Upload fine-tuned retriever model
Browse files- README.md +0 -0
- model.safetensors +1 -1
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- tokenizer.json +2 -14
- trainer_state.json +457 -0
- training_args.bin +3 -0
README.md
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437951328
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d05117916dd2f05c48a94cb660140809176d7ec524a6553afa607f255126543
|
| 3 |
size 437951328
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f92bed52aef294289761229cd2b9c10cdc364828591d9a6c390d132f98fe6efa
|
| 3 |
+
size 871298443
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8dad59ceff6a75c7525a825b923fab0998a8fbc895091d0047c16e887a7bf0a
|
| 3 |
+
size 14645
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:911449e67f3112a5e15b8316033a123bafd40147919c93233393f8ca44c64005
|
| 3 |
+
size 1383
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cffa310dc5601509fc9547a5f27d963431f42ade920d24c479ed135940d3be02
|
| 3 |
+
size 1465
|
tokenizer.json
CHANGED
|
@@ -1,19 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": "BatchLongest",
|
| 11 |
-
"direction": "Right",
|
| 12 |
-
"pad_to_multiple_of": null,
|
| 13 |
-
"pad_id": 0,
|
| 14 |
-
"pad_type_id": 0,
|
| 15 |
-
"pad_token": "[PAD]"
|
| 16 |
-
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
trainer_state.json
ADDED
|
@@ -0,0 +1,457 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 450,
|
| 3 |
+
"best_metric": 0.8513853904282116,
|
| 4 |
+
"best_model_checkpoint": "../models/retriever_trainer_bge_base/checkpoint-450",
|
| 5 |
+
"epoch": 1.9148936170212765,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 450,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0425531914893617,
|
| 14 |
+
"grad_norm": 0.8533166646957397,
|
| 15 |
+
"learning_rate": 1.5254237288135596e-06,
|
| 16 |
+
"loss": 0.2054,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0851063829787234,
|
| 21 |
+
"grad_norm": 0.7839147448539734,
|
| 22 |
+
"learning_rate": 3.2203389830508473e-06,
|
| 23 |
+
"loss": 0.2017,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.1276595744680851,
|
| 28 |
+
"grad_norm": 0.9631144404411316,
|
| 29 |
+
"learning_rate": 4.915254237288136e-06,
|
| 30 |
+
"loss": 0.197,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1702127659574468,
|
| 35 |
+
"grad_norm": 1.077710747718811,
|
| 36 |
+
"learning_rate": 6.610169491525424e-06,
|
| 37 |
+
"loss": 0.1913,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.2127659574468085,
|
| 42 |
+
"grad_norm": 0.8926519155502319,
|
| 43 |
+
"learning_rate": 8.305084745762712e-06,
|
| 44 |
+
"loss": 0.1827,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2127659574468085,
|
| 49 |
+
"eval_accuracy_at_0.5_thresh": 0.7808510638297872,
|
| 50 |
+
"eval_f1_at_0.5_thresh": 0.7444168734491315,
|
| 51 |
+
"eval_loss": 0.18353447318077087,
|
| 52 |
+
"eval_precision_at_0.5_thresh": 0.7389162561576355,
|
| 53 |
+
"eval_recall_at_0.5_thresh": 0.75,
|
| 54 |
+
"eval_runtime": 1.2282,
|
| 55 |
+
"eval_samples_per_second": 382.661,
|
| 56 |
+
"eval_steps_per_second": 12.213,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.2553191489361702,
|
| 61 |
+
"grad_norm": 1.0001214742660522,
|
| 62 |
+
"learning_rate": 1e-05,
|
| 63 |
+
"loss": 0.1897,
|
| 64 |
+
"step": 60
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.2978723404255319,
