Hritik
commited on
Commit
•
a88c987
1
Parent(s):
47adeb4
first commit
Browse files- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +816 -0
- training_args.bin +3 -0
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a4c8341d772f9a71bfc3481f2616a0721b3651c231ee04ed3e4210adcab702f
|
| 3 |
+
size 134358981
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5ac96bcedd2453d32162690d0458bd9599c7895436541c9530f8c37cea23adc
|
| 3 |
+
size 7074279085
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d152c322ccb6c2b2de355ea6d185cc25d7807cbd026d0d0c251368c76d3c8c9
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a9231265124867f19e61ab3114384304e7fcaf669e948772279f4fae1a4b413
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a183dde7057304298c24481ed4707b640a5c16f56af9175a2cc55341df222027
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,816 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.985976939856653,
|
| 5 |
+
"global_step": 4000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 4.2e-05,
|
| 13 |
+
"loss": 0.8909,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 9.1e-05,
|
| 19 |
+
"loss": 0.8023,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.12,
|
| 24 |
+
"eval_loss": 0.7678152918815613,
|
| 25 |
+
"eval_runtime": 2324.1166,
|
| 26 |
+
"eval_samples_per_second": 0.632,
|
| 27 |
+
"eval_steps_per_second": 0.632,
|
| 28 |
+
"step": 100
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.19,
|
| 32 |
+
"learning_rate": 9.895140664961637e-05,
|
| 33 |
+
"loss": 0.7815,
|
| 34 |
+
"step": 150
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.25,
|
| 38 |
+
"learning_rate": 9.767263427109975e-05,
|
| 39 |
+
"loss": 0.8184,
|
| 40 |
+
"step": 200
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.25,
|
| 44 |
+
"eval_loss": 0.7796664834022522,
|
| 45 |
+
"eval_runtime": 2323.4202,
|
| 46 |
+
"eval_samples_per_second": 0.633,
|
| 47 |
+
"eval_steps_per_second": 0.633,
|
| 48 |
+
"step": 200
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.31,
|
| 52 |
+
"learning_rate": 9.639386189258313e-05,
|
| 53 |
+
"loss": 0.7501,
|
| 54 |
+
"step": 250
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.37,
|
| 58 |
+
"learning_rate": 9.51150895140665e-05,
|
| 59 |
+
"loss": 0.7786,
|
| 60 |
+
"step": 300
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.37,
|
| 64 |
+
"eval_loss": 0.7461986541748047,
|
| 65 |
+
"eval_runtime": 2323.156,
|
| 66 |
+
"eval_samples_per_second": 0.633,
|
| 67 |
+
"eval_steps_per_second": 0.633,
|
| 68 |
+
"step": 300
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.44,
|
| 72 |
+
"learning_rate": 9.383631713554988e-05,
|
| 73 |
+
"loss": 0.7247,
|
| 74 |
+
"step": 350
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.5,
|
| 78 |
+
"learning_rate": 9.255754475703325e-05,
|
| 79 |
+
"loss": 0.699,
|
| 80 |
+
"step": 400
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5,
|
| 84 |
+
"eval_loss": 0.7154579162597656,
|
| 85 |
+
"eval_runtime": 2326.716,
|
| 86 |
+
"eval_samples_per_second": 0.632,
|
| 87 |
+
"eval_steps_per_second": 0.632,
|
| 88 |
+
"step": 400
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.56,
|
| 92 |
+
"learning_rate": 9.127877237851663e-05,
|
| 93 |
+
"loss": 0.7498,
|
| 94 |
+
"step": 450
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.62,
|
| 98 |
+
"learning_rate": 9e-05,
|
| 99 |
+
"loss": 0.6729,
|
| 100 |
+
"step": 500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.62,
|
| 104 |
+
"eval_loss": 0.6918142437934875,
