Training in progress, step 5000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737580392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24857bc4b164a0fc3e6179ea07b38593c6c2d12e6d0172627df2d50db6fea93d
|
| 3 |
size 737580392
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475248442
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd9a1d0b8c63d7b12cdde7d50236f1a919f3ab5b10dee3efa64febf5e045dd28
|
| 3 |
size 1475248442
|
last-checkpoint/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 sha256:0dce7b39374d406c6e9a2e0a52c3d989921f1d308f3e0a976795e1defff56359
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fed7e74ecc01b85f3fc063ed097046907474fb7f4b9c36a632434be797d10982
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 250,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -3063,6 +3063,770 @@
|
|
| 3063 |
"eval_spearman_manhattan": 0.8111787861762638,
|
| 3064 |
"eval_steps_per_second": 26.053,
|
| 3065 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3066 |
}
|
| 3067 |
],
|
| 3068 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.3430178069353325,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 5000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 3063 |
"eval_spearman_manhattan": 0.8111787861762638,
|
| 3064 |
"eval_steps_per_second": 26.053,
|
| 3065 |
"step": 4000
|
| 3066 |
+
},
|
| 3067 |
+
{
|
| 3068 |
+
"epoch": 1.879100281162137,
|
| 3069 |
+
"grad_norm": 1.9940646886825562,
|
| 3070 |
+
"learning_rate": 1.8825562324273666e-05,
|
| 3071 |
+
"loss": 0.2141,
|
| 3072 |
+
"step": 4010
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 1.8837863167760074,
|
| 3076 |
+
"grad_norm": 1.5724692344665527,
|
| 3077 |
+
"learning_rate": 1.8822633552014996e-05,
|
| 3078 |
+
"loss": 0.2202,
|
| 3079 |
+
"step": 4020
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 1.8884723523898783,
|
| 3083 |
+
"grad_norm": 1.880194067955017,
|
| 3084 |
+
"learning_rate": 1.881970477975633e-05,
|
| 3085 |
+
"loss": 0.245,
|
| 3086 |
+
"step": 4030
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 1.8931583880037488,
|
| 3090 |
+
"grad_norm": 1.6564527750015259,
|
| 3091 |
+
"learning_rate": 1.8816776007497658e-05,
|
| 3092 |
+
"loss": 0.2367,
|
| 3093 |
+
"step": 4040
|
| 3094 |
+
},
|
| 3095 |
+
{
|
| 3096 |
+
"epoch": 1.8978444236176195,
|
| 3097 |
+
"grad_norm": 1.3603813648223877,
|
| 3098 |
+
"learning_rate": 1.8813847235238987e-05,
|
| 3099 |
+
"loss": 0.2219,
|
| 3100 |
+
"step": 4050
|
| 3101 |
+
},
|
| 3102 |
+
{
|
| 3103 |
+
"epoch": 1.9025304592314902,
|
| 3104 |
+
"grad_norm": 2.0585732460021973,
|
| 3105 |
+
"learning_rate": 1.881091846298032e-05,
|
| 3106 |
+
"loss": 0.27,
|
| 3107 |
+
"step": 4060
|
| 3108 |
+
},
|
| 3109 |
+
{
|
| 3110 |
+
"epoch": 1.9072164948453607,
|
| 3111 |
+
"grad_norm": 2.4080166816711426,
|
| 3112 |
+
"learning_rate": 1.880798969072165e-05,
|
| 3113 |
+
"loss": 0.2569,
|
| 3114 |
+
"step": 4070
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 1.9119025304592316,
|
| 3118 |
+
"grad_norm": 2.0260493755340576,
|
| 3119 |
+
"learning_rate": 1.8805060918462983e-05,
|
| 3120 |
+
"loss": 0.2239,
|
| 3121 |
+
"step": 4080
|
| 3122 |
+
},
|
| 3123 |
+
{
|
| 3124 |
+
"epoch": 1.9165885660731021,
|
| 3125 |
+
"grad_norm": 1.6909536123275757,
|
| 3126 |
+
"learning_rate": 1.8802132146204312e-05,
|
| 3127 |
+
"loss": 0.2229,
|
| 3128 |
+
"step": 4090
