Training in progress, step 56
Browse files- model.safetensors +1 -1
- run-s28vy89y/checkpoint-56/config.json +22 -0
- run-s28vy89y/checkpoint-56/model.safetensors +3 -0
- run-s28vy89y/checkpoint-56/optimizer.pt +3 -0
- run-s28vy89y/checkpoint-56/rng_state.pth +3 -0
- run-s28vy89y/checkpoint-56/scheduler.pt +3 -0
- run-s28vy89y/checkpoint-56/trainer_state.json +460 -0
- run-s28vy89y/checkpoint-56/training_args.bin +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 605156676
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e469f4e5e0aebde708d69422bfec5a756da896a8d5d32ccbed422c7319a0700f
|
| 3 |
size 605156676
|
run-s28vy89y/checkpoint-56/config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openai/clip-vit-base-patch32",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPModel"
|
| 5 |
+
],
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"logit_scale_init_value": 2.6592,
|
| 8 |
+
"model_type": "clip",
|
| 9 |
+
"projection_dim": 512,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"dropout": 0.0,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"model_type": "clip_text_model"
|
| 15 |
+
},
|
| 16 |
+
"torch_dtype": "float32",
|
| 17 |
+
"transformers_version": "4.42.0.dev0",
|
| 18 |
+
"vision_config": {
|
| 19 |
+
"dropout": 0.0,
|
| 20 |
+
"model_type": "clip_vision_model"
|
| 21 |
+
}
|
| 22 |
+
}
|
run-s28vy89y/checkpoint-56/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e469f4e5e0aebde708d69422bfec5a756da896a8d5d32ccbed422c7319a0700f
|
| 3 |
+
size 605156676
|
run-s28vy89y/checkpoint-56/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdc9bfa0c5e4f8b16828b99229e3be7d0c2a3f8646bdbc56eec98b8367e0148f
|
| 3 |
+
size 1210551612
|
run-s28vy89y/checkpoint-56/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa60fcccd210fbce94ddbc859c60cbfe614bd8a2e7a77c981415dbc28c811cd8
|
| 3 |
+
size 14244
|
run-s28vy89y/checkpoint-56/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4388113874687ca286bafb6a30e9edf634a664b45d873dea35e14ac5bdf40657
|
| 3 |
+
size 1064
|
run-s28vy89y/checkpoint-56/trainer_state.json
ADDED
|
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 2,
|
| 6 |
+
"global_step": 56,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07142857142857142,
|
| 13 |
+
"grad_norm": 499.6013488769531,
|
| 14 |
+
"learning_rate": 0.00035333138396736785,
|
| 15 |
+
"loss": 5.7451,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07142857142857142,
|
| 20 |
+
"eval_loss": 4.145218372344971,
|
| 21 |
+
"eval_runtime": 115.5605,
|
| 22 |
+
"eval_samples_per_second": 3.029,
|
| 23 |
+
"eval_steps_per_second": 0.052,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.14285714285714285,
|
| 28 |
+
"grad_norm": 41.22399139404297,
|
| 29 |
+
"learning_rate": 0.0003402450364130209,
|
| 30 |
+
"loss": 5.3316,
|
| 31 |
+
"step": 4
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.14285714285714285,
|
| 35 |
+
"eval_loss": 4.5622239112854,
|
| 36 |
+
"eval_runtime": 159.5,
|
| 37 |
+
"eval_samples_per_second": 2.194,
|
| 38 |
+
"eval_steps_per_second": 0.038,
|
| 39 |
+
"step": 4
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.21428571428571427,
|
| 43 |
+
"grad_norm": 2.202932596206665,
|
| 44 |
+
"learning_rate": 0.00032715868885867396,
|
| 45 |
+
"loss": 5.0703,
|
| 46 |
+
"step": 6
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.21428571428571427,
