Upload fine-tuned Llama model for order analysis
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +408 -114
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -21,12 +21,12 @@
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"q_proj",
|
|
|
|
| 24 |
"down_proj",
|
| 25 |
-
"k_proj",
|
| 26 |
"up_proj",
|
| 27 |
-
"o_proj",
|
| 28 |
"v_proj",
|
| 29 |
-
"gate_proj"
|
|
|
|
| 30 |
],
|
| 31 |
"task_type": "CAUSAL_LM",
|
| 32 |
"use_dora": false,
|
|
|
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
"q_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
"down_proj",
|
|
|
|
| 26 |
"up_proj",
|
|
|
|
| 27 |
"v_proj",
|
| 28 |
+
"gate_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 22573704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f387711e63c8ab74a59664fd7c1a08083964c4f023e8f9c181ad0376b5caf698
|
| 3 |
size 22573704
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 45276986
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e545c92e8a29e73b2a708438df82a773c90ac81fb95e3d77084344d71129ce4c
|
| 3 |
size 45276986
|
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 sha256:134bd3caf7fa7a05a76100cdc2365343eb2f59dc0c82afde6756800f9549f1f9
|
| 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:d154ed8833a95231b13495341f4d5eda62192ea0a3a9aa2af2ce186e4e571f34
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -3,210 +3,504 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 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": 2.
|
| 16 |
"step": 20
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 40
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 60
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 80
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 1.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 100
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 8.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 120
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm": 1.
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 140
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 160
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 180
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 200
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 220
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm": 1.
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 240
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 260
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 280
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"grad_norm": 1.
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 300
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 0.
|
| 118 |
-
"grad_norm": 1.
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 320
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"grad_norm": 1.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 340
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"grad_norm": 1.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 360
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"grad_norm": 1.
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 380
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch": 0.
|
| 146 |
-
"grad_norm": 1.
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 400
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 0.
|
| 153 |
-
"grad_norm":
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 420
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 0.
|
| 160 |
-
"grad_norm": 1.
|
| 161 |
-
"learning_rate":
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 440
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch": 0.
|
| 167 |
-
"grad_norm": 1.
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 460
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"grad_norm": 1.
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 480
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"grad_norm": 1.
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 500
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch": 0.
|
| 188 |
-
"grad_norm": 1.
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 520
