Commit
·
e07dc6f
1
Parent(s):
be0f9b9
End of training
Browse files- pytorch_model.bin +1 -1
- tokenizer.json +14 -2
- trainer_state.json +702 -6
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 105666297
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35fb753e7e3cdca765a1357f59bfef6a95b36d2feb92a5a07d8388f0cf0d33c4
|
| 3 |
size 105666297
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,19 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 2048,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": "BatchLongest",
|
| 11 |
+
"direction": "Right",
|
| 12 |
+
"pad_to_multiple_of": null,
|
| 13 |
+
"pad_id": 1,
|
| 14 |
+
"pad_type_id": 0,
|
| 15 |
+
"pad_token": "[PAD]"
|
| 16 |
+
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
trainer_state.json
CHANGED
|
@@ -1,15 +1,711 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
-
"log_history": [
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"trial_name": null,
|
| 14 |
"trial_params": null
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 50835,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 4.899281990754402e-05,
|
| 13 |
+
"loss": 0.2509,
|
| 14 |
+
"step": 1024
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.1,
|
| 18 |
+
"eval_loss": 0.42676058411598206,
|
| 19 |
+
"eval_runtime": 32.3598,
|
| 20 |
+
"eval_samples_per_second": 106.212,
|
| 21 |
+
"eval_steps_per_second": 3.337,
|
| 22 |
+
"step": 1024
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.2,
|
| 26 |
+
"learning_rate": 4.798563981508803e-05,
|
| 27 |
+
"loss": 0.2521,
|
| 28 |
+
"step": 2048
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.2,
|
| 32 |
+
"eval_loss": 0.4283539652824402,
|
| 33 |
+
"eval_runtime": 32.4193,
|
| 34 |
+
"eval_samples_per_second": 106.017,
|
| 35 |
+
"eval_steps_per_second": 3.331,
|
| 36 |
+
"step": 2048
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.3,
|
| 40 |
+
"learning_rate": 4.697845972263204e-05,
|
| 41 |
+
"loss": 0.2533,
|
| 42 |
+
"step": 3072
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.3,
|
| 46 |
+
"eval_loss": 0.42187923192977905,
|
| 47 |
+
"eval_runtime": 32.3798,
|
| 48 |
+
"eval_samples_per_second": 106.146,
|
| 49 |
+
"eval_steps_per_second": 3.335,
|
| 50 |
+
"step": 3072
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.4,
|
| 54 |
+
"learning_rate": 4.597127963017606e-05,
|
| 55 |
+
"loss": 0.2517,
|
| 56 |
+
"step": 4096
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.4,
|
| 60 |
+
"eval_loss": 0.42451202869415283,
|
| 61 |
+
"eval_runtime": 32.3385,
|
| 62 |
+
"eval_samples_per_second": 106.282,
|
| 63 |
+
"eval_steps_per_second": 3.34,
|
| 64 |
+
"step": 4096
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.5,
|
| 68 |
+
"learning_rate": 4.496409953772008e-05,
|
| 69 |
+
"loss": 0.2512,
|
| 70 |
+
"step": 5120
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.5,
|
| 74 |
+
"eval_loss": 0.42285656929016113,
|
| 75 |
+
"eval_runtime": 32.3235,
|
| 76 |
+
"eval_samples_per_second": 106.331,
|
| 77 |
+
"eval_steps_per_second": 3.341,
|
| 78 |
+
"step": 5120
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.6,
|
| 82 |
+
"learning_rate": 4.3956919445264097e-05,
|
| 83 |
+
"loss": 0.2506,
|
| 84 |
+
"step": 6144
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.6,
|
| 88 |
+
"eval_loss": 0.4190705716609955,
|
| 89 |
+
"eval_runtime": 32.4437,
|
| 90 |
+
"eval_samples_per_second": 105.937,
|
| 91 |
+
"eval_steps_per_second": 3.329,
|
| 92 |
+
"step": 6144
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.71,
|
| 96 |
+
"learning_rate": 4.294973935280811e-05,
|
| 97 |
+
"loss": 0.2512,
|
| 98 |
+
"step": 7168
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.71,
|
| 102 |