|
| 68 |
+
"grad_norm": 0.8536041378974915,
|
| 69 |
+
"learning_rate": 1.169491525423729e-05,
|
| 70 |
+
"loss": 0.1811,
|
| 71 |
+
"step": 70
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.3404255319148936,
|
| 75 |
+
"grad_norm": 0.9402114748954773,
|
| 76 |
+
"learning_rate": 1.3389830508474577e-05,
|
| 77 |
+
"loss": 0.1777,
|
| 78 |
+
"step": 80
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.3829787234042553,
|
| 82 |
+
"grad_norm": 0.9630193710327148,
|
| 83 |
+
"learning_rate": 1.5084745762711865e-05,
|
| 84 |
+
"loss": 0.1697,
|
| 85 |
+
"step": 90
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.425531914893617,
|
| 89 |
+
"grad_norm": 1.079608678817749,
|
| 90 |
+
"learning_rate": 1.6779661016949154e-05,
|
| 91 |
+
"loss": 0.166,
|
| 92 |
+
"step": 100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.425531914893617,
|
| 96 |
+
"eval_accuracy_at_0.5_thresh": 0.8063829787234043,
|
| 97 |
+
"eval_f1_at_0.5_thresh": 0.723404255319149,
|
| 98 |
+
"eval_loss": 0.15719293057918549,
|
| 99 |
+
"eval_precision_at_0.5_thresh": 0.9224806201550387,
|
| 100 |
+
"eval_recall_at_0.5_thresh": 0.595,
|
| 101 |
+
"eval_runtime": 1.1886,
|
| 102 |
+
"eval_samples_per_second": 395.432,
|
| 103 |
+
"eval_steps_per_second": 12.62,
|
| 104 |
+
"step": 100
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.46808510638297873,
|
| 108 |
+
"grad_norm": 1.0034838914871216,
|
| 109 |
+
"learning_rate": 1.8474576271186443e-05,
|
| 110 |
+
"loss": 0.1685,
|
| 111 |
+
"step": 110
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.5106382978723404,
|
| 115 |
+
"grad_norm": 0.9138811230659485,
|
| 116 |
+
"learning_rate": 1.9981078524124883e-05,
|
| 117 |
+
"loss": 0.1708,
|
| 118 |
+
"step": 120
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.5531914893617021,
|
| 122 |
+
"grad_norm": 0.9457395076751709,
|
| 123 |
+
"learning_rate": 1.97918637653737e-05,
|
| 124 |
+
"loss": 0.1524,
|
| 125 |
+
"step": 130
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.5957446808510638,
|
| 129 |
+
"grad_norm": 1.1439883708953857,
|
| 130 |
+
"learning_rate": 1.960264900662252e-05,
|
| 131 |
+
"loss": 0.1642,
|
| 132 |
+
"step": 140
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.6382978723404256,
|
| 136 |
+
"grad_norm": 0.900199830532074,
|
| 137 |
+
"learning_rate": 1.9413434247871333e-05,
|
| 138 |
+
"loss": 0.1612,
|
| 139 |
+
"step": 150
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.6382978723404256,
|
| 143 |
+
"eval_accuracy_at_0.5_thresh": 0.8553191489361702,
|
| 144 |
+
"eval_f1_at_0.5_thresh": 0.8308457711442786,
|
| 145 |
+
"eval_loss": 0.14183281362056732,
|
| 146 |
+
"eval_precision_at_0.5_thresh": 0.8267326732673267,
|
| 147 |
+
"eval_recall_at_0.5_thresh": 0.835,
|
| 148 |
+
"eval_runtime": 1.1664,
|
| 149 |
+
"eval_samples_per_second": 402.933,
|
| 150 |
+
"eval_steps_per_second": 12.86,
|
| 151 |
+
"step": 150
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.6808510638297872,
|
| 155 |
+
"grad_norm": 1.2067737579345703,
|
| 156 |
+
"learning_rate": 1.922421948912015e-05,
|
| 157 |
+
"loss": 0.1553,
|
| 158 |
+
"step": 160
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.723404255319149,
|
| 162 |
+
"grad_norm": 1.0066120624542236,
|
| 163 |
+
"learning_rate": 1.9035004730368973e-05,
|
| 164 |
+
"loss": 0.1495,
|
| 165 |
+
"step": 170