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 1.9212746016869728,
|
| 3132 |
+
"grad_norm": 1.7024294137954712,
|
| 3133 |
+
"learning_rate": 1.8799203373945642e-05,
|
| 3134 |
+
"loss": 0.2078,
|
| 3135 |
+
"step": 4100
|
| 3136 |
+
},
|
| 3137 |
+
{
|
| 3138 |
+
"epoch": 1.9259606373008435,
|
| 3139 |
+
"grad_norm": 1.7406731843948364,
|
| 3140 |
+
"learning_rate": 1.8796274601686975e-05,
|
| 3141 |
+
"loss": 0.2456,
|
| 3142 |
+
"step": 4110
|
| 3143 |
+
},
|
| 3144 |
+
{
|
| 3145 |
+
"epoch": 1.930646672914714,
|
| 3146 |
+
"grad_norm": 1.4349228143692017,
|
| 3147 |
+
"learning_rate": 1.8793345829428304e-05,
|
| 3148 |
+
"loss": 0.2296,
|
| 3149 |
+
"step": 4120
|
| 3150 |
+
},
|
| 3151 |
+
{
|
| 3152 |
+
"epoch": 1.935332708528585,
|
| 3153 |
+
"grad_norm": 1.7777549028396606,
|
| 3154 |
+
"learning_rate": 1.8790417057169637e-05,
|
| 3155 |
+
"loss": 0.2121,
|
| 3156 |
+
"step": 4130
|
| 3157 |
+
},
|
| 3158 |
+
{
|
| 3159 |
+
"epoch": 1.9400187441424555,
|
| 3160 |
+
"grad_norm": 2.259178638458252,
|
| 3161 |
+
"learning_rate": 1.8787488284910967e-05,
|
| 3162 |
+
"loss": 0.2606,
|
| 3163 |
+
"step": 4140
|
| 3164 |
+
},
|
| 3165 |
+
{
|
| 3166 |
+
"epoch": 1.9447047797563262,
|
| 3167 |
+
"grad_norm": 2.10732364654541,
|
| 3168 |
+
"learning_rate": 1.87845595126523e-05,
|
| 3169 |
+
"loss": 0.2492,
|
| 3170 |
+
"step": 4150
|
| 3171 |
+
},
|
| 3172 |
+
{
|
| 3173 |
+
"epoch": 1.9493908153701969,
|
| 3174 |
+
"grad_norm": 2.2768290042877197,
|
| 3175 |
+
"learning_rate": 1.878163074039363e-05,
|
| 3176 |
+
"loss": 0.2155,
|
| 3177 |
+
"step": 4160
|
| 3178 |
+
},
|
| 3179 |
+
{
|
| 3180 |
+
"epoch": 1.9540768509840674,
|
| 3181 |
+
"grad_norm": 1.8602643013000488,
|
| 3182 |
+
"learning_rate": 1.8778701968134962e-05,
|
| 3183 |
+
"loss": 0.2396,
|
| 3184 |
+
"step": 4170
|
| 3185 |
+
},
|
| 3186 |
+
{
|
| 3187 |
+
"epoch": 1.9587628865979383,
|
| 3188 |
+
"grad_norm": 2.197460412979126,
|
| 3189 |
+
"learning_rate": 1.877577319587629e-05,
|
| 3190 |
+
"loss": 0.2169,
|
| 3191 |
+
"step": 4180
|
| 3192 |
+
},
|
| 3193 |
+
{
|
| 3194 |
+
"epoch": 1.9634489222118088,
|
| 3195 |
+
"grad_norm": 1.5060274600982666,
|
| 3196 |
+
"learning_rate": 1.877284442361762e-05,
|
| 3197 |
+
"loss": 0.2306,
|
| 3198 |
+
"step": 4190
|
| 3199 |
+
},
|
| 3200 |
+
{
|
| 3201 |
+
"epoch": 1.9681349578256795,
|
| 3202 |
+
"grad_norm": 2.116128921508789,
|
| 3203 |
+
"learning_rate": 1.876991565135895e-05,
|
| 3204 |
+
"loss": 0.2164,
|
| 3205 |
+
"step": 4200
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 1.9728209934395502,
|
| 3209 |
+
"grad_norm": 2.097766399383545,
|
| 3210 |
+
"learning_rate": 1.8766986879100283e-05,
|
| 3211 |
+
"loss": 0.2574,
|
| 3212 |
+
"step": 4210
|
| 3213 |
+
},
|
| 3214 |
+
{
|
| 3215 |
+
"epoch": 1.9775070290534207,
|
| 3216 |
+
"grad_norm": 1.824741244316101,
|
| 3217 |
+
"learning_rate": 1.8764058106841613e-05,
|
| 3218 |
+
"loss": 0.249,
|
| 3219 |
+
"step": 4220
|
| 3220 |
+
},
|
| 3221 |
+
{
|
| 3222 |
+
"epoch": 1.9821930646672916,
|
| 3223 |
+
"grad_norm": 2.2704122066497803,
|
| 3224 |
+
"learning_rate": 1.8761129334582942e-05,
|
| 3225 |
+
"loss": 0.2316,
|
| 3226 |
+
"step": 4230
|
| 3227 |
+
},
|
| 3228 |
+
{
|
| 3229 |
+
"epoch": 1.986879100281162,
|
| 3230 |
+
"grad_norm": 1.8285561800003052,
|
| 3231 |
+
"learning_rate": 1.8758200562324275e-05,
|
| 3232 |
+
"loss": 0.2489,
