Gerson Fabian Buenahora Ormaza
commited on
Commit
•
1a45c77
1
Parent(s):
5d7af2a
Upload 12 files
Browse files- config.json +1 -1
- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +7 -1
- tokenizer.json +0 -0
- trainer_state.json +265 -90
- training_args.bin +1 -1
- vocab.json +0 -0
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "BueormLLC/
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "BueormLLC/RAGPT-2",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497774208
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cccf36dbb1232f726dd86b9fd5cab7b9ab38dad643e4bb7b73ae7d6475a11509
|
| 3 |
size 497774208
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995642298
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f50bfe1def334ee87b42a6fb6f30891e8e72704f52892b5f894f307cb58b8964
|
| 3 |
size 995642298
|
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 sha256:39031638812cf8937efb39b99f8e04816250b75127fac74c34e34812d023c9de
|
| 3 |
size 14244
|
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:f4848d97de2f99c7cf83c5cf8ad176114ae8a5a8c5ff5c71446432e90c8eb1c6
|
| 3 |
size 1064
|
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<|endoftext|>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<|endoftext|>",
|
| 25 |
"lstrip": false,
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_state.json
CHANGED
|
@@ -1,159 +1,334 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 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": 0.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 500
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
-
"learning_rate": 4.
|
| 22 |
-
"loss":
|
| 23 |
"step": 1000
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch":
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 4.
|
| 29 |
-
"loss":
|
| 30 |
"step": 1500
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch":
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate": 4.
|
| 36 |
-
"loss":
|
| 37 |
"step": 2000
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch":
|
| 41 |
-
"grad_norm": 1.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 2500
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
"step": 3000
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch":
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss":
|
| 58 |
"step": 3500
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch":
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss":
|
| 65 |
"step": 4000
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch":
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss":
|
| 72 |
"step": 4500
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss":
|
| 79 |
"step": 5000
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch":
|
| 83 |
-
"
|
| 84 |
-
"
|
| 85 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
"step": 5500
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss":
|
| 93 |
"step": 6000
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"grad_norm":
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss":
|
| 100 |
"step": 6500
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch":
|
| 104 |
-
"grad_norm":
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss":
|
| 107 |
"step": 7000
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch":
|
| 111 |
-
"grad_norm": 1.
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss":
|
| 114 |
"step": 7500
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch":
|
| 118 |
-
"grad_norm":
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss":
|
| 121 |
"step": 8000
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch":
|
| 125 |
-
"
|
| 126 |
-
"
|
| 127 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
"step": 8500
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"grad_norm":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss":
|
| 135 |
"step": 9000
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"grad_norm":
