Upload folder using huggingface_hub
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 +339 -51
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -19,12 +19,12 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
| 22 |
"o_proj",
|
| 23 |
-
"up_proj",
|
| 24 |
"q_proj",
|
| 25 |
"gate_proj",
|
| 26 |
-
"v_proj",
|
| 27 |
"k_proj",
|
|
|
|
| 28 |
"down_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"v_proj",
|
| 23 |
"o_proj",
|
|
|
|
| 24 |
"q_proj",
|
| 25 |
"gate_proj",
|
|
|
|
| 26 |
"k_proj",
|
| 27 |
+
"up_proj",
|
| 28 |
"down_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 276869160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dd67baec71aece20a60155a6101783007b9913a5959740bb42fb8d6b6630984
|
| 3 |
size 276869160
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 553854714
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8077feaa96893fb650dcb9656796c694c4648b7c916165b633cde8bf4e155f95
|
| 3 |
size 553854714
|
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 sha256:76d7c7f54fc5396598b8785e4b837226cd9d977162fd91a5dbb7b9db4b5e5932
|
| 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 sha256:125d43444f1813249da3606d71ed977ab54afa10359eef2e59ffd6fef0ad576c
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 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,
|
|
@@ -11,154 +11,442 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 0.04,
|
| 13 |
"learning_rate": 0.0,
|
| 14 |
-
"loss": 1.
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.08,
|
| 19 |
"learning_rate": 0.0,
|
| 20 |
-
"loss": 2.
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.12,
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss": 2.
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.16,
|
| 31 |
-
"learning_rate": 1.
|
| 32 |
-
"loss": 2.
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.21,
|
| 37 |
-
"learning_rate": 1.
|
| 38 |
-
"loss": 2.
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.25,
|
| 43 |
-
"learning_rate": 1.
|
| 44 |
-
"loss": 2.
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.29,
|
| 49 |
-
"learning_rate": 1.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.33,
|
| 55 |
-
"learning_rate": 1.
|
| 56 |
-
"loss": 2.
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.37,
|
| 61 |
-
"learning_rate": 1.
|
| 62 |
-
"loss": 2.
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.41,
|
| 67 |
-
"learning_rate": 1.
|
| 68 |
-
"loss": 2.
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.45,
|
| 73 |
-
"learning_rate": 1.
|
| 74 |
-
"loss": 2.
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.49,
|
| 79 |
-
"learning_rate": 1.
|
| 80 |
-
"loss": 2.
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.53,
|
| 85 |
-
"learning_rate": 1.
|
| 86 |
-
"loss": 1.
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.57,
|
| 91 |
-
"learning_rate": 1.
|
| 92 |
-
"loss":
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.62,
|
| 97 |
-
"learning_rate": 1.
|
| 98 |
-
"loss": 2.
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.66,
|
| 103 |
-
"learning_rate":
|
| 104 |
-
"loss": 2.
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.7,
|
| 109 |
-
"learning_rate":
|
| 110 |
-
"loss": 2.
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.74,
|
| 115 |
-
"learning_rate":
|
| 116 |
-
"loss": 2.
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.78,
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 1.
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.82,
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss": 2.
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.86,
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 2.
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.9,
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss": 2.
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.94,
|
| 145 |
-
"learning_rate": 1.
|
| 146 |
-
"loss": 2.
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.98,
|
| 151 |
-
"learning_rate": 1.
|
| 152 |
-
"loss": 2.
