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 143153376
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f41d83e93f05f82b1f18896d71019460704c9e5c5e181e619d19b0bc430c5c2
|
| 3 |
size 143153376
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 286365498
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:561fa0e4f1c1c2f4f6321e4b9a0d39815943f57f543bb5e3af94dae44304cb15
|
| 3 |
size 286365498
|
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 sha256:91e55d1ed0d033e2c9661dc247ee4414532721e92046d1c8f82738ed4390c787
|
| 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": 0.
|
| 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": 0.
|
| 28 |
"learning_rate": 0.0002,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 750
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch":
|
| 34 |
-
"grad_norm": 1.
|
| 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": 0.8166529536247253,
|
| 14 |
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 0.8718,
|
| 16 |
"step": 250
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.1817520901490367,
|
| 20 |
+
"grad_norm": 0.8011488914489746,
|
| 21 |
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 0.5089,
|
| 23 |
"step": 500
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.27262813522355506,
|
| 27 |
+
"grad_norm": 0.8325187563896179,
|
| 28 |
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 0.3852,
|
| 30 |
"step": 750
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.3635041802980734,
|
| 34 |
+
"grad_norm": 1.6889874935150146,
|
| 35 |
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 0.3127,
|
| 37 |
"step": 1000
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.45438022537259176,
|
| 41 |
+
"grad_norm": 0.6524374485015869,
|
| 42 |
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 0.2749,
|
| 44 |
"step": 1250
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.5452562704471101,
|
| 48 |
+
"grad_norm": 0.8681249022483826,
|
| 49 |
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.2379,
|
| 51 |
"step": 1500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6361323155216285,
|
| 55 |
+
"grad_norm": 0.9492128491401672,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 0.2204,
|
| 58 |
+
"step": 1750
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7270083605961468,
|
| 62 |
+
"grad_norm": 0.35517942905426025,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 0.2017,
|
| 65 |
+
"step": 2000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.8178844056706652,
|
| 69 |
+
"grad_norm": 0.5566073060035706,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 0.1898,
|
| 72 |
+
"step": 2250
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.9087604507451835,
|
| 76 |
+
"grad_norm": 0.23202739655971527,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 0.1788,
|
| 79 |
+
"step": 2500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.9996364958197019,
|
| 83 |
+
"grad_norm": 0.4493115246295929,
|
| 84 |
+
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 0.1736,
|
| 86 |
+
"step": 2750
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0905125408942202,
|
| 90 |
+
"grad_norm": 0.41077283024787903,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.1647,
|
| 93 |
+
"step": 3000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.1813885859687385,
|
| 97 |
+
"grad_norm": 0.24447296559810638,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 0.1598,
|
| 100 |
+
"step": 3250
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.272264631043257,
|
| 104 |
+
"grad_norm": 0.3004068434238434,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 0.1594,
|
| 107 |
+
"step": 3500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.3631406761177753,
|
| 111 |
+
"grad_norm": 0.20352505147457123,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 0.1554,
|
| 114 |
+
"step": 3750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.4540167211922936,
|
| 118 |
+
"grad_norm": 0.2659279704093933,
|
| 119 |
+
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 0.1502,
|
| 121 |
+
"step": 4000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.5448927662668122,
|
| 125 |
+
"grad_norm": 0.616990327835083,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 0.1485,
|
| 128 |
+
"step": 4250
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.6357688113413305,
|
| 132 |
+
"grad_norm": 0.1787092685699463,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 0.1465,
|
| 135 |
+
"step": 4500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.7266448564158487,
|
| 139 |
+
"grad_norm": 0.26382288336753845,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 0.1452,
|
| 142 |
+
"step": 4750
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.8175209014903673,
|
| 146 |
+
"grad_norm": 0.22121331095695496,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 0.1429,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.9083969465648853,