|
| 50 |
+
"eval_loss": 4.1197967529296875,
|
| 51 |
+
"eval_runtime": 110.2677,
|
| 52 |
+
"eval_samples_per_second": 3.174,
|
| 53 |
+
"eval_steps_per_second": 0.054,
|
| 54 |
+
"step": 6
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.2857142857142857,
|
| 58 |
+
"grad_norm": 0.4056661128997803,
|
| 59 |
+
"learning_rate": 0.00031407234130432696,
|
| 60 |
+
"loss": 4.869,
|
| 61 |
+
"step": 8
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.2857142857142857,
|
| 65 |
+
"eval_loss": 4.0951642990112305,
|
| 66 |
+
"eval_runtime": 133.7942,
|
| 67 |
+
"eval_samples_per_second": 2.616,
|
| 68 |
+
"eval_steps_per_second": 0.045,
|
| 69 |
+
"step": 8
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.35714285714285715,
|
| 73 |
+
"grad_norm": 0.29455429315567017,
|
| 74 |
+
"learning_rate": 0.00030098599374998,
|
| 75 |
+
"loss": 4.854,
|
| 76 |
+
"step": 10
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.35714285714285715,
|
| 80 |
+
"eval_loss": 4.096081733703613,
|
| 81 |
+
"eval_runtime": 117.4958,
|
| 82 |
+
"eval_samples_per_second": 2.979,
|
| 83 |
+
"eval_steps_per_second": 0.051,
|
| 84 |
+
"step": 10
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.42857142857142855,
|
| 88 |
+
"grad_norm": 0.10492418706417084,
|
| 89 |
+
"learning_rate": 0.00028789964619563307,
|
| 90 |
+
"loss": 4.8537,
|
| 91 |
+
"step": 12
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.42857142857142855,
|
| 95 |
+
"eval_loss": 4.0943403244018555,
|
| 96 |
+
"eval_runtime": 134.1581,
|
| 97 |
+
"eval_samples_per_second": 2.609,
|
| 98 |
+
"eval_steps_per_second": 0.045,
|
| 99 |
+
"step": 12
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.5,
|
| 103 |
+
"grad_norm": 0.016932426020503044,
|
| 104 |
+
"learning_rate": 0.0002748132986412861,
|
| 105 |
+
"loss": 4.8523,
|
| 106 |
+
"step": 14
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.5,
|
| 110 |
+
"eval_loss": 4.094045162200928,
|
| 111 |
+
"eval_runtime": 151.7694,
|
| 112 |
+
"eval_samples_per_second": 2.306,
|
| 113 |
+
"eval_steps_per_second": 0.04,
|
| 114 |
+
"step": 14
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5714285714285714,
|
| 118 |
+
"grad_norm": 0.024902725592255592,
|
| 119 |
+
"learning_rate": 0.0002617269510869391,
|
| 120 |
+
"loss": 4.8522,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5714285714285714,
|
| 125 |
+
"eval_loss": 4.094315528869629,
|
| 126 |
+
"eval_runtime": 180.0495,
|
| 127 |
+
"eval_samples_per_second": 1.944,
|
| 128 |
+
"eval_steps_per_second": 0.033,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6428571428571429,
|
| 133 |
+
"grad_norm": 0.03983244299888611,
|
| 134 |
+
"learning_rate": 0.0002486406035325922,
|
| 135 |
+
"loss": 4.8525,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6428571428571429,
|
| 140 |
+
"eval_loss": 4.094301223754883,
|
| 141 |
+
"eval_runtime": 111.1902,
|
| 142 |
+
"eval_samples_per_second": 3.148,
|
| 143 |
+
"eval_steps_per_second": 0.054,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.7142857142857143,
|
| 148 |
+
"grad_norm": 0.021751634776592255,
|
| 149 |
+
"learning_rate": 0.00023555425597824523,
|
| 150 |
+
"loss": 4.8524,
|
| 151 |
+
"step": 20
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.7142857142857143,
|
| 155 |
+
"eval_loss": 4.094165802001953,
|
| 156 |
+
