Training in progress, step 56
Browse files- model.safetensors +1 -1
- run-nsu9scd5/checkpoint-56/config.json +22 -0
- run-nsu9scd5/checkpoint-56/model.safetensors +3 -0
- run-nsu9scd5/checkpoint-56/optimizer.pt +3 -0
- run-nsu9scd5/checkpoint-56/rng_state.pth +3 -0
- run-nsu9scd5/checkpoint-56/scheduler.pt +3 -0
- run-nsu9scd5/checkpoint-56/trainer_state.json +460 -0
- run-nsu9scd5/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:ea75ee0344de87c7ffa24006ad39ca5534d5f213aa8a5c56bdc1d43d375b2824
|
| 3 |
size 605156676
|
run-nsu9scd5/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-nsu9scd5/checkpoint-56/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea75ee0344de87c7ffa24006ad39ca5534d5f213aa8a5c56bdc1d43d375b2824
|
| 3 |
+
size 605156676
|
run-nsu9scd5/checkpoint-56/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cd2c8015dc891b12a057b46af44413d2b055db119d8fb6ea43ef7bd74926a16
|
| 3 |
+
size 1210551612
|
run-nsu9scd5/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-nsu9scd5/checkpoint-56/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a727781721b06e2c90a1e7e3f45bbd9ea06e67bcf0647950ffd80ad0dc058f86
|
| 3 |
+
size 1064
|
run-nsu9scd5/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": 268.4626770019531,
|
| 14 |
+
"learning_rate": 0.0005621725453848409,
|
| 15 |
+
"loss": 4.6194,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07142857142857142,
|
| 20 |
+
"eval_loss": 4.2445478439331055,
|
| 21 |
+
"eval_runtime": 108.1522,
|
| 22 |
+
"eval_samples_per_second": 3.236,
|
| 23 |
+
"eval_steps_per_second": 0.055,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.14285714285714285,
|
| 28 |
+
"grad_norm": 71.9693374633789,
|
| 29 |
+
"learning_rate": 0.0005413513400002172,
|
| 30 |
+
"loss": 6.5579,
|
| 31 |
+
"step": 4
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.14285714285714285,
|
| 35 |
+
"eval_loss": 4.125729560852051,
|
| 36 |
+
"eval_runtime": 146.7071,
|
| 37 |
+
"eval_samples_per_second": 2.386,
|
| 38 |
+
"eval_steps_per_second": 0.041,
|
| 39 |
+
"step": 4
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.21428571428571427,
|
| 43 |
+
"grad_norm": 5.648405075073242,
|
| 44 |
+
"learning_rate": 0.0005205301346155935,
|
| 45 |
+
"loss": 4.9826,
|
| 46 |
+
"step": 6
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.21428571428571427,
|
| 50 |
+
"eval_loss": 5.672520160675049,
|
| 51 |
+
"eval_runtime": 142.0721,
|
| 52 |
+
"eval_samples_per_second": 2.464,
|
| 53 |
+
"eval_steps_per_second": 0.042,
|
| 54 |
+
"step": 6
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.2857142857142857,
|
| 58 |
+
"grad_norm": 6.27989387512207,
|
| 59 |
+
"learning_rate": 0.0004997089292309697,
|
| 60 |
+
"loss": 5.9002,
|
| 61 |
+
"step": 8
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.2857142857142857,
|
| 65 |
+
"eval_loss": 4.104394912719727,
|
| 66 |
+
"eval_runtime": 135.6009,
|
| 67 |
+
"eval_samples_per_second": 2.581,
|
| 68 |
+
"eval_steps_per_second": 0.044,
|
| 69 |
+
"step": 8
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.35714285714285715,
|
| 73 |
+
"grad_norm": 0.1307026743888855,
|
| 74 |
+
"learning_rate": 0.000478887723846346,
|
| 75 |
+
"loss": 4.8597,
|
| 76 |
+
"step": 10
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.35714285714285715,
|
| 80 |
+
"eval_loss": 4.095502853393555,
|
| 81 |
+
"eval_runtime": 111.3151,
|
| 82 |
+
"eval_samples_per_second": 3.144,
|
| 83 |
+
"eval_steps_per_second": 0.054,
|
| 84 |
+
"step": 10
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.42857142857142855,
|
| 88 |
+
"grad_norm": 0.01885412447154522,
|
| 89 |
+
"learning_rate": 0.00045806651846172226,
|
| 90 |
+
"loss": 4.8531,
|
| 91 |
+
"step": 12
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.42857142857142855,
