.7419,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.13,
|
| 583 |
+
"learning_rate": 9.575892412653102e-06,
|
| 584 |
+
"loss": 4.8213,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.13,
|
| 589 |
+
"learning_rate": 9.567141220246136e-06,
|
| 590 |
+
"loss": 4.4465,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.13,
|
| 595 |
+
"learning_rate": 9.55830474243961e-06,
|
| 596 |
+
"loss": 4.3745,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.14,
|
| 601 |
+
"learning_rate": 9.549383144243213e-06,
|
| 602 |
+
"loss": 4.8063,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.14,
|
| 607 |
+
"learning_rate": 9.540376592256142e-06,
|
| 608 |
+
"loss": 4.2272,
|
| 609 |
+
"step": 100
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 1,
|
| 613 |
+
"max_steps": 727,
|
| 614 |
+
"num_train_epochs": 1,
|
| 615 |
+
"save_steps": 25,
|
| 616 |
+
"total_flos": 2.4358617964044288e+17,
|
| 617 |
+
"trial_name": null,
|
| 618 |
+
"trial_params": null
|
| 619 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c42aaf2174ad5ae869b72a3e32f7e9cb08492775bd8975f1af0df2b52e382b76
|
| 3 |
+
size 4536
|