Upload 17 files
Browse filesUpdate model, new version
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +318 -59
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
|
|
|
| 26 |
"v_proj",
|
| 27 |
-
"up_proj",
|
| 28 |
-
"q_proj",
|
| 29 |
"gate_proj",
|
| 30 |
-
"
|
| 31 |
"down_proj",
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
+
"o_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
"v_proj",
|
|
|
|
|
|
|
| 29 |
"gate_proj",
|
| 30 |
+
"q_proj",
|
| 31 |
"down_proj",
|
| 32 |
+
"up_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"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 2118301632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:948f6262dafd5b5ddcf25e37fc4e8508aac2f4ec710c58eb57772d4c0305953b
|
| 3 |
size 2118301632
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1990270808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:deef029ef7f888736b60df04b9783af0ff28917986016b4ea5b120b1e62f6890
|
| 3 |
size 1990270808
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1006719368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e7bff07f11bee8fc75b40e42ebbe73636112a72e199a310dc6206396b829f5a
|
| 3 |
size 1006719368
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 34007674
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22e8891df7ee74875e965dcd91e7db8d2130bb7a4758e6a66f1f69a8f7b48bf8
|
| 3 |
size 34007674
|
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 sha256:5d156686ae62d2dd6e7c2996e6ec40caf5c5d66591403237deeba81bfda597c8
|
| 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:cf3863c8948e41c40f37017b57744f08214b2c38da69d49fe98001649774bc48
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,144 +1,403 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 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": 0.05431093007467753,
|
| 13 |
-
"grad_norm": 1.
|
| 14 |
-
"learning_rate": 0.
|
| 15 |
-
"loss": 3.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.10862186014935506,
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
-
"learning_rate": 0.
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.1629327902240326,
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.2172437202987101,
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss": 1.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.27155465037338766,
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.3258655804480652,
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.3801765105227427,
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.4344874405974202,
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.48879837067209775,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss":
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.5431093007467753,
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.5974202308214528,
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss":
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.6517311608961304,
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.7060420909708078,
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.7603530210454854,
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.814663951120163,
|
| 111 |
-
"grad_norm":
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.8689748811948405,
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.923285811269518,
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.9775967413441955,
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
}
|
| 137 |
],
|
| 138 |
"logging_steps": 10,
|
| 139 |
-
"max_steps":
|
| 140 |
"num_input_tokens_seen": 0,
|
| 141 |
-
"num_train_epochs":
|
| 142 |
"save_steps": 500,
|
| 143 |
"stateful_callbacks": {
|
| 144 |
"TrainerControl": {
|
|
@@ -152,7 +411,7 @@
|
|
| 152 |
"attributes": {}
|
| 153 |
}
|
| 154 |
},
|
| 155 |
-
"total_flos":
|
| 156 |
"train_batch_size": 1,
|
| 157 |