+
"eval_loss": 0.4247213900089264,
|
| 103 |
+
"eval_runtime": 32.3289,
|
| 104 |
+
"eval_samples_per_second": 106.314,
|
| 105 |
+
"eval_steps_per_second": 3.341,
|
| 106 |
+
"step": 7168
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.81,
|
| 110 |
+
"learning_rate": 4.194255926035212e-05,
|
| 111 |
+
"loss": 0.2483,
|
| 112 |
+
"step": 8192
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.81,
|
| 116 |
+
"eval_loss": 0.4238651394844055,
|
| 117 |
+
"eval_runtime": 32.3862,
|
| 118 |
+
"eval_samples_per_second": 106.126,
|
| 119 |
+
"eval_steps_per_second": 3.335,
|
| 120 |
+
"step": 8192
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.91,
|
| 124 |
+
"learning_rate": 4.093537916789614e-05,
|
| 125 |
+
"loss": 0.2479,
|
| 126 |
+
"step": 9216
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.91,
|
| 130 |
+
"eval_loss": 0.4259129762649536,
|
| 131 |
+
"eval_runtime": 32.4627,
|
| 132 |
+
"eval_samples_per_second": 105.875,
|
| 133 |
+
"eval_steps_per_second": 3.327,
|
| 134 |
+
"step": 9216
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.01,
|
| 138 |
+
"learning_rate": 3.9928199075440155e-05,
|
| 139 |
+
"loss": 0.2498,
|
| 140 |
+
"step": 10240
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.01,
|
| 144 |
+
"eval_loss": 0.4262418746948242,
|
| 145 |
+
"eval_runtime": 32.3999,
|
| 146 |
+
"eval_samples_per_second": 106.081,
|
| 147 |
+
"eval_steps_per_second": 3.333,
|
| 148 |
+
"step": 10240
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.11,
|
| 152 |
+
"learning_rate": 3.8921018982984166e-05,
|
| 153 |
+
"loss": 0.2467,
|
| 154 |
+
"step": 11264
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.11,
|
| 158 |
+
"eval_loss": 0.4267333149909973,
|
| 159 |
+
"eval_runtime": 32.3308,
|
| 160 |
+
"eval_samples_per_second": 106.307,
|
| 161 |
+
"eval_steps_per_second": 3.34,
|
| 162 |
+
"step": 11264
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.21,
|
| 166 |
+
"learning_rate": 3.791482246483722e-05,
|
| 167 |
+
"loss": 0.2466,
|
| 168 |
+
"step": 12288
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.21,
|
| 172 |
+
"eval_loss": 0.4263165295124054,
|
| 173 |
+
"eval_runtime": 32.4348,
|
| 174 |
+
"eval_samples_per_second": 105.967,
|
| 175 |
+
"eval_steps_per_second": 3.33,
|
| 176 |
+
"step": 12288
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.31,
|
| 180 |
+
"learning_rate": 3.690764237238124e-05,
|
| 181 |
+
"loss": 0.2449,
|
| 182 |
+
"step": 13312
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.31,
|
| 186 |
+
"eval_loss": 0.42505738139152527,
|
| 187 |
+
"eval_runtime": 32.3762,
|
| 188 |
+
"eval_samples_per_second": 106.158,
|
| 189 |
+
"eval_steps_per_second": 3.336,
|
| 190 |
+
"step": 13312
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.41,
|
| 194 |
+
"learning_rate": 3.590144585423429e-05,
|
| 195 |
+
"loss": 0.2452,
|
| 196 |
+
"step": 14336
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.41,
|
| 200 |
+
"eval_loss": 0.42740598320961,
|
| 201 |
+
"eval_runtime": 32.44,
|
| 202 |
+
"eval_samples_per_second": 105.949,
|
| 203 |
+
"eval_steps_per_second": 3.329,
|
| 204 |
+
"step": 14336
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.51,
|
| 208 |
+
"learning_rate": 3.489426576177831e-05,
|
| 209 |
+
"loss": 0.2449,
|
| 210 |
+
"step": 15360
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.51,
|
| 214 |
+
"eval_loss": 0.42628249526023865,
|
| 215 |
+
"eval_runtime": 32.3172,
|
| 216 |
+
"eval_samples_per_second": 106.352,
|
| 217 |
+
"eval_steps_per_second": 3.342,
|
| 218 |
+
"step": 15360
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.61,
|
| 222 |
+
"learning_rate": 3.388708566932232e-05,
|
| 223 |
+
"loss": 0.2444,
|