|
| 3233 |
+
"step": 4240
|
| 3234 |
+
},
|
| 3235 |
+
{
|
| 3236 |
+
"epoch": 1.9915651358950328,
|
| 3237 |
+
"grad_norm": 1.4909926652908325,
|
| 3238 |
+
"learning_rate": 1.8755271790065605e-05,
|
| 3239 |
+
"loss": 0.2472,
|
| 3240 |
+
"step": 4250
|
| 3241 |
+
},
|
| 3242 |
+
{
|
| 3243 |
+
"epoch": 1.9915651358950328,
|
| 3244 |
+
"eval_loss": 0.03996381163597107,
|
| 3245 |
+
"eval_pearson_cosine": 0.820344828031935,
|
| 3246 |
+
"eval_pearson_dot": 0.7317039255282225,
|
| 3247 |
+
"eval_pearson_euclidean": 0.8039609112737356,
|
| 3248 |
+
"eval_pearson_manhattan": 0.8052691930531775,
|
| 3249 |
+
"eval_runtime": 3.5603,
|
| 3250 |
+
"eval_samples_per_second": 421.311,
|
| 3251 |
+
"eval_spearman_cosine": 0.8224163636565568,
|
| 3252 |
+
"eval_spearman_dot": 0.7308283663168708,
|
| 3253 |
+
"eval_spearman_euclidean": 0.8146988265770505,
|
| 3254 |
+
"eval_spearman_manhattan": 0.8160453182060199,
|
| 3255 |
+
"eval_steps_per_second": 26.402,
|
| 3256 |
+
"step": 4250
|
| 3257 |
+
},
|
| 3258 |
+
{
|
| 3259 |
+
"epoch": 1.9962511715089035,
|
| 3260 |
+
"grad_norm": 1.7931636571884155,
|
| 3261 |
+
"learning_rate": 1.8752343017806937e-05,
|
| 3262 |
+
"loss": 0.2324,
|
| 3263 |
+
"step": 4260
|
| 3264 |
+
},
|
| 3265 |
+
{
|
| 3266 |
+
"epoch": 2.000937207122774,
|
| 3267 |
+
"grad_norm": 1.267348289489746,
|
| 3268 |
+
"learning_rate": 1.8749414245548267e-05,
|
| 3269 |
+
"loss": 0.2053,
|
| 3270 |
+
"step": 4270
|
| 3271 |
+
},
|
| 3272 |
+
{
|
| 3273 |
+
"epoch": 2.005623242736645,
|
| 3274 |
+
"grad_norm": 1.977459192276001,
|
| 3275 |
+
"learning_rate": 1.87464854732896e-05,
|
| 3276 |
+
"loss": 0.1835,
|
| 3277 |
+
"step": 4280
|
| 3278 |
+
},
|
| 3279 |
+
{
|
| 3280 |
+
"epoch": 2.0103092783505154,
|
| 3281 |
+
"grad_norm": 1.8532277345657349,
|
| 3282 |
+
"learning_rate": 1.874355670103093e-05,
|
| 3283 |
+
"loss": 0.1941,
|
| 3284 |
+
"step": 4290
|
| 3285 |
+
},
|
| 3286 |
+
{
|
| 3287 |
+
"epoch": 2.014995313964386,
|
| 3288 |
+
"grad_norm": 1.478722095489502,
|
| 3289 |
+
"learning_rate": 1.874062792877226e-05,
|
| 3290 |
+
"loss": 0.1674,
|
| 3291 |
+
"step": 4300
|
| 3292 |
+
},
|
| 3293 |
+
{
|
| 3294 |
+
"epoch": 2.019681349578257,
|
| 3295 |
+
"grad_norm": 1.7603696584701538,
|
| 3296 |
+
"learning_rate": 1.8737699156513592e-05,
|
| 3297 |
+
"loss": 0.1752,
|
| 3298 |
+
"step": 4310
|
| 3299 |
+
},
|
| 3300 |
+
{
|
| 3301 |
+
"epoch": 2.0243673851921273,
|
| 3302 |
+
"grad_norm": 2.0662457942962646,
|
| 3303 |
+
"learning_rate": 1.873477038425492e-05,
|
| 3304 |
+
"loss": 0.1638,
|
| 3305 |
+
"step": 4320
|
| 3306 |
+
},
|
| 3307 |
+
{
|
| 3308 |
+
"epoch": 2.0290534208059983,
|
| 3309 |
+
"grad_norm": 1.3146560192108154,
|
| 3310 |
+
"learning_rate": 1.8731841611996254e-05,
|
| 3311 |
+
"loss": 0.1368,
|
| 3312 |
+
"step": 4330
|
| 3313 |
+
},
|
| 3314 |
+
{
|
| 3315 |
+
"epoch": 2.0337394564198688,
|
| 3316 |
+
"grad_norm": 1.8261940479278564,
|
| 3317 |
+
"learning_rate": 1.8728912839737584e-05,
|
| 3318 |
+
"loss": 0.1643,
|
| 3319 |
+
"step": 4340
|
| 3320 |
+
},
|
| 3321 |
+
{
|
| 3322 |
+
"epoch": 2.0384254920337392,
|
| 3323 |
+
"grad_norm": 1.4603139162063599,
|
| 3324 |
+
"learning_rate": 1.8725984067478917e-05,
|
| 3325 |
+
"loss": 0.1655,
|
| 3326 |
+
"step": 4350
|
| 3327 |
+
},
|
| 3328 |
+
{
|
| 3329 |
+
"epoch": 2.04311152764761,
|
| 3330 |
+
"grad_norm": 1.811943531036377,
