Upload 14 files
Browse files- config.json +2 -2
- model.safetensors +2 -2
- optimizer.pt +2 -2
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +1 -1
- trainer_state.json +262 -104
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "microsoft/
|
| 3 |
"architectures": [
|
| 4 |
"DebertaV2ForSequenceClassification"
|
| 5 |
],
|
|
@@ -42,5 +42,5 @@
|
|
| 42 |
"torch_dtype": "float32",
|
| 43 |
"transformers_version": "4.46.3",
|
| 44 |
"type_vocab_size": 0,
|
| 45 |
-
"vocab_size":
|
| 46 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "microsoft/mdeberta-v3-base",
|
| 3 |
"architectures": [
|
| 4 |
"DebertaV2ForSequenceClassification"
|
| 5 |
],
|
|
|
|
| 42 |
"torch_dtype": "float32",
|
| 43 |
"transformers_version": "4.46.3",
|
| 44 |
"type_vocab_size": 0,
|
| 45 |
+
"vocab_size": 251000
|
| 46 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2c014245ee7a2d39769e223503c03bc2cca57313e7aa8543efcaa4b802a3f61
|
| 3 |
+
size 1115271284
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d9cabf3a82eb8e3c7d9c74c3f1cd32f6b4fe3199c1016050950c7fd5d3cac9a
|
| 3 |
+
size 2230662138
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fba9836d3d5d131b179fe7b16872f0458f9ebf0e4b1ed6cead0b06f1011984f3
|
| 3 |
+
size 15984
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2a0c7025936f28ccadaeabad382f47beb7500bee229d6cadbca163725ffe1d4
|
| 3 |
+
size 15984
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1871450a718945b3a8f0c9b05f32928beaa2dff494f7f8ae0d7acbbe8ab99575
|
| 3 |
+
size 15984
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a278fb64096b400bcb71e42326226b98095346679b386a45020136626e71c84
|
| 3 |
+
size 15984
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85f8fd5c6381ed996cfc981c90e784927522bf727a148c2dc7644a129148cc28
|
| 3 |
+
size 15984
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0280f37d29580c31bc7d1d6228c906b4878d32927af739cb82e4228ba73fd30
|
| 3 |
+
size 15984
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36d8cbfbca6b874820791af59a1b4320c909ebd361dd3955e8c6b7343461bb43
|
| 3 |
+
size 15984
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cafaea57a4cda8ba3e730c6f5572f696d7c678648476ef37977a5cc4650e5e25
|
| 3 |
+
size 15984
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e6703b36d6b79a3ae4291228a28a3b0975b7538704440c681042f431f22e174
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,168 +1,326 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/shevtsov/
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"learning_rate": 5e-06,
|
| 15 |
-
"loss": 0.
|
| 16 |
-
"step":
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.0,
|
| 20 |
-
"eval_accuracy": 0.
|
| 21 |
-
"eval_f1": 0.
|
| 22 |
-
"eval_loss":
|
| 23 |
-
"eval_precision": 0.
|
| 24 |
-
"eval_recall": 0.
|
| 25 |
-
"eval_runtime":
|
| 26 |
-
"eval_samples_per_second":
|
| 27 |
-
"eval_steps_per_second":
|
| 28 |
-
"step":
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"epoch": 2.0,
|
| 32 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
"learning_rate": 4.849231551964771e-06,
|
| 34 |
-
"loss": 0.
|
| 35 |
-
"step":
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 2.0,
|
| 39 |
-
"eval_accuracy": 0.
|
| 40 |
-
"eval_f1": 0.
|
| 41 |
-
"eval_loss": 0.
|
| 42 |
-
"eval_precision": 0.
|
| 43 |
-
"eval_recall": 0.
|
| 44 |
-
"eval_runtime":
|
| 45 |
-
"eval_samples_per_second":
|
| 46 |
-
"eval_steps_per_second":
|
| 47 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"epoch": 3.0,
|
| 51 |
-
"grad_norm":
|
| 52 |
"learning_rate": 4.415111107797445e-06,
|
| 53 |
-
"loss": 0.