|
| 105 |
+
"eval_runtime": 2326.9582,
|
| 106 |
+
"eval_samples_per_second": 0.632,
|
| 107 |
+
"eval_steps_per_second": 0.632,
|
| 108 |
+
"step": 500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.69,
|
| 112 |
+
"learning_rate": 8.872122762148338e-05,
|
| 113 |
+
"loss": 0.6821,
|
| 114 |
+
"step": 550
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.75,
|
| 118 |
+
"learning_rate": 8.744245524296676e-05,
|
| 119 |
+
"loss": 0.7392,
|
| 120 |
+
"step": 600
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.75,
|
| 124 |
+
"eval_loss": 0.6949509978294373,
|
| 125 |
+
"eval_runtime": 2328.8704,
|
| 126 |
+
"eval_samples_per_second": 0.631,
|
| 127 |
+
"eval_steps_per_second": 0.631,
|
| 128 |
+
"step": 600
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.81,
|
| 132 |
+
"learning_rate": 8.616368286445013e-05,
|
| 133 |
+
"loss": 0.6848,
|
| 134 |
+
"step": 650
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.87,
|
| 138 |
+
"learning_rate": 8.488491048593351e-05,
|
| 139 |
+
"loss": 0.7601,
|
| 140 |
+
"step": 700
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.87,
|
| 144 |
+
"eval_loss": 0.6541839241981506,
|
| 145 |
+
"eval_runtime": 2322.3854,
|
| 146 |
+
"eval_samples_per_second": 0.633,
|
| 147 |
+
"eval_steps_per_second": 0.633,
|
| 148 |
+
"step": 700
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.93,
|
| 152 |
+
"learning_rate": 8.360613810741689e-05,
|
| 153 |
+
"loss": 0.7163,
|
| 154 |
+
"step": 750
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.0,
|
| 158 |
+
"learning_rate": 8.232736572890026e-05,
|
| 159 |
+
"loss": 0.7121,
|
| 160 |
+
"step": 800
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.0,
|
| 164 |
+
"eval_loss": 0.7020866274833679,
|
| 165 |
+
"eval_runtime": 2329.0246,
|
| 166 |
+
"eval_samples_per_second": 0.631,
|
| 167 |
+
"eval_steps_per_second": 0.631,
|
| 168 |
+
"step": 800
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.06,
|
| 172 |
+
"learning_rate": 8.104859335038364e-05,
|
| 173 |
+
"loss": 0.6303,
|
| 174 |
+
"step": 850
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.12,
|
| 178 |
+
"learning_rate": 7.992327365728901e-05,
|
| 179 |
+
"loss": 0.834,
|
| 180 |
+
"step": 900
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.12,
|
| 184 |
+
"eval_loss": 0.8280826210975647,
|
| 185 |
+
"eval_runtime": 2322.7118,
|
| 186 |
+
"eval_samples_per_second": 0.633,
|
| 187 |
+
"eval_steps_per_second": 0.633,
|
| 188 |
+
"step": 900
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.18,
|
| 192 |
+
"learning_rate": 7.867007672634272e-05,
|
| 193 |
+
"loss": 0.7102,
|
| 194 |
+
"step": 950
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.25,
|
| 198 |
+
"learning_rate": 7.73913043478261e-05,
|
| 199 |
+
"loss": 0.6845,
|
| 200 |
+
"step": 1000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.25,
|
| 204 |
+
"eval_loss": 0.684939444065094,
|
| 205 |
+
"eval_runtime": 2322.9147,
|
| 206 |
+
"eval_samples_per_second": 0.633,
|
| 207 |
+
"eval_steps_per_second": 0.633,
|
| 208 |
+
"step": 1000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.31,
|
| 212 |
+
"learning_rate": 7.611253196930947e-05,
|
| 213 |
+
"loss": 0.6918,
|
| 214 |
+
"step": 1050
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.37,
|
| 218 |
+
"learning_rate": 7.483375959079285e-05,
|
| 219 |
+
"loss": 0.7139,
|
| 220 |
+
"step": 1100
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.37,
|
| 224 |
+
"eval_loss": 0.682366132736206,
|
| 225 |