|
| 3331 |
+
"learning_rate": 1.8723055295220246e-05,
|
| 3332 |
+
"loss": 0.1617,
|
| 3333 |
+
"step": 4360
|
| 3334 |
+
},
|
| 3335 |
+
{
|
| 3336 |
+
"epoch": 2.0477975632614807,
|
| 3337 |
+
"grad_norm": 2.325777769088745,
|
| 3338 |
+
"learning_rate": 1.8720126522961576e-05,
|
| 3339 |
+
"loss": 0.1708,
|
| 3340 |
+
"step": 4370
|
| 3341 |
+
},
|
| 3342 |
+
{
|
| 3343 |
+
"epoch": 2.0524835988753516,
|
| 3344 |
+
"grad_norm": 1.7482625246047974,
|
| 3345 |
+
"learning_rate": 1.871719775070291e-05,
|
| 3346 |
+
"loss": 0.1758,
|
| 3347 |
+
"step": 4380
|
| 3348 |
+
},
|
| 3349 |
+
{
|
| 3350 |
+
"epoch": 2.057169634489222,
|
| 3351 |
+
"grad_norm": 1.916061520576477,
|
| 3352 |
+
"learning_rate": 1.8714268978444238e-05,
|
| 3353 |
+
"loss": 0.1729,
|
| 3354 |
+
"step": 4390
|
| 3355 |
+
},
|
| 3356 |
+
{
|
| 3357 |
+
"epoch": 2.0618556701030926,
|
| 3358 |
+
"grad_norm": 1.4515407085418701,
|
| 3359 |
+
"learning_rate": 1.8711340206185567e-05,
|
| 3360 |
+
"loss": 0.1739,
|
| 3361 |
+
"step": 4400
|
| 3362 |
+
},
|
| 3363 |
+
{
|
| 3364 |
+
"epoch": 2.0665417057169635,
|
| 3365 |
+
"grad_norm": 1.7637025117874146,
|
| 3366 |
+
"learning_rate": 1.8708411433926897e-05,
|
| 3367 |
+
"loss": 0.1648,
|
| 3368 |
+
"step": 4410
|
| 3369 |
+
},
|
| 3370 |
+
{
|
| 3371 |
+
"epoch": 2.071227741330834,
|
| 3372 |
+
"grad_norm": 2.1204230785369873,
|
| 3373 |
+
"learning_rate": 1.870548266166823e-05,
|
| 3374 |
+
"loss": 0.1725,
|
| 3375 |
+
"step": 4420
|
| 3376 |
+
},
|
| 3377 |
+
{
|
| 3378 |
+
"epoch": 2.075913776944705,
|
| 3379 |
+
"grad_norm": 1.7462095022201538,
|
| 3380 |
+
"learning_rate": 1.870255388940956e-05,
|
| 3381 |
+
"loss": 0.154,
|
| 3382 |
+
"step": 4430
|
| 3383 |
+
},
|
| 3384 |
+
{
|
| 3385 |
+
"epoch": 2.0805998125585754,
|
| 3386 |
+
"grad_norm": 1.6449689865112305,
|
| 3387 |
+
"learning_rate": 1.8699625117150892e-05,
|
| 3388 |
+
"loss": 0.1651,
|
| 3389 |
+
"step": 4440
|
| 3390 |
+
},
|
| 3391 |
+
{
|
| 3392 |
+
"epoch": 2.085285848172446,
|
| 3393 |
+
"grad_norm": 1.8776732683181763,
|
| 3394 |
+
"learning_rate": 1.869669634489222e-05,
|
| 3395 |
+
"loss": 0.1752,
|
| 3396 |
+
"step": 4450
|
| 3397 |
+
},
|
| 3398 |
+
{
|
| 3399 |
+
"epoch": 2.089971883786317,
|
| 3400 |
+
"grad_norm": 1.5373666286468506,
|
| 3401 |
+
"learning_rate": 1.8693767572633555e-05,
|
| 3402 |
+
"loss": 0.1551,
|
| 3403 |
+
"step": 4460
|
| 3404 |
+
},
|
| 3405 |
+
{
|
| 3406 |
+
"epoch": 2.0946579194001873,
|
| 3407 |
+
"grad_norm": 1.9183931350708008,
|
| 3408 |
+
"learning_rate": 1.8690838800374884e-05,
|
| 3409 |
+
"loss": 0.1562,
|
| 3410 |
+
"step": 4470
|
| 3411 |
+
},
|
| 3412 |
+
{
|
| 3413 |
+
"epoch": 2.0993439550140582,
|
| 3414 |
+
"grad_norm": 2.184581995010376,
|
| 3415 |
+
"learning_rate": 1.8687910028116217e-05,
|
| 3416 |
+
"loss": 0.1544,
|
| 3417 |
+
"step": 4480
|
| 3418 |
+
},
|
| 3419 |
+
{
|
| 3420 |
+
"epoch": 2.1040299906279287,
|
| 3421 |
+
"grad_norm": 1.1829646825790405,
|
| 3422 |
+
"learning_rate": 1.8684981255857546e-05,
|
| 3423 |
+
"loss": 0.1474,
|
| 3424 |
+
"step": 4490
|
| 3425 |
+
},
|
| 3426 |
+
{
|
| 3427 |
+
"epoch": 2.108716026241799,
|
| 3428 |
+
"grad_norm": 1.7661231756210327,
|
| 3429 |
+
"learning_rate": 1.8682052483598876e-05,
|
| 3430 |
+
"loss": 0.1838,
|
| 3431 |
+
"step": 4500
|
| 3432 |
+
},
|
| 3433 |
+
{
|
| 3434 |
+
"epoch": 2.108716026241799,
|
| 3435 |
+
