Commit
·
a1c52f7
1
Parent(s):
21305e6
Update fine-tuned model
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- generation_config.json +0 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +627 -102
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -20,13 +20,13 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
|
|
|
| 24 |
"q_proj",
|
| 25 |
-
"
|
| 26 |
-
"k_proj",
|
| 27 |
"down_proj",
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
],
|
| 31 |
"task_type": " CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
"q_proj",
|
| 26 |
+
"up_proj",
|
|
|
|
| 27 |
"down_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
],
|
| 31 |
"task_type": " CAUSAL_LM",
|
| 32 |
"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 159967880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37b490722f3569809ed7c7cb49dfdfde96cd02bb09eca68190d6348486f92870
|
| 3 |
size 159967880
|
generation_config.json
CHANGED
|
@@ -6,7 +6,6 @@
|
|
| 6 |
"max_memory": {
|
| 7 |
"cpu": 329543315456
|
| 8 |
},
|
| 9 |
-
"max_new_tokens": 200,
|
| 10 |
"no_split_module_classes": [
|
| 11 |
"LlamaDecoderLayer"
|
| 12 |
],
|
|
|
|
| 6 |
"max_memory": {
|
| 7 |
"cpu": 329543315456
|
| 8 |
},
|
|
|
|
| 9 |
"no_split_module_classes": [
|
| 10 |
"LlamaDecoderLayer"
|
| 11 |
],
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 852876198
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea55423e4e64cc1df1cb888ee6add0a8ca300f6b05a938af8f450ce220634a17
|
| 3 |
size 852876198
|
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:ebe50cfc9f72a4e33361d0d5c02fcc47dea8ac99f35f6913af8ed7d198ed0376
|
| 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 sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -3,189 +3,714 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 5.0,
|
| 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":
|
| 15 |
-
"loss":
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss":
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss":
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch":
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss":
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss":
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss":
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch":
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss":
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch":
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch":
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate": 0.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate": 0.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch":
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch":
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch":
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch":
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch":
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch":
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 24
|
| 178 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 179 |
{
|
| 180 |
"epoch": 5.0,
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
"learning_rate": 0.0,
|
| 183 |
-
"loss": 0.
|
| 184 |
-
"step":
|
| 185 |
}
|
| 186 |
],
|
| 187 |
"logging_steps": 1,
|
| 188 |
-
"max_steps":
|
| 189 |
"num_input_tokens_seen": 0,
|
| 190 |
"num_train_epochs": 5,
|
| 191 |
"save_steps": 500,
|
|
@@ -201,7 +726,7 @@
|
|
| 201 |
"attributes": {}
|
| 202 |
}
|
| 203 |
},
|
| 204 |
-
"total_flos":
|
| 205 |
"train_batch_size": 1,
|
| 206 |
"trial_name": null,
|
| 207 |
"trial_params": null
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 5.0,
|
| 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": 0.05,
|
| 13 |
+
"grad_norm": 4.447973251342773,
|
| 14 |
+
"learning_rate": 4e-05,
