Upload folder using huggingface_hub
Browse files- checkpoint-13500/config.json +33 -0
- checkpoint-13500/generation_config.json +7 -0
- checkpoint-13500/model.safetensors +3 -0
- checkpoint-13500/optimizer.pt +3 -0
- checkpoint-13500/rng_state.pth +3 -0
- checkpoint-13500/scheduler.pt +3 -0
- checkpoint-13500/trainer_state.json +253 -0
- checkpoint-13500/training_args.bin +3 -0
- checkpoint-14000/config.json +33 -0
- checkpoint-14000/generation_config.json +7 -0
- checkpoint-14000/model.safetensors +3 -0
- checkpoint-14000/optimizer.pt +3 -0
- checkpoint-14000/rng_state.pth +3 -0
- checkpoint-14000/scheduler.pt +3 -0
- checkpoint-14000/trainer_state.json +259 -0
- checkpoint-14000/training_args.bin +3 -0
- checkpoint-14500/config.json +33 -0
- checkpoint-14500/generation_config.json +7 -0
- checkpoint-14500/model.safetensors +3 -0
- checkpoint-14500/optimizer.pt +3 -0
- checkpoint-14500/rng_state.pth +3 -0
- checkpoint-14500/scheduler.pt +3 -0
- checkpoint-14500/trainer_state.json +265 -0
- checkpoint-14500/training_args.bin +3 -0
- config.json +33 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- runs/Nov29_19-42-21_ea2ffa840b9b/events.out.tfevents.1701286949.ea2ffa840b9b.184.0 +3 -0
- training_args.bin +3 -0
checkpoint-13500/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 24,
|
| 22 |
+
"num_heads": 16,
|
| 23 |
+
"num_layers": 24,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.35.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32128
|
| 33 |
+
}
|
checkpoint-13500/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.35.2"
|
| 7 |
+
}
|
checkpoint-13500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:611554d9ed7a4cc1563120414965e243d181e7158746597e0b13dc25f0c6419f
|
| 3 |
+
size 3132668808
|
checkpoint-13500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b29fb5812a372735c027d4a0e34c55f01b28ad5b744b0ca6a0aec5e16645ecbf
|
| 3 |
+
size 6265677800
|
checkpoint-13500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d588b8c2545c1788e49ec90f8090b49dfc8508c9b6e05a1f86ddb192d6e0ce69
|
| 3 |
+
size 14244
|
checkpoint-13500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:297365d56683b294241aec2c06f0fc50ae325619a514110926355954e2ec319f
|
| 3 |
+
size 1064
|
checkpoint-13500/trainer_state.json
ADDED
|
@@ -0,0 +1,253 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.08479138627187,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 13500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.34,
|
| 13 |
+
"learning_rate": 1.932705248990579e-05,
|
| 14 |
+
"loss": 0.2243,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.67,
|
| 19 |
+
"learning_rate": 1.8654104979811575e-05,
|
| 20 |
+
"loss": 0.1513,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.0,
|
| 25 |
+
"eval_loss": 0.15557065606117249,
|
| 26 |
+
"eval_runtime": 122.4795,
|
| 27 |
+
"eval_samples_per_second": 12.141,
|
| 28 |
+
"eval_steps_per_second": 3.037,
|
| 29 |
+
"step": 1486
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.01,
|
| 33 |
+
"learning_rate": 1.7981157469717363e-05,
|
| 34 |
+
"loss": 0.1319,
|
| 35 |
+
"step": 1500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.35,
|
| 39 |
+
"learning_rate": 1.730820995962315e-05,
|
| 40 |
+
"loss": 0.1161,
|
| 41 |
+
"step": 2000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.68,
|
| 45 |
+
"learning_rate": 1.6635262449528936e-05,
|
| 46 |
+
"loss": 0.1161,
|
| 47 |
+
"step": 2500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_loss": 0.09562207758426666,
|
| 52 |
+
"eval_runtime": 122.4632,
|
| 53 |
+
"eval_samples_per_second": 12.142,
|
| 54 |
+
"eval_steps_per_second": 3.038,
|
| 55 |
+
"step": 2972
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.02,
|
| 59 |
+
"learning_rate": 1.5962314939434724e-05,
|
| 60 |
+
"loss": 0.1072,
|
| 61 |
+
"step": 3000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.36,
|
| 65 |
+
"learning_rate": 1.5289367429340512e-05,
|
| 66 |
+
"loss": 0.0999,
