Commit
•
b581ffc
1
Parent(s):
e9a460f
Replace with latest checkpoint files
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +441 -21
- training_args.bin +2 -2
adapter_config.json
CHANGED
|
@@ -20,8 +20,8 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 109069176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec8239232e0f2dcdeb9dfe412ca9e41f461a6b3a109ba6d16a538d3031ddac8c
|
| 3 |
size 109069176
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 218182586
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81958cc04d548bec047dcfcbe0bd46c64c0b5519bb4deeb748f6fa3e781d7688
|
| 3 |
size 218182586
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5cbd6873f1f63673bdbb5d594bdfa74c36de5a961b16beb18c4f4dfa6bbf36c
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63eb06e12174e4b2f92f6537cab5ba2dff7b98defaece3a64b5c306232cb8bfc
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -3,56 +3,476 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
"learning_rate": 0.0002,
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 250
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch":
|
| 20 |
-
"grad_norm":
|
| 21 |
"learning_rate": 0.0002,
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 500
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch":
|
| 27 |
-
"grad_norm":
|
| 28 |
"learning_rate": 0.0002,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 750
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch":
|
| 34 |
-
"grad_norm":
|
| 35 |
"learning_rate": 0.0002,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 1000
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch":
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
"learning_rate": 0.0002,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 1250
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
"learning_rate": 0.0002,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
}
|
| 53 |
],
|
| 54 |
"logging_steps": 250,
|
| 55 |
-
"max_steps":
|
| 56 |
"num_input_tokens_seen": 0,
|
| 57 |
"num_train_epochs": 6,
|
| 58 |
"save_steps": 250,
|
|
@@ -68,7 +488,7 @@
|
|
| 68 |
"attributes": {}
|
| 69 |
}
|
| 70 |
},
|
| 71 |
-
"total_flos": 2.
|
| 72 |
"train_batch_size": 4,
|
| 73 |
"trial_name": null,
|
| 74 |
"trial_params": null
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 6.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 16506,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.09087604507451835,
|
| 13 |
+
"grad_norm": 1.2130728960037231,
|
| 14 |
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 0.9008,
|
| 16 |
"step": 250
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.1817520901490367,
|
| 20 |
+
"grad_norm": 1.1032902002334595,
|
| 21 |
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 0.5317,
|
| 23 |
"step": 500
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.27262813522355506,
|
| 27 |
+
"grad_norm": 1.0168739557266235,
|
| 28 |
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 0.4231,
|
| 30 |
"step": 750
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.3635041802980734,
|
| 34 |
+
"grad_norm": 1.888968825340271,
|
| 35 |
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 0.3506,
|
| 37 |
"step": 1000
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.45438022537259176,
|
| 41 |
+
"grad_norm": 0.7193501591682434,
|
| 42 |
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 0.3049,
|
| 44 |
"step": 1250
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.5452562704471101,
|
| 48 |
+
"grad_norm": 0.958330512046814,
|
| 49 |
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.2575,
|
| 51 |
"step": 1500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6361323155216285,
|
| 55 |
+
"grad_norm": 0.9223587512969971,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 0.2395,
|
| 58 |
+
"step": 1750
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7270083605961468,
|
| 62 |
+
"grad_norm": 0.639679491519928,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 0.2213,
|
| 65 |
+
"step": 2000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.8178844056706652,
|
| 69 |
+