|
| 15 |
+
"loss": 2.7672,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 4.150802135467529,
|
| 21 |
+
"learning_rate": 8e-05,
|
| 22 |
+
"loss": 2.6287,
|
| 23 |
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 3.937238931655884,
|
| 28 |
+
"learning_rate": 0.00012,
|
| 29 |
+
"loss": 2.5862,
|
| 30 |
"step": 3
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 3.001154899597168,
|
| 35 |
+
"learning_rate": 0.00016,
|
| 36 |
+
"loss": 2.1841,
|
| 37 |
"step": 4
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 2.4711031913757324,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 1.8194,
|
| 44 |
"step": 5
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 1.8626506328582764,
|
| 49 |
+
"learning_rate": 0.00019994532573409262,
|
| 50 |
+
"loss": 1.5182,
|
| 51 |
"step": 6
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 1.5748854875564575,
|
| 56 |
+
"learning_rate": 0.00019978136272187747,
|
| 57 |
+
"loss": 1.2377,
|
| 58 |
"step": 7
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 1.3064329624176025,
|
| 63 |
+
"learning_rate": 0.00019950829025450114,
|
| 64 |
+
"loss": 1.0241,
|
| 65 |
"step": 8
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 1.1094794273376465,
|
| 70 |
+
"learning_rate": 0.00019912640693269752,
|
| 71 |
+
"loss": 0.963,
|
| 72 |
"step": 9
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 1.3718185424804688,
|
| 77 |
+
"learning_rate": 0.00019863613034027224,
|
| 78 |
+
"loss": 0.919,
|
| 79 |
"step": 10
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.55,
|
| 83 |
+
"grad_norm": 0.6297829151153564,
|
| 84 |
+
"learning_rate": 0.00019803799658748094,
|
| 85 |
+
"loss": 0.8479,
|
| 86 |
"step": 11
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"grad_norm": 0.5934209227561951,
|
| 91 |
+
"learning_rate": 0.0001973326597248006,
|
| 92 |
+
"loss": 0.8286,
|
| 93 |
"step": 12
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"grad_norm": 0.5935357809066772,
|
| 98 |
+
"learning_rate": 0.00019652089102773488,
|
| 99 |
+
"loss": 0.7957,
|
| 100 |
"step": 13
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.7,
|
| 104 |
+
"grad_norm": 0.4544467031955719,
|
| 105 |
+
"learning_rate": 0.00019560357815343577,
|
| 106 |
+
"loss": 0.7723,
|
| 107 |
"step": 14
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.75,
|
| 111 |
+
"grad_norm": 0.3061223030090332,
|
| 112 |
+
"learning_rate": 0.00019458172417006347,
|
| 113 |
+
"loss": 0.7505,
|
| 114 |
"step": 15
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"grad_norm": 0.4051577150821686,
|
| 119 |
+
"learning_rate": 0.0001934564464599461,
|
| 120 |
+
"loss": 0.774,
|
| 121 |
"step": 16
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.85,
|
| 125 |
+
"grad_norm": 0.35342541337013245,
|
| 126 |
+
"learning_rate": 0.00019222897549773848,
|
| 127 |
+
"loss": 0.7647,
|
| 128 |
"step": 17
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"grad_norm": 0.2566414773464203,
|
| 133 |
+
"learning_rate": 0.00019090065350491626,
|
| 134 |
+
"loss": 0.7316,
|
| 135 |
"step": 18
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.95,
|
| 139 |
+
"grad_norm": 0.27759572863578796,
|
| 140 |
+
"learning_rate": 0.00018947293298207635,
|
| 141 |
+
"loss": 0.74,
|
| 142 |
"step": 19
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"grad_norm": 0.2516538202762604,
|
| 147 |
+
"learning_rate": 0.0001879473751206489,
|
| 148 |
+
"loss": 0.7862,
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 1.05,
|
| 153 |
+
"grad_norm": 0.291866660118103,
|
| 154 |
+
"learning_rate": 0.00018632564809575742,
|
| 155 |
+
"loss": 0.6802,
|
| 156 |
"step": 21
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 1.1,
|
| 160 |
+
"grad_norm": 0.26497676968574524,
|
| 161 |
+