|
| 153 |
"step": 48
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 154 |
}
|
| 155 |
],
|
| 156 |
"logging_steps": 2,
|
| 157 |
-
"max_steps":
|
| 158 |
"num_input_tokens_seen": 0,
|
| 159 |
-
"num_train_epochs":
|
| 160 |
"save_steps": 500,
|
| 161 |
-
"total_flos":
|
| 162 |
"train_batch_size": 1,
|
| 163 |
"trial_name": null,
|
| 164 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.953846153846154,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 144,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 0.04,
|
| 13 |
"learning_rate": 0.0,
|
| 14 |
+
"loss": 1.8359,
|
| 15 |
"step": 2
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.08,
|
| 19 |
"learning_rate": 0.0,
|
| 20 |
+
"loss": 2.0644,
|
| 21 |
"step": 4
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.12,
|
| 25 |
+
"learning_rate": 4.000000000000001e-06,
|
| 26 |
+
"loss": 2.265,
|
| 27 |
"step": 6
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.16,
|
| 31 |
+
"learning_rate": 1.2e-05,
|
| 32 |
+
"loss": 2.2443,
|
| 33 |
"step": 8
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.21,
|
| 37 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 38 |
+
"loss": 2.4286,
|
| 39 |
"step": 10
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.25,
|
| 43 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 44 |
+
"loss": 2.704,
|
| 45 |
"step": 12
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.29,
|
| 49 |
+
"learning_rate": 1.999744599547812e-05,
|
| 50 |
+
"loss": 1.9173,
|
| 51 |
"step": 14
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.33,
|
| 55 |
+
"learning_rate": 1.99770217861636e-05,
|
| 56 |
+
"loss": 2.1814,
|
| 57 |
"step": 16
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.37,
|
| 61 |
+
"learning_rate": 1.9936215093023884e-05,
|
| 62 |
+
"loss": 2.3203,
|
| 63 |
"step": 18
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.41,
|
| 67 |
+
"learning_rate": 1.9875109281794828e-05,
|
| 68 |
+
"loss": 2.1449,
|
| 69 |
"step": 20
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.45,
|
| 73 |
+
"learning_rate": 1.9793829188147406e-05,
|
| 74 |
+
"loss": 2.2452,
|
| 75 |
"step": 22
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.49,
|
| 79 |
+
"learning_rate": 1.9692540862655587e-05,
|
| 80 |
+
"loss": 2.4673,
|
| 81 |
"step": 24
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 0.53,
|
| 85 |
+
"learning_rate": 1.9571451231564523e-05,
|
| 86 |
+
"loss": 1.9931,
|
| 87 |
"step": 26
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 0.57,
|
| 91 |
+
"learning_rate": 1.9430807674052092e-05,
|
| 92 |
+
"loss": 2.2818,
|
| 93 |
"step": 28
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.62,
|
| 97 |
+
"learning_rate": 1.9270897516847406e-05,
|
| 98 |
+
"loss": 2.1631,
|
| 99 |
"step": 30
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.66,
|
| 103 |
+
"learning_rate": 1.9092047447238775e-05,
|
| 104 |
+
"loss": 2.1008,
|
| 105 |
"step": 32
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 0.7,
|
| 109 |
+
"learning_rate": 1.8894622845670282e-05,
|
| 110 |
+
"loss": 2.1732,
|
| 111 |
"step": 34
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.74,
|
| 115 |
+
"learning_rate": 1.86790270392905e-05,
|
| 116 |
+
"loss": 2.4445,
|
| 117 |
"step": 36
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 0.78,
|
| 121 |
+
"learning_rate": 1.8445700477978207e-05,
|
| 122 |
+
"loss": 1.7119,
|
| 123 |
"step": 38
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.82,
|
| 127 |
+
"learning_rate": 1.8195119834528535e-05,
|
| 128 |
+
"loss": 2.056,
|
| 129 |
"step": 40
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 0.86,
|
| 133 |
+
"learning_rate": 1.792779703083777e-05,
|
| 134 |
+
"loss": 2.1947,
|
| 135 |
"step": 42
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.9,
|
| 139 |
+
"learning_rate": 1.764427819207624e-05,
|
| 140 |
+
"loss": 2.2409,
|
| 141 |
"step": 44
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.94,
|
| 145 |
+
"learning_rate": 1.734514253098589e-05,
|
| 146 |
+
"loss": 2.0962,
|
| 147 |
"step": 46
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.98,
|
| 151 |
+
"learning_rate": 1.7031001164581828e-05,