|
| 54 |
-
"step":
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 3.0,
|
| 58 |
-
"eval_accuracy": 0.
|
| 59 |
-
"eval_f1": 0.
|
| 60 |
-
"eval_loss":
|
| 61 |
-
"eval_precision": 0.
|
| 62 |
-
"eval_recall": 0.
|
| 63 |
-
"eval_runtime":
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second":
|
| 66 |
-
"step":
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 4.0,
|
| 70 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
"learning_rate": 3.7500000000000005e-06,
|
| 72 |
-
"loss": 0.
|
| 73 |
-
"step":
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 4.0,
|
| 77 |
-
"eval_accuracy": 0.
|
| 78 |
-
"eval_f1": 0.
|
| 79 |
-
"eval_loss":
|
| 80 |
-
"eval_precision": 0.
|
| 81 |
-
"eval_recall": 0.
|
| 82 |
-
"eval_runtime":
|
| 83 |
-
"eval_samples_per_second":
|
| 84 |
-
"eval_steps_per_second":
|
| 85 |
-
"step":
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"epoch": 5.0,
|
| 89 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
"learning_rate": 2.9341204441673267e-06,
|
| 91 |
-
"loss": 0.
|
| 92 |
-
"step":
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 5.0,
|
| 96 |
-
"eval_accuracy": 0.
|
| 97 |
-
"eval_f1": 0.
|
| 98 |
-
"eval_loss":
|
| 99 |
-
"eval_precision": 0.
|
| 100 |
-
"eval_recall": 0.
|
| 101 |
-
"eval_runtime":
|
| 102 |
-
"eval_samples_per_second":
|
| 103 |
-
"eval_steps_per_second":
|
| 104 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 6.0,
|
| 108 |
-
"grad_norm":
|
| 109 |
"learning_rate": 2.0658795558326745e-06,
|
| 110 |
-
"loss": 0.
|
| 111 |
-
"step":
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 6.0,
|
| 115 |
-
"eval_accuracy": 0.
|
| 116 |
-
"eval_f1": 0.
|
| 117 |
-
"eval_loss":
|
| 118 |
-
"eval_precision": 0.
|
| 119 |
-
"eval_recall": 0.
|
| 120 |
-
"eval_runtime":
|
| 121 |
-
"eval_samples_per_second":
|
| 122 |
-
"eval_steps_per_second":
|
| 123 |
-
"step":
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 7.0,
|
| 127 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
"learning_rate": 1.2500000000000007e-06,
|
| 129 |
-
"loss": 0.
|
| 130 |
-
"step":
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 7.0,
|
| 134 |
-
"eval_accuracy": 0.
|
| 135 |
-
"eval_f1": 0.
|
| 136 |
-
"eval_loss":
|
| 137 |
-
"eval_precision": 0.
|
| 138 |
-
"eval_recall": 0.
|
| 139 |
-
"eval_runtime":
|
| 140 |
-
"eval_samples_per_second":
|
| 141 |
-
"eval_steps_per_second":
|
| 142 |
-
"step":
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 8.0,
|
| 146 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
"learning_rate": 5.848888922025553e-07,
|
| 148 |
-
"loss": 0.
|
| 149 |
-
"step":
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 8.0,
|
| 153 |
-
"eval_accuracy": 0.
|
| 154 |
-
"eval_f1": 0.
|
| 155 |
-
"eval_loss":
|
| 156 |
-
"eval_precision": 0.
|
| 157 |
-
"eval_recall": 0.