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.7659574468085106,
|
| 169 |
+
"grad_norm": 1.0830472707748413,
|
| 170 |
+
"learning_rate": 1.8845789971617787e-05,
|
| 171 |
+
"loss": 0.1364,
|
| 172 |
+
"step": 180
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.8085106382978723,
|
| 176 |
+
"grad_norm": 0.9800769686698914,
|
| 177 |
+
"learning_rate": 1.8656575212866605e-05,
|
| 178 |
+
"loss": 0.1295,
|
| 179 |
+
"step": 190
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.851063829787234,
|
| 183 |
+
"grad_norm": 0.9936037659645081,
|
| 184 |
+
"learning_rate": 1.8467360454115423e-05,
|
| 185 |
+
"loss": 0.1545,
|
| 186 |
+
"step": 200
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.851063829787234,
|
| 190 |
+
"eval_accuracy_at_0.5_thresh": 0.8382978723404255,
|
| 191 |
+
"eval_f1_at_0.5_thresh": 0.8020833333333334,
|
| 192 |
+
"eval_loss": 0.13116958737373352,
|
| 193 |
+
"eval_precision_at_0.5_thresh": 0.8369565217391305,
|
| 194 |
+
"eval_recall_at_0.5_thresh": 0.77,
|
| 195 |
+
"eval_runtime": 1.1719,
|
| 196 |
+
"eval_samples_per_second": 401.047,
|
| 197 |
+
"eval_steps_per_second": 12.799,
|
| 198 |
+
"step": 200
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8936170212765957,
|
| 202 |
+
"grad_norm": 0.9179720878601074,
|
| 203 |
+
"learning_rate": 1.827814569536424e-05,
|
| 204 |
+
"loss": 0.1328,
|
| 205 |
+
"step": 210
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9361702127659575,
|
| 209 |
+
"grad_norm": 1.5345299243927002,
|
| 210 |
+
"learning_rate": 1.808893093661306e-05,
|
| 211 |
+
"loss": 0.1355,
|
| 212 |
+
"step": 220
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9787234042553191,
|
| 216 |
+
"grad_norm": 1.037996530532837,
|
| 217 |
+
"learning_rate": 1.7899716177861873e-05,
|
| 218 |
+
"loss": 0.1289,
|
| 219 |
+
"step": 230
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0212765957446808,
|
| 223 |
+
"grad_norm": 1.2900911569595337,
|
| 224 |
+
"learning_rate": 1.771050141911069e-05,
|
| 225 |
+
"loss": 0.1245,
|
| 226 |
+
"step": 240
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0638297872340425,
|
| 230 |
+
"grad_norm": 0.7172983884811401,
|
| 231 |
+
"learning_rate": 1.752128666035951e-05,
|
| 232 |
+
"loss": 0.1067,
|
| 233 |
+
"step": 250
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.0638297872340425,
|
| 237 |
+
"eval_accuracy_at_0.5_thresh": 0.8425531914893617,
|
| 238 |
+
"eval_f1_at_0.5_thresh": 0.8131313131313131,
|
| 239 |
+
"eval_loss": 0.12659965455532074,
|
| 240 |
+
"eval_precision_at_0.5_thresh": 0.8214285714285714,
|
| 241 |
+
"eval_recall_at_0.5_thresh": 0.805,
|
| 242 |
+
"eval_runtime": 1.1658,
|
| 243 |
+
"eval_samples_per_second": 403.141,
|
| 244 |
+
"eval_steps_per_second": 12.866,
|
| 245 |
+
"step": 250
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.1063829787234043,
|
| 249 |
+
"grad_norm": 1.0125339031219482,
|
| 250 |
+
"learning_rate": 1.7332071901608327e-05,
|
| 251 |
+
"loss": 0.1177,
|
| 252 |
+
"step": 260
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.148936170212766,
|
| 256 |
+
"grad_norm": 1.0160564184188843,
|
| 257 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 258 |
+
"loss": 0.1034,
|
| 259 |
+
"step": 270
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.1914893617021276,
|
| 263 |
+
"grad_norm": 1.3702187538146973,
|
| 264 |