"eval_loss": 0.03478589281439781,
|
| 3436 |
+
"eval_pearson_cosine": 0.8183668280938576,
|
| 3437 |
+
"eval_pearson_dot": 0.7494542878437821,
|
| 3438 |
+
"eval_pearson_euclidean": 0.8004851343617361,
|
| 3439 |
+
"eval_pearson_manhattan": 0.8022690605878324,
|
| 3440 |
+
"eval_runtime": 3.3337,
|
| 3441 |
+
"eval_samples_per_second": 449.946,
|
| 3442 |
+
"eval_spearman_cosine": 0.819061603084573,
|
| 3443 |
+
"eval_spearman_dot": 0.7480798887745068,
|
| 3444 |
+
"eval_spearman_euclidean": 0.8085010936446739,
|
| 3445 |
+
"eval_spearman_manhattan": 0.8099334586781558,
|
| 3446 |
+
"eval_steps_per_second": 28.197,
|
| 3447 |
+
"step": 4500
|
| 3448 |
+
},
|
| 3449 |
+
{
|
| 3450 |
+
"epoch": 2.11340206185567,
|
| 3451 |
+
"grad_norm": 1.5288666486740112,
|
| 3452 |
+
"learning_rate": 1.867912371134021e-05,
|
| 3453 |
+
"loss": 0.1483,
|
| 3454 |
+
"step": 4510
|
| 3455 |
+
},
|
| 3456 |
+
{
|
| 3457 |
+
"epoch": 2.1180880974695406,
|
| 3458 |
+
"grad_norm": 1.8518108129501343,
|
| 3459 |
+
"learning_rate": 1.867619493908154e-05,
|
| 3460 |
+
"loss": 0.1556,
|
| 3461 |
+
"step": 4520
|
| 3462 |
+
},
|
| 3463 |
+
{
|
| 3464 |
+
"epoch": 2.1227741330834116,
|
| 3465 |
+
"grad_norm": 1.7130534648895264,
|
| 3466 |
+
"learning_rate": 1.867326616682287e-05,
|
| 3467 |
+
"loss": 0.2054,
|
| 3468 |
+
"step": 4530
|
| 3469 |
+
},
|
| 3470 |
+
{
|
| 3471 |
+
"epoch": 2.127460168697282,
|
| 3472 |
+
"grad_norm": 1.6781951189041138,
|
| 3473 |
+
"learning_rate": 1.86703373945642e-05,
|
| 3474 |
+
"loss": 0.1563,
|
| 3475 |
+
"step": 4540
|
| 3476 |
+
},
|
| 3477 |
+
{
|
| 3478 |
+
"epoch": 2.1321462043111525,
|
| 3479 |
+
"grad_norm": 1.960902452468872,
|
| 3480 |
+
"learning_rate": 1.866740862230553e-05,
|
| 3481 |
+
"loss": 0.1666,
|
| 3482 |
+
"step": 4550
|
| 3483 |
+
},
|
| 3484 |
+
{
|
| 3485 |
+
"epoch": 2.1368322399250235,
|
| 3486 |
+
"grad_norm": 1.9517632722854614,
|
| 3487 |
+
"learning_rate": 1.8664479850046863e-05,
|
| 3488 |
+
"loss": 0.1863,
|
| 3489 |
+
"step": 4560
|
| 3490 |
+
},
|
| 3491 |
+
{
|
| 3492 |
+
"epoch": 2.141518275538894,
|
| 3493 |
+
"grad_norm": 1.7729823589324951,
|
| 3494 |
+
"learning_rate": 1.8661551077788193e-05,
|
| 3495 |
+
"loss": 0.1783,
|
| 3496 |
+
"step": 4570
|
| 3497 |
+
},
|
| 3498 |
+
{
|
| 3499 |
+
"epoch": 2.146204311152765,
|
| 3500 |
+
"grad_norm": 2.2520790100097656,
|
| 3501 |
+
"learning_rate": 1.8658622305529522e-05,
|
| 3502 |
+
"loss": 0.208,
|
| 3503 |
+
"step": 4580
|
| 3504 |
+
},
|
| 3505 |
+
{
|
| 3506 |
+
"epoch": 2.1508903467666354,
|
| 3507 |
+
"grad_norm": 1.4760936498641968,
|
| 3508 |
+
"learning_rate": 1.8655693533270855e-05,
|
| 3509 |
+
"loss": 0.1842,
|
| 3510 |
+
"step": 4590
|
| 3511 |
+
},
|
| 3512 |
+
{
|
| 3513 |
+
"epoch": 2.155576382380506,
|
| 3514 |
+
"grad_norm": 1.8456919193267822,
|
| 3515 |
+
"learning_rate": 1.8652764761012184e-05,
|
| 3516 |
+
"loss": 0.1616,
|
| 3517 |
+
"step": 4600
|
| 3518 |
+
},
|
| 3519 |
+
{
|
| 3520 |
+
"epoch": 2.160262417994377,
|
| 3521 |
+
"grad_norm": 1.528846263885498,
|
| 3522 |
+
"learning_rate": 1.8649835988753514e-05,
|
| 3523 |
+
"loss": 0.1342,
|
| 3524 |
+
"step": 4610
|
| 3525 |
+
},
|
| 3526 |
+
{
|
| 3527 |
+
"epoch": 2.1649484536082473,
|
| 3528 |
+
"grad_norm": 1.1334350109100342,
|
| 3529 |
+
"learning_rate": 1.8646907216494847e-05,
|
| 3530 |
+
"loss": 0.1655,
|
| 3531 |
+
"step": 4620
|
| 3532 |