"learning_rate": 0.00018460952524209355,
|
| 162 |
+
"loss": 0.6779,
|
| 163 |
"step": 22
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 1.15,
|
| 167 |
+
"grad_norm": 0.29328078031539917,
|
| 168 |
+
"learning_rate": 0.00018280088311480201,
|
| 169 |
+
"loss": 0.6612,
|
| 170 |
"step": 23
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 1.2,
|
| 174 |
+
"grad_norm": 0.24686995148658752,
|
| 175 |
+
"learning_rate": 0.00018090169943749476,
|
| 176 |
+
"loss": 0.6859,
|
| 177 |
"step": 24
|
| 178 |
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.25,
|
| 181 |
+
"grad_norm": 0.24599069356918335,
|
| 182 |
+
"learning_rate": 0.00017891405093963938,
|
| 183 |
+
"loss": 0.6753,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.3,
|
| 188 |
+
"grad_norm": 0.22834160923957825,
|
| 189 |
+
"learning_rate": 0.00017684011108568592,
|
| 190 |
+
"loss": 0.677,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.35,
|
| 195 |
+
"grad_norm": 0.24461103975772858,
|
| 196 |
+
"learning_rate": 0.0001746821476984154,
|
| 197 |
+
"loss": 0.6418,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.4,
|
| 202 |
+
"grad_norm": 0.21487152576446533,
|
| 203 |
+
"learning_rate": 0.00017244252047910892,
|
| 204 |
+
"loss": 0.6358,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.45,
|
| 209 |
+
"grad_norm": 0.21681031584739685,
|
| 210 |
+
"learning_rate": 0.00017012367842724887,
|
| 211 |
+
"loss": 0.6218,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.5,
|
| 216 |
+
"grad_norm": 0.2119208723306656,
|
| 217 |
+
"learning_rate": 0.00016772815716257412,
|
| 218 |
+
"loss": 0.5886,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.55,
|
| 223 |
+
"grad_norm": 0.22078657150268555,
|
| 224 |
+
"learning_rate": 0.00016525857615241687,
|
| 225 |
+
"loss": 0.6381,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.6,
|
| 230 |
+
"grad_norm": 0.22970253229141235,
|
| 231 |
+
"learning_rate": 0.0001627176358473537,
|
| 232 |
+
"loss": 0.6165,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.65,
|
| 237 |
+
"grad_norm": 0.2325950413942337,
|
| 238 |
+
"learning_rate": 0.00016010811472830252,
|
| 239 |
+
"loss": 0.6287,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.7,
|
| 244 |
+
"grad_norm": 0.21151460707187653,
|
| 245 |
+
"learning_rate": 0.00015743286626829437,
|
| 246 |
+
"loss": 0.567,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.75,
|
| 251 |
+
"grad_norm": 0.22438429296016693,
|
| 252 |
+
"learning_rate": 0.00015469481581224272,
|
| 253 |
+
"loss": 0.6076,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.8,
|
| 258 |
+
"grad_norm": 0.21426045894622803,
|
| 259 |
+
"learning_rate": 0.00015189695737812152,
|
| 260 |
+
"loss": 0.6024,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.85,
|
| 265 |
+
"grad_norm": 0.21215516328811646,
|
| 266 |
+
"learning_rate": 0.00014904235038305083,
|
| 267 |
+
"loss": 0.6146,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.9,
|
| 272 |
+
"grad_norm": 0.2205992490053177,
|
| 273 |
+
"learning_rate": 0.0001461341162978688,
|
| 274 |
+
"loss": 0.5927,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.95,
|
| 279 |
+
"grad_norm": 0.2277802973985672,
|
| 280 |
+
"learning_rate": 0.00014317543523384928,
|
| 281 |
+
"loss": 0.5872,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.0,
|
| 286 |
+
"grad_norm": 0.22207193076610565,
|
| 287 |
+
"learning_rate": 0.00014016954246529696,
|
| 288 |
+
"loss": 0.6077,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.05,
|
| 293 |
+
"grad_norm": 0.2099306583404541,
|
| 294 |
+
"learning_rate": 0.00013711972489182208,
|
| 295 |
+
"loss": 0.571,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.1,
|
| 300 |
+
"grad_norm": 0.2039865106344223,
|
| 301 |
+
"learning_rate": 0.00013402931744416433,