"grad_norm": 0.5571266412734985,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 0.2057,
|
| 72 |
+
"step": 2250
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.9087604507451835,
|
| 76 |
+
"grad_norm": 0.5572911500930786,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 0.1926,
|
| 79 |
+
"step": 2500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.9996364958197019,
|
| 83 |
+
"grad_norm": 0.7683030366897583,
|
| 84 |
+
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 0.1848,
|
| 86 |
+
"step": 2750
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0905125408942202,
|
| 90 |
+
"grad_norm": 0.6649575233459473,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.1757,
|
| 93 |
+
"step": 3000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.1813885859687385,
|
| 97 |
+
"grad_norm": 1.3259624242782593,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 0.1724,
|
| 100 |
+
"step": 3250
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.272264631043257,
|
| 104 |
+
"grad_norm": 0.5268917083740234,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 0.1696,
|
| 107 |
+
"step": 3500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.3631406761177753,
|
| 111 |
+
"grad_norm": 0.7535058856010437,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 0.1676,
|
| 114 |
+
"step": 3750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.4540167211922936,
|
| 118 |
+
"grad_norm": 0.3919288218021393,
|
| 119 |
+
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 0.1615,
|
| 121 |
+
"step": 4000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.5448927662668122,
|
| 125 |
+
"grad_norm": 0.2522818446159363,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 0.1596,
|
| 128 |
+
"step": 4250
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.6357688113413305,
|
| 132 |
+
"grad_norm": 0.574805498123169,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 0.1579,
|
| 135 |
+
"step": 4500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.7266448564158487,
|
| 139 |
+
"grad_norm": 0.35280880331993103,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 0.1572,
|
| 142 |
+
"step": 4750
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.8175209014903673,
|
| 146 |
+
"grad_norm": 0.343710333108902,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 0.1529,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.9083969465648853,
|
| 153 |
+
"grad_norm": 0.6308000683784485,
|
| 154 |
+
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 0.1514,
|
| 156 |
+
"step": 5250
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.9992729916394039,
|
| 160 |
+
"grad_norm": 0.7428322434425354,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 0.1504,
|
| 163 |
+
"step": 5500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.0901490367139224,
|
| 167 |
+
"grad_norm": 0.816819965839386,
|
| 168 |
+
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 0.1455,
|
| 170 |
+
"step": 5750
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.1810250817884405,
|
| 174 |
+
"grad_norm": 0.31729263067245483,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 0.1467,
|
| 177 |
+
"step": 6000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.271901126862959,
|
| 181 |
+
"grad_norm": 0.3655836582183838,
|
| 182 |
+
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 0.1447,
|
| 184 |
+
"step": 6250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.362777171937477,
|
| 188 |
+
"grad_norm": 0.34890076518058777,
|
| 189 |
+
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 0.1449,
|
| 191 |
+
"step": 6500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.4536532170119956,
|
| 195 |
+
"grad_norm": 0.25036028027534485,
|
| 196 |
+
"learning_rate": 0.0002,
|
| 197 |
+
"loss": 0.1446,
|
| 198 |
+
"step": 6750
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.544529262086514,
|
| 202 |
+
"grad_norm": 0.37913835048675537,
|
| 203 |
+
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 0.1429,
|
| 205 |
+
"step": 7000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.635405307161032,
|
| 209 |
+
"grad_norm": 0.6284835934638977,
|
| 210 |
+