| 224 |
+
"step": 16384
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.61,
|
| 228 |
+
"eval_loss": 0.42398524284362793,
|
| 229 |
+
"eval_runtime": 32.2909,
|
| 230 |
+
"eval_samples_per_second": 106.439,
|
| 231 |
+
"eval_steps_per_second": 3.345,
|
| 232 |
+
"step": 16384
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.71,
|
| 236 |
+
"learning_rate": 3.287990557686633e-05,
|
| 237 |
+
"loss": 0.2428,
|
| 238 |
+
"step": 17408
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.71,
|
| 242 |
+
"eval_loss": 0.42891454696655273,
|
| 243 |
+
"eval_runtime": 32.3773,
|
| 244 |
+
"eval_samples_per_second": 106.155,
|
| 245 |
+
"eval_steps_per_second": 3.336,
|
| 246 |
+
"step": 17408
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.81,
|
| 250 |
+
"learning_rate": 3.1873709058719384e-05,
|
| 251 |
+
"loss": 0.2425,
|
| 252 |
+
"step": 18432
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.81,
|
| 256 |
+
"eval_loss": 0.4228712022304535,
|
| 257 |
+
"eval_runtime": 32.4341,
|
| 258 |
+
"eval_samples_per_second": 105.969,
|
| 259 |
+
"eval_steps_per_second": 3.33,
|
| 260 |
+
"step": 18432
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.91,
|
| 264 |
+
"learning_rate": 3.08665289662634e-05,
|
| 265 |
+
"loss": 0.2424,
|
| 266 |
+
"step": 19456
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.91,
|
| 270 |
+
"eval_loss": 0.4291061758995056,
|
| 271 |
+
"eval_runtime": 32.3192,
|
| 272 |
+
"eval_samples_per_second": 106.345,
|
| 273 |
+
"eval_steps_per_second": 3.342,
|
| 274 |
+
"step": 19456
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.01,
|
| 278 |
+
"learning_rate": 2.985934887380742e-05,
|
| 279 |
+
"loss": 0.2422,
|
| 280 |
+
"step": 20480
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.01,
|
| 284 |
+
"eval_loss": 0.4246675968170166,
|
| 285 |
+
"eval_runtime": 32.2862,
|
| 286 |
+
"eval_samples_per_second": 106.454,
|
| 287 |
+
"eval_steps_per_second": 3.345,
|
| 288 |
+
"step": 20480
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.12,
|
| 292 |
+
"learning_rate": 2.8853152355660473e-05,
|
| 293 |
+
"loss": 0.2397,
|
| 294 |
+
"step": 21504
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.12,
|
| 298 |
+
"eval_loss": 0.42707231640815735,
|
| 299 |
+
"eval_runtime": 32.3373,
|
| 300 |
+
"eval_samples_per_second": 106.286,
|
| 301 |
+
"eval_steps_per_second": 3.34,
|
| 302 |
+
"step": 21504
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.22,
|
| 306 |
+
"learning_rate": 2.7846955837513527e-05,
|
| 307 |
+
"loss": 0.2397,
|
| 308 |
+
"step": 22528
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.22,
|
| 312 |
+
"eval_loss": 0.42262786626815796,
|
| 313 |
+
"eval_runtime": 32.3328,
|
| 314 |
+
"eval_samples_per_second": 106.301,
|
| 315 |
+
"eval_steps_per_second": 3.34,
|
| 316 |
+
"step": 22528
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.32,
|
| 320 |
+
"learning_rate": 2.6839775745057538e-05,
|
| 321 |
+
"loss": 0.2411,
|
| 322 |
+
"step": 23552
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.32,
|
| 326 |
+
"eval_loss": 0.42685696482658386,
|
| 327 |
+
"eval_runtime": 32.3962,
|
| 328 |
+
"eval_samples_per_second": 106.093,
|
| 329 |
+
"eval_steps_per_second": 3.334,
|
| 330 |
+
"step": 23552
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.42,
|
| 334 |
+
"learning_rate": 2.5832595652601556e-05,
|
| 335 |
+
"loss": 0.2408,
|
| 336 |
+
"step": 24576
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.42,
|
| 340 |
+
"eval_loss": 0.42877742648124695,
|
| 341 |
+
"eval_runtime": 32.3163,
|
| 342 |
+
"eval_samples_per_second": 106.355,
|
| 343 |
+
"eval_steps_per_second": 3.342,
|
| 344 |
+
"step": 24576
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.52,