|
| 152 |
+
"loss": 2.347,
|
| 153 |
"step": 48
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.03,
|
| 157 |
+
"learning_rate": 1.670249586567531e-05,
|
| 158 |
+
"loss": 1.9654,
|
| 159 |
+
"step": 50
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.07,
|
| 163 |
+
"learning_rate": 1.636029775176862e-05,
|
| 164 |
+
"loss": 1.918,
|
| 165 |
+
"step": 52
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.11,
|
| 169 |
+
"learning_rate": 1.6005105914000508e-05,
|
| 170 |
+
"loss": 2.0105,
|
| 171 |
+
"step": 54
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.15,
|
| 175 |
+
"learning_rate": 1.5637645988943008e-05,
|
| 176 |
+
"loss": 2.2175,
|
| 177 |
+
"step": 56
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.19,
|
| 181 |
+
"learning_rate": 1.5258668676167548e-05,
|
| 182 |
+
"loss": 1.8879,
|
| 183 |
+
"step": 58
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.23,
|
| 187 |
+
"learning_rate": 1.48689482046087e-05,
|
| 188 |
+
"loss": 2.2379,
|
| 189 |
+
"step": 60
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.27,
|
| 193 |
+
"learning_rate": 1.4469280750858854e-05,
|
| 194 |
+
"loss": 1.9181,
|
| 195 |
+
"step": 62
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.31,
|
| 199 |
+
"learning_rate": 1.4060482812625055e-05,
|
| 200 |
+
"loss": 1.9695,
|
| 201 |
+
"step": 64
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.35,
|
| 205 |
+
"learning_rate": 1.3643389540670963e-05,
|
| 206 |
+
"loss": 2.1585,
|
| 207 |
+
"step": 66
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.39,
|
| 211 |
+
"learning_rate": 1.3218853032651719e-05,
|
| 212 |
+
"loss": 2.2469,
|
| 213 |
+
"step": 68
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.44,
|
| 217 |
+
"learning_rate": 1.2787740592327232e-05,
|
| 218 |
+
"loss": 2.158,
|
| 219 |
+
"step": 70
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.48,
|
| 223 |
+
"learning_rate": 1.2350932957710322e-05,
|
| 224 |
+
"loss": 2.1121,
|
| 225 |
+
"step": 72
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.52,
|
| 229 |
+
"learning_rate": 1.1909322501769407e-05,
|
| 230 |
+
"loss": 1.9493,
|
| 231 |
+
"step": 74
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.56,
|
| 235 |
+
"learning_rate": 1.1463811409361667e-05,
|
| 236 |
+
"loss": 1.9611,
|
| 237 |
+
"step": 76
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.6,
|
| 241 |
+
"learning_rate": 1.1015309834121083e-05,
|
| 242 |
+
"loss": 2.182,
|
| 243 |
+
"step": 78
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.64,
|
| 247 |
+
"learning_rate": 1.05647340390667e-05,
|
| 248 |
+
"loss": 2.0111,
|
| 249 |
+
"step": 80
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.68,
|
| 253 |
+
"learning_rate": 1.01130045247298e-05,
|
| 254 |
+
"loss": 2.2589,
|
| 255 |
+
"step": 82
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.72,
|
| 259 |
+
"learning_rate": 9.661044148624038e-06,
|
| 260 |
+
"loss": 2.0812,
|
| 261 |
+
"step": 84
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.76,
|
| 265 |
+
"learning_rate": 9.209776239900453e-06,
|
| 266 |
+
"loss": 2.0365,
|
| 267 |
+
"step": 86
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.81,
|
| 271 |
+
"learning_rate": 8.76012271303888e-06,
|
| 272 |
+
"loss": 2.09,
|
| 273 |
+
"step": 88
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.85,
|
| 277 |
+
"learning_rate": 8.313002184429529e-06,
|
| 278 |
+
"loss": 2.0565,
|
| 279 |
+
"step": 90
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.89,
|
| 283 |
+
"learning_rate": 7.869328095692313e-06,
|
| 284 |
+
"loss": 2.1456,
|
| 285 |
+
"step": 92
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.93,
|
| 289 |
+
"learning_rate": 7.430006847567972e-06,
|
| 290 |
+
"loss": 1.9832,
|
| 291 |
+
"step": 94
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.97,
|
| 295 |
+
"learning_rate": 6.995935948193294e-06,
|
| 296 |
+
"loss": 2.1603,
|
| 297 |
+
"step": 96
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.01,
|
| 301 |
+
"learning_rate": 6.568002179543409e-06,
|
| 302 |
+
"loss": 2.0932,
|
| 303 |
+
"step": 98
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.05,
|
| 307 |
+