|
| 95 |
+
"eval_loss": 4.094283580780029,
|
| 96 |
+
"eval_runtime": 109.2586,
|
| 97 |
+
"eval_samples_per_second": 3.203,
|
| 98 |
+
"eval_steps_per_second": 0.055,
|
| 99 |
+
"step": 12
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.5,
|
| 103 |
+
"grad_norm": 0.010488088242709637,
|
| 104 |
+
"learning_rate": 0.0004372453130770985,
|
| 105 |
+
"loss": 4.8523,
|
| 106 |
+
"step": 14
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.5,
|
| 110 |
+
"eval_loss": 4.094061851501465,
|
| 111 |
+
"eval_runtime": 137.8714,
|
| 112 |
+
"eval_samples_per_second": 2.539,
|
| 113 |
+
"eval_steps_per_second": 0.044,
|
| 114 |
+
"step": 14
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5714285714285714,
|
| 118 |
+
"grad_norm": 0.006233076564967632,
|
| 119 |
+
"learning_rate": 0.00041642410769247477,
|
| 120 |
+
"loss": 4.8521,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5714285714285714,
|
| 125 |
+
"eval_loss": 4.093998432159424,
|
| 126 |
+
"eval_runtime": 129.4726,
|
| 127 |
+
"eval_samples_per_second": 2.703,
|
| 128 |
+
"eval_steps_per_second": 0.046,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.6428571428571429,
|
| 133 |
+
"grad_norm": 0.02763601951301098,
|
| 134 |
+
"learning_rate": 0.00039560290230785105,
|
| 135 |
+
"loss": 4.8521,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6428571428571429,
|
| 140 |
+
"eval_loss": 4.09397554397583,
|
| 141 |
+
"eval_runtime": 109.2369,
|
| 142 |
+
"eval_samples_per_second": 3.204,
|
| 143 |
+
"eval_steps_per_second": 0.055,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.7142857142857143,
|
| 148 |
+
"grad_norm": 0.005364938639104366,
|
| 149 |
+
"learning_rate": 0.00037478169692322733,
|
| 150 |
+
"loss": 4.8521,
|
| 151 |
+
"step": 20
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.7142857142857143,
|
| 155 |
+
"eval_loss": 4.093966960906982,
|
| 156 |
+
"eval_runtime": 129.3687,
|
| 157 |
+
"eval_samples_per_second": 2.705,
|
| 158 |
+
"eval_steps_per_second": 0.046,
|
| 159 |
+
"step": 20
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.7857142857142857,
|
| 163 |
+
"grad_norm": 0.0038224116433411837,
|
| 164 |
+
"learning_rate": 0.00035396049153860355,
|
| 165 |
+
"loss": 4.8521,
|
| 166 |
+
"step": 22
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.7857142857142857,
|
| 170 |
+
"eval_loss": 4.093982219696045,
|
| 171 |
+
"eval_runtime": 110.6155,
|
| 172 |
+
"eval_samples_per_second": 3.164,
|
| 173 |
+
"eval_steps_per_second": 0.054,
|
| 174 |
+
"step": 22
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.8571428571428571,
|
| 178 |
+
"grad_norm": 0.005476065911352634,
|
| 179 |
+
"learning_rate": 0.0003331392861539798,
|
| 180 |
+
"loss": 4.8521,
|
| 181 |
+
"step": 24
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.8571428571428571,
|
| 185 |
+
"eval_loss": 4.093994140625,
|
| 186 |
+
"eval_runtime": 108.8427,
|
| 187 |
+
"eval_samples_per_second": 3.216,
|
| 188 |
+
"eval_steps_per_second": 0.055,
|
| 189 |
+
"step": 24
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.9285714285714286,
|
| 193 |
+
"grad_norm": 0.00341013353317976,
|
| 194 |
+
"learning_rate": 0.00031231808076935606,
|
| 195 |
+
"loss": 4.8521,
|
| 196 |
+
"step": 26
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.9285714285714286,
|
| 200 |
+
"eval_loss": 4.093983173370361,
|
| 201 |
+
"eval_runtime": 109.5893,
|
| 202 |
+
"eval_samples_per_second": 3.194,
|
| 203 |
+
"eval_steps_per_second": 0.055,
|
| 204 |
+
"step": 26
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.0,
|
| 208 |
+
"grad_norm": 0.004943197127431631,
|
| 209 |
+
"learning_rate": 0.00029149687538473234,
|
| 210 |
+
"loss": 4.3067,
|
| 211 |
+
"step": 28