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss":
|
| 142 |
"step": 9500
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch":
|
| 146 |
-
"grad_norm":
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss":
|
| 149 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 150 |
}
|
| 151 |
],
|
| 152 |
"logging_steps": 500,
|
| 153 |
-
"max_steps":
|
| 154 |
"num_input_tokens_seen": 0,
|
| 155 |
-
"num_train_epochs":
|
| 156 |
-
"save_steps":
|
| 157 |
"stateful_callbacks": {
|
| 158 |
"TrainerControl": {
|
| 159 |
"args": {
|
|
@@ -161,13 +336,13 @@
|
|
| 161 |
"should_evaluate": false,
|
| 162 |
"should_log": false,
|
| 163 |
"should_save": true,
|
| 164 |
-
"should_training_stop":
|
| 165 |
},
|
| 166 |
"attributes": {}
|
| 167 |
}
|
| 168 |
},
|
| 169 |
-
"total_flos":
|
| 170 |
-
"train_batch_size":
|
| 171 |
"trial_name": null,
|
| 172 |
"trial_params": null
|
| 173 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8724454641342163,
|
| 3 |
+
"best_model_checkpoint": "./results/checkpoint-2700",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 18900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.18518518518518517,
|
| 13 |
+
"grad_norm": 2.5104269981384277,
|
| 14 |
+
"learning_rate": 4.94212962962963e-05,
|
| 15 |
+
"loss": 0.9092,
|
| 16 |
"step": 500
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.37037037037037035,
|
| 20 |
+
"grad_norm": 1.030969262123108,
|
| 21 |
+
"learning_rate": 4.8842592592592595e-05,
|
| 22 |
+
"loss": 0.869,
|
| 23 |
"step": 1000
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.5555555555555556,
|
| 27 |
+
"grad_norm": 0.49540138244628906,
|
| 28 |
+
"learning_rate": 4.8263888888888895e-05,
|
| 29 |
+
"loss": 0.8595,
|
| 30 |
"step": 1500
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.7407407407407407,
|
| 34 |
+
"grad_norm": 0.6758684515953064,
|
| 35 |
+
"learning_rate": 4.768518518518519e-05,
|
| 36 |
+
"loss": 0.8446,
|
| 37 |
"step": 2000
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.9259259259259259,
|
| 41 |
+
"grad_norm": 1.0114092826843262,
|
| 42 |
+
"learning_rate": 4.710648148148149e-05,
|
| 43 |
+
"loss": 0.8403,
|
| 44 |
"step": 2500
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_loss": 0.8724454641342163,
|
| 49 |
+
"eval_runtime": 30.4341,
|
| 50 |
+
"eval_samples_per_second": 39.43,
|
| 51 |
+
"eval_steps_per_second": 9.857,
|
| 52 |
+
"step": 2700
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.1111111111111112,
|
| 56 |
+
"grad_norm": 0.8358873128890991,
|
| 57 |
+
"learning_rate": 4.652777777777778e-05,
|
| 58 |
+
"loss": 0.8109,
|
| 59 |
"step": 3000
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 1.2962962962962963,
|
| 63 |
+
"grad_norm": 0.8434183597564697,
|
| 64 |
+
"learning_rate": 4.594907407407408e-05,
|
| 65 |
+
"loss": 0.7912,
|
| 66 |
"step": 3500
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 1.4814814814814814,
|
| 70 |
+
"grad_norm": 1.2122215032577515,
|
| 71 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 72 |
+
"loss": 0.7891,
|
| 73 |
"step": 4000
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 1.6666666666666665,
|
| 77 |
+
"grad_norm": 0.7747897505760193,
|
| 78 |
+
"learning_rate": 4.4791666666666673e-05,
|
| 79 |
+
"loss": 0.8132,
|
| 80 |
"step": 4500
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 1.8518518518518519,
|
| 84 |
+
"grad_norm": 0.9554975032806396,
|
| 85 |
+
"learning_rate": 4.4212962962962966e-05,
|
| 86 |
+
"loss": 0.8047,
|
| 87 |
"step": 5000
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 2.0,
|
| 91 |
+
"eval_loss": 0.8918996453285217,
|
| 92 |
+
"eval_runtime": 30.4698,
|
| 93 |
+
"eval_samples_per_second": 39.383,
|
| 94 |
+
"eval_steps_per_second": 9.846,
|
| 95 |
+
"step": 5400
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.037037037037037,
|
| 99 |
+
"grad_norm": 0.6646651029586792,
|
| 100 |
+
"learning_rate": 4.3634259259259266e-05,
|
| 101 |
+
"loss": 0.8091,