"trial_name": null,
|
| 158 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.988458927359131,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 552,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.05431093007467753,
|
| 13 |
+
"grad_norm": 1.4870964288711548,
|
| 14 |
+
"learning_rate": 0.00019997351589651408,
|
| 15 |
+
"loss": 3.4965,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.10862186014935506,
|
| 20 |
+
"grad_norm": 1.784044861793518,
|
| 21 |
+
"learning_rate": 0.00019967573081342103,
|
| 22 |
+
"loss": 2.065,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.1629327902240326,
|
| 27 |
+
"grad_norm": 0.7305468916893005,
|
| 28 |
+
"learning_rate": 0.00019904804439875633,
|
| 29 |
+
"loss": 1.2421,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.2172437202987101,
|
| 34 |
+
"grad_norm": 0.6995559930801392,
|
| 35 |
+
"learning_rate": 0.00019809253413499565,
|
| 36 |
+
"loss": 1.093,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.27155465037338766,
|
| 41 |
+
"grad_norm": 0.6627448201179504,
|
| 42 |
+
"learning_rate": 0.00019681236251822273,
|
| 43 |
+
"loss": 1.0856,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.3258655804480652,
|
| 48 |
+
"grad_norm": 0.7160666584968567,
|
| 49 |
+
"learning_rate": 0.00019521176659107142,
|
| 50 |
+
"loss": 1.013,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.3801765105227427,
|
| 55 |
+
"grad_norm": 0.6306814551353455,
|
| 56 |
+
"learning_rate": 0.0001932960439191915,
|
| 57 |
+
"loss": 1.0374,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.4344874405974202,
|
| 62 |
+
"grad_norm": 0.7758208513259888,
|
| 63 |
+
"learning_rate": 0.00019107153505765306,
|
| 64 |
+
"loss": 0.9474,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.48879837067209775,
|
| 69 |
+
"grad_norm": 1.2394300699234009,
|
| 70 |
+
"learning_rate": 0.000188545602565321,
|
| 71 |
+
"loss": 0.9932,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.5431093007467753,
|
| 76 |
+
"grad_norm": 0.829031229019165,
|
| 77 |
+
"learning_rate": 0.0001857266066366567,
|
| 78 |
+
"loss": 0.9204,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.5974202308214528,
|
| 83 |
+
"grad_norm": 0.7629134654998779,
|
| 84 |
+
"learning_rate": 0.0001826238774315995,
|
| 85 |
+
"loss": 0.9457,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.6517311608961304,
|
| 90 |
+
"grad_norm": 0.8157823085784912,
|
| 91 |
+
"learning_rate": 0.00017924768419510904,
|
| 92 |
+
"loss": 0.8539,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.7060420909708078,
|
| 97 |
+
"grad_norm": 0.7475631237030029,
|
| 98 |
+
"learning_rate": 0.0001756092012685749,
|
| 99 |
+
"loss": 0.82,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.7603530210454854,
|
| 104 |
+
"grad_norm": 0.6592528223991394,
|
| 105 |
+
"learning_rate": 0.000171720471105587,
|
| 106 |
+
"loss": 0.8846,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.814663951120163,
|
| 111 |
+
"grad_norm": 0.6989027857780457,
|
| 112 |
+
"learning_rate": 0.00016759436441447545,
|
| 113 |
+
"loss": 0.8367,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.8689748811948405,
|
| 118 |
+
"grad_norm": 0.7253873348236084,
|
| 119 |
+
"learning_rate": 0.00016324453755953773,
|
| 120 |
+
"loss": 0.8068,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.923285811269518,
|
| 125 |
+
"grad_norm": 0.7640873193740845,
|
| 126 |
+
"learning_rate": 0.00015868538736194427,
|
| 127 |
+
"loss": 0.8169,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.9775967413441955,
|
| 132 |
+
"grad_norm": 0.7669989466667175,
|
| 133 |
+
"learning_rate": 0.00015393200344991995,
|
| 134 |
+
"loss": 0.8355,
|
| 135 |
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0271554650373387,
|
| 139 |
+
"grad_norm": 0.7532988786697388,
|
| 140 |
+
"learning_rate": 0.0001490001183159105,
|
| 141 |
+