+
},
|
| 3533 |
+
{
|
| 3534 |
+
"epoch": 2.169634489222118,
|
| 3535 |
+
"grad_norm": 1.359473705291748,
|
| 3536 |
+
"learning_rate": 1.8643978444236176e-05,
|
| 3537 |
+
"loss": 0.1667,
|
| 3538 |
+
"step": 4630
|
| 3539 |
+
},
|
| 3540 |
+
{
|
| 3541 |
+
"epoch": 2.1743205248359887,
|
| 3542 |
+
"grad_norm": 1.6595484018325806,
|
| 3543 |
+
"learning_rate": 1.864104967197751e-05,
|
| 3544 |
+
"loss": 0.1597,
|
| 3545 |
+
"step": 4640
|
| 3546 |
+
},
|
| 3547 |
+
{
|
| 3548 |
+
"epoch": 2.179006560449859,
|
| 3549 |
+
"grad_norm": 1.9534510374069214,
|
| 3550 |
+
"learning_rate": 1.863812089971884e-05,
|
| 3551 |
+
"loss": 0.18,
|
| 3552 |
+
"step": 4650
|
| 3553 |
+
},
|
| 3554 |
+
{
|
| 3555 |
+
"epoch": 2.18369259606373,
|
| 3556 |
+
"grad_norm": 2.137612819671631,
|
| 3557 |
+
"learning_rate": 1.863519212746017e-05,
|
| 3558 |
+
"loss": 0.1649,
|
| 3559 |
+
"step": 4660
|
| 3560 |
+
},
|
| 3561 |
+
{
|
| 3562 |
+
"epoch": 2.1883786316776006,
|
| 3563 |
+
"grad_norm": 1.4351214170455933,
|
| 3564 |
+
"learning_rate": 1.86322633552015e-05,
|
| 3565 |
+
"loss": 0.1798,
|
| 3566 |
+
"step": 4670
|
| 3567 |
+
},
|
| 3568 |
+
{
|
| 3569 |
+
"epoch": 2.1930646672914715,
|
| 3570 |
+
"grad_norm": 1.5940383672714233,
|
| 3571 |
+
"learning_rate": 1.8629334582942834e-05,
|
| 3572 |
+
"loss": 0.1762,
|
| 3573 |
+
"step": 4680
|
| 3574 |
+
},
|
| 3575 |
+
{
|
| 3576 |
+
"epoch": 2.197750702905342,
|
| 3577 |
+
"grad_norm": 1.1390234231948853,
|
| 3578 |
+
"learning_rate": 1.8626405810684164e-05,
|
| 3579 |
+
"loss": 0.1575,
|
| 3580 |
+
"step": 4690
|
| 3581 |
+
},
|
| 3582 |
+
{
|
| 3583 |
+
"epoch": 2.2024367385192125,
|
| 3584 |
+
"grad_norm": 1.7934620380401611,
|
| 3585 |
+
"learning_rate": 1.8623477038425493e-05,
|
| 3586 |
+
"loss": 0.16,
|
| 3587 |
+
"step": 4700
|
| 3588 |
+
},
|
| 3589 |
+
{
|
| 3590 |
+
"epoch": 2.2071227741330834,
|
| 3591 |
+
"grad_norm": 1.5120437145233154,
|
| 3592 |
+
"learning_rate": 1.8620548266166826e-05,
|
| 3593 |
+
"loss": 0.1711,
|
| 3594 |
+
"step": 4710
|
| 3595 |
+
},
|
| 3596 |
+
{
|
| 3597 |
+
"epoch": 2.211808809746954,
|
| 3598 |
+
"grad_norm": 1.8935743570327759,
|
| 3599 |
+
"learning_rate": 1.8617619493908155e-05,
|
| 3600 |
+
"loss": 0.1396,
|
| 3601 |
+
"step": 4720
|
| 3602 |
+
},
|
| 3603 |
+
{
|
| 3604 |
+
"epoch": 2.216494845360825,
|
| 3605 |
+
"grad_norm": 1.7621512413024902,
|
| 3606 |
+
"learning_rate": 1.8614690721649485e-05,
|
| 3607 |
+
"loss": 0.1953,
|
| 3608 |
+
"step": 4730
|
| 3609 |
+
},
|
| 3610 |
+
{
|
| 3611 |
+
"epoch": 2.2211808809746953,
|
| 3612 |
+
"grad_norm": 9.526521682739258,
|
| 3613 |
+
"learning_rate": 1.8611761949390818e-05,
|
| 3614 |
+
"loss": 0.1781,
|
| 3615 |
+
"step": 4740
|
| 3616 |
+
},
|
| 3617 |
+
{
|
| 3618 |
+
"epoch": 2.2258669165885663,
|
| 3619 |
+
"grad_norm": 1.4335854053497314,
|
| 3620 |
+
"learning_rate": 1.8608833177132147e-05,
|
| 3621 |
+
"loss": 0.1509,
|
| 3622 |
+
"step": 4750
|
| 3623 |
+
},
|
| 3624 |
+
{
|
| 3625 |
+
"epoch": 2.2258669165885663,
|
| 3626 |
+
"eval_loss": 0.03594741225242615,
|
| 3627 |
+
"eval_pearson_cosine": 0.8116579897427059,
|
| 3628 |
+
"eval_pearson_dot": 0.734380652885136,
|
| 3629 |
+
"eval_pearson_euclidean": 0.7957971930124614,
|
| 3630 |
+
"eval_pearson_manhattan": 0.7976626643154123,
|
| 3631 |
+
"eval_runtime": 3.4015,
|
| 3632 |
+
"eval_samples_per_second": 440.981,
|
| 3633 |