+
"learning_rate": 1.6953642384105963e-05,
|
| 265 |
+
"loss": 0.1117,
|
| 266 |
+
"step": 280
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.2340425531914894,
|
| 270 |
+
"grad_norm": 1.317497730255127,
|
| 271 |
+
"learning_rate": 1.676442762535478e-05,
|
| 272 |
+
"loss": 0.1235,
|
| 273 |
+
"step": 290
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.2765957446808511,
|
| 277 |
+
"grad_norm": 0.8722613453865051,
|
| 278 |
+
"learning_rate": 1.6575212866603596e-05,
|
| 279 |
+
"loss": 0.0933,
|
| 280 |
+
"step": 300
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.2765957446808511,
|
| 284 |
+
"eval_accuracy_at_0.5_thresh": 0.8489361702127659,
|
| 285 |
+
"eval_f1_at_0.5_thresh": 0.8202531645569621,
|
| 286 |
+
"eval_loss": 0.1204555556178093,
|
| 287 |
+
"eval_precision_at_0.5_thresh": 0.8307692307692308,
|
| 288 |
+
"eval_recall_at_0.5_thresh": 0.81,
|
| 289 |
+
"eval_runtime": 1.1714,
|
| 290 |
+
"eval_samples_per_second": 401.236,
|
| 291 |
+
"eval_steps_per_second": 12.805,
|
| 292 |
+
"step": 300
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.3191489361702127,
|
| 296 |
+
"grad_norm": 1.0289169549942017,
|
| 297 |
+
"learning_rate": 1.6385998107852414e-05,
|
| 298 |
+
"loss": 0.1039,
|
| 299 |
+
"step": 310
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.3617021276595744,
|
| 303 |
+
"grad_norm": 0.9575484991073608,
|
| 304 |
+
"learning_rate": 1.619678334910123e-05,
|
| 305 |
+
"loss": 0.1161,
|
| 306 |
+
"step": 320
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.4042553191489362,
|
| 310 |
+
"grad_norm": 1.3465416431427002,
|
| 311 |
+
"learning_rate": 1.600756859035005e-05,
|
| 312 |
+
"loss": 0.0912,
|
| 313 |
+
"step": 330
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 1.4468085106382977,
|
| 317 |
+
"grad_norm": 0.9446049332618713,
|
| 318 |
+
"learning_rate": 1.5818353831598864e-05,
|
| 319 |
+
"loss": 0.0868,
|
| 320 |
+
"step": 340
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.4893617021276595,
|
| 324 |
+
"grad_norm": 1.3670283555984497,
|
| 325 |
+
"learning_rate": 1.5629139072847682e-05,
|
| 326 |
+
"loss": 0.0984,
|
| 327 |
+
"step": 350
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.4893617021276595,
|
| 331 |
+
"eval_accuracy_at_0.5_thresh": 0.8617021276595744,
|
| 332 |
+
"eval_f1_at_0.5_thresh": 0.8387096774193549,
|
| 333 |
+
"eval_loss": 0.12064016610383987,
|
| 334 |
+
"eval_precision_at_0.5_thresh": 0.8325123152709359,
|
| 335 |
+
"eval_recall_at_0.5_thresh": 0.845,
|
| 336 |
+
"eval_runtime": 1.1704,
|
| 337 |
+
"eval_samples_per_second": 401.579,
|
| 338 |
+
"eval_steps_per_second": 12.816,
|
| 339 |
+
"step": 350
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.5319148936170213,
|
| 343 |
+
"grad_norm": 1.2213770151138306,
|
| 344 |
+
"learning_rate": 1.54399243140965e-05,
|
| 345 |
+
"loss": 0.109,
|
| 346 |
+
"step": 360
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.574468085106383,
|
| 350 |
+
"grad_norm": 0.8301506638526917,
|
| 351 |
+
"learning_rate": 1.5250709555345318e-05,
|
| 352 |
+
"loss": 0.1014,
|
| 353 |
+
"step": 370
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.6170212765957448,
|
| 357 |
+
"grad_norm": 1.2703402042388916,
|
| 358 |
+
"learning_rate": 1.5061494796594136e-05,
|
| 359 |
+
"loss": 0.1054,
|
| 360 |
+
"step": 380