"loss": 0.7339,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0814663951120163,
|
| 146 |
+
"grad_norm": 0.7974510192871094,
|
| 147 |
+
"learning_rate": 0.0001439060552460318,
|
| 148 |
+
"loss": 0.8186,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.1357773251866938,
|
| 153 |
+
"grad_norm": 0.9017219543457031,
|
| 154 |
+
"learning_rate": 0.0001386666742941419,
|
| 155 |
+
"loss": 0.775,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.1900882552613714,
|
| 160 |
+
"grad_norm": 0.8205109238624573,
|
| 161 |
+
"learning_rate": 0.00013329931647934883,
|
| 162 |
+
"loss": 0.7421,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.2443991853360488,
|
| 167 |
+
"grad_norm": 0.866692066192627,
|
| 168 |
+
"learning_rate": 0.0001278217463916453,
|
| 169 |
+
"loss": 0.7113,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.2987101154107263,
|
| 174 |
+
"grad_norm": 0.8832337856292725,
|
| 175 |
+
"learning_rate": 0.00012225209339563145,
|
| 176 |
+
"loss": 0.7545,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.353021045485404,
|
| 181 |
+
"grad_norm": 1.0796443223953247,
|
| 182 |
+
"learning_rate": 0.00011660879162692675,
|
| 183 |
+
"loss": 0.7085,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.4073319755600815,
|
| 188 |
+
"grad_norm": 0.9231683015823364,
|
| 189 |
+
"learning_rate": 0.00011091051897986678,
|
| 190 |
+
"loss": 0.7168,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.461642905634759,
|
| 195 |
+
"grad_norm": 0.8881363272666931,
|
| 196 |
+
"learning_rate": 0.00010517613528842097,
|
| 197 |
+
"loss": 0.7606,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.5159538357094364,
|
| 202 |
+
"grad_norm": 0.8930597901344299,
|
| 203 |
+
"learning_rate": 9.942461990493625e-05,
|
| 204 |
+
"loss": 0.6926,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.570264765784114,
|
| 209 |
+
"grad_norm": 1.0270030498504639,
|
| 210 |
+
"learning_rate": 9.367500888330545e-05,
|
| 211 |
+
"loss": 0.7571,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.6245756958587916,
|
| 216 |
+
"grad_norm": 0.8959159255027771,
|
| 217 |
+
"learning_rate": 8.79463319744677e-05,
|
| 218 |
+
"loss": 0.7786,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.6788866259334692,
|
| 223 |
+
"grad_norm": 0.8595919013023376,
|
| 224 |
+
"learning_rate": 8.225754964277018e-05,
|
| 225 |
+
"loss": 0.6935,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.7331975560081467,
|
| 230 |
+
"grad_norm": 0.953175961971283,
|
| 231 |
+
"learning_rate": 7.662749031165092e-05,
|
| 232 |
+
"loss": 0.6901,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.787508486082824,
|
| 237 |
+
"grad_norm": 0.985431969165802,
|
| 238 |
+
"learning_rate": 7.107478804634325e-05,
|
| 239 |
+
"loss": 0.7101,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.8418194161575017,
|
| 244 |
+
"grad_norm": 1.0016827583312988,
|
| 245 |
+
"learning_rate": 6.561782087985681e-05,
|
| 246 |
+
"loss": 0.707,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.8961303462321792,
|
| 251 |
+
"grad_norm": 0.9732582569122314,
|
| 252 |
+
"learning_rate": 6.02746499863599e-05,
|
| 253 |
+
"loss": 0.7426,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.9504412763068566,
|
| 258 |
+
"grad_norm": 0.9253762364387512,
|
| 259 |
+
"learning_rate": 5.506295990328385e-05,
|
| 260 |
+
"loss": 0.7273,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.0,
|
| 265 |
+
"grad_norm": 2.792293071746826,
|
| 266 |
+
"learning_rate": 5.000000000000002e-05,
|
| 267 |
+
"loss": 0.7256,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.0543109300746774,
|
| 272 |
+
"grad_norm": 0.9254827499389648,
|
| 273 |
+
"learning_rate": 4.510252738679136e-05,
|
| 274 |
+
"loss": 0.6432,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.108621860149355,
|
| 279 |
+
"grad_norm": 1.0876941680908203,
|
| 280 |
+