"learning_rate": 6.147079785787038e-06,
|
| 308 |
+
"loss": 2.0403,
|
| 309 |
+
"step": 100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.09,
|
| 313 |
+
"learning_rate": 5.7340286872557515e-06,
|
| 314 |
+
"loss": 1.9059,
|
| 315 |
+
"step": 102
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.13,
|
| 319 |
+
"learning_rate": 5.329692723675994e-06,
|
| 320 |
+
"loss": 2.1737,
|
| 321 |
+
"step": 104
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.17,
|
| 325 |
+
"learning_rate": 4.934897930252887e-06,
|
| 326 |
+
"loss": 2.0443,
|
| 327 |
+
"step": 106
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.22,
|
| 331 |
+
"learning_rate": 4.550450850127626e-06,
|
| 332 |
+
"loss": 2.0404,
|
| 333 |
+
"step": 108
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.26,
|
| 337 |
+
"learning_rate": 4.177136886656067e-06,
|
| 338 |
+
"loss": 1.9976,
|
| 339 |
+
"step": 110
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.3,
|
| 343 |
+
"learning_rate": 3.815718698874672e-06,
|
| 344 |
+
"loss": 1.8335,
|
| 345 |
+
"step": 112
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.34,
|
| 349 |
+
"learning_rate": 3.466934643431795e-06,
|
| 350 |
+
"loss": 2.2607,
|
| 351 |
+
"step": 114
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.38,
|
| 355 |
+
"learning_rate": 3.1314972661673572e-06,
|
| 356 |
+
"loss": 2.098,
|
| 357 |
+
"step": 116
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.42,
|
| 361 |
+
"learning_rate": 2.8100918464225304e-06,
|
| 362 |
+
"loss": 1.9934,
|
| 363 |
+
"step": 118
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.46,
|
| 367 |
+
"learning_rate": 2.5033749970533015e-06,
|
| 368 |
+
"loss": 2.0058,
|
| 369 |
+
"step": 120
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.5,
|
| 373 |
+
"learning_rate": 2.211973323008041e-06,
|
| 374 |
+
"loss": 2.0931,
|
| 375 |
+
"step": 122
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.54,
|
| 379 |
+
"learning_rate": 1.936482141209486e-06,
|
| 380 |
+
"loss": 1.763,
|
| 381 |
+
"step": 124
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.58,
|
| 385 |
+
"learning_rate": 1.6774642643563955e-06,
|
| 386 |
+
"loss": 1.9877,
|
| 387 |
+
"step": 126
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.63,
|
| 391 |
+
"learning_rate": 1.4354488511294418e-06,
|
| 392 |
+
"loss": 2.2412,
|
| 393 |
+
"step": 128
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.67,
|
| 397 |
+
"learning_rate": 1.2109303251503434e-06,
|
| 398 |
+
"loss": 2.067,
|
| 399 |
+
"step": 130
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.71,
|
| 403 |
+
"learning_rate": 1.0043673649027519e-06,
|
| 404 |
+
"loss": 2.123,
|
| 405 |
+
"step": 132
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.75,
|
| 409 |
+
"learning_rate": 8.161819666783888e-07,
|
| 410 |
+
"loss": 2.0428,
|
| 411 |
+
"step": 134
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.79,
|
| 415 |
+
"learning_rate": 6.467585824627886e-07,
|
| 416 |
+
"loss": 1.8645,
|
| 417 |
+
"step": 136
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.83,
|
| 421 |
+
"learning_rate": 4.964433345219354e-07,
|
| 422 |
+
"loss": 2.1057,
|
| 423 |
+
"step": 138
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.87,
|
| 427 |
+
"learning_rate": 3.6554330829429716e-07,
|
| 428 |
+
"loss": 2.0721,
|
| 429 |
+
"step": 140
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.91,
|
| 433 |
+
"learning_rate": 2.5432592503288e-07,
|
| 434 |
+
"loss": 2.1623,
|
| 435 |
+
"step": 142
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.95,
|
| 439 |
+
"learning_rate": 1.630183954789233e-07,
|
| 440 |
+
"loss": 2.2136,
|
| 441 |
+
"step": 144
|
| 442 |
}
|
| 443 |
],
|
| 444 |
"logging_steps": 2,
|
| 445 |
+
"max_steps": 144,
|
| 446 |
"num_input_tokens_seen": 0,
|
| 447 |
+
"num_train_epochs": 3,
|
| 448 |
"save_steps": 500,
|
| 449 |
+
"total_flos": 1.275170572624896e+16,
|
| 450 |
"train_batch_size": 1,
|
| 451 |
"trial_name": null,
|
| 452 |
"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 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c52b3fc8b85d6cfe69705aad5966ccce8b92bad58312e1a1a9c7566b8df64b99
|
| 3 |
size 4728
|