|
| 302 |
+
"loss": 0.5606,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.15,
|
| 307 |
+
"grad_norm": 0.20860564708709717,
|
| 308 |
+
"learning_rate": 0.00013090169943749476,
|
| 309 |
+
"loss": 0.5544,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.2,
|
| 314 |
+
"grad_norm": 0.22982315719127655,
|
| 315 |
+
"learning_rate": 0.00012774029087618446,
|
| 316 |
+
"loss": 0.5526,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.25,
|
| 321 |
+
"grad_norm": 0.20864799618721008,
|
| 322 |
+
"learning_rate": 0.00012454854871407994,
|
| 323 |
+
"loss": 0.5237,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.3,
|
| 328 |
+
"grad_norm": 0.21810759603977203,
|
| 329 |
+
"learning_rate": 0.0001213299630743747,
|
| 330 |
+
"loss": 0.5299,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.35,
|
| 335 |
+
"grad_norm": 0.21522781252861023,
|
| 336 |
+
"learning_rate": 0.000118088053433211,
|
| 337 |
+
"loss": 0.5316,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.4,
|
| 342 |
+
"grad_norm": 0.20544247329235077,
|
| 343 |
+
"learning_rate": 0.0001148263647711842,
|
| 344 |
+
"loss": 0.5068,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.45,
|
| 349 |
+
"grad_norm": 0.2135314643383026,
|
| 350 |
+
"learning_rate": 0.00011154846369695863,
|
| 351 |
+
"loss": 0.5364,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.5,
|
| 356 |
+
"grad_norm": 0.21021024882793427,
|
| 357 |
+
"learning_rate": 0.00010825793454723325,
|
| 358 |
+
"loss": 0.5186,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.55,
|
| 363 |
+
"grad_norm": 0.2136543244123459,
|
| 364 |
+
"learning_rate": 0.00010495837546732224,
|
| 365 |
+
"loss": 0.5339,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.6,
|
| 370 |
+
"grad_norm": 0.23084285855293274,
|
| 371 |
+
"learning_rate": 0.00010165339447663587,
|
| 372 |
+
"loss": 0.5378,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.65,
|
| 377 |
+
"grad_norm": 0.20442883670330048,
|
| 378 |
+
"learning_rate": 9.834660552336415e-05,
|
| 379 |
+
"loss": 0.5268,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.7,
|
| 384 |
+
"grad_norm": 0.22932833433151245,
|
| 385 |
+
"learning_rate": 9.504162453267777e-05,
|
| 386 |
+
"loss": 0.5174,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.75,
|
| 391 |
+
"grad_norm": 0.22436076402664185,
|
| 392 |
+
"learning_rate": 9.174206545276677e-05,
|
| 393 |
+
"loss": 0.5377,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.8,
|
| 398 |
+
"grad_norm": 0.2104436308145523,
|
| 399 |
+
"learning_rate": 8.845153630304139e-05,
|
| 400 |
+
"loss": 0.4974,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.85,
|
| 405 |
+
"grad_norm": 0.2314048409461975,
|
| 406 |
+
"learning_rate": 8.517363522881579e-05,
|
| 407 |
+
"loss": 0.5499,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.9,
|
| 412 |
+
"grad_norm": 0.22638021409511566,
|
| 413 |
+
"learning_rate": 8.191194656678904e-05,
|
| 414 |
+
"loss": 0.5341,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.95,
|
| 419 |
+
"grad_norm": 0.21407343447208405,
|
| 420 |
+
"learning_rate": 7.867003692562534e-05,
|
| 421 |
+
"loss": 0.5386,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.0,
|
| 426 |
+
"grad_norm": 0.224117249250412,
|
| 427 |
+
"learning_rate": 7.54514512859201e-05,
|
| 428 |
+
"loss": 0.5139,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 3.05,
|
| 433 |
+
"grad_norm": 0.20954056084156036,
|
| 434 |
+
"learning_rate": 7.225970912381556e-05,
|
| 435 |
+
"loss": 0.5009,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 3.1,
|
| 440 |
+
"grad_norm": 0.21707436442375183,
|
| 441 |
+
"learning_rate": 6.909830056250527e-05,
|
| 442 |
+
"loss": 0.5039,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.15,
|
| 447 |
+