|
| 348 |
+
"learning_rate": 2.482541556014557e-05,
|
| 349 |
+
"loss": 0.2392,
|
| 350 |
+
"step": 25600
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.52,
|
| 354 |
+
"eval_loss": 0.42227810621261597,
|
| 355 |
+
"eval_runtime": 32.369,
|
| 356 |
+
"eval_samples_per_second": 106.182,
|
| 357 |
+
"eval_steps_per_second": 3.337,
|
| 358 |
+
"step": 25600
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.62,
|
| 362 |
+
"learning_rate": 2.3819219041998624e-05,
|
| 363 |
+
"loss": 0.2391,
|
| 364 |
+
"step": 26624
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.62,
|
| 368 |
+
"eval_loss": 0.4296777546405792,
|
| 369 |
+
"eval_runtime": 32.4315,
|
| 370 |
+
"eval_samples_per_second": 105.977,
|
| 371 |
+
"eval_steps_per_second": 3.33,
|
| 372 |
+
"step": 26624
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.72,
|
| 376 |
+
"learning_rate": 2.2812038949542638e-05,
|
| 377 |
+
"loss": 0.2385,
|
| 378 |
+
"step": 27648
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.72,
|
| 382 |
+
"eval_loss": 0.4252742528915405,
|
| 383 |
+
"eval_runtime": 32.4362,
|
| 384 |
+
"eval_samples_per_second": 105.962,
|
| 385 |
+
"eval_steps_per_second": 3.33,
|
| 386 |
+
"step": 27648
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.82,
|
| 390 |
+
"learning_rate": 2.180584243139569e-05,
|
| 391 |
+
"loss": 0.2371,
|
| 392 |
+
"step": 28672
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.82,
|
| 396 |
+
"eval_loss": 0.42966845631599426,
|
| 397 |
+
"eval_runtime": 32.3834,
|
| 398 |
+
"eval_samples_per_second": 106.135,
|
| 399 |
+
"eval_steps_per_second": 3.335,
|
| 400 |
+
"step": 28672
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.92,
|
| 404 |
+
"learning_rate": 2.079866233893971e-05,
|
| 405 |
+
"loss": 0.2373,
|
| 406 |
+
"step": 29696
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.92,
|
| 410 |
+
"eval_loss": 0.4231690466403961,
|
| 411 |
+
"eval_runtime": 32.3708,
|
| 412 |
+
"eval_samples_per_second": 106.176,
|
| 413 |
+
"eval_steps_per_second": 3.336,
|
| 414 |
+
"step": 29696
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.02,
|
| 418 |
+
"learning_rate": 1.97934493951018e-05,
|
| 419 |
+
"loss": 0.2368,
|
| 420 |
+
"step": 30720
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 3.02,
|
| 424 |
+
"eval_loss": 0.42956846952438354,
|
| 425 |
+
"eval_runtime": 32.3442,
|
| 426 |
+
"eval_samples_per_second": 106.263,
|
| 427 |
+
"eval_steps_per_second": 3.339,
|
| 428 |
+
"step": 30720
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.12,
|
| 432 |
+
"learning_rate": 1.8786269302645816e-05,
|
| 433 |
+
"loss": 0.2355,
|
| 434 |
+
"step": 31744
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.12,
|
| 438 |
+
"eval_loss": 0.43274641036987305,
|
| 439 |
+
"eval_runtime": 32.3365,
|
| 440 |
+
"eval_samples_per_second": 106.289,
|
| 441 |
+
"eval_steps_per_second": 3.34,
|
| 442 |
+
"step": 31744
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 3.22,
|
| 446 |
+
"learning_rate": 1.777908921018983e-05,
|
| 447 |
+
"loss": 0.2354,
|
| 448 |
+
"step": 32768
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 3.22,
|
| 452 |
+
"eval_loss": 0.4304845929145813,
|
| 453 |
+
"eval_runtime": 32.2799,
|
| 454 |
+
"eval_samples_per_second": 106.475,
|
| 455 |
+
"eval_steps_per_second": 3.346,
|
| 456 |
+
"step": 32768
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.32,
|
| 460 |
+
"learning_rate": 1.6771909117733845e-05,
|
| 461 |
+
"loss": 0.2345,
|
| 462 |
+
"step": 33792
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 3.32,
|
| 466 |
+
"eval_loss": 0.4286292791366577,
|
| 467 |
+
"eval_runtime": 32.4389,
|
| 468 |
+
"eval_samples_per_second": 105.953,
|