|
| 158 |
-
"eval_runtime":
|
| 159 |
-
"eval_samples_per_second":
|
| 160 |
-
"eval_steps_per_second":
|
| 161 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 162 |
}
|
| 163 |
],
|
| 164 |
"logging_steps": 500,
|
| 165 |
-
"max_steps":
|
| 166 |
"num_input_tokens_seen": 0,
|
| 167 |
"num_train_epochs": 10,
|
| 168 |
"save_steps": 500,
|
|
@@ -173,13 +331,13 @@
|
|
| 173 |
"should_evaluate": false,
|
| 174 |
"should_log": false,
|
| 175 |
"should_save": true,
|
| 176 |
-
"should_training_stop":
|
| 177 |
},
|
| 178 |
"attributes": {}
|
| 179 |
}
|
| 180 |
},
|
| 181 |
-
"total_flos":
|
| 182 |
-
"train_batch_size":
|
| 183 |
"trial_name": null,
|
| 184 |
"trial_params": null
|
| 185 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7399751659163123,
|
| 3 |
+
"best_model_checkpoint": "/opt/dlami/nvme/shevtsov/sent_checkpoints/checkpoint-102510",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 102510,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"step": 10251,
|
| 14 |
+
"train_accuracy": 0.9232076630758701,
|
| 15 |
+
"train_f1": 0.9284970394554347,
|
| 16 |
+
"train_loss": 0.08324012160301208,
|
| 17 |
+
"train_precision": 0.9395995876182259,
|
| 18 |
+
"train_recall": 0.9232076630758701,
|
| 19 |
+
"train_runtime": 5077.4566,
|
| 20 |
+
"train_samples_per_second": 775.226,
|
| 21 |
+
"train_steps_per_second": 2.019
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.0,
|
| 25 |
+
"grad_norm": 2.202436923980713,
|
| 26 |
"learning_rate": 5e-06,
|
| 27 |
+
"loss": 0.1512,
|
| 28 |
+
"step": 10251
|
| 29 |
},
|
| 30 |
{
|
| 31 |
"epoch": 1.0,
|
| 32 |
+
"eval_accuracy": 0.5906430303537085,
|
| 33 |
+
"eval_f1": 0.5953154182610875,
|
| 34 |
+
"eval_loss": 1.1822575330734253,
|
| 35 |
+
"eval_precision": 0.7605817989645098,
|
| 36 |
+
"eval_recall": 0.5906430303537085,
|
| 37 |
+
"eval_runtime": 31.2064,
|
| 38 |
+
"eval_samples_per_second": 766.446,
|
| 39 |
+
"eval_steps_per_second": 2.019,
|
| 40 |
+
"step": 10251
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 2.0,
|
| 44 |
+
"step": 20502,
|
| 45 |
+
"train_accuracy": 0.9251504125579815,
|
| 46 |
+
"train_f1": 0.9318479879378413,
|
| 47 |
+
"train_loss": 0.06029369682073593,
|
| 48 |
+
"train_precision": 0.9457024638382566,
|
| 49 |
+
"train_recall": 0.9251504125579815,
|
| 50 |
+
"train_runtime": 5078.2486,
|
| 51 |
+
"train_samples_per_second": 775.105,
|
| 52 |
+
"train_steps_per_second": 2.019
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.0,
|
| 56 |
+
"grad_norm": 2.3391969203948975,
|
| 57 |
"learning_rate": 4.849231551964771e-06,
|
| 58 |
+
"loss": 0.0727,
|
| 59 |
+
"step": 20502
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 2.0,
|
| 63 |
+
"eval_accuracy": 0.5809850321933272,
|
| 64 |
+
"eval_f1": 0.5827904211311477,
|
| 65 |
+
"eval_loss": 0.8601031303405762,
|
| 66 |
+
"eval_precision": 0.7707426917608643,
|
| 67 |
+
"eval_recall": 0.5809850321933272,
|
| 68 |
+
"eval_runtime": 31.1947,
|
| 69 |
+
"eval_samples_per_second": 766.734,
|
| 70 |
+
"eval_steps_per_second": 2.02,
|
| 71 |
+
"step": 20502
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.0,
|
| 75 |
+
"step": 30753,
|
| 76 |