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.0,
|
| 215 |
+
"eval_loss": 4.093968868255615,
|
| 216 |
+
"eval_runtime": 109.4688,
|
| 217 |
+
"eval_samples_per_second": 3.197,
|
| 218 |
+
"eval_steps_per_second": 0.055,
|
| 219 |
+
"step": 28
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0714285714285714,
|
| 223 |
+
"grad_norm": 0.002467899350449443,
|
| 224 |
+
"learning_rate": 0.0002706756700001086,
|
| 225 |
+
"loss": 4.8521,
|
| 226 |
+
"step": 30
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0714285714285714,
|
| 230 |
+
"eval_loss": 4.093968868255615,
|
| 231 |
+
"eval_runtime": 108.5053,
|
| 232 |
+
"eval_samples_per_second": 3.226,
|
| 233 |
+
"eval_steps_per_second": 0.055,
|
| 234 |
+
"step": 30
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.1428571428571428,
|
| 238 |
+
"grad_norm": 0.004230957478284836,
|
| 239 |
+
"learning_rate": 0.00024985446461548485,
|
| 240 |
+
"loss": 4.8521,
|
| 241 |
+
"step": 32
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.1428571428571428,
|
| 245 |
+
"eval_loss": 4.093967914581299,
|
| 246 |
+
"eval_runtime": 121.2409,
|
| 247 |
+
"eval_samples_per_second": 2.887,
|
| 248 |
+
"eval_steps_per_second": 0.049,
|
| 249 |
+
"step": 32
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.2142857142857142,
|
| 253 |
+
"grad_norm": 0.0021761604584753513,
|
| 254 |
+
"learning_rate": 0.00022903325923086113,
|
| 255 |
+
"loss": 4.8521,
|
| 256 |
+
"step": 34
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.2142857142857142,
|
| 260 |
+
"eval_loss": 4.093955993652344,
|
| 261 |
+
"eval_runtime": 150.1791,
|
| 262 |
+
"eval_samples_per_second": 2.331,
|
| 263 |
+
"eval_steps_per_second": 0.04,
|
| 264 |
+
"step": 34
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.2857142857142856,
|
| 268 |
+
"grad_norm": 0.0025435429997742176,
|
| 269 |
+
"learning_rate": 0.00020821205384623738,
|
| 270 |
+
"loss": 4.8521,
|
| 271 |
+
"step": 36
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.2857142857142856,
|
| 275 |
+
"eval_loss": 4.093955039978027,
|
| 276 |
+
"eval_runtime": 138.5452,
|
| 277 |
+
"eval_samples_per_second": 2.526,
|
| 278 |
+
"eval_steps_per_second": 0.043,
|
| 279 |
+
"step": 36
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.3571428571428572,
|
| 283 |
+
"grad_norm": 0.0025120778009295464,
|
| 284 |
+
"learning_rate": 0.00018739084846161366,
|
| 285 |
+
"loss": 4.852,
|
| 286 |
+
"step": 38
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.3571428571428572,
|
| 290 |
+
"eval_loss": 4.093952178955078,
|
| 291 |
+
"eval_runtime": 159.7134,
|
| 292 |
+
"eval_samples_per_second": 2.191,
|
| 293 |
+
"eval_steps_per_second": 0.038,
|
| 294 |
+
"step": 38
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.4285714285714286,
|
| 298 |
+
"grad_norm": 0.0023238961584866047,
|
| 299 |
+
"learning_rate": 0.0001665696430769899,
|
| 300 |
+
"loss": 4.852,
|
| 301 |
+
"step": 40
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 1.4285714285714286,
|
| 305 |
+
"eval_loss": 4.093949317932129,
|
| 306 |
+
"eval_runtime": 143.6861,
|
| 307 |
+
"eval_samples_per_second": 2.436,
|
| 308 |
+
"eval_steps_per_second": 0.042,
|
| 309 |
+
"step": 40
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.5,
|
| 313 |
+
"grad_norm": 0.0012704160762950778,
|
| 314 |
+
"learning_rate": 0.00014574843769236617,
|
| 315 |
+
"loss": 4.852,
|
| 316 |
+
"step": 42
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.5,
|
| 320 |
+
"eval_loss": 4.0939459800720215,
|
| 321 |
+
"eval_runtime": 122.8463,
|
| 322 |
+
"eval_samples_per_second": 2.849,
|
| 323 |
+
"eval_steps_per_second": 0.049,
|
| 324 |
+
"step": 42
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.5714285714285714,
|
| 328 |
+
"grad_norm": 0.0016051293350756168,