"eval_runtime": 122.9871,
|
| 157 |
+
"eval_samples_per_second": 2.846,
|
| 158 |
+
"eval_steps_per_second": 0.049,
|
| 159 |
+
"step": 20
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.7857142857142857,
|
| 163 |
+
"grad_norm": 0.01534917950630188,
|
| 164 |
+
"learning_rate": 0.00022246790842389826,
|
| 165 |
+
"loss": 4.8522,
|
| 166 |
+
"step": 22
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.7857142857142857,
|
| 170 |
+
"eval_loss": 4.094093322753906,
|
| 171 |
+
"eval_runtime": 155.9317,
|
| 172 |
+
"eval_samples_per_second": 2.245,
|
| 173 |
+
"eval_steps_per_second": 0.038,
|
| 174 |
+
"step": 22
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.8571428571428571,
|
| 178 |
+
"grad_norm": 0.01246840413659811,
|
| 179 |
+
"learning_rate": 0.0002093815608695513,
|
| 180 |
+
"loss": 4.8522,
|
| 181 |
+
"step": 24
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.8571428571428571,
|
| 185 |
+
"eval_loss": 4.094055652618408,
|
| 186 |
+
"eval_runtime": 199.4288,
|
| 187 |
+
"eval_samples_per_second": 1.755,
|
| 188 |
+
"eval_steps_per_second": 0.03,
|
| 189 |
+
"step": 24
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.9285714285714286,
|
| 193 |
+
"grad_norm": 0.00821756012737751,
|
| 194 |
+
"learning_rate": 0.00019629521331520434,
|
| 195 |
+
"loss": 4.8521,
|
| 196 |
+
"step": 26
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.9285714285714286,
|
| 200 |
+
"eval_loss": 4.094019412994385,
|
| 201 |
+
"eval_runtime": 110.2163,
|
| 202 |
+
"eval_samples_per_second": 3.176,
|
| 203 |
+
"eval_steps_per_second": 0.054,
|
| 204 |
+
"step": 26
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.0,
|
| 208 |
+
"grad_norm": 0.00944442953914404,
|
| 209 |
+
"learning_rate": 0.0001832088657608574,
|
| 210 |
+
"loss": 4.3067,
|
| 211 |
+
"step": 28
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.0,
|
| 215 |
+
"eval_loss": 4.093985557556152,
|
| 216 |
+
"eval_runtime": 109.3834,
|
| 217 |
+
"eval_samples_per_second": 3.2,
|
| 218 |
+
"eval_steps_per_second": 0.055,
|
| 219 |
+
"step": 28
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0714285714285714,
|
| 223 |
+
"grad_norm": 0.0032597698736935854,
|
| 224 |
+
"learning_rate": 0.00017012251820651045,
|
| 225 |
+
"loss": 4.8521,
|
| 226 |
+
"step": 30
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0714285714285714,
|
| 230 |
+
"eval_loss": 4.093966960906982,
|
| 231 |
+
"eval_runtime": 110.1116,
|
| 232 |
+
"eval_samples_per_second": 3.179,
|
| 233 |
+
"eval_steps_per_second": 0.054,
|
| 234 |
+
"step": 30
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.1428571428571428,
|
| 238 |
+
"grad_norm": 0.0018325659912079573,
|
| 239 |
+
"learning_rate": 0.00015703617065216348,
|
| 240 |
+
"loss": 4.8521,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.1428571428571428,
|
| 245 |
+
"eval_loss": 4.093964099884033,
|
| 246 |
+
"eval_runtime": 110.0212,
|
| 247 |
+
"eval_samples_per_second": 3.181,
|
| 248 |
+
"eval_steps_per_second": 0.055,
|
| 249 |
+
"step": 32
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.2142857142857142,
|
| 253 |
+
"grad_norm": 0.002593304729089141,
|
| 254 |
+
"learning_rate": 0.00014394982309781654,
|
| 255 |
+
"loss": 4.8521,
|
| 256 |
+
"step": 34
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.2142857142857142,
|
| 260 |
+
"eval_loss": 4.093966007232666,