"grad_norm": 0.21246309578418732,
|
| 448 |
+
"learning_rate": 6.59706825558357e-05,
|
| 449 |
+
"loss": 0.4932,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.2,
|
| 454 |
+
"grad_norm": 0.22075852751731873,
|
| 455 |
+
"learning_rate": 6.28802751081779e-05,
|
| 456 |
+
"loss": 0.4946,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 3.25,
|
| 461 |
+
"grad_norm": 0.2115776240825653,
|
| 462 |
+
"learning_rate": 5.983045753470308e-05,
|
| 463 |
+
"loss": 0.4816,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.3,
|
| 468 |
+
"grad_norm": 0.2231447845697403,
|
| 469 |
+
"learning_rate": 5.6824564766150726e-05,
|
| 470 |
+
"loss": 0.4471,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.35,
|
| 475 |
+
"grad_norm": 0.2261902540922165,
|
| 476 |
+
"learning_rate": 5.386588370213124e-05,
|
| 477 |
+
"loss": 0.4758,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 3.4,
|
| 482 |
+
"grad_norm": 0.23066717386245728,
|
| 483 |
+
"learning_rate": 5.095764961694922e-05,
|
| 484 |
+
"loss": 0.4946,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 3.45,
|
| 489 |
+
"grad_norm": 0.23373715579509735,
|
| 490 |
+
"learning_rate": 4.810304262187852e-05,
|
| 491 |
+
"loss": 0.4551,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 3.5,
|
| 496 |
+
"grad_norm": 0.22016406059265137,
|
| 497 |
+
"learning_rate": 4.530518418775733e-05,
|
| 498 |
+
"loss": 0.4678,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 3.55,
|
| 503 |
+
"grad_norm": 0.22911153733730316,
|
| 504 |
+
"learning_rate": 4.256713373170564e-05,
|
| 505 |
+
"loss": 0.4621,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.6,
|
| 510 |
+
"grad_norm": 0.2464921772480011,
|
| 511 |
+
"learning_rate": 3.9891885271697496e-05,
|
| 512 |
+
"loss": 0.4524,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 3.65,
|
| 517 |
+
"grad_norm": 0.22986730933189392,
|
| 518 |
+
"learning_rate": 3.7282364152646297e-05,
|
| 519 |
+
"loss": 0.4619,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 3.7,
|
| 524 |
+
"grad_norm": 0.2360897809267044,
|
| 525 |
+
"learning_rate": 3.4741423847583134e-05,
|
| 526 |
+
"loss": 0.4873,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 3.75,
|
| 531 |
+
"grad_norm": 0.23576760292053223,
|
| 532 |
+
"learning_rate": 3.227184283742591e-05,
|
| 533 |
+
"loss": 0.4566,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.8,
|
| 538 |
+
"grad_norm": 0.23615522682666779,
|
| 539 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 540 |
+
"loss": 0.479,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 3.85,
|
| 545 |
+
"grad_norm": 0.2297057807445526,
|
| 546 |
+
"learning_rate": 2.7557479520891104e-05,
|
| 547 |
+
"loss": 0.4453,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.9,
|
| 552 |
+
"grad_norm": 0.23760643601417542,
|
| 553 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 554 |
+
"loss": 0.4603,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.95,
|
| 559 |
+
"grad_norm": 0.23733963072299957,
|
| 560 |
+
"learning_rate": 2.315988891431412e-05,
|
| 561 |
+
"loss": 0.4904,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 4.0,
|
| 566 |
+
"grad_norm": 0.23631036281585693,
|
| 567 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 568 |
+
"loss": 0.4378,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 4.05,
|
| 573 |
+
"grad_norm": 0.21698763966560364,
|
| 574 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 575 |
+
"loss": 0.4746,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 4.1,
|
| 580 |
+
"grad_norm": 0.22145631909370422,
|
| 581 |
+
"learning_rate": 1.7199116885197995e-05,
|
| 582 |
+
"loss": 0.4326,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 4.15,
|
| 587 |
+
"grad_norm": 0.2206316590309143,
|
| 588 |
+
"learning_rate": 1.5390474757906446e-05,