|
| 153 |
+
"grad_norm": 0.23968210816383362,
|
| 154 |
+
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 0.1415,
|
| 156 |
+
"step": 5250
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.9992729916394039,
|
| 160 |
+
"grad_norm": 0.20464320480823517,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 0.1392,
|
| 163 |
+
"step": 5500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.0901490367139224,
|
| 167 |
+
"grad_norm": 0.23473434150218964,
|
| 168 |
+
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 0.1363,
|
| 170 |
+
"step": 5750
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.1810250817884405,
|
| 174 |
+
"grad_norm": 0.3769285976886749,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 0.1373,
|
| 177 |
+
"step": 6000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.271901126862959,
|
| 181 |
+
"grad_norm": 0.11411458998918533,
|
| 182 |
+
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 0.1355,
|
| 184 |
+
"step": 6250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.362777171937477,
|
| 188 |
+
"grad_norm": 0.14283251762390137,
|
| 189 |
+
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 0.1351,
|
| 191 |
+
"step": 6500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.4536532170119956,
|
| 195 |
+
"grad_norm": 0.1278432458639145,
|
| 196 |
+
"learning_rate": 0.0002,
|
| 197 |
+
"loss": 0.1344,
|
| 198 |
+
"step": 6750
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.544529262086514,
|
| 202 |
+
"grad_norm": 0.1538127213716507,
|
| 203 |
+
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 0.1351,
|
| 205 |
+
"step": 7000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.635405307161032,
|
| 209 |
+
"grad_norm": 0.1636444330215454,
|
| 210 |
+
"learning_rate": 0.0002,
|
| 211 |
+
"loss": 0.1341,
|
| 212 |
+
"step": 7250
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.7262813522355507,
|
| 216 |
+
"grad_norm": 0.23468904197216034,
|
| 217 |
+
"learning_rate": 0.0002,
|
| 218 |
+
"loss": 0.1343,
|
| 219 |
+
"step": 7500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.817157397310069,
|
| 223 |
+
"grad_norm": 0.34467971324920654,
|
| 224 |
+
"learning_rate": 0.0002,
|
| 225 |
+
"loss": 0.1342,
|
| 226 |
+
"step": 7750
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.9080334423845873,
|
| 230 |
+
"grad_norm": 0.15800316631793976,
|
| 231 |
+
"learning_rate": 0.0002,
|
| 232 |
+
"loss": 0.1331,
|
| 233 |
+
"step": 8000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.998909487459106,
|
| 237 |
+
"grad_norm": 0.18056762218475342,
|
| 238 |
+
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 0.1324,
|
| 240 |
+
"step": 8250
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.0897855325336243,
|
| 244 |
+
"grad_norm": 0.12928904592990875,
|
| 245 |
+
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 0.1301,
|
| 247 |
+
"step": 8500
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.1806615776081424,
|
| 251 |
+
"grad_norm": 0.10186909139156342,
|
| 252 |
+
"learning_rate": 0.0002,
|
| 253 |
+
"loss": 0.1299,
|
| 254 |
+
"step": 8750
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.271537622682661,
|
| 258 |
+
"grad_norm": 0.1294797658920288,
|
| 259 |
+
"learning_rate": 0.0002,
|
| 260 |
+
"loss": 0.1311,
|
| 261 |
+
"step": 9000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.3624136677571794,
|
| 265 |
+
"grad_norm": 0.96567702293396,
|
| 266 |
+
"learning_rate": 0.0002,
|
| 267 |
+
"loss": 0.1292,
|
| 268 |
+
"step": 9250
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.4532897128316975,
|
| 272 |
+
"grad_norm": 0.7819355130195618,
|
| 273 |
+
"learning_rate": 0.0002,
|
| 274 |
+
"loss": 0.1289,
|
| 275 |
+
"step": 9500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.544165757906216,
|
| 279 |
+
"grad_norm": 0.19112642109394073,
|
| 280 |
+
"learning_rate": 0.0002,
|
| 281 |
+
"loss": 0.1305,
|
| 282 |
+
"step": 9750
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.6350418029807345,
|
| 286 |
+
"grad_norm": 0.09955710917711258,
|
| 287 |
+
"learning_rate": 0.0002,
|
| 288 |
+
"loss": 0.1298,
|
| 289 |
+
"step": 10000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.7259178480552526,
|
| 293 |
+
"grad_norm": 0.13611435890197754,
|
| 294 |
+
"learning_rate": 0.0002,
|
| 295 |
+
"loss": 0.1286,
|
| 296 |
+
"step": 10250
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.816793893129771,
|
| 300 |
+
"grad_norm": 0.11884398013353348,
|
| 301 |
+
"learning_rate": 0.0002,
|
| 302 |
+
"loss": 0.1307,
|
| 303 |
+
"step": 10500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.907669938204289,
|
| 307 |
+
"grad_norm": 0.1615493893623352,
|
| 308 |
+
"learning_rate": 0.0002,
|
| 309 |
+
"loss": 0.1284,
|
| 310 |
+
"step": 10750
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 3.9985459832788077,
|
| 314 |
+