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"grad_norm": 1.
|
| 196 |
-
"learning_rate":
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 540
|
| 199 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 200 |
{
|
| 201 |
"epoch": 1.0,
|
| 202 |
-
"grad_norm": 1.
|
| 203 |
"learning_rate": 0.0,
|
| 204 |
-
"loss": 0.
|
| 205 |
-
"step":
|
| 206 |
}
|
| 207 |
],
|
| 208 |
"logging_steps": 20,
|
| 209 |
-
"max_steps":
|
| 210 |
"num_input_tokens_seen": 0,
|
| 211 |
"num_train_epochs": 1,
|
| 212 |
"save_steps": 50,
|
|
@@ -223,7 +517,7 @@
|
|
| 223 |
}
|
| 224 |
},
|
| 225 |
"total_flos": 8419093040332800.0,
|
| 226 |
-
"train_batch_size":
|
| 227 |
"trial_name": null,
|
| 228 |
"trial_params": null
|
| 229 |
}
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.014285714285714285,
|
| 13 |
+
"grad_norm": 2.279883623123169,
|
| 14 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 15 |
+
"loss": 2.5982,
|
| 16 |
"step": 20
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.02857142857142857,
|
| 20 |
+
"grad_norm": 1.5012547969818115,
|
| 21 |
+
"learning_rate": 2.857142857142857e-05,
|
| 22 |
+
"loss": 2.3142,
|
| 23 |
"step": 40
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.04285714285714286,
|
| 27 |
+
"grad_norm": 1.7552474737167358,
|
| 28 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 29 |
+
"loss": 1.7833,
|
| 30 |
"step": 60
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.05714285714285714,
|
| 34 |
+
"grad_norm": 1.8790605068206787,
|
| 35 |
+
"learning_rate": 5.714285714285714e-05,
|
| 36 |
+
"loss": 1.2697,
|
| 37 |
"step": 80
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.07142857142857142,
|
| 41 |
+
"grad_norm": 1.6815859079360962,
|
| 42 |
+
"learning_rate": 7.142857142857143e-05,
|
| 43 |
+
"loss": 1.049,
|
| 44 |
"step": 100
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.08571428571428572,
|
| 48 |
+
"grad_norm": 1.561714768409729,
|
| 49 |
+
"learning_rate": 8.571428571428571e-05,
|
| 50 |
+
"loss": 0.9491,
|
| 51 |
"step": 120
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.1,
|
| 55 |
+
"grad_norm": 1.4625489711761475,
|
| 56 |
+
"learning_rate": 0.0001,
|
| 57 |
+
"loss": 0.8847,
|
| 58 |
"step": 140
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.11428571428571428,
|
| 62 |
+
"grad_norm": 2.1226258277893066,
|
| 63 |
+
"learning_rate": 9.841269841269841e-05,
|
| 64 |
+
"loss": 0.8167,
|
| 65 |
"step": 160
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.12857142857142856,
|
| 69 |
+
"grad_norm": 1.3709640502929688,
|
| 70 |
+
"learning_rate": 9.682539682539682e-05,
|
| 71 |
+
"loss": 0.7321,
|
| 72 |
"step": 180
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.14285714285714285,
|
| 76 |
+
"grad_norm": 1.2312499284744263,
|
| 77 |
+
"learning_rate": 9.523809523809524e-05,
|
| 78 |
+
"loss": 0.693,
|
| 79 |
"step": 200
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.15714285714285714,
|
| 83 |
+
"grad_norm": 1.4416557550430298,
|
| 84 |
+
"learning_rate": 9.365079365079366e-05,
|
| 85 |
+
"loss": 0.6389,
|
| 86 |
"step": 220
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.17142857142857143,
|
| 90 |
+
"grad_norm": 1.7498096227645874,
|
| 91 |
+
"learning_rate": 9.206349206349206e-05,
|
| 92 |
+
"loss": 0.6421,
|
| 93 |
"step": 240
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.18571428571428572,
|
| 97 |
+
"grad_norm": 1.6708226203918457,
|
| 98 |
+
"learning_rate": 9.047619047619048e-05,
|
| 99 |
+
"loss": 0.6309,
|
| 100 |
"step": 260
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.2,
|
| 104 |
+
"grad_norm": 1.7032530307769775,
|
| 105 |
+
"learning_rate": 8.888888888888889e-05,
|
| 106 |
+
"loss": 0.6388,
|
| 107 |
"step": 280
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.21428571428571427,
|
| 111 |
+
"grad_norm": 1.1614326238632202,
|
| 112 |
+
"learning_rate": 8.730158730158731e-05,
|
| 113 |
+
"loss": 0.5888,
|
| 114 |
"step": 300
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.22857142857142856,
|
| 118 |
+
"grad_norm": 1.7418193817138672,
|
| 119 |
+
"learning_rate": 8.571428571428571e-05,