"learning_rate": 4.038675145307747e-05,
|
| 281 |
+
"loss": 0.6256,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.1629327902240325,
|
| 286 |
+
"grad_norm": 0.916249692440033,
|
| 287 |
+
"learning_rate": 3.5868280218455796e-05,
|
| 288 |
+
"loss": 0.6442,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.2172437202987103,
|
| 293 |
+
"grad_norm": 0.9240853190422058,
|
| 294 |
+
"learning_rate": 3.1562068674124344e-05,
|
| 295 |
+
"loss": 0.5883,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.2715546503733877,
|
| 300 |
+
"grad_norm": 1.2008038759231567,
|
| 301 |
+
"learning_rate": 2.7482369285662378e-05,
|
| 302 |
+
"loss": 0.6987,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.325865580448065,
|
| 307 |
+
"grad_norm": 1.2723044157028198,
|
| 308 |
+
"learning_rate": 2.364268482099218e-05,
|
| 309 |
+
"loss": 0.708,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.380176510522743,
|
| 314 |
+
"grad_norm": 0.9695908427238464,
|
| 315 |
+
"learning_rate": 2.0055723659649904e-05,
|
| 316 |
+
"loss": 0.6782,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.43448744059742,
|
| 321 |
+
"grad_norm": 1.044391393661499,
|
| 322 |
+
"learning_rate": 1.6733357731279377e-05,
|
| 323 |
+
"loss": 0.5803,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.4887983706720975,
|
| 328 |
+
"grad_norm": 0.9964624643325806,
|
| 329 |
+
"learning_rate": 1.368658322256311e-05,
|
| 330 |
+
"loss": 0.6112,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.5431093007467753,
|
| 335 |
+
"grad_norm": 1.004639744758606,
|
| 336 |
+
"learning_rate": 1.0925484182639467e-05,
|
| 337 |
+
"loss": 0.6322,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.5974202308214527,
|
| 342 |
+
"grad_norm": 1.1456069946289062,
|
| 343 |
+
"learning_rate": 8.45919914746337e-06,
|
| 344 |
+
"loss": 0.5633,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.6517311608961305,
|
| 349 |
+
"grad_norm": 1.1862763166427612,
|
| 350 |
+
"learning_rate": 6.2958908935752955e-06,
|
| 351 |
+
"loss": 0.5859,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.706042090970808,
|
| 356 |
+
"grad_norm": 1.1233826875686646,
|
| 357 |
+
"learning_rate": 4.442719421385922e-06,
|
| 358 |
+
"loss": 0.6147,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.7603530210454856,
|
| 363 |
+
"grad_norm": 1.0159374475479126,
|
| 364 |
+
"learning_rate": 2.905818257394799e-06,
|
| 365 |
+
"loss": 0.5829,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.814663951120163,
|
| 370 |
+
"grad_norm": 1.053791880607605,
|
| 371 |
+
"learning_rate": 1.6902741537767609e-06,
|
| 372 |
+
"loss": 0.5938,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.8689748811948403,
|
| 377 |
+
"grad_norm": 1.0928566455841064,
|
| 378 |
+
"learning_rate": 8.00110252525299e-07,
|
| 379 |
+
"loss": 0.6136,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.923285811269518,
|
| 384 |
+
"grad_norm": 1.1599104404449463,
|
| 385 |
+
"learning_rate": 2.382727698752474e-07,
|
| 386 |
+
"loss": 0.6389,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.9775967413441955,
|
| 391 |
+
"grad_norm": 1.2020913362503052,
|
| 392 |
+
"learning_rate": 6.621245075910665e-09,
|
| 393 |
+
"loss": 0.6719,
|
| 394 |
+
"step": 550
|
| 395 |
}
|
| 396 |
],
|
| 397 |
"logging_steps": 10,
|
| 398 |
+
"max_steps": 552,
|
| 399 |
"num_input_tokens_seen": 0,
|
| 400 |
+
"num_train_epochs": 3,
|
| 401 |
"save_steps": 500,
|
| 402 |
"stateful_callbacks": {
|
| 403 |
"TrainerControl": {
|
|
|
|
| 411 |
"attributes": {}
|
| 412 |
}
|
| 413 |
},
|
| 414 |
+
"total_flos": 4322859040948224.0,
|
| 415 |
"train_batch_size": 1,
|
| 416 |
"trial_name": null,
|
| 417 |
"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 5624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75132bb50a07de61eeb928311e97947df98a7dedcfa8b9670cb9777490844360
|
| 3 |
size 5624
|