|
| 329 |
+
"learning_rate": 0.00012492723230774242,
|
| 330 |
+
"loss": 4.852,
|
| 331 |
+
"step": 44
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.5714285714285714,
|
| 335 |
+
"eval_loss": 4.093944549560547,
|
| 336 |
+
"eval_runtime": 107.8466,
|
| 337 |
+
"eval_samples_per_second": 3.245,
|
| 338 |
+
"eval_steps_per_second": 0.056,
|
| 339 |
+
"step": 44
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.6428571428571428,
|
| 343 |
+
"grad_norm": 0.0015636960742995143,
|
| 344 |
+
"learning_rate": 0.00010410602692311869,
|
| 345 |
+
"loss": 4.852,
|
| 346 |
+
"step": 46
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.6428571428571428,
|
| 350 |
+
"eval_loss": 4.093943119049072,
|
| 351 |
+
"eval_runtime": 129.3014,
|
| 352 |
+
"eval_samples_per_second": 2.707,
|
| 353 |
+
"eval_steps_per_second": 0.046,
|
| 354 |
+
"step": 46
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.7142857142857144,
|
| 358 |
+
"grad_norm": 0.001410445780493319,
|
| 359 |
+
"learning_rate": 8.328482153849495e-05,
|
| 360 |
+
"loss": 4.8521,
|
| 361 |
+
"step": 48
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.7142857142857144,
|
| 365 |
+
"eval_loss": 4.093941688537598,
|
| 366 |
+
"eval_runtime": 109.6222,
|
| 367 |
+
"eval_samples_per_second": 3.193,
|
| 368 |
+
"eval_steps_per_second": 0.055,
|
| 369 |
+
"step": 48
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.7857142857142856,
|
| 373 |
+
"grad_norm": 0.001393631100654602,
|
| 374 |
+
"learning_rate": 6.246361615387121e-05,
|
| 375 |
+
"loss": 4.852,
|
| 376 |
+
"step": 50
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.7857142857142856,
|
| 380 |
+
"eval_loss": 4.093940734863281,
|
| 381 |
+
"eval_runtime": 122.8998,
|
| 382 |
+
"eval_samples_per_second": 2.848,
|
| 383 |
+
"eval_steps_per_second": 0.049,
|
| 384 |
+
"step": 50
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.8571428571428572,
|
| 388 |
+
"grad_norm": 0.0009566438966430724,
|
| 389 |
+
"learning_rate": 4.164241076924747e-05,
|
| 390 |
+
"loss": 4.852,
|
| 391 |
+
"step": 52
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 1.8571428571428572,
|
| 395 |
+
"eval_loss": 4.093940258026123,
|
| 396 |
+
"eval_runtime": 134.9009,
|
| 397 |
+
"eval_samples_per_second": 2.594,
|
| 398 |
+
"eval_steps_per_second": 0.044,
|
| 399 |
+
"step": 52
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.9285714285714286,
|
| 403 |
+
"grad_norm": 0.0013086905237287283,
|
| 404 |
+
"learning_rate": 2.0821205384623736e-05,
|
| 405 |
+
"loss": 4.852,
|
| 406 |
+
"step": 54
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.9285714285714286,
|
| 410 |
+
"eval_loss": 4.093940258026123,
|
| 411 |
+
"eval_runtime": 126.2369,
|
| 412 |
+
"eval_samples_per_second": 2.773,
|
| 413 |
+
"eval_steps_per_second": 0.048,
|
| 414 |
+
"step": 54
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.0,
|
| 418 |
+
"grad_norm": 0.0012161381309852004,
|
| 419 |
+
"learning_rate": 0.0,
|
| 420 |
+
"loss": 4.3066,
|
| 421 |
+
"step": 56
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 2.0,
|
| 425 |
+
"eval_loss": 4.093940258026123,
|
| 426 |
+
"eval_runtime": 110.6877,
|
| 427 |
+
"eval_samples_per_second": 3.162,
|
| 428 |
+
"eval_steps_per_second": 0.054,
|
| 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": 0.0005829937507694647,
|
| 457 |
+
"metric": "eval/loss",
|
| 458 |
+
"per_device_train_batch_size": 128
|
| 459 |
+
}
|
| 460 |
+
}
|
run-nsu9scd5/checkpoint-56/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e65c9b9f2148f5abc16017a7c21702c049735777ed8cef5c9a4444b3bd55cc1
|
| 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 sha256:7e65c9b9f2148f5abc16017a7c21702c049735777ed8cef5c9a4444b3bd55cc1
|
| 3 |
size 5112
|