+
"train_accuracy": 0.9311338878819889,
|
| 77 |
+
"train_f1": 0.9367318532276315,
|
| 78 |
+
"train_loss": 0.05340421944856644,
|
| 79 |
+
"train_precision": 0.948615352312463,
|
| 80 |
+
"train_recall": 0.9311338878819889,
|
| 81 |
+
"train_runtime": 5078.9472,
|
| 82 |
+
"train_samples_per_second": 774.998,
|
| 83 |
+
"train_steps_per_second": 2.018
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 3.0,
|
| 87 |
+
"grad_norm": 3.368744134902954,
|
| 88 |
"learning_rate": 4.415111107797445e-06,
|
| 89 |
+
"loss": 0.064,
|
| 90 |
+
"step": 30753
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 3.0,
|
| 94 |
+
"eval_accuracy": 0.6280207375198595,
|
| 95 |
+
"eval_f1": 0.6341902420521265,
|
| 96 |
+
"eval_loss": 1.0681450366973877,
|
| 97 |
+
"eval_precision": 0.768741241964947,
|
| 98 |
+
"eval_recall": 0.6280207375198595,
|
| 99 |
+
"eval_runtime": 31.2028,
|
| 100 |
+
"eval_samples_per_second": 766.535,
|
| 101 |
+
"eval_steps_per_second": 2.019,
|
| 102 |
+
"step": 30753
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 4.0,
|
| 106 |
+
"step": 41004,
|
| 107 |
+
"train_accuracy": 0.941354218588914,
|
| 108 |
+
"train_f1": 0.9444982035100681,
|
| 109 |
+
"train_loss": 0.0493415892124176,
|
| 110 |
+
"train_precision": 0.9518003283876015,
|
| 111 |
+
"train_recall": 0.941354218588914,
|
| 112 |
+
"train_runtime": 5080.4688,
|
| 113 |
+
"train_samples_per_second": 774.766,
|
| 114 |
+
"train_steps_per_second": 2.018
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.0,
|
| 118 |
+
"grad_norm": 7.862049579620361,
|
| 119 |
"learning_rate": 3.7500000000000005e-06,
|
| 120 |
+
"loss": 0.0585,
|
| 121 |
+
"step": 41004
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 4.0,
|
| 125 |
+
"eval_accuracy": 0.6900660590350364,
|
| 126 |
+
"eval_f1": 0.6986283009597273,
|
| 127 |
+
"eval_loss": 1.4099539518356323,
|
| 128 |
+
"eval_precision": 0.7671384440115526,
|
| 129 |
+
"eval_recall": 0.6900660590350364,
|
| 130 |
+
"eval_runtime": 31.2008,
|
| 131 |
+
"eval_samples_per_second": 766.584,
|
| 132 |
+
"eval_steps_per_second": 2.019,
|
| 133 |
+
"step": 41004
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 5.0,
|
| 137 |
+
"step": 51255,
|
| 138 |
+
"train_accuracy": 0.9479113474150279,
|
| 139 |
+
"train_f1": 0.9498162368391557,
|
| 140 |
+
"train_loss": 0.04905932769179344,
|
| 141 |
+
"train_precision": 0.9544620214289802,
|
| 142 |
+
"train_recall": 0.9479113474150279,
|
| 143 |
+
"train_runtime": 5088.1804,
|
| 144 |
+
"train_samples_per_second": 773.592,
|
| 145 |
+
"train_steps_per_second": 2.015
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 5.0,
|
| 149 |
+
"grad_norm": 1.6737421751022339,
|
| 150 |
"learning_rate": 2.9341204441673267e-06,
|
| 151 |
+
"loss": 0.0543,
|
| 152 |
+
"step": 51255
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 5.0,
|
| 156 |
+
"eval_accuracy": 0.7279454803913371,
|
| 157 |
+
"eval_f1": 0.7344324841621389,
|
| 158 |
+
"eval_loss": 2.154353618621826,
|
| 159 |
+
"eval_precision": 0.7651689935562233,
|
| 160 |
+
"eval_recall": 0.7279454803913371,
|
| 161 |
+
"eval_runtime": 31.2388,
|
| 162 |
+
"eval_samples_per_second": 765.65,