|
| 261 |
+
"eval_runtime": 162.0241,
|
| 262 |
+
"eval_samples_per_second": 2.16,
|
| 263 |
+
"eval_steps_per_second": 0.037,
|
| 264 |
+
"step": 34
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.2857142857142856,
|
| 268 |
+
"grad_norm": 0.003515275428071618,
|
| 269 |
+
"learning_rate": 0.00013086347554346956,
|
| 270 |
+
"loss": 4.8521,
|
| 271 |
+
"step": 36
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.2857142857142856,
|
| 275 |
+
"eval_loss": 4.093967437744141,
|
| 276 |
+
"eval_runtime": 113.1292,
|
| 277 |
+
"eval_samples_per_second": 3.094,
|
| 278 |
+
"eval_steps_per_second": 0.053,
|
| 279 |
+
"step": 36
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.3571428571428572,
|
| 283 |
+
"grad_norm": 0.004078236408531666,
|
| 284 |
+
"learning_rate": 0.00011777712798912262,
|
| 285 |
+
"loss": 4.8521,
|
| 286 |
+
"step": 38
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.3571428571428572,
|
| 290 |
+
"eval_loss": 4.09396505355835,
|
| 291 |
+
"eval_runtime": 184.5537,
|
| 292 |
+
"eval_samples_per_second": 1.896,
|
| 293 |
+
"eval_steps_per_second": 0.033,
|
| 294 |
+
"step": 38
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.4285714285714286,
|
| 298 |
+
"grad_norm": 0.003892536973580718,
|
| 299 |
+
"learning_rate": 0.00010469078043477564,
|
| 300 |
+
"loss": 4.8521,
|
| 301 |
+
"step": 40
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.4285714285714286,
|
| 305 |
+
"eval_loss": 4.093959331512451,
|
| 306 |
+
"eval_runtime": 113.0981,
|
| 307 |
+
"eval_samples_per_second": 3.095,
|
| 308 |
+
"eval_steps_per_second": 0.053,
|
| 309 |
+
"step": 40
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.5,
|
| 313 |
+
"grad_norm": 0.0023005367256700993,
|
| 314 |
+
"learning_rate": 9.16044328804287e-05,
|
| 315 |
+
"loss": 4.852,
|
| 316 |
+
"step": 42
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.5,
|
| 320 |
+
"eval_loss": 4.093954563140869,
|
| 321 |
+
"eval_runtime": 118.4819,
|
| 322 |
+
"eval_samples_per_second": 2.954,
|
| 323 |
+
"eval_steps_per_second": 0.051,
|
| 324 |
+
"step": 42
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.5714285714285714,
|
| 328 |
+
"grad_norm": 0.0026939427480101585,
|
| 329 |
+
"learning_rate": 7.851808532608174e-05,
|
| 330 |
+
"loss": 4.852,
|
| 331 |
+
"step": 44
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.5714285714285714,
|
| 335 |
+
"eval_loss": 4.09395170211792,
|
| 336 |
+
"eval_runtime": 139.5353,
|
| 337 |
+
"eval_samples_per_second": 2.508,
|
| 338 |
+
"eval_steps_per_second": 0.043,
|
| 339 |
+
"step": 44
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6428571428571428,
|
| 343 |
+
"grad_norm": 0.0018068618373945355,
|
| 344 |
+
"learning_rate": 6.543173777173478e-05,
|
| 345 |
+
"loss": 4.852,
|
| 346 |
+
"step": 46
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.6428571428571428,
|
| 350 |
+
"eval_loss": 4.0939507484436035,
|
| 351 |
+
"eval_runtime": 119.3509,
|
| 352 |
+
"eval_samples_per_second": 2.933,
|
| 353 |
+
"eval_steps_per_second": 0.05,
|
| 354 |
+
"step": 46
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.7142857142857144,
|
| 358 |
+
"grad_norm": 0.0018717749044299126,
|
| 359 |
+
"learning_rate": 5.234539021738782e-05,
|
| 360 |
+
"loss": 4.852,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.7142857142857144,
|