+
"eval_spearman_cosine": 0.8119603885409888,
|
| 3634 |
+
"eval_spearman_dot": 0.7343109043661656,
|
| 3635 |
+
"eval_spearman_euclidean": 0.803610294766424,
|
| 3636 |
+
"eval_spearman_manhattan": 0.8054368058373911,
|
| 3637 |
+
"eval_steps_per_second": 27.635,
|
| 3638 |
+
"step": 4750
|
| 3639 |
+
},
|
| 3640 |
+
{
|
| 3641 |
+
"epoch": 2.2305529522024368,
|
| 3642 |
+
"grad_norm": 1.9357318878173828,
|
| 3643 |
+
"learning_rate": 1.8605904404873477e-05,
|
| 3644 |
+
"loss": 0.1464,
|
| 3645 |
+
"step": 4760
|
| 3646 |
+
},
|
| 3647 |
+
{
|
| 3648 |
+
"epoch": 2.2352389878163073,
|
| 3649 |
+
"grad_norm": 1.958662986755371,
|
| 3650 |
+
"learning_rate": 1.860297563261481e-05,
|
| 3651 |
+
"loss": 0.1699,
|
| 3652 |
+
"step": 4770
|
| 3653 |
+
},
|
| 3654 |
+
{
|
| 3655 |
+
"epoch": 2.239925023430178,
|
| 3656 |
+
"grad_norm": 1.9908474683761597,
|
| 3657 |
+
"learning_rate": 1.860004686035614e-05,
|
| 3658 |
+
"loss": 0.1763,
|
| 3659 |
+
"step": 4780
|
| 3660 |
+
},
|
| 3661 |
+
{
|
| 3662 |
+
"epoch": 2.2446110590440487,
|
| 3663 |
+
"grad_norm": 1.8446073532104492,
|
| 3664 |
+
"learning_rate": 1.859711808809747e-05,
|
| 3665 |
+
"loss": 0.1972,
|
| 3666 |
+
"step": 4790
|
| 3667 |
+
},
|
| 3668 |
+
{
|
| 3669 |
+
"epoch": 2.2492970946579196,
|
| 3670 |
+
"grad_norm": 1.9557933807373047,
|
| 3671 |
+
"learning_rate": 1.85941893158388e-05,
|
| 3672 |
+
"loss": 0.177,
|
| 3673 |
+
"step": 4800
|
| 3674 |
+
},
|
| 3675 |
+
{
|
| 3676 |
+
"epoch": 2.25398313027179,
|
| 3677 |
+
"grad_norm": 1.9075273275375366,
|
| 3678 |
+
"learning_rate": 1.859126054358013e-05,
|
| 3679 |
+
"loss": 0.1719,
|
| 3680 |
+
"step": 4810
|
| 3681 |
+
},
|
| 3682 |
+
{
|
| 3683 |
+
"epoch": 2.2586691658856606,
|
| 3684 |
+
"grad_norm": 1.6813454627990723,
|
| 3685 |
+
"learning_rate": 1.8588331771321464e-05,
|
| 3686 |
+
"loss": 0.1555,
|
| 3687 |
+
"step": 4820
|
| 3688 |
+
},
|
| 3689 |
+
{
|
| 3690 |
+
"epoch": 2.2633552014995315,
|
| 3691 |
+
"grad_norm": 1.677162528038025,
|
| 3692 |
+
"learning_rate": 1.8585402999062793e-05,
|
| 3693 |
+
"loss": 0.1585,
|
| 3694 |
+
"step": 4830
|
| 3695 |
+
},
|
| 3696 |
+
{
|
| 3697 |
+
"epoch": 2.268041237113402,
|
| 3698 |
+
"grad_norm": 1.9858368635177612,
|
| 3699 |
+
"learning_rate": 1.8582474226804126e-05,
|
| 3700 |
+
"loss": 0.1627,
|
| 3701 |
+
"step": 4840
|
| 3702 |
+
},
|
| 3703 |
+
{
|
| 3704 |
+
"epoch": 2.2727272727272725,
|
| 3705 |
+
"grad_norm": 1.6848777532577515,
|
| 3706 |
+
"learning_rate": 1.8579545454545456e-05,
|
| 3707 |
+
"loss": 0.1576,
|
| 3708 |
+
"step": 4850
|
| 3709 |
+
},
|
| 3710 |
+
{
|
| 3711 |
+
"epoch": 2.2774133083411434,
|
| 3712 |
+
"grad_norm": 2.0122177600860596,
|
| 3713 |
+
"learning_rate": 1.857661668228679e-05,
|
| 3714 |
+
"loss": 0.172,
|
| 3715 |
+
"step": 4860
|
| 3716 |
+
},
|
| 3717 |
+
{
|
| 3718 |
+
"epoch": 2.282099343955014,
|
| 3719 |
+
"grad_norm": 1.666049599647522,
|
| 3720 |
+
"learning_rate": 1.8573687910028118e-05,
|
| 3721 |
+
"loss": 0.1554,
|
| 3722 |
+
"step": 4870
|
| 3723 |
+
},
|
| 3724 |
+
{
|
| 3725 |
+
"epoch": 2.286785379568885,
|
| 3726 |
+
"grad_norm": 1.4426305294036865,
|
| 3727 |
+
"learning_rate": 1.857075913776945e-05,
|
| 3728 |
+
"loss": 0.1268,
|
| 3729 |
+
"step": 4880
|
| 3730 |
+
},
|
| 3731 |
+
{
|
| 3732 |
+
"epoch": 2.2914714151827553,
|
| 3733 |
+
"grad_norm": 1.8807013034820557,
|
| 3734 |
+