"grad_norm": 0.31517332792282104,
|
| 315 |
+
"learning_rate": 0.0002,
|
| 316 |
+
"loss": 0.1291,
|
| 317 |
+
"step": 11000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.089422028353326,
|
| 321 |
+
"grad_norm": 0.6462264060974121,
|
| 322 |
+
"learning_rate": 0.0002,
|
| 323 |
+
"loss": 0.1276,
|
| 324 |
+
"step": 11250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.180298073427845,
|
| 328 |
+
"grad_norm": 0.09960414469242096,
|
| 329 |
+
"learning_rate": 0.0002,
|
| 330 |
+
"loss": 0.1265,
|
| 331 |
+
"step": 11500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.271174118502363,
|
| 335 |
+
"grad_norm": 0.09911854565143585,
|
| 336 |
+
"learning_rate": 0.0002,
|
| 337 |
+
"loss": 0.1286,
|
| 338 |
+
"step": 11750
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.362050163576881,
|
| 342 |
+
"grad_norm": 0.12108103185892105,
|
| 343 |
+
"learning_rate": 0.0002,
|
| 344 |
+
"loss": 0.1282,
|
| 345 |
+
"step": 12000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.4529262086514,
|
| 349 |
+
"grad_norm": 0.09403906762599945,
|
| 350 |
+
"learning_rate": 0.0002,
|
| 351 |
+
"loss": 0.1277,
|
| 352 |
+
"step": 12250
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.543802253725918,
|
| 356 |
+
"grad_norm": 0.12478747963905334,
|
| 357 |
+
"learning_rate": 0.0002,
|
| 358 |
+
"loss": 0.1294,
|
| 359 |
+
"step": 12500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.634678298800436,
|
| 363 |
+
"grad_norm": 0.5839309692382812,
|
| 364 |
+
"learning_rate": 0.0002,
|
| 365 |
+
"loss": 0.128,
|
| 366 |
+
"step": 12750
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 4.725554343874954,
|
| 370 |
+
"grad_norm": 0.0925154760479927,
|
| 371 |
+
"learning_rate": 0.0002,
|
| 372 |
+
"loss": 0.1278,
|
| 373 |
+
"step": 13000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 4.816430388949473,
|
| 377 |
+
"grad_norm": 0.09721515327692032,
|
| 378 |
+
"learning_rate": 0.0002,
|
| 379 |
+
"loss": 0.1243,
|
| 380 |
+
"step": 13250
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.907306434023991,
|
| 384 |
+
"grad_norm": 0.11027718335390091,
|
| 385 |
+
"learning_rate": 0.0002,
|
| 386 |
+
"loss": 0.1264,
|
| 387 |
+
"step": 13500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.99818247909851,
|
| 391 |
+
"grad_norm": 0.24596811830997467,
|
| 392 |
+
"learning_rate": 0.0002,
|
| 393 |
+
"loss": 0.1247,
|
| 394 |
+
"step": 13750
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.089058524173028,
|
| 398 |
+
"grad_norm": 0.3751857876777649,
|
| 399 |
+
"learning_rate": 0.0002,
|
| 400 |
+
"loss": 0.1244,
|
| 401 |
+
"step": 14000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.179934569247546,
|
| 405 |
+
"grad_norm": 0.0758715569972992,
|
| 406 |
+
"learning_rate": 0.0002,
|
| 407 |
+
"loss": 0.1235,
|
| 408 |
+
"step": 14250
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.270810614322064,
|
| 412 |
+
"grad_norm": 0.10280770063400269,
|
| 413 |
+
"learning_rate": 0.0002,
|
| 414 |
+
"loss": 0.1263,
|
| 415 |
+
"step": 14500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 5.361686659396583,
|
| 419 |
+
"grad_norm": 0.10937105864286423,
|
| 420 |
+
"learning_rate": 0.0002,
|
| 421 |
+
"loss": 0.1247,
|
| 422 |
+
"step": 14750
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.452562704471101,
|
| 426 |
+
"grad_norm": 0.10805700719356537,
|
| 427 |
+
"learning_rate": 0.0002,
|
| 428 |
+
"loss": 0.1257,
|
| 429 |
+
"step": 15000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.543438749545619,
|
| 433 |
+
"grad_norm": 0.1117258295416832,
|
| 434 |
+
"learning_rate": 0.0002,
|
| 435 |
+
"loss": 0.1289,
|
| 436 |
+
"step": 15250
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 5.634314794620138,
|
| 440 |
+
"grad_norm": 0.08629261702299118,
|
| 441 |
+
"learning_rate": 0.0002,
|
| 442 |
+
"loss": 0.1258,
|
| 443 |
+
"step": 15500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.7251908396946565,
|
| 447 |
+
"grad_norm": 0.10845168679952621,
|
| 448 |
+
"learning_rate": 0.0002,
|
| 449 |
+
"loss": 0.1259,
|
| 450 |
+
"step": 15750
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 5.8160668847691745,
|
| 454 |
+
"grad_norm": 0.08773403614759445,
|
| 455 |
+
"learning_rate": 0.0002,
|
| 456 |
+
"loss": 0.1255,
|
| 457 |
+
"step": 16000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 5.9069429298436935,
|
| 461 |
+
"grad_norm": 0.08745443820953369,
|
| 462 |
+
"learning_rate": 0.0002,
|
| 463 |
+
"loss": 0.1268,
|
| 464 |
+
"step": 16250
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.997818974918212,
|
| 468 |
+
"grad_norm": 0.29043182730674744,
|
| 469 |
+
"learning_rate": 0.0002,
|
| 470 |
+
"loss": 0.1253,
|
| 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": 2.32857340165632e+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:b892adc3be2c7e7d600dabe0134a5f34f67eedf5ff3198066090267311d2b200
|
| 3 |
+
size 5688
|