+
"eval_runtime": 2323.8642,
|
| 226 |
+
"eval_samples_per_second": 0.633,
|
| 227 |
+
"eval_steps_per_second": 0.633,
|
| 228 |
+
"step": 1100
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.43,
|
| 232 |
+
"learning_rate": 7.355498721227622e-05,
|
| 233 |
+
"loss": 0.6513,
|
| 234 |
+
"step": 1150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.5,
|
| 238 |
+
"learning_rate": 7.22762148337596e-05,
|
| 239 |
+
"loss": 0.6515,
|
| 240 |
+
"step": 1200
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.5,
|
| 244 |
+
"eval_loss": 0.6614900827407837,
|
| 245 |
+
"eval_runtime": 2324.2619,
|
| 246 |
+
"eval_samples_per_second": 0.632,
|
| 247 |
+
"eval_steps_per_second": 0.632,
|
| 248 |
+
"step": 1200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.56,
|
| 252 |
+
"learning_rate": 7.099744245524297e-05,
|
| 253 |
+
"loss": 0.6325,
|
| 254 |
+
"step": 1250
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.62,
|
| 258 |
+
"learning_rate": 6.971867007672635e-05,
|
| 259 |
+
"loss": 0.6658,
|
| 260 |
+
"step": 1300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.62,
|
| 264 |
+
"eval_loss": 0.6691812872886658,
|
| 265 |
+
"eval_runtime": 2322.8992,
|
| 266 |
+
"eval_samples_per_second": 0.633,
|
| 267 |
+
"eval_steps_per_second": 0.633,
|
| 268 |
+
"step": 1300
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.68,
|
| 272 |
+
"learning_rate": 6.843989769820973e-05,
|
| 273 |
+
"loss": 0.6709,
|
| 274 |
+
"step": 1350
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.75,
|
| 278 |
+
"learning_rate": 6.71611253196931e-05,
|
| 279 |
+
"loss": 0.6571,
|
| 280 |
+
"step": 1400
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.75,
|
| 284 |
+
"eval_loss": 0.7406654357910156,
|
| 285 |
+
"eval_runtime": 2323.316,
|
| 286 |
+
"eval_samples_per_second": 0.633,
|
| 287 |
+
"eval_steps_per_second": 0.633,
|
| 288 |
+
"step": 1400
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.81,
|
| 292 |
+
"learning_rate": 6.588235294117648e-05,
|
| 293 |
+
"loss": 0.6527,
|
| 294 |
+
"step": 1450
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.87,
|
| 298 |
+
"learning_rate": 6.460358056265985e-05,
|
| 299 |
+
"loss": 0.6432,
|
| 300 |
+
"step": 1500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.87,
|
| 304 |
+
"eval_loss": 0.6645843982696533,
|
| 305 |
+
"eval_runtime": 2325.3057,
|
| 306 |
+
"eval_samples_per_second": 0.632,
|
| 307 |
+
"eval_steps_per_second": 0.632,
|
| 308 |
+
"step": 1500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.93,
|
| 312 |
+
"learning_rate": 6.332480818414323e-05,
|
| 313 |
+
"loss": 0.6998,
|
| 314 |
+
"step": 1550
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.99,
|
| 318 |
+
"learning_rate": 6.20460358056266e-05,
|
| 319 |
+
"loss": 0.6777,
|
| 320 |
+
"step": 1600
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.99,
|
| 324 |
+
"eval_loss": 0.7001596093177795,
|
| 325 |
+
"eval_runtime": 2324.698,
|
| 326 |
+
"eval_samples_per_second": 0.632,
|
| 327 |
+
"eval_steps_per_second": 0.632,
|
| 328 |
+
"step": 1600
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.06,
|
| 332 |
+
"learning_rate": 6.0767263427109976e-05,
|
| 333 |
+
"loss": 0.63,
|
| 334 |
+
"step": 1650
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.12,
|
| 338 |
+
"learning_rate": 5.948849104859335e-05,
|
| 339 |
+
"loss": 0.6027,
|
| 340 |
+
"step": 1700
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.12,
|
| 344 |
+
"eval_loss": 0.6740280389785767,
|
| 345 |
+