"learning_rate": 1.856783036551078e-05,
|
| 3735 |
+
"loss": 0.1892,
|
| 3736 |
+
"step": 4890
|
| 3737 |
+
},
|
| 3738 |
+
{
|
| 3739 |
+
"epoch": 2.296157450796626,
|
| 3740 |
+
"grad_norm": 1.6185581684112549,
|
| 3741 |
+
"learning_rate": 1.856490159325211e-05,
|
| 3742 |
+
"loss": 0.1645,
|
| 3743 |
+
"step": 4900
|
| 3744 |
+
},
|
| 3745 |
+
{
|
| 3746 |
+
"epoch": 2.3008434864104967,
|
| 3747 |
+
"grad_norm": 1.7439680099487305,
|
| 3748 |
+
"learning_rate": 1.8561972820993443e-05,
|
| 3749 |
+
"loss": 0.1677,
|
| 3750 |
+
"step": 4910
|
| 3751 |
+
},
|
| 3752 |
+
{
|
| 3753 |
+
"epoch": 2.3055295220243672,
|
| 3754 |
+
"grad_norm": 1.9492429494857788,
|
| 3755 |
+
"learning_rate": 1.8559044048734773e-05,
|
| 3756 |
+
"loss": 0.1626,
|
| 3757 |
+
"step": 4920
|
| 3758 |
+
},
|
| 3759 |
+
{
|
| 3760 |
+
"epoch": 2.310215557638238,
|
| 3761 |
+
"grad_norm": 1.7018874883651733,
|
| 3762 |
+
"learning_rate": 1.8556115276476102e-05,
|
| 3763 |
+
"loss": 0.1581,
|
| 3764 |
+
"step": 4930
|
| 3765 |
+
},
|
| 3766 |
+
{
|
| 3767 |
+
"epoch": 2.3149015932521086,
|
| 3768 |
+
"grad_norm": 1.5858055353164673,
|
| 3769 |
+
"learning_rate": 1.855318650421743e-05,
|
| 3770 |
+
"loss": 0.2029,
|
| 3771 |
+
"step": 4940
|
| 3772 |
+
},
|
| 3773 |
+
{
|
| 3774 |
+
"epoch": 2.319587628865979,
|
| 3775 |
+
"grad_norm": 2.1818623542785645,
|
| 3776 |
+
"learning_rate": 1.8550257731958764e-05,
|
| 3777 |
+
"loss": 0.2094,
|
| 3778 |
+
"step": 4950
|
| 3779 |
+
},
|
| 3780 |
+
{
|
| 3781 |
+
"epoch": 2.32427366447985,
|
| 3782 |
+
"grad_norm": 1.5739350318908691,
|
| 3783 |
+
"learning_rate": 1.8547328959700094e-05,
|
| 3784 |
+
"loss": 0.1565,
|
| 3785 |
+
"step": 4960
|
| 3786 |
+
},
|
| 3787 |
+
{
|
| 3788 |
+
"epoch": 2.3289597000937206,
|
| 3789 |
+
"grad_norm": 1.1287211179733276,
|
| 3790 |
+
"learning_rate": 1.8544400187441427e-05,
|
| 3791 |
+
"loss": 0.1982,
|
| 3792 |
+
"step": 4970
|
| 3793 |
+
},
|
| 3794 |
+
{
|
| 3795 |
+
"epoch": 2.3336457357075915,
|
| 3796 |
+
"grad_norm": 1.8876228332519531,
|
| 3797 |
+
"learning_rate": 1.8541471415182756e-05,
|
| 3798 |
+
"loss": 0.1571,
|
| 3799 |
+
"step": 4980
|
| 3800 |
+
},
|
| 3801 |
+
{
|
| 3802 |
+
"epoch": 2.338331771321462,
|
| 3803 |
+
"grad_norm": 2.1654696464538574,
|
| 3804 |
+
"learning_rate": 1.8538542642924086e-05,
|
| 3805 |
+
"loss": 0.163,
|
| 3806 |
+
"step": 4990
|
| 3807 |
+
},
|
| 3808 |
+
{
|
| 3809 |
+
"epoch": 2.3430178069353325,
|
| 3810 |
+
"grad_norm": 1.3975324630737305,
|
| 3811 |
+
"learning_rate": 1.853561387066542e-05,
|
| 3812 |
+
"loss": 0.1816,
|
| 3813 |
+
"step": 5000
|
| 3814 |
+
},
|
| 3815 |
+
{
|
| 3816 |
+
"epoch": 2.3430178069353325,
|
| 3817 |
+
"eval_loss": 0.033037662506103516,
|
| 3818 |
+
"eval_pearson_cosine": 0.8184973777993747,
|
| 3819 |
+
"eval_pearson_dot": 0.750740290890306,
|
| 3820 |
+
"eval_pearson_euclidean": 0.7978417286720072,
|
| 3821 |
+
"eval_pearson_manhattan": 0.7999562879189881,
|
| 3822 |
+
"eval_runtime": 3.3021,
|
| 3823 |
+
"eval_samples_per_second": 454.257,
|
| 3824 |
+
"eval_spearman_cosine": 0.8181019655563226,
|
| 3825 |
+
"eval_spearman_dot": 0.750101463474286,
|
| 3826 |
+
"eval_spearman_euclidean": 0.8059752038134308,
|
| 3827 |
+
"eval_spearman_manhattan": 0.807850996089844,
|
| 3828 |
+
"eval_steps_per_second": 28.467,
|
| 3829 |
+
"step": 5000
|
| 3830 |
}
|
| 3831 |
],
|
| 3832 |
"logging_steps": 10,
|