| 365 |
+
"eval_loss": 4.093950271606445,
|
| 366 |
+
"eval_runtime": 127.677,
|
| 367 |
+
"eval_samples_per_second": 2.741,
|
| 368 |
+
"eval_steps_per_second": 0.047,
|
| 369 |
+
"step": 48
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.7857142857142856,
|
| 373 |
+
"grad_norm": 0.001300295814871788,
|
| 374 |
+
"learning_rate": 3.925904266304087e-05,
|
| 375 |
+
"loss": 4.852,
|
| 376 |
+
"step": 50
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.7857142857142856,
|
| 380 |
+
"eval_loss": 4.093948841094971,
|
| 381 |
+
"eval_runtime": 140.3917,
|
| 382 |
+
"eval_samples_per_second": 2.493,
|
| 383 |
+
"eval_steps_per_second": 0.043,
|
| 384 |
+
"step": 50
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.8571428571428572,
|
| 388 |
+
"grad_norm": 0.0016825235215947032,
|
| 389 |
+
"learning_rate": 2.617269510869391e-05,
|
| 390 |
+
"loss": 4.852,
|
| 391 |
+
"step": 52
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.8571428571428572,
|
| 395 |
+
"eval_loss": 4.093948841094971,
|
| 396 |
+
"eval_runtime": 132.6149,
|
| 397 |
+
"eval_samples_per_second": 2.639,
|
| 398 |
+
"eval_steps_per_second": 0.045,
|
| 399 |
+
"step": 52
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.9285714285714286,
|
| 403 |
+
"grad_norm": 0.0014735407894477248,
|
| 404 |
+
"learning_rate": 1.3086347554346956e-05,
|
| 405 |
+
"loss": 4.852,
|
| 406 |
+
"step": 54
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.9285714285714286,
|
| 410 |
+
"eval_loss": 4.093948841094971,
|
| 411 |
+
"eval_runtime": 123.3755,
|
| 412 |
+
"eval_samples_per_second": 2.837,
|
| 413 |
+
"eval_steps_per_second": 0.049,
|
| 414 |
+
"step": 54
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.0,
|
| 418 |
+
"grad_norm": 0.0010560819646343589,
|
| 419 |
+
"learning_rate": 0.0,
|
| 420 |
+
"loss": 4.3066,
|
| 421 |
+
"step": 56
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.0,
|
| 425 |
+
"eval_loss": 4.093948841094971,
|
| 426 |
+
"eval_runtime": 107.7247,
|
| 427 |
+
"eval_samples_per_second": 3.249,
|
| 428 |
+
"eval_steps_per_second": 0.056,
|
| 429 |
+
"step": 56
|
| 430 |
+
}
|
| 431 |
+
],
|
| 432 |
+
"logging_steps": 2,
|
| 433 |
+
"max_steps": 56,
|
| 434 |
+
"num_input_tokens_seen": 0,
|
| 435 |
+
"num_train_epochs": 2,
|
| 436 |
+
"save_steps": 500,
|
| 437 |
+
"stateful_callbacks": {
|
| 438 |
+
"TrainerControl": {
|
| 439 |
+
"args": {
|
| 440 |
+
"should_epoch_stop": false,
|
| 441 |
+
"should_evaluate": false,
|
| 442 |
+
"should_log": false,
|
| 443 |
+
"should_save": true,
|
| 444 |
+
"should_training_stop": true
|
| 445 |
+
},
|
| 446 |
+
"attributes": {}
|
| 447 |
+
}
|
| 448 |
+
},
|
| 449 |
+
"total_flos": 407052651766068.0,
|
| 450 |
+
"train_batch_size": 128,
|
| 451 |
+
"trial_name": null,
|
| 452 |
+
"trial_params": {
|
| 453 |
+
"_wandb": {},
|
| 454 |
+
"assignments": {},
|
| 455 |
+
"decay": 0.01,
|
| 456 |
+
"learning_rate": 0.0003664177315217148,
|
| 457 |
+
"metric": "eval/loss",
|
| 458 |
+
"per_device_train_batch_size": 128
|
| 459 |
+
}
|
| 460 |
+
}
|
run-s28vy89y/checkpoint-56/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec583036ee75123b3ad43a5af2bca340e80c9be115a3e221d0646ea35625512c
|
| 3 |
+
size 5112
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec583036ee75123b3ad43a5af2bca340e80c9be115a3e221d0646ea35625512c
|
| 3 |
size 5112
|