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.6595744680851063,
|
| 364 |
+
"grad_norm": 1.1871310472488403,
|
| 365 |
+
"learning_rate": 1.4872280037842952e-05,
|
| 366 |
+
"loss": 0.1043,
|
| 367 |
+
"step": 390
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.702127659574468,
|
| 371 |
+
"grad_norm": 0.7756622433662415,
|
| 372 |
+
"learning_rate": 1.468306527909177e-05,
|
| 373 |
+
"loss": 0.1052,
|
| 374 |
+
"step": 400
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.702127659574468,
|
| 378 |
+
"eval_accuracy_at_0.5_thresh": 0.8659574468085106,
|
| 379 |
+
"eval_f1_at_0.5_thresh": 0.8372093023255814,
|
| 380 |
+
"eval_loss": 0.1149349957704544,
|
| 381 |
+
"eval_precision_at_0.5_thresh": 0.8663101604278075,
|
| 382 |
+
"eval_recall_at_0.5_thresh": 0.81,
|
| 383 |
+
"eval_runtime": 1.1721,
|
| 384 |
+
"eval_samples_per_second": 400.999,
|
| 385 |
+
"eval_steps_per_second": 12.798,
|
| 386 |
+
"step": 400
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.7446808510638299,
|
| 390 |
+
"grad_norm": 1.2976441383361816,
|
| 391 |
+
"learning_rate": 1.4493850520340588e-05,
|
| 392 |
+
"loss": 0.1295,
|
| 393 |
+
"step": 410
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.7872340425531914,
|
| 397 |
+
"grad_norm": 1.139825463294983,
|
| 398 |
+
"learning_rate": 1.4304635761589404e-05,
|
| 399 |
+
"loss": 0.1032,
|
| 400 |
+
"step": 420
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.8297872340425532,
|
| 404 |
+
"grad_norm": 1.3335371017456055,
|
| 405 |
+
"learning_rate": 1.4115421002838224e-05,
|
| 406 |
+
"loss": 0.1001,
|
| 407 |
+
"step": 430
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 1.872340425531915,
|
| 411 |
+
"grad_norm": 1.33684241771698,
|
| 412 |
+
"learning_rate": 1.3926206244087039e-05,
|
| 413 |
+
"loss": 0.1052,
|
| 414 |
+
"step": 440
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.9148936170212765,
|
| 418 |
+
"grad_norm": 1.1832659244537354,
|
| 419 |
+
"learning_rate": 1.3736991485335858e-05,
|
| 420 |
+
"loss": 0.1064,
|
| 421 |
+
"step": 450
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 1.9148936170212765,
|
| 425 |
+
"eval_accuracy_at_0.5_thresh": 0.874468085106383,
|
| 426 |
+
"eval_f1_at_0.5_thresh": 0.8513853904282116,
|
| 427 |
+
"eval_loss": 0.11494793742895126,
|
| 428 |
+
"eval_precision_at_0.5_thresh": 0.8578680203045685,
|
| 429 |
+
"eval_recall_at_0.5_thresh": 0.845,
|
| 430 |
+
"eval_runtime": 1.1713,
|
| 431 |
+
"eval_samples_per_second": 401.267,
|
| 432 |
+
"eval_steps_per_second": 12.806,
|
| 433 |
+
"step": 450
|
| 434 |
+
}
|
| 435 |
+
],
|
| 436 |
+
"logging_steps": 10,
|
| 437 |
+
"max_steps": 1175,
|
| 438 |
+
"num_input_tokens_seen": 0,
|
| 439 |
+
"num_train_epochs": 5,
|
| 440 |
+
"save_steps": 50,
|
| 441 |
+
"stateful_callbacks": {
|
| 442 |
+
"TrainerControl": {
|
| 443 |
+
"args": {
|
| 444 |
+
"should_epoch_stop": false,
|
| 445 |
+
"should_evaluate": false,
|
| 446 |
+
"should_log": false,
|
| 447 |
+
"should_save": true,
|
| 448 |
+
"should_training_stop": false
|
| 449 |
+
},
|
| 450 |
+
"attributes": {}
|
| 451 |
+
}
|
| 452 |
+
},
|
| 453 |
+
"total_flos": 0.0,
|
| 454 |
+
"train_batch_size": 16,
|
| 455 |
+
"trial_name": null,
|
| 456 |
+
"trial_params": null
|
| 457 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ed40793a99548d59325ef3b9fb84abc4853c5ba98258ada966204fd517a80d4
|
| 3 |
+
size 5713
|