"eval_runtime": 2325.0824,
|
| 346 |
+
"eval_samples_per_second": 0.632,
|
| 347 |
+
"eval_steps_per_second": 0.632,
|
| 348 |
+
"step": 1700
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.18,
|
| 352 |
+
"learning_rate": 5.820971867007673e-05,
|
| 353 |
+
"loss": 0.6171,
|
| 354 |
+
"step": 1750
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.24,
|
| 358 |
+
"learning_rate": 5.6930946291560104e-05,
|
| 359 |
+
"loss": 0.5711,
|
| 360 |
+
"step": 1800
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.24,
|
| 364 |
+
"eval_loss": 0.6770710349082947,
|
| 365 |
+
"eval_runtime": 2324.7006,
|
| 366 |
+
"eval_samples_per_second": 0.632,
|
| 367 |
+
"eval_steps_per_second": 0.632,
|
| 368 |
+
"step": 1800
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.31,
|
| 372 |
+
"learning_rate": 5.565217391304348e-05,
|
| 373 |
+
"loss": 0.6193,
|
| 374 |
+
"step": 1850
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.37,
|
| 378 |
+
"learning_rate": 5.4373401534526856e-05,
|
| 379 |
+
"loss": 0.6544,
|
| 380 |
+
"step": 1900
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.37,
|
| 384 |
+
"eval_loss": 0.7468971014022827,
|
| 385 |
+
"eval_runtime": 2324.7323,
|
| 386 |
+
"eval_samples_per_second": 0.632,
|
| 387 |
+
"eval_steps_per_second": 0.632,
|
| 388 |
+
"step": 1900
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.43,
|
| 392 |
+
"learning_rate": 5.309462915601023e-05,
|
| 393 |
+
"loss": 0.6559,
|
| 394 |
+
"step": 1950
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.49,
|
| 398 |
+
"learning_rate": 5.181585677749361e-05,
|
| 399 |
+
"loss": 0.6981,
|
| 400 |
+
"step": 2000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.49,
|
| 404 |
+
"eval_loss": 0.6552309393882751,
|
| 405 |
+
"eval_runtime": 2325.8405,
|
| 406 |
+
"eval_samples_per_second": 0.632,
|
| 407 |
+
"eval_steps_per_second": 0.632,
|
| 408 |
+
"step": 2000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.56,
|
| 412 |
+
"learning_rate": 5.0537084398976984e-05,
|
| 413 |
+
"loss": 0.6161,
|
| 414 |
+
"step": 2050
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.62,
|
| 418 |
+
"learning_rate": 4.925831202046036e-05,
|
| 419 |
+
"loss": 0.6425,
|
| 420 |
+
"step": 2100
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.62,
|
| 424 |
+
"eval_loss": 0.6608405113220215,
|
| 425 |
+
"eval_runtime": 2324.8602,
|
| 426 |
+
"eval_samples_per_second": 0.632,
|
| 427 |
+
"eval_steps_per_second": 0.632,
|
| 428 |
+
"step": 2100
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.68,
|
| 432 |
+
"learning_rate": 4.7979539641943737e-05,
|
| 433 |
+
"loss": 0.5966,
|
| 434 |
+
"step": 2150
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.74,
|
| 438 |
+
"learning_rate": 4.670076726342711e-05,
|
| 439 |
+
"loss": 0.6435,
|
| 440 |
+
"step": 2200
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.74,
|
| 444 |
+
"eval_loss": 0.6722382307052612,
|
| 445 |
+
"eval_runtime": 2325.4748,
|
| 446 |
+
"eval_samples_per_second": 0.632,
|
| 447 |
+
"eval_steps_per_second": 0.632,
|
| 448 |
+
"step": 2200
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.8,
|
| 452 |
+
"learning_rate": 4.542199488491049e-05,
|
| 453 |
+
"loss": 0.6493,
|
| 454 |
+
"step": 2250
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 2.87,
|
| 458 |
+
"learning_rate": 4.4143222506393865e-05,
|
| 459 |
+
"loss": 0.6281,
|
| 460 |
+
"step": 2300
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.87,
|
| 464 |
+
"eval_loss": 0.6553158760070801,
|