"learning_rate": 0.0002,
|
| 211 |
+
"loss": 0.1427,
|
| 212 |
+
"step": 7250
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.7262813522355507,
|
| 216 |
+
"grad_norm": 0.18296529352664948,
|
| 217 |
+
"learning_rate": 0.0002,
|
| 218 |
+
"loss": 0.1425,
|
| 219 |
+
"step": 7500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.817157397310069,
|
| 223 |
+
"grad_norm": 0.31024783849716187,
|
| 224 |
+
"learning_rate": 0.0002,
|
| 225 |
+
"loss": 0.1405,
|
| 226 |
+
"step": 7750
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.9080334423845873,
|
| 230 |
+
"grad_norm": 0.2511535584926605,
|
| 231 |
+
"learning_rate": 0.0002,
|
| 232 |
+
"loss": 0.1393,
|
| 233 |
+
"step": 8000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.998909487459106,
|
| 237 |
+
"grad_norm": 0.2819952070713043,
|
| 238 |
+
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 0.1394,
|
| 240 |
+
"step": 8250
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.0897855325336243,
|
| 244 |
+
"grad_norm": 0.2572026252746582,
|
| 245 |
+
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 0.1352,
|
| 247 |
+
"step": 8500
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.1806615776081424,
|
| 251 |
+
"grad_norm": 0.6162417531013489,
|
| 252 |
+
"learning_rate": 0.0002,
|
| 253 |
+
"loss": 0.1367,
|
| 254 |
+
"step": 8750
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.271537622682661,
|
| 258 |
+
"grad_norm": 0.6815608143806458,
|
| 259 |
+
"learning_rate": 0.0002,
|
| 260 |
+
"loss": 0.136,
|
| 261 |
+
"step": 9000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.3624136677571794,
|
| 265 |
+
"grad_norm": 0.4514828324317932,
|
| 266 |
+
"learning_rate": 0.0002,
|
| 267 |
+
"loss": 0.1387,
|
| 268 |
+
"step": 9250
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.4532897128316975,
|
| 272 |
+
"grad_norm": 0.14196833968162537,
|
| 273 |
+
"learning_rate": 0.0002,
|
| 274 |
+
"loss": 0.1354,
|
| 275 |
+
"step": 9500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.544165757906216,
|
| 279 |
+
"grad_norm": 0.2632617950439453,
|
| 280 |
+
"learning_rate": 0.0002,
|
| 281 |
+
"loss": 0.1358,
|
| 282 |
+
"step": 9750
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.6350418029807345,
|
| 286 |
+
"grad_norm": 0.15455371141433716,
|
| 287 |
+
"learning_rate": 0.0002,
|
| 288 |
+
"loss": 0.1363,
|
| 289 |
+
"step": 10000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.7259178480552526,
|
| 293 |
+
"grad_norm": 0.14311546087265015,
|
| 294 |
+
"learning_rate": 0.0002,
|
| 295 |
+
"loss": 0.136,
|
| 296 |
+
"step": 10250
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.816793893129771,
|
| 300 |
+
"grad_norm": 0.21806533634662628,
|
| 301 |
+
"learning_rate": 0.0002,
|
| 302 |
+
"loss": 0.1336,
|
| 303 |
+
"step": 10500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.907669938204289,
|
| 307 |
+
"grad_norm": 0.6075801253318787,
|
| 308 |
+
"learning_rate": 0.0002,
|
| 309 |
+
"loss": 0.1339,
|
| 310 |
+
"step": 10750
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 3.9985459832788077,
|
| 314 |
+
"grad_norm": 0.38970544934272766,
|
| 315 |
+
"learning_rate": 0.0002,
|
| 316 |
+
"loss": 0.134,
|
| 317 |
+
"step": 11000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.089422028353326,
|
| 321 |
+
"grad_norm": 0.12462722510099411,
|
| 322 |
+
"learning_rate": 0.0002,
|
| 323 |
+
"loss": 0.1341,
|
| 324 |
+
"step": 11250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.180298073427845,
|
| 328 |
+
"grad_norm": 0.12478788197040558,
|
| 329 |
+
"learning_rate": 0.0002,
|
| 330 |
+
"loss": 0.1311,
|
| 331 |
+
"step": 11500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.271174118502363,
|
| 335 |
+
"grad_norm": 0.17592966556549072,
|
| 336 |
+
"learning_rate": 0.0002,
|
| 337 |
+
"loss": 0.1334,
|
| 338 |
+
"step": 11750
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.362050163576881,
|
| 342 |
+
"grad_norm": 0.16919384896755219,
|
| 343 |
+
"learning_rate": 0.0002,
|
| 344 |
+
"loss": 0.1315,
|
| 345 |
+
"step": 12000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.4529262086514,
|
| 349 |
+
"grad_norm": 0.232040673494339,