|
| 67 |
+
"step": 3500
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.69,
|
| 71 |
+
"learning_rate": 1.46164199192463e-05,
|
| 72 |
+
"loss": 0.0765,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.0,
|
| 77 |
+
"eval_loss": 0.11794405430555344,
|
| 78 |
+
"eval_runtime": 122.4644,
|
| 79 |
+
"eval_samples_per_second": 12.142,
|
| 80 |
+
"eval_steps_per_second": 3.038,
|
| 81 |
+
"step": 4458
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.03,
|
| 85 |
+
"learning_rate": 1.3943472409152087e-05,
|
| 86 |
+
"loss": 0.0886,
|
| 87 |
+
"step": 4500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.36,
|
| 91 |
+
"learning_rate": 1.3270524899057875e-05,
|
| 92 |
+
"loss": 0.0793,
|
| 93 |
+
"step": 5000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.7,
|
| 97 |
+
"learning_rate": 1.2597577388963662e-05,
|
| 98 |
+
"loss": 0.0798,
|
| 99 |
+
"step": 5500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.0,
|
| 103 |
+
"eval_loss": 0.11743835359811783,
|
| 104 |
+
"eval_runtime": 122.4332,
|
| 105 |
+
"eval_samples_per_second": 12.145,
|
| 106 |
+
"eval_steps_per_second": 3.038,
|
| 107 |
+
"step": 5944
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 4.04,
|
| 111 |
+
"learning_rate": 1.192462987886945e-05,
|
| 112 |
+
"loss": 0.0737,
|
| 113 |
+
"step": 6000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 4.37,
|
| 117 |
+
"learning_rate": 1.1251682368775237e-05,
|
| 118 |
+
"loss": 0.0739,
|
| 119 |
+
"step": 6500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.71,
|
| 123 |
+
"learning_rate": 1.0578734858681023e-05,
|
| 124 |
+
"loss": 0.0705,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 5.0,
|
| 129 |
+
"eval_loss": 0.09409211575984955,
|
| 130 |
+
"eval_runtime": 122.4407,
|
| 131 |
+
"eval_samples_per_second": 12.145,
|
| 132 |
+
"eval_steps_per_second": 3.038,
|
| 133 |
+
"step": 7430
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 5.05,
|
| 137 |
+
"learning_rate": 9.905787348586811e-06,
|
| 138 |
+
"loss": 0.0668,
|
| 139 |
+
"step": 7500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 5.38,
|
| 143 |
+
"learning_rate": 9.2328398384926e-06,
|
| 144 |
+
"loss": 0.0558,
|
| 145 |
+
"step": 8000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 5.72,
|
| 149 |
+
"learning_rate": 8.559892328398386e-06,
|
| 150 |
+
"loss": 0.0609,
|
| 151 |
+
"step": 8500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 6.0,
|
| 155 |
+
"eval_loss": 0.12117910385131836,
|
| 156 |
+
"eval_runtime": 122.4449,
|
| 157 |
+
"eval_samples_per_second": 12.144,
|
| 158 |
+
"eval_steps_per_second": 3.038,
|
| 159 |
+
"step": 8916
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 6.06,
|
| 163 |
+
"learning_rate": 7.886944818304172e-06,
|
| 164 |
+
"loss": 0.0617,
|
| 165 |
+
"step": 9000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 6.39,
|
| 169 |
+
"learning_rate": 7.21399730820996e-06,
|
| 170 |
+
"loss": 0.0537,
|
| 171 |
+
"step": 9500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.73,
|
| 175 |
+
"learning_rate": 6.541049798115747e-06,
|
| 176 |
+
"loss": 0.0542,
|
| 177 |
+
"step": 10000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.0,
|
| 181 |
+
"eval_loss": 0.10626289248466492,
|
| 182 |
+
"eval_runtime": 122.4232,
|
| 183 |
+
"eval_samples_per_second": 12.146,
|
| 184 |
+
"eval_steps_per_second": 3.039,
|
| 185 |
+
"step": 10402
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 7.07,
|
| 189 |
+
"learning_rate": 5.8681022880215346e-06,
|
| 190 |
+
"loss": 0.0485,
|
| 191 |
+
"step": 10500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 7.4,
|
| 195 |
+
"learning_rate": 5.195154777927323e-06,
|
| 196 |
+
"loss": 0.0522,
|
| 197 |
+
"step": 11000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 7.74,
|
| 201 |
+
"learning_rate": 4.522207267833109e-06,
|
| 202 |
+
"loss": 0.0542,
|
| 203 |
+
"step": 11500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 8.0,
|
| 207 |