|
| 102 |
"step": 5500
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 2.2222222222222223,
|
| 106 |
+
"grad_norm": 4.084255218505859,
|
| 107 |
+
"learning_rate": 4.305555555555556e-05,
|
| 108 |
+
"loss": 0.7432,
|
| 109 |
"step": 6000
|
| 110 |
},
|
| 111 |
{
|
| 112 |
+
"epoch": 2.4074074074074074,
|
| 113 |
+
"grad_norm": 2.1203970909118652,
|
| 114 |
+
"learning_rate": 4.247685185185186e-05,
|
| 115 |
+
"loss": 0.7355,
|
| 116 |
"step": 6500
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 2.5925925925925926,
|
| 120 |
+
"grad_norm": 4.367093086242676,
|
| 121 |
+
"learning_rate": 4.1898148148148145e-05,
|
| 122 |
+
"loss": 0.751,
|
| 123 |
"step": 7000
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 2.7777777777777777,
|
| 127 |
+
"grad_norm": 1.1563506126403809,
|
| 128 |
+
"learning_rate": 4.1319444444444445e-05,
|
| 129 |
+
"loss": 0.7632,
|
| 130 |
"step": 7500
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"epoch": 2.962962962962963,
|
| 134 |
+
"grad_norm": 0.9595785140991211,
|
| 135 |
+
"learning_rate": 4.074074074074074e-05,
|
| 136 |
+
"loss": 0.7714,
|
| 137 |
"step": 8000
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 3.0,
|
| 141 |
+
"eval_loss": 0.9504669308662415,
|
| 142 |
+
"eval_runtime": 30.5135,
|
| 143 |
+
"eval_samples_per_second": 39.327,
|
| 144 |
+
"eval_steps_per_second": 9.832,
|
| 145 |
+
"step": 8100
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.148148148148148,
|
| 149 |
+
"grad_norm": 0.6189069747924805,
|
| 150 |
+
"learning_rate": 4.016203703703704e-05,
|
| 151 |
+
"loss": 0.7277,
|
| 152 |
"step": 8500
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 3.3333333333333335,
|
| 156 |
+
"grad_norm": 0.6079156994819641,
|
| 157 |
+
"learning_rate": 3.958333333333333e-05,
|
| 158 |
+
"loss": 0.7373,
|
| 159 |
"step": 9000
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 3.5185185185185186,
|
| 163 |
+
"grad_norm": 0.4996514320373535,
|
| 164 |
+
"learning_rate": 3.900462962962963e-05,
|
| 165 |
+
"loss": 0.7206,
|
| 166 |
"step": 9500
|
| 167 |
},
|
| 168 |
{
|
| 169 |
+
"epoch": 3.7037037037037037,
|
| 170 |
+
"grad_norm": 0.9442146420478821,
|
| 171 |
+
"learning_rate": 3.8425925925925924e-05,
|
| 172 |
+
"loss": 0.7215,
|
| 173 |
"step": 10000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.888888888888889,
|
| 177 |
+
"grad_norm": 0.46321621537208557,
|
| 178 |
+
"learning_rate": 3.7847222222222224e-05,
|
| 179 |
+
"loss": 0.7238,
|
| 180 |
+
"step": 10500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 4.0,
|
| 184 |
+
"eval_loss": 1.0164023637771606,
|
| 185 |
+
"eval_runtime": 30.4613,
|
| 186 |
+
"eval_samples_per_second": 39.394,
|
| 187 |
+
"eval_steps_per_second": 9.849,
|
| 188 |
+
"step": 10800
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.074074074074074,
|
| 192 |
+
"grad_norm": 0.808857798576355,
|
| 193 |
+
"learning_rate": 3.726851851851852e-05,
|
| 194 |
+
"loss": 0.7143,
|
| 195 |
+
"step": 11000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.2592592592592595,
|
| 199 |
+
"grad_norm": 0.2266809195280075,
|
| 200 |
+
"learning_rate": 3.6689814814814816e-05,
|
| 201 |
+
"loss": 0.7017,
|
| 202 |
+
"step": 11500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.444444444444445,
|
| 206 |
+
"grad_norm": 0.8129966259002686,
|
| 207 |
+
"learning_rate": 3.611111111111111e-05,
|
| 208 |
+
"loss": 0.7165,
|
| 209 |
+
"step": 12000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.62962962962963,
|
| 213 |
+
"grad_norm": 0.7154943943023682,
|
| 214 |
+
"learning_rate": 3.553240740740741e-05,
|
| 215 |
+
"loss": 0.6892,
|
| 216 |
+
"step": 12500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.814814814814815,
|
| 220 |
+
"grad_norm": 0.823897659778595,
|
| 221 |
+
"learning_rate": 3.49537037037037e-05,
|
| 222 |
+
"loss": 0.7026,
|
| 223 |
+
"step": 13000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.0,
|
| 227 |
+