|
| 120 |
+
"loss": 0.5878,
|
| 121 |
"step": 320
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.24285714285714285,
|
| 125 |
+
"grad_norm": 1.3387174606323242,
|
| 126 |
+
"learning_rate": 8.412698412698413e-05,
|
| 127 |
+
"loss": 0.5962,
|
| 128 |
"step": 340
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.2571428571428571,
|
| 132 |
+
"grad_norm": 1.1994811296463013,
|
| 133 |
+
"learning_rate": 8.253968253968255e-05,
|
| 134 |
+
"loss": 0.6093,
|
| 135 |
"step": 360
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.2714285714285714,
|
| 139 |
+
"grad_norm": 1.5204330682754517,
|
| 140 |
+
"learning_rate": 8.095238095238096e-05,
|
| 141 |
+
"loss": 0.6045,
|
| 142 |
"step": 380
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.2857142857142857,
|
| 146 |
+
"grad_norm": 1.2687711715698242,
|
| 147 |
+
"learning_rate": 7.936507936507937e-05,
|
| 148 |
+
"loss": 0.5934,
|
| 149 |
"step": 400
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.3,
|
| 153 |
+
"grad_norm": 1.4332380294799805,
|
| 154 |
+
"learning_rate": 7.777777777777778e-05,
|
| 155 |
+
"loss": 0.5883,
|
| 156 |
"step": 420
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.3142857142857143,
|
| 160 |
+
"grad_norm": 1.5756443738937378,
|
| 161 |
+
"learning_rate": 7.619047619047618e-05,
|
| 162 |
+
"loss": 0.5605,
|
| 163 |
"step": 440
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.32857142857142857,
|
| 167 |
+
"grad_norm": 1.405213713645935,
|
| 168 |
+
"learning_rate": 7.460317460317461e-05,
|
| 169 |
+
"loss": 0.5993,
|
| 170 |
"step": 460
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.34285714285714286,
|
| 174 |
+
"grad_norm": 1.480230450630188,
|
| 175 |
+
"learning_rate": 7.301587301587302e-05,
|
| 176 |
+
"loss": 0.5896,
|
| 177 |
"step": 480
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.35714285714285715,
|
| 181 |
+
"grad_norm": 1.472406029701233,
|
| 182 |
+
"learning_rate": 7.142857142857143e-05,
|
| 183 |
+
"loss": 0.5661,
|
| 184 |
"step": 500
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 0.37142857142857144,
|
| 188 |
+
"grad_norm": 1.408607006072998,
|
| 189 |
+
"learning_rate": 6.984126984126984e-05,
|
| 190 |
+
"loss": 0.545,
|
| 191 |
"step": 520
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 0.38571428571428573,
|
| 195 |
+
"grad_norm": 1.3194152116775513,
|
| 196 |
+
"learning_rate": 6.825396825396825e-05,
|
| 197 |
+
"loss": 0.5366,
|
| 198 |
"step": 540
|
| 199 |
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4,
|
| 202 |
+
"grad_norm": 1.5078984498977661,
|
| 203 |
+
"learning_rate": 6.666666666666667e-05,
|
| 204 |
+
"loss": 0.5236,
|
| 205 |
+
"step": 560
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.4142857142857143,
|
| 209 |
+
"grad_norm": 1.3387917280197144,
|
| 210 |
+
"learning_rate": 6.507936507936509e-05,
|
| 211 |
+
"loss": 0.5545,
|
| 212 |
+
"step": 580
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.42857142857142855,
|
| 216 |
+
"grad_norm": 1.1835085153579712,
|
| 217 |
+
"learning_rate": 6.349206349206349e-05,
|
| 218 |
+
"loss": 0.563,
|
| 219 |
+
"step": 600
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.44285714285714284,
|
| 223 |
+
"grad_norm": 1.424862027168274,
|
| 224 |
+
"learning_rate": 6.19047619047619e-05,
|
| 225 |
+
"loss": 0.5369,
|
| 226 |
+
"step": 620
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.45714285714285713,
|
| 230 |
+
"grad_norm": 1.3369919061660767,
|
| 231 |
+
"learning_rate": 6.0317460317460316e-05,
|
| 232 |
+
"loss": 0.576,
|
| 233 |
+
"step": 640
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4714285714285714,
|
| 237 |
+
"grad_norm": 1.2523393630981445,
|
| 238 |
+
"learning_rate": 5.873015873015873e-05,
|
| 239 |
+
"loss": 0.5245,
|
| 240 |
+
"step": 660
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4857142857142857,
|
| 244 |
+
"grad_norm": 1.6725609302520752,
|
| 245 |
+
"learning_rate": 5.714285714285714e-05,
|
| 246 |
+
"loss": 0.5047,
|
| 247 |
+
"step": 680
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5,
|
| 251 |
+
"grad_norm": 1.3288273811340332,
|
| 252 |
+
"learning_rate": 5.555555555555556e-05,