+
"eval_loss": 0.13295996189117432,
|
| 208 |
+
"eval_runtime": 122.4378,
|
| 209 |
+
"eval_samples_per_second": 12.145,
|
| 210 |
+
"eval_steps_per_second": 3.038,
|
| 211 |
+
"step": 11888
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 8.08,
|
| 215 |
+
"learning_rate": 3.849259757738897e-06,
|
| 216 |
+
"loss": 0.0545,
|
| 217 |
+
"step": 12000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 8.41,
|
| 221 |
+
"learning_rate": 3.176312247644684e-06,
|
| 222 |
+
"loss": 0.0391,
|
| 223 |
+
"step": 12500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 8.75,
|
| 227 |
+
"learning_rate": 2.503364737550471e-06,
|
| 228 |
+
"loss": 0.0418,
|
| 229 |
+
"step": 13000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 9.0,
|
| 233 |
+
"eval_loss": 0.1395300030708313,
|
| 234 |
+
"eval_runtime": 122.4262,
|
| 235 |
+
"eval_samples_per_second": 12.146,
|
| 236 |
+
"eval_steps_per_second": 3.039,
|
| 237 |
+
"step": 13374
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.08,
|
| 241 |
+
"learning_rate": 1.8304172274562585e-06,
|
| 242 |
+
"loss": 0.0385,
|
| 243 |
+
"step": 13500
|
| 244 |
+
}
|
| 245 |
+
],
|
| 246 |
+
"logging_steps": 500,
|
| 247 |
+
"max_steps": 14860,
|
| 248 |
+
"num_train_epochs": 10,
|
| 249 |
+
"save_steps": 500,
|
| 250 |
+
"total_flos": 2.43080994816e+17,
|
| 251 |
+
"trial_name": null,
|
| 252 |
+
"trial_params": null
|
| 253 |
+
}
|
checkpoint-13500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe0e860512f8469e428abf5b40149ed383475cb1fb119ba3f4a814c039cc7eba
|
| 3 |
+
size 4536
|
checkpoint-14000/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 24,
|
| 22 |
+
"num_heads": 16,
|
| 23 |
+
"num_layers": 24,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.35.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32128
|
| 33 |
+
}
|
checkpoint-14000/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.35.2"
|
| 7 |
+
}
|
checkpoint-14000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8433652cde6da8f4854767cd62c407ab28d8de09440f60cc26279838d365f818
|
| 3 |
+
size 3132668808
|
checkpoint-14000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e2e8155c2ab0c261ed5db8471ddb5db249b653caa84ef5463975d900f00ceda
|
| 3 |
+
size 6265677800
|
checkpoint-14000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a267235be5b9bf8e1870dfdde9c3697965bc525ff98f24c201bab8603ab241
|
| 3 |
+
size 14244
|
checkpoint-14000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08e18e5e867da87cd3106e12d2e225fc519957d25509642ff8038e25fdfa9d0b
|
| 3 |
+
size 1064
|
checkpoint-14000/trainer_state.json
ADDED
|
@@ -0,0 +1,259 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.421265141318978,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 14000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.34,
|
| 13 |
+
"learning_rate": 1.932705248990579e-05,
|
| 14 |
+
"loss": 0.2243,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.67,
|
| 19 |
+
"learning_rate": 1.8654104979811575e-05,
|
| 20 |
+
"loss": 0.1513,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.0,
|
| 25 |
+
"eval_loss": 0.15557065606117249,
|
| 26 |
+
"eval_runtime": 122.4795,
|
| 27 |
+
"eval_samples_per_second": 12.141,
|
| 28 |
+
"eval_steps_per_second": 3.037,
|
| 29 |
+
"step": 1486
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.01,
|
| 33 |
+
"learning_rate": 1.7981157469717363e-05,
|
| 34 |
+
"loss": 0.1319,
|
| 35 |
+
"step": 1500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.35,
|
| 39 |
+
"learning_rate": 1.730820995962315e-05,
|
| 40 |
+
"loss": 0.1161,
|
| 41 |
+
"step": 2000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.68,
|
| 45 |
+
"learning_rate": 1.6635262449528936e-05,
|
| 46 |
+
"loss": 0.1161,
|
| 47 |
+
"step": 2500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_loss": 0.09562207758426666,
|
| 52 |
+
"eval_runtime": 122.4632,
|
| 53 |
+
"eval_samples_per_second": 12.142,
|
| 54 |
+
"eval_steps_per_second": 3.038,