| 469 |
+
"eval_steps_per_second": 3.329,
|
| 470 |
+
"step": 33792
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.42,
|
| 474 |
+
"learning_rate": 1.5765712599586898e-05,
|
| 475 |
+
"loss": 0.2355,
|
| 476 |
+
"step": 34816
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.42,
|
| 480 |
+
"eval_loss": 0.4350430965423584,
|
| 481 |
+
"eval_runtime": 32.3371,
|
| 482 |
+
"eval_samples_per_second": 106.287,
|
| 483 |
+
"eval_steps_per_second": 3.34,
|
| 484 |
+
"step": 34816
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 3.53,
|
| 488 |
+
"learning_rate": 1.4758532507130915e-05,
|
| 489 |
+
"loss": 0.2353,
|
| 490 |
+
"step": 35840
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 3.53,
|
| 494 |
+
"eval_loss": 0.4268806278705597,
|
| 495 |
+
"eval_runtime": 32.3956,
|
| 496 |
+
"eval_samples_per_second": 106.095,
|
| 497 |
+
"eval_steps_per_second": 3.334,
|
| 498 |
+
"step": 35840
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 3.63,
|
| 502 |
+
"learning_rate": 1.375233598898397e-05,
|
| 503 |
+
"loss": 0.2351,
|
| 504 |
+
"step": 36864
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 3.63,
|
| 508 |
+
"eval_loss": 0.43005427718162537,
|
| 509 |
+
"eval_runtime": 32.3262,
|
| 510 |
+
"eval_samples_per_second": 106.323,
|
| 511 |
+
"eval_steps_per_second": 3.341,
|
| 512 |
+
"step": 36864
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.73,
|
| 516 |
+
"learning_rate": 1.2745155896527982e-05,
|
| 517 |
+
"loss": 0.2336,
|
| 518 |
+
"step": 37888
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.73,
|
| 522 |
+
"eval_loss": 0.4301435649394989,
|
| 523 |
+
"eval_runtime": 32.4031,
|
| 524 |
+
"eval_samples_per_second": 106.07,
|
| 525 |
+
"eval_steps_per_second": 3.333,
|
| 526 |
+
"step": 37888
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 3.83,
|
| 530 |
+
"learning_rate": 1.1737975804071997e-05,
|
| 531 |
+
"loss": 0.2344,
|
| 532 |
+
"step": 38912
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 3.83,
|
| 536 |
+
"eval_loss": 0.43188127875328064,
|
| 537 |
+
"eval_runtime": 32.3893,
|
| 538 |
+
"eval_samples_per_second": 106.115,
|
| 539 |
+
"eval_steps_per_second": 3.334,
|
| 540 |
+
"step": 38912
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.93,
|
| 544 |
+
"learning_rate": 1.0730795711616013e-05,
|
| 545 |
+
"loss": 0.2339,
|
| 546 |
+
"step": 39936
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.93,
|
| 550 |
+
"eval_loss": 0.4304964244365692,
|
| 551 |
+
"eval_runtime": 32.4411,
|
| 552 |
+
"eval_samples_per_second": 105.946,
|
| 553 |
+
"eval_steps_per_second": 3.329,
|
| 554 |
+
"step": 39936
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 4.03,
|
| 558 |
+
"learning_rate": 9.724599193469066e-06,
|
| 559 |
+
"loss": 0.2326,
|
| 560 |
+
"step": 40960
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.03,
|
| 564 |
+
"eval_loss": 0.4298175573348999,
|
| 565 |
+
"eval_runtime": 32.3377,
|
| 566 |
+
"eval_samples_per_second": 106.285,
|
| 567 |
+
"eval_steps_per_second": 3.34,
|
| 568 |
+
"step": 40960
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 4.13,
|
| 572 |
+
"learning_rate": 8.718402675322121e-06,
|
| 573 |
+
"loss": 0.2316,
|
| 574 |
+
"step": 41984
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 4.13,
|
| 578 |
+
"eval_loss": 0.43077352643013,
|
| 579 |
+
"eval_runtime": 32.3835,
|
| 580 |
+
"eval_samples_per_second": 106.134,
|
| 581 |
+
"eval_steps_per_second": 3.335,
|
| 582 |
+
"step": 41984
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 4.23,
|
| 586 |
+
"learning_rate": 7.711222582866136e-06,
|
| 587 |
+
"loss": 0.2311,
|
| 588 |
+
"step": 43008
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 4.23,
|
| 592 |
+