|
| 253 |
+
"loss": 0.5396,
|
| 254 |
+
"step": 700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5142857142857142,
|
| 258 |
+
"grad_norm": 1.492069125175476,
|
| 259 |
+
"learning_rate": 5.396825396825397e-05,
|
| 260 |
+
"loss": 0.5099,
|
| 261 |
+
"step": 720
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5285714285714286,
|
| 265 |
+
"grad_norm": 1.508617639541626,
|
| 266 |
+
"learning_rate": 5.2380952380952384e-05,
|
| 267 |
+
"loss": 0.503,
|
| 268 |
+
"step": 740
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.5428571428571428,
|
| 272 |
+
"grad_norm": 1.6115648746490479,
|
| 273 |
+
"learning_rate": 5.0793650793650794e-05,
|
| 274 |
+
"loss": 0.5571,
|
| 275 |
+
"step": 760
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5571428571428572,
|
| 279 |
+
"grad_norm": 1.4812785387039185,
|
| 280 |
+
"learning_rate": 4.9206349206349204e-05,
|
| 281 |
+
"loss": 0.5036,
|
| 282 |
+
"step": 780
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5714285714285714,
|
| 286 |
+
"grad_norm": 1.555457353591919,
|
| 287 |
+
"learning_rate": 4.761904761904762e-05,
|
| 288 |
+
"loss": 0.518,
|
| 289 |
+
"step": 800
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5857142857142857,
|
| 293 |
+
"grad_norm": 1.6743320226669312,
|
| 294 |
+
"learning_rate": 4.603174603174603e-05,
|
| 295 |
+
"loss": 0.523,
|
| 296 |
+
"step": 820
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6,
|
| 300 |
+
"grad_norm": 1.6365365982055664,
|
| 301 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 302 |
+
"loss": 0.5112,
|
| 303 |
+
"step": 840
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6142857142857143,
|
| 307 |
+
"grad_norm": 1.4804445505142212,
|
| 308 |
+
"learning_rate": 4.2857142857142856e-05,
|
| 309 |
+
"loss": 0.5177,
|
| 310 |
+
"step": 860
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6285714285714286,
|
| 314 |
+
"grad_norm": 1.5929114818572998,
|
| 315 |
+
"learning_rate": 4.126984126984127e-05,
|
| 316 |
+
"loss": 0.4895,
|
| 317 |
+
"step": 880
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6428571428571429,
|
| 321 |
+
"grad_norm": 1.512065052986145,
|
| 322 |
+
"learning_rate": 3.968253968253968e-05,
|
| 323 |
+
"loss": 0.5158,
|
| 324 |
+
"step": 900
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6571428571428571,
|
| 328 |
+
"grad_norm": 1.5385123491287231,
|
| 329 |
+
"learning_rate": 3.809523809523809e-05,
|
| 330 |
+
"loss": 0.5188,
|
| 331 |
+
"step": 920
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6714285714285714,
|
| 335 |
+
"grad_norm": 1.7010993957519531,
|
| 336 |
+
"learning_rate": 3.650793650793651e-05,
|
| 337 |
+
"loss": 0.5039,
|
| 338 |
+
"step": 940
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6857142857142857,
|
| 342 |
+
"grad_norm": 1.4756510257720947,
|
| 343 |
+
"learning_rate": 3.492063492063492e-05,
|
| 344 |
+
"loss": 0.5004,
|
| 345 |
+
"step": 960
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7,
|
| 349 |
+
"grad_norm": 1.407616376876831,
|
| 350 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 351 |
+
"loss": 0.4947,
|
| 352 |
+
"step": 980
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.7142857142857143,
|
| 356 |
+
"grad_norm": 1.376063346862793,
|
| 357 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 358 |
+
"loss": 0.4797,
|
| 359 |
+
"step": 1000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7285714285714285,
|
| 363 |
+
"grad_norm": 1.6061830520629883,
|
| 364 |
+
"learning_rate": 3.0158730158730158e-05,
|
| 365 |
+
"loss": 0.4872,
|
| 366 |
+
"step": 1020
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7428571428571429,
|
| 370 |
+
"grad_norm": 1.4005217552185059,
|
| 371 |
+
"learning_rate": 2.857142857142857e-05,
|
| 372 |
+
"loss": 0.4648,
|
| 373 |
+
"step": 1040
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7571428571428571,
|
| 377 |
+
"grad_norm": 1.4235899448394775,
|
| 378 |
+
"learning_rate": 2.6984126984126984e-05,
|
| 379 |
+
"loss": 0.463,
|
| 380 |
+
"step": 1060
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7714285714285715,
|
| 384 |
+
"grad_norm": 1.210481882095337,