"grad_norm": 0.7548332810401917,
|
| 228 |
+
"learning_rate": 3.4375e-05,
|
| 229 |
+
"loss": 0.7019,
|
| 230 |
+
"step": 13500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.0,
|
| 234 |
+
"eval_loss": 1.056677222251892,
|
| 235 |
+
"eval_runtime": 30.3702,
|
| 236 |
+
"eval_samples_per_second": 39.512,
|
| 237 |
+
"eval_steps_per_second": 9.878,
|
| 238 |
+
"step": 13500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 5.185185185185185,
|
| 242 |
+
"grad_norm": 0.6250707507133484,
|
| 243 |
+
"learning_rate": 3.3796296296296295e-05,
|
| 244 |
+
"loss": 0.7107,
|
| 245 |
+
"step": 14000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.37037037037037,
|
| 249 |
+
"grad_norm": 0.7014070749282837,
|
| 250 |
+
"learning_rate": 3.3217592592592595e-05,
|
| 251 |
+
"loss": 0.696,
|
| 252 |
+
"step": 14500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.555555555555555,
|
| 256 |
+
"grad_norm": 0.8305183053016663,
|
| 257 |
+
"learning_rate": 3.263888888888889e-05,
|
| 258 |
+
"loss": 0.6858,
|
| 259 |
+
"step": 15000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.7407407407407405,
|
| 263 |
+
"grad_norm": 0.5459818840026855,
|
| 264 |
+
"learning_rate": 3.206018518518519e-05,
|
| 265 |
+
"loss": 0.6828,
|
| 266 |
+
"step": 15500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.925925925925926,
|
| 270 |
+
"grad_norm": 0.40176087617874146,
|
| 271 |
+
"learning_rate": 3.148148148148148e-05,
|
| 272 |
+
"loss": 0.6841,
|
| 273 |
+
"step": 16000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.0,
|
| 277 |
+
"eval_loss": 1.0900229215621948,
|
| 278 |
+
"eval_runtime": 30.4123,
|
| 279 |
+
"eval_samples_per_second": 39.458,
|
| 280 |
+
"eval_steps_per_second": 9.864,
|
| 281 |
+
"step": 16200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 6.111111111111111,
|
| 285 |
+
"grad_norm": 0.4161689281463623,
|
| 286 |
+
"learning_rate": 3.090277777777778e-05,
|
| 287 |
+
"loss": 0.6615,
|
| 288 |
+
"step": 16500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 6.296296296296296,
|
| 292 |
+
"grad_norm": 0.7132428288459778,
|
| 293 |
+
"learning_rate": 3.0324074074074077e-05,
|
| 294 |
+
"loss": 0.683,
|
| 295 |
+
"step": 17000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.481481481481482,
|
| 299 |
+
"grad_norm": 0.6823524236679077,
|
| 300 |
+
"learning_rate": 2.9745370370370373e-05,
|
| 301 |
+
"loss": 0.6692,
|
| 302 |
+
"step": 17500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.666666666666667,
|
| 306 |
+
"grad_norm": 0.3051627278327942,
|
| 307 |
+
"learning_rate": 2.916666666666667e-05,
|
| 308 |
+
"loss": 0.6771,
|
| 309 |
+
"step": 18000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.851851851851852,
|
| 313 |
+
"grad_norm": 0.5912793278694153,
|
| 314 |
+
"learning_rate": 2.8587962962962966e-05,
|
| 315 |
+
"loss": 0.6959,
|
| 316 |
+
"step": 18500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 7.0,
|
| 320 |
+
"eval_loss": 1.12686288356781,
|
| 321 |
+
"eval_runtime": 30.4381,
|
| 322 |
+
"eval_samples_per_second": 39.424,
|
| 323 |
+
"eval_steps_per_second": 9.856,
|
| 324 |
+
"step": 18900
|
| 325 |
}
|
| 326 |
],
|
| 327 |
"logging_steps": 500,
|
| 328 |
+
"max_steps": 43200,
|
| 329 |
"num_input_tokens_seen": 0,
|
| 330 |
+
"num_train_epochs": 16,
|
| 331 |
+
"save_steps": 500,
|
| 332 |
"stateful_callbacks": {
|
| 333 |
"TrainerControl": {
|
| 334 |
"args": {
|
|
|
|
| 336 |
"should_evaluate": false,
|
| 337 |
"should_log": false,
|
| 338 |
"should_save": true,
|
| 339 |
+
"should_training_stop": false
|
| 340 |
},
|
| 341 |
"attributes": {}
|
| 342 |
}
|
| 343 |
},
|
| 344 |
+
"total_flos": 1.97536776192e+16,
|
| 345 |
+
"train_batch_size": 4,
|
| 346 |
"trial_name": null,
|
| 347 |
"trial_params": null
|
| 348 |
}
|
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:b099f7fb886c1c9a23e2c84872a02a97862f45cdd77dbcdbacca1ddcaa8b3c5f
|
| 3 |
size 5112
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|