|
| 163 |
+
"eval_steps_per_second": 2.017,
|
| 164 |
+
"step": 51255
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.0,
|
| 168 |
+
"step": 61506,
|
| 169 |
+
"train_accuracy": 0.944803507162031,
|
| 170 |
+
"train_f1": 0.9475462857180277,
|
| 171 |
+
"train_loss": 0.0426737517118454,
|
| 172 |
+
"train_precision": 0.9540200071722176,
|
| 173 |
+
"train_recall": 0.944803507162031,
|
| 174 |
+
"train_runtime": 5078.4022,
|
| 175 |
+
"train_samples_per_second": 775.081,
|
| 176 |
+
"train_steps_per_second": 2.019
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 6.0,
|
| 180 |
+
"grad_norm": 2.879870653152466,
|
| 181 |
"learning_rate": 2.0658795558326745e-06,
|
| 182 |
+
"loss": 0.051,
|
| 183 |
+
"step": 61506
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 6.0,
|
| 187 |
+
"eval_accuracy": 0.7079187223011958,
|
| 188 |
+
"eval_f1": 0.7155283465045912,
|
| 189 |
+
"eval_loss": 2.2507946491241455,
|
| 190 |
+
"eval_precision": 0.7570941064333973,
|
| 191 |
+
"eval_recall": 0.7079187223011958,
|
| 192 |
+
"eval_runtime": 31.2026,
|
| 193 |
+
"eval_samples_per_second": 766.538,
|
| 194 |
+
"eval_steps_per_second": 2.019,
|
| 195 |
+
"step": 61506
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 7.0,
|
| 199 |
+
"step": 71757,
|
| 200 |
+
"train_accuracy": 0.9474675154096338,
|
| 201 |
+
"train_f1": 0.9497025418465336,
|
| 202 |
+
"train_loss": 0.0410270020365715,
|
| 203 |
+
"train_precision": 0.9551267616744933,
|
| 204 |
+
"train_recall": 0.9474675154096338,
|
| 205 |
+
"train_runtime": 5080.7556,
|
| 206 |
+
"train_samples_per_second": 774.722,
|
| 207 |
+
"train_steps_per_second": 2.018
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 7.0,
|
| 211 |
+
"grad_norm": 1.4426418542861938,
|
| 212 |
"learning_rate": 1.2500000000000007e-06,
|
| 213 |
+
"loss": 0.0486,
|
| 214 |
+
"step": 71757
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 7.0,
|
| 218 |
+
"eval_accuracy": 0.7198344343172506,
|
| 219 |
+
"eval_f1": 0.726834352850576,
|
| 220 |
+
"eval_loss": 2.45487380027771,
|
| 221 |
+
"eval_precision": 0.7590566392960729,
|
| 222 |
+
"eval_recall": 0.7198344343172506,
|
| 223 |
+
"eval_runtime": 31.2049,
|
| 224 |
+
"eval_samples_per_second": 766.482,
|
| 225 |
+
"eval_steps_per_second": 2.019,
|
| 226 |
+
"step": 71757
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 8.0,
|
| 230 |
+
"step": 82008,
|
| 231 |
+
"train_accuracy": 0.9504046315025708,
|
| 232 |
+
"train_f1": 0.9520763661297328,
|
| 233 |
+
"train_loss": 0.0410199835896492,
|
| 234 |
+
"train_precision": 0.9562815819971588,
|
| 235 |
+
"train_recall": 0.9504046315025708,
|
| 236 |
+
"train_runtime": 5079.0768,
|
| 237 |
+
"train_samples_per_second": 774.978,
|
| 238 |
+
"train_steps_per_second": 2.018
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 8.0,
|
| 242 |
+
"grad_norm": 1.1270148754119873,
|
| 243 |
"learning_rate": 5.848888922025553e-07,
|
| 244 |
+
"loss": 0.0468,
|
| 245 |
+
"step": 82008
|
| 246 |
},
|
| 247 |
{
|
| 248 |
"epoch": 8.0,
|
| 249 |
+
"eval_accuracy": 0.7316665273016139,
|
| 250 |
+
"eval_f1": 0.737640105520052,
|
| 251 |
+
"eval_loss": 2.602576494216919,
|
| 252 |