"eval_loss": 0.43301910161972046,
|
| 593 |
+
"eval_runtime": 32.3178,
|
| 594 |
+
"eval_samples_per_second": 106.35,
|
| 595 |
+
"eval_steps_per_second": 3.342,
|
| 596 |
+
"step": 43008
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 4.33,
|
| 600 |
+
"learning_rate": 6.704042490410151e-06,
|
| 601 |
+
"loss": 0.2315,
|
| 602 |
+
"step": 44032
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 4.33,
|
| 606 |
+
"eval_loss": 0.4313049912452698,
|
| 607 |
+
"eval_runtime": 32.3292,
|
| 608 |
+
"eval_samples_per_second": 106.313,
|
| 609 |
+
"eval_steps_per_second": 3.341,
|
| 610 |
+
"step": 44032
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 4.43,
|
| 614 |
+
"learning_rate": 5.697845972263205e-06,
|
| 615 |
+
"loss": 0.2305,
|
| 616 |
+
"step": 45056
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 4.43,
|
| 620 |
+
"eval_loss": 0.43192604184150696,
|
| 621 |
+
"eval_runtime": 32.2814,
|
| 622 |
+
"eval_samples_per_second": 106.47,
|
| 623 |
+
"eval_steps_per_second": 3.346,
|
| 624 |
+
"step": 45056
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 4.53,
|
| 628 |
+
"learning_rate": 4.69066587980722e-06,
|
| 629 |
+
"loss": 0.2328,
|
| 630 |
+
"step": 46080
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 4.53,
|
| 634 |
+
"eval_loss": 0.42917123436927795,
|
| 635 |
+
"eval_runtime": 32.2788,
|
| 636 |
+
"eval_samples_per_second": 106.479,
|
| 637 |
+
"eval_steps_per_second": 3.346,
|
| 638 |
+
"step": 46080
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.63,
|
| 642 |
+
"learning_rate": 3.6834857873512347e-06,
|
| 643 |
+
"loss": 0.232,
|
| 644 |
+
"step": 47104
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 4.63,
|
| 648 |
+
"eval_loss": 0.4288509488105774,
|
| 649 |
+
"eval_runtime": 32.3263,
|
| 650 |
+
"eval_samples_per_second": 106.322,
|
| 651 |
+
"eval_steps_per_second": 3.341,
|
| 652 |
+
"step": 47104
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 4.73,
|
| 656 |
+
"learning_rate": 2.6763056948952493e-06,
|
| 657 |
+
"loss": 0.2309,
|
| 658 |
+
"step": 48128
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 4.73,
|
| 662 |
+
"eval_loss": 0.43027371168136597,
|
| 663 |
+
"eval_runtime": 32.3873,
|
| 664 |
+
"eval_samples_per_second": 106.122,
|
| 665 |
+
"eval_steps_per_second": 3.335,
|
| 666 |
+
"step": 48128
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 4.83,
|
| 670 |
+
"learning_rate": 1.6701091767483034e-06,
|
| 671 |
+
"loss": 0.23,
|
| 672 |
+
"step": 49152
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 4.83,
|
| 676 |
+
"eval_loss": 0.4316680133342743,
|
| 677 |
+
"eval_runtime": 32.3291,
|
| 678 |
+
"eval_samples_per_second": 106.313,
|
| 679 |
+
"eval_steps_per_second": 3.341,
|
| 680 |
+
"step": 49152
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.94,
|
| 684 |
+
"learning_rate": 6.629290842923184e-07,
|
| 685 |
+
"loss": 0.2315,
|
| 686 |
+
"step": 50176
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 4.94,
|
| 690 |
+
"eval_loss": 0.4303137958049774,
|
| 691 |
+
"eval_runtime": 32.4187,
|
| 692 |
+
"eval_samples_per_second": 106.019,
|
| 693 |
+
"eval_steps_per_second": 3.331,
|
| 694 |
+
"step": 50176
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 5.0,
|
| 698 |
+
"step": 50835,
|
| 699 |
+
"total_flos": 4.2534856293423514e+17,
|
| 700 |
+
"train_loss": 0.24000135361532715,
|
| 701 |
+
"train_runtime": 35584.6801,
|
| 702 |
+
"train_samples_per_second": 51.426,
|
| 703 |
+
"train_steps_per_second": 1.429
|
| 704 |
+
}
|
| 705 |
+
],
|
| 706 |
+
"max_steps": 50835,
|
| 707 |
+
"num_train_epochs": 5,
|
| 708 |
+
"total_flos": 4.2534856293423514e+17,
|
| 709 |
"trial_name": null,
|
| 710 |
"trial_params": null
|
| 711 |
}
|