| 465 |
+
"eval_runtime": 2324.9442,
|
| 466 |
+
"eval_samples_per_second": 0.632,
|
| 467 |
+
"eval_steps_per_second": 0.632,
|
| 468 |
+
"step": 2300
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.93,
|
| 472 |
+
"learning_rate": 4.286445012787724e-05,
|
| 473 |
+
"loss": 0.5495,
|
| 474 |
+
"step": 2350
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.99,
|
| 478 |
+
"learning_rate": 4.158567774936061e-05,
|
| 479 |
+
"loss": 0.6129,
|
| 480 |
+
"step": 2400
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.99,
|
| 484 |
+
"eval_loss": 0.6536511182785034,
|
| 485 |
+
"eval_runtime": 2325.6669,
|
| 486 |
+
"eval_samples_per_second": 0.632,
|
| 487 |
+
"eval_steps_per_second": 0.632,
|
| 488 |
+
"step": 2400
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.05,
|
| 492 |
+
"learning_rate": 4.0306905370843986e-05,
|
| 493 |
+
"loss": 0.5085,
|
| 494 |
+
"step": 2450
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.12,
|
| 498 |
+
"learning_rate": 3.902813299232736e-05,
|
| 499 |
+
"loss": 0.5443,
|
| 500 |
+
"step": 2500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.12,
|
| 504 |
+
"eval_loss": 0.659809947013855,
|
| 505 |
+
"eval_runtime": 2326.2914,
|
| 506 |
+
"eval_samples_per_second": 0.632,
|
| 507 |
+
"eval_steps_per_second": 0.632,
|
| 508 |
+
"step": 2500
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 3.18,
|
| 512 |
+
"learning_rate": 3.774936061381074e-05,
|
| 513 |
+
"loss": 0.5447,
|
| 514 |
+
"step": 2550
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 3.24,
|
| 518 |
+
"learning_rate": 3.6470588235294114e-05,
|
| 519 |
+
"loss": 0.535,
|
| 520 |
+
"step": 2600
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 3.24,
|
| 524 |
+
"eval_loss": 0.6724178194999695,
|
| 525 |
+
"eval_runtime": 2327.4156,
|
| 526 |
+
"eval_samples_per_second": 0.632,
|
| 527 |
+
"eval_steps_per_second": 0.632,
|
| 528 |
+
"step": 2600
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 3.3,
|
| 532 |
+
"learning_rate": 3.519181585677749e-05,
|
| 533 |
+
"loss": 0.6094,
|
| 534 |
+
"step": 2650
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.37,
|
| 538 |
+
"learning_rate": 3.3913043478260867e-05,
|
| 539 |
+
"loss": 0.5347,
|
| 540 |
+
"step": 2700
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.37,
|
| 544 |
+
"eval_loss": 0.6599487662315369,
|
| 545 |
+
"eval_runtime": 2327.143,
|
| 546 |
+
"eval_samples_per_second": 0.632,
|
| 547 |
+
"eval_steps_per_second": 0.632,
|
| 548 |
+
"step": 2700
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.43,
|
| 552 |
+
"learning_rate": 3.263427109974424e-05,
|
| 553 |
+
"loss": 0.572,
|
| 554 |
+
"step": 2750
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.49,
|
| 558 |
+
"learning_rate": 3.135549872122762e-05,
|
| 559 |
+
"loss": 0.5493,
|
| 560 |
+
"step": 2800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.49,
|
| 564 |
+
"eval_loss": 0.6231494545936584,
|
| 565 |
+
"eval_runtime": 2326.2678,
|
| 566 |
+
"eval_samples_per_second": 0.632,
|
| 567 |
+
"eval_steps_per_second": 0.632,
|
| 568 |
+
"step": 2800
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.55,
|
| 572 |
+
"learning_rate": 3.0076726342710998e-05,
|
| 573 |
+
"loss": 0.5566,
|
| 574 |
+
"step": 2850
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 3.61,
|
| 578 |
+
"learning_rate": 2.8797953964194374e-05,
|
| 579 |
+
"loss": 0.5564,
|
| 580 |
+
"step": 2900
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 3.61,
|
| 584 |
+
"eval_loss": 0.6593871116638184,