|
| 589 |
+
"loss": 0.4661,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 4.2,
|
| 594 |
+
"grad_norm": 0.22402209043502808,
|
| 595 |
+
"learning_rate": 1.3674351904242611e-05,
|
| 596 |
+
"loss": 0.4242,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 4.25,
|
| 601 |
+
"grad_norm": 0.2289542257785797,
|
| 602 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 603 |
+
"loss": 0.4374,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 4.3,
|
| 608 |
+
"grad_norm": 0.22736269235610962,
|
| 609 |
+
"learning_rate": 1.0527067017923654e-05,
|
| 610 |
+
"loss": 0.4555,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.35,
|
| 615 |
+
"grad_norm": 0.23473459482192993,
|
| 616 |
+
"learning_rate": 9.09934649508375e-06,
|
| 617 |
+
"loss": 0.457,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 4.4,
|
| 622 |
+
"grad_norm": 0.23741869628429413,
|
| 623 |
+
"learning_rate": 7.771024502261526e-06,
|
| 624 |
+
"loss": 0.4488,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 4.45,
|
| 629 |
+
"grad_norm": 0.2166988104581833,
|
| 630 |
+
"learning_rate": 6.543553540053926e-06,
|
| 631 |
+
"loss": 0.4071,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 4.5,
|
| 636 |
+
"grad_norm": 0.2260877788066864,
|
| 637 |
+
"learning_rate": 5.418275829936537e-06,
|
| 638 |
+
"loss": 0.4167,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 4.55,
|
| 643 |
+
"grad_norm": 0.2313169240951538,
|
| 644 |
+
"learning_rate": 4.3964218465642355e-06,
|
| 645 |
+
"loss": 0.4316,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 4.6,
|
| 650 |
+
"grad_norm": 0.23149524629116058,
|
| 651 |
+
"learning_rate": 3.4791089722651436e-06,
|
| 652 |
+
"loss": 0.4373,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 4.65,
|
| 657 |
+
"grad_norm": 0.2258220762014389,
|
| 658 |
+
"learning_rate": 2.667340275199426e-06,
|
| 659 |
+
"loss": 0.4298,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 4.7,
|
| 664 |
+
"grad_norm": 0.23423810303211212,
|
| 665 |
+
"learning_rate": 1.9620034125190644e-06,
|
| 666 |
+
"loss": 0.4717,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 4.75,
|
| 671 |
+
"grad_norm": 0.22674737870693207,
|
| 672 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 673 |
+
"loss": 0.4406,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 4.8,
|
| 678 |
+
"grad_norm": 0.22755774855613708,
|
| 679 |
+
"learning_rate": 8.735930673024806e-07,
|
| 680 |
+
"loss": 0.4683,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 4.85,
|
| 685 |
+
"grad_norm": 0.232791468501091,
|
| 686 |
+
"learning_rate": 4.917097454988584e-07,
|
| 687 |
+
"loss": 0.4585,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 4.9,
|
| 692 |
+
"grad_norm": 0.24561770260334015,
|
| 693 |
+
"learning_rate": 2.1863727812254653e-07,
|
| 694 |
+
"loss": 0.4532,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 4.95,
|
| 699 |
+
"grad_norm": 0.22012515366077423,
|
| 700 |
+
"learning_rate": 5.467426590739511e-08,
|
| 701 |
+
"loss": 0.4229,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
{
|
| 705 |
"epoch": 5.0,
|
| 706 |
+
"grad_norm": 0.21987777948379517,
|
| 707 |
"learning_rate": 0.0,
|
| 708 |
+
"loss": 0.4361,
|
| 709 |
+
"step": 100
|
| 710 |
}
|
| 711 |
],
|
| 712 |
"logging_steps": 1,
|
| 713 |
+
"max_steps": 100,
|
| 714 |
"num_input_tokens_seen": 0,
|
| 715 |
"num_train_epochs": 5,
|
| 716 |
"save_steps": 500,
|
|
|
|
| 726 |
"attributes": {}
|
| 727 |
}
|
| 728 |
},
|
| 729 |
+
"total_flos": 1.2238732695148954e+17,
|
| 730 |
"train_batch_size": 1,
|
| 731 |
"trial_name": null,
|
| 732 |
"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 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:635b848f06b7d2b4ab9ffa5a32c51e45ab3ca81a799c2aa5cd95d237aaba0745
|
| 3 |
size 5240
|