|
| 350 |
+
"learning_rate": 0.0002,
|
| 351 |
+
"loss": 0.1324,
|
| 352 |
+
"step": 12250
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.543802253725918,
|
| 356 |
+
"grad_norm": 0.14165472984313965,
|
| 357 |
+
"learning_rate": 0.0002,
|
| 358 |
+
"loss": 0.1336,
|
| 359 |
+
"step": 12500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.634678298800436,
|
| 363 |
+
"grad_norm": 0.17017216980457306,
|
| 364 |
+
"learning_rate": 0.0002,
|
| 365 |
+
"loss": 0.1336,
|
| 366 |
+
"step": 12750
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 4.725554343874954,
|
| 370 |
+
"grad_norm": 0.15150970220565796,
|
| 371 |
+
"learning_rate": 0.0002,
|
| 372 |
+
"loss": 0.1316,
|
| 373 |
+
"step": 13000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 4.816430388949473,
|
| 377 |
+
"grad_norm": 0.7836107611656189,
|
| 378 |
+
"learning_rate": 0.0002,
|
| 379 |
+
"loss": 0.1328,
|
| 380 |
+
"step": 13250
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.907306434023991,
|
| 384 |
+
"grad_norm": 0.28059402108192444,
|
| 385 |
+
"learning_rate": 0.0002,
|
| 386 |
+
"loss": 0.1323,
|
| 387 |
+
"step": 13500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.99818247909851,
|
| 391 |
+
"grad_norm": 0.5553152561187744,
|
| 392 |
+
"learning_rate": 0.0002,
|
| 393 |
+
"loss": 0.1317,
|
| 394 |
+
"step": 13750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.089058524173028,
|
| 398 |
+
"grad_norm": 0.18768849968910217,
|
| 399 |
+
"learning_rate": 0.0002,
|
| 400 |
+
"loss": 0.1307,
|
| 401 |
+
"step": 14000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.179934569247546,
|
| 405 |
+
"grad_norm": 0.12853963673114777,
|
| 406 |
+
"learning_rate": 0.0002,
|
| 407 |
+
"loss": 0.1305,
|
| 408 |
+
"step": 14250
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.270810614322064,
|
| 412 |
+
"grad_norm": 0.13940949738025665,
|
| 413 |
+
"learning_rate": 0.0002,
|
| 414 |
+
"loss": 0.1314,
|
| 415 |
+
"step": 14500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 5.361686659396583,
|
| 419 |
+
"grad_norm": 0.12992176413536072,
|
| 420 |
+
"learning_rate": 0.0002,
|
| 421 |
+
"loss": 0.1291,
|
| 422 |
+
"step": 14750
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.452562704471101,
|
| 426 |
+
"grad_norm": 0.17497240006923676,
|
| 427 |
+
"learning_rate": 0.0002,
|
| 428 |
+
"loss": 0.1309,
|
| 429 |
+
"step": 15000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.543438749545619,
|
| 433 |
+
"grad_norm": 0.1531759798526764,
|
| 434 |
+
"learning_rate": 0.0002,
|
| 435 |
+
"loss": 0.1303,
|
| 436 |
+
"step": 15250
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 5.634314794620138,
|
| 440 |
+
"grad_norm": 0.1523718535900116,
|
| 441 |
+
"learning_rate": 0.0002,
|
| 442 |
+
"loss": 0.1295,
|
| 443 |
+
"step": 15500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.7251908396946565,
|
| 447 |
+
"grad_norm": 0.17395178973674774,
|
| 448 |
+
"learning_rate": 0.0002,
|
| 449 |
+
"loss": 0.1313,
|
| 450 |
+
"step": 15750
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 5.8160668847691745,
|
| 454 |
+
"grad_norm": 0.10413607209920883,
|
| 455 |
+
"learning_rate": 0.0002,
|
| 456 |
+
"loss": 0.1328,
|
| 457 |
+
"step": 16000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 5.9069429298436935,
|
| 461 |
+
"grad_norm": 0.24993538856506348,
|
| 462 |
+
"learning_rate": 0.0002,
|
| 463 |
+
"loss": 0.1297,
|
| 464 |
+
"step": 16250
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.997818974918212,
|
| 468 |
+
"grad_norm": 0.30852416157722473,
|
| 469 |
+
"learning_rate": 0.0002,
|
| 470 |
+
"loss": 0.13,
|
| 471 |
+
"step": 16500
|
| 472 |
}
|
| 473 |
],
|
| 474 |
"logging_steps": 250,
|
| 475 |
+
"max_steps": 16506,
|
| 476 |
"num_input_tokens_seen": 0,
|
| 477 |
"num_train_epochs": 6,
|
| 478 |
"save_steps": 250,
|
|
|
|
| 488 |
"attributes": {}
|
| 489 |
}
|
| 490 |
},
|
| 491 |
+
"total_flos": 2.098309604079698e+17,
|
| 492 |
"train_batch_size": 4,
|
| 493 |
"trial_name": null,
|
| 494 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:beda80817400974be0a6cbfead6dc2c996ba4550054363b35944a1e96f1f3fa0
|
| 3 |
+
size 5688
|