|
| 585 |
+
"eval_runtime": 2327.2395,
|
| 586 |
+
"eval_samples_per_second": 0.632,
|
| 587 |
+
"eval_steps_per_second": 0.632,
|
| 588 |
+
"step": 2900
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 3.68,
|
| 592 |
+
"learning_rate": 2.751918158567775e-05,
|
| 593 |
+
"loss": 0.5787,
|
| 594 |
+
"step": 2950
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 3.74,
|
| 598 |
+
"learning_rate": 2.6240409207161126e-05,
|
| 599 |
+
"loss": 0.509,
|
| 600 |
+
"step": 3000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 3.74,
|
| 604 |
+
"eval_loss": 0.6348086595535278,
|
| 605 |
+
"eval_runtime": 2326.4619,
|
| 606 |
+
"eval_samples_per_second": 0.632,
|
| 607 |
+
"eval_steps_per_second": 0.632,
|
| 608 |
+
"step": 3000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.8,
|
| 612 |
+
"learning_rate": 2.4961636828644502e-05,
|
| 613 |
+
"loss": 0.5356,
|
| 614 |
+
"step": 3050
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.86,
|
| 618 |
+
"learning_rate": 2.368286445012788e-05,
|
| 619 |
+
"loss": 0.52,
|
| 620 |
+
"step": 3100
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.86,
|
| 624 |
+
"eval_loss": 0.6384520530700684,
|
| 625 |
+
"eval_runtime": 2327.6186,
|
| 626 |
+
"eval_samples_per_second": 0.632,
|
| 627 |
+
"eval_steps_per_second": 0.632,
|
| 628 |
+
"step": 3100
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 3.93,
|
| 632 |
+
"learning_rate": 2.2404092071611255e-05,
|
| 633 |
+
"loss": 0.5418,
|
| 634 |
+
"step": 3150
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 3.99,
|
| 638 |
+
"learning_rate": 2.112531969309463e-05,
|
| 639 |
+
"loss": 0.5569,
|
| 640 |
+
"step": 3200
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.99,
|
| 644 |
+
"eval_loss": 0.6191104650497437,
|
| 645 |
+
"eval_runtime": 2329.026,
|
| 646 |
+
"eval_samples_per_second": 0.631,
|
| 647 |
+
"eval_steps_per_second": 0.631,
|
| 648 |
+
"step": 3200
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 4.05,
|
| 652 |
+
"learning_rate": 1.9846547314578007e-05,
|
| 653 |
+
"loss": 0.4716,
|
| 654 |
+
"step": 3250
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.11,
|
| 658 |
+
"learning_rate": 1.8567774936061383e-05,
|
| 659 |
+
"loss": 0.501,
|
| 660 |
+
"step": 3300
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 4.11,
|
| 664 |
+
"eval_loss": 0.6244591474533081,
|
| 665 |
+
"eval_runtime": 2328.4154,
|
| 666 |
+
"eval_samples_per_second": 0.631,
|
| 667 |
+
"eval_steps_per_second": 0.631,
|
| 668 |
+
"step": 3300
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.18,
|
| 672 |
+
"learning_rate": 1.728900255754476e-05,
|
| 673 |
+
"loss": 0.4853,
|
| 674 |
+
"step": 3350
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 4.24,
|
| 678 |
+
"learning_rate": 1.6010230179028135e-05,
|
| 679 |
+
"loss": 0.5105,
|
| 680 |
+
"step": 3400
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 4.24,
|
| 684 |
+
"eval_loss": 0.6227459907531738,
|
| 685 |
+
"eval_runtime": 2328.6203,
|
| 686 |
+
"eval_samples_per_second": 0.631,
|
| 687 |
+
"eval_steps_per_second": 0.631,
|
| 688 |
+
"step": 3400
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 4.3,
|
| 692 |
+
"learning_rate": 1.4731457800511508e-05,
|
| 693 |
+
"loss": 0.4757,
|
| 694 |
+
"step": 3450
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 4.36,
|
| 698 |
+
"learning_rate": 1.3452685421994884e-05,
|
| 699 |
+
"loss": 0.5064,
|
| 700 |
+
"step": 3500
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 4.36,
|