+
"eval_precision": 0.7612609852108917,
|
| 253 |
+
"eval_recall": 0.7316665273016139,
|
| 254 |
+
"eval_runtime": 31.1916,
|
| 255 |
+
"eval_samples_per_second": 766.809,
|
| 256 |
+
"eval_steps_per_second": 2.02,
|
| 257 |
+
"step": 82008
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 9.0,
|
| 261 |
+
"step": 92259,
|
| 262 |
+
"train_accuracy": 0.9505296259769004,
|
| 263 |
+
"train_f1": 0.9522083394688067,
|
| 264 |
+
"train_loss": 0.03998752683401108,
|
| 265 |
+
"train_precision": 0.9564247374560226,
|
| 266 |
+
"train_recall": 0.9505296259769004,
|
| 267 |
+
"train_runtime": 5078.0822,
|
| 268 |
+
"train_samples_per_second": 775.13,
|
| 269 |
+
"train_steps_per_second": 2.019
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 9.0,
|
| 273 |
+
"grad_norm": 1.666390061378479,
|
| 274 |
+
"learning_rate": 1.507684480352292e-07,
|
| 275 |
+
"loss": 0.0457,
|
| 276 |
+
"step": 92259
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 9.0,
|
| 280 |
+
"eval_accuracy": 0.7320010034283803,
|
| 281 |
+
"eval_f1": 0.7378168031871946,
|
| 282 |
+
"eval_loss": 2.8211002349853516,
|
| 283 |
+
"eval_precision": 0.7595695441249473,
|
| 284 |
+
"eval_recall": 0.7320010034283803,
|
| 285 |
+
"eval_runtime": 31.2132,
|
| 286 |
+
"eval_samples_per_second": 766.278,
|
| 287 |
+
"eval_steps_per_second": 2.018,
|
| 288 |
+
"step": 92259
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 10.0,
|
| 292 |
+
"step": 102510,
|
| 293 |
+
"train_accuracy": 0.9510209660446921,
|
| 294 |
+
"train_f1": 0.9526073589638447,
|
| 295 |
+
"train_loss": 0.040298543870449066,
|
| 296 |
+
"train_precision": 0.9566123120238171,
|
| 297 |
+
"train_recall": 0.9510209660446921,
|
| 298 |
+
"train_runtime": 5078.6508,
|
| 299 |
+
"train_samples_per_second": 775.043,
|
| 300 |
+
"train_steps_per_second": 2.018
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 10.0,
|
| 304 |
+
"grad_norm": 1.6141560077667236,
|
| 305 |
+
"learning_rate": 0.0,
|
| 306 |
+
"loss": 0.0451,
|
| 307 |
+
"step": 102510
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 10.0,
|
| 311 |
+
"eval_accuracy": 0.7345095743791287,
|
| 312 |
+
"eval_f1": 0.7399751659163123,
|
| 313 |
+
"eval_loss": 2.884028911590576,
|
| 314 |
+
"eval_precision": 0.759520061975123,
|
| 315 |
+
"eval_recall": 0.7345095743791287,
|
| 316 |
+
"eval_runtime": 31.2146,
|
| 317 |
+
"eval_samples_per_second": 766.243,
|
| 318 |
+
"eval_steps_per_second": 2.018,
|
| 319 |
+
"step": 102510
|
| 320 |
}
|
| 321 |
],
|
| 322 |
"logging_steps": 500,
|
| 323 |
+
"max_steps": 102510,
|
| 324 |
"num_input_tokens_seen": 0,
|
| 325 |
"num_train_epochs": 10,
|
| 326 |
"save_steps": 500,
|
|
|
|
| 331 |
"should_evaluate": false,
|
| 332 |
"should_log": false,
|
| 333 |
"should_save": true,
|
| 334 |
+
"should_training_stop": true
|
| 335 |
},
|
| 336 |
"attributes": {}
|
| 337 |
}
|
| 338 |
},
|
| 339 |
+
"total_flos": 1.0357340434899927e+19,
|
| 340 |
+
"train_batch_size": 48,
|
| 341 |
"trial_name": null,
|
| 342 |
"trial_params": null
|
| 343 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08fbbf6707e209de037bb4bc3ece3924dd1369ff37078a607f53ee446b0de5b1
|
| 3 |
size 5304
|