|
| 385 |
+
"learning_rate": 2.5396825396825397e-05,
|
| 386 |
+
"loss": 0.4728,
|
| 387 |
+
"step": 1080
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7857142857142857,
|
| 391 |
+
"grad_norm": 1.6099470853805542,
|
| 392 |
+
"learning_rate": 2.380952380952381e-05,
|
| 393 |
+
"loss": 0.485,
|
| 394 |
+
"step": 1100
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8,
|
| 398 |
+
"grad_norm": 1.6083734035491943,
|
| 399 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 400 |
+
"loss": 0.4594,
|
| 401 |
+
"step": 1120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.8142857142857143,
|
| 405 |
+
"grad_norm": 1.350246548652649,
|
| 406 |
+
"learning_rate": 2.0634920634920636e-05,
|
| 407 |
+
"loss": 0.4763,
|
| 408 |
+
"step": 1140
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.8285714285714286,
|
| 412 |
+
"grad_norm": 1.3000835180282593,
|
| 413 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 414 |
+
"loss": 0.4705,
|
| 415 |
+
"step": 1160
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8428571428571429,
|
| 419 |
+
"grad_norm": 1.2059348821640015,
|
| 420 |
+
"learning_rate": 1.746031746031746e-05,
|
| 421 |
+
"loss": 0.4876,
|
| 422 |
+
"step": 1180
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8571428571428571,
|
| 426 |
+
"grad_norm": 1.3652459383010864,
|
| 427 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 428 |
+
"loss": 0.4919,
|
| 429 |
+
"step": 1200
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8714285714285714,
|
| 433 |
+
"grad_norm": 1.451910376548767,
|
| 434 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 435 |
+
"loss": 0.463,
|
| 436 |
+
"step": 1220
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8857142857142857,
|
| 440 |
+
"grad_norm": 1.4704546928405762,
|
| 441 |
+
"learning_rate": 1.2698412698412699e-05,
|
| 442 |
+
"loss": 0.4768,
|
| 443 |
+
"step": 1240
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.9,
|
| 447 |
+
"grad_norm": 1.5009324550628662,
|
| 448 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 449 |
+
"loss": 0.4516,
|
| 450 |
+
"step": 1260
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9142857142857143,
|
| 454 |
+
"grad_norm": 1.5519717931747437,
|
| 455 |
+
"learning_rate": 9.523809523809523e-06,
|
| 456 |
+
"loss": 0.4517,
|
| 457 |
+
"step": 1280
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9285714285714286,
|
| 461 |
+
"grad_norm": 1.5606343746185303,
|
| 462 |
+
"learning_rate": 7.936507936507936e-06,
|
| 463 |
+
"loss": 0.4732,
|
| 464 |
+
"step": 1300
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9428571428571428,
|
| 468 |
+
"grad_norm": 1.3639295101165771,
|
| 469 |
+
"learning_rate": 6.349206349206349e-06,
|
| 470 |
+
"loss": 0.4791,
|
| 471 |
+
"step": 1320
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.9571428571428572,
|
| 475 |
+
"grad_norm": 1.6867655515670776,
|
| 476 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 477 |
+
"loss": 0.4968,
|
| 478 |
+
"step": 1340
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.9714285714285714,
|
| 482 |
+
"grad_norm": 1.4185600280761719,
|
| 483 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 484 |
+
"loss": 0.4902,
|
| 485 |
+
"step": 1360
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9857142857142858,
|
| 489 |
+
"grad_norm": 1.7370814085006714,
|
| 490 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 491 |
+
"loss": 0.4564,
|
| 492 |
+
"step": 1380
|
| 493 |
+
},
|
| 494 |
{
|
| 495 |
"epoch": 1.0,
|
| 496 |
+
"grad_norm": 1.6167285442352295,
|
| 497 |
"learning_rate": 0.0,
|
| 498 |
+
"loss": 0.4652,
|
| 499 |
+
"step": 1400
|
| 500 |
}
|
| 501 |
],
|
| 502 |
"logging_steps": 20,
|
| 503 |
+
"max_steps": 1400,
|
| 504 |
"num_input_tokens_seen": 0,
|
| 505 |
"num_train_epochs": 1,
|
| 506 |
"save_steps": 50,
|
|
|
|
| 517 |
}
|
| 518 |
},
|
| 519 |
"total_flos": 8419093040332800.0,
|
| 520 |
+
"train_batch_size": 2,
|
| 521 |
"trial_name": null,
|
| 522 |
"trial_params": null
|
| 523 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39f98817715f279a5f40c38dd70904c7137598047d2e35bac717a82d7f015fd1
|
| 3 |
size 5560
|