| 704 |
+
"eval_loss": 0.628924548625946,
|
| 705 |
+
"eval_runtime": 2328.7385,
|
| 706 |
+
"eval_samples_per_second": 0.631,
|
| 707 |
+
"eval_steps_per_second": 0.631,
|
| 708 |
+
"step": 3500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 4.43,
|
| 712 |
+
"learning_rate": 1.2173913043478261e-05,
|
| 713 |
+
"loss": 0.5107,
|
| 714 |
+
"step": 3550
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 4.49,
|
| 718 |
+
"learning_rate": 1.0895140664961638e-05,
|
| 719 |
+
"loss": 0.5088,
|
| 720 |
+
"step": 3600
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 4.49,
|
| 724 |
+
"eval_loss": 0.620337724685669,
|
| 725 |
+
"eval_runtime": 2329.0799,
|
| 726 |
+
"eval_samples_per_second": 0.631,
|
| 727 |
+
"eval_steps_per_second": 0.631,
|
| 728 |
+
"step": 3600
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 4.55,
|
| 732 |
+
"learning_rate": 9.616368286445012e-06,
|
| 733 |
+
"loss": 0.5184,
|
| 734 |
+
"step": 3650
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 4.61,
|
| 738 |
+
"learning_rate": 8.337595907928388e-06,
|
| 739 |
+
"loss": 0.5246,
|
| 740 |
+
"step": 3700
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.61,
|
| 744 |
+
"eval_loss": 0.618162989616394,
|
| 745 |
+
"eval_runtime": 2327.9739,
|
| 746 |
+
"eval_samples_per_second": 0.631,
|
| 747 |
+
"eval_steps_per_second": 0.631,
|
| 748 |
+
"step": 3700
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 4.67,
|
| 752 |
+
"learning_rate": 7.058823529411765e-06,
|
| 753 |
+
"loss": 0.5027,
|
| 754 |
+
"step": 3750
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 4.74,
|
| 758 |
+
"learning_rate": 5.780051150895141e-06,
|
| 759 |
+
"loss": 0.4927,
|
| 760 |
+
"step": 3800
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 4.74,
|
| 764 |
+
"eval_loss": 0.6198447942733765,
|
| 765 |
+
"eval_runtime": 2328.8672,
|
| 766 |
+
"eval_samples_per_second": 0.631,
|
| 767 |
+
"eval_steps_per_second": 0.631,
|
| 768 |
+
"step": 3800
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.8,
|
| 772 |
+
"learning_rate": 4.501278772378517e-06,
|
| 773 |
+
"loss": 0.5568,
|
| 774 |
+
"step": 3850
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 4.86,
|
| 778 |
+
"learning_rate": 3.2225063938618927e-06,
|
| 779 |
+
"loss": 0.5038,
|
| 780 |
+
"step": 3900
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 4.86,
|
| 784 |
+
"eval_loss": 0.6127236485481262,
|
| 785 |
+
"eval_runtime": 2329.1619,
|
| 786 |
+
"eval_samples_per_second": 0.631,
|
| 787 |
+
"eval_steps_per_second": 0.631,
|
| 788 |
+
"step": 3900
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 4.92,
|
| 792 |
+
"learning_rate": 1.943734015345269e-06,
|
| 793 |
+
"loss": 0.5114,
|
| 794 |
+
"step": 3950
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 4.99,
|
| 798 |
+
"learning_rate": 6.649616368286445e-07,
|
| 799 |
+
"loss": 0.5494,
|
| 800 |
+
"step": 4000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 4.99,
|
| 804 |
+
"eval_loss": 0.614413321018219,
|
| 805 |
+
"eval_runtime": 2328.9991,
|
| 806 |
+
"eval_samples_per_second": 0.631,
|
| 807 |
+
"eval_steps_per_second": 0.631,
|
| 808 |
+
"step": 4000
|
| 809 |
+
}
|
| 810 |
+
],
|
| 811 |
+
"max_steps": 4010,
|
| 812 |
+
"num_train_epochs": 5,
|
| 813 |
+
"total_flos": 3.2509882552308204e+18,
|
| 814 |
+
"trial_name": null,
|
| 815 |
+
"trial_params": null
|
| 816 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b429dc1da5ecc6af491b3db29c7d759edf5a407a82e094de4d15506500ff1084
|
| 3 |
+
size 4027
|