|
| 55 |
+
"step": 2972
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.02,
|
| 59 |
+
"learning_rate": 1.5962314939434724e-05,
|
| 60 |
+
"loss": 0.1072,
|
| 61 |
+
"step": 3000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.36,
|
| 65 |
+
"learning_rate": 1.5289367429340512e-05,
|
| 66 |
+
"loss": 0.0999,
|
| 67 |
+
"step": 3500
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.69,
|
| 71 |
+
"learning_rate": 1.46164199192463e-05,
|
| 72 |
+
"loss": 0.0765,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.0,
|
| 77 |
+
"eval_loss": 0.11794405430555344,
|
| 78 |
+
"eval_runtime": 122.4644,
|
| 79 |
+
"eval_samples_per_second": 12.142,
|
| 80 |
+
"eval_steps_per_second": 3.038,
|
| 81 |
+
"step": 4458
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.03,
|
| 85 |
+
"learning_rate": 1.3943472409152087e-05,
|
| 86 |
+
"loss": 0.0886,
|
| 87 |
+
"step": 4500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.36,
|
| 91 |
+
"learning_rate": 1.3270524899057875e-05,
|
| 92 |
+
"loss": 0.0793,
|
| 93 |
+
"step": 5000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.7,
|
| 97 |
+
"learning_rate": 1.2597577388963662e-05,
|
| 98 |
+
"loss": 0.0798,
|
| 99 |
+
"step": 5500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.0,
|
| 103 |
+
"eval_loss": 0.11743835359811783,
|
| 104 |
+
"eval_runtime": 122.4332,
|
| 105 |
+
"eval_samples_per_second": 12.145,
|
| 106 |
+
"eval_steps_per_second": 3.038,
|
| 107 |
+
"step": 5944
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 4.04,
|
| 111 |
+
"learning_rate": 1.192462987886945e-05,
|
| 112 |
+
"loss": 0.0737,
|
| 113 |
+
"step": 6000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 4.37,
|
| 117 |
+
"learning_rate": 1.1251682368775237e-05,
|
| 118 |
+
"loss": 0.0739,
|
| 119 |
+
"step": 6500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.71,
|
| 123 |
+
"learning_rate": 1.0578734858681023e-05,
|
| 124 |
+
"loss": 0.0705,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 5.0,
|
| 129 |
+
"eval_loss": 0.09409211575984955,
|
| 130 |
+
"eval_runtime": 122.4407,
|
| 131 |
+
"eval_samples_per_second": 12.145,
|
| 132 |
+
"eval_steps_per_second": 3.038,
|
| 133 |
+
"step": 7430
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 5.05,
|
| 137 |
+
"learning_rate": 9.905787348586811e-06,
|
| 138 |
+
"loss": 0.0668,
|
| 139 |
+
"step": 7500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 5.38,
|
| 143 |
+
"learning_rate": 9.2328398384926e-06,
|
| 144 |
+
"loss": 0.0558,
|
| 145 |
+
"step": 8000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 5.72,
|
| 149 |
+
"learning_rate": 8.559892328398386e-06,
|
| 150 |
+
"loss": 0.0609,
|
| 151 |
+
"step": 8500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 6.0,
|
| 155 |
+
"eval_loss": 0.12117910385131836,
|
| 156 |
+
"eval_runtime": 122.4449,
|
| 157 |
+
"eval_samples_per_second": 12.144,
|
| 158 |
+
"eval_steps_per_second": 3.038,
|
| 159 |
+
"step": 8916
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 6.06,
|
| 163 |
+
"learning_rate": 7.886944818304172e-06,
|
| 164 |
+
"loss": 0.0617,
|
| 165 |
+
"step": 9000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 6.39,
|
| 169 |
+
"learning_rate": 7.21399730820996e-06,
|
| 170 |
+
"loss": 0.0537,
|
| 171 |
+
"step": 9500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.73,
|
| 175 |
+
"learning_rate": 6.541049798115747e-06,
|
| 176 |
+
"loss": 0.0542,
|
| 177 |
+
"step": 10000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.0,
|
| 181 |
+
"eval_loss": 0.10626289248466492,
|
| 182 |
+
"eval_runtime": 122.4232,
|
| 183 |
+
"eval_samples_per_second": 12.146,
|
| 184 |
+
"eval_steps_per_second": 3.039,
|
| 185 |
+
"step": 10402
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 7.07,
|
| 189 |
+
"learning_rate": 5.8681022880215346e-06,
|
| 190 |
+
"loss": 0.0485,
|
| 191 |
+
"step": 10500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 7.4,
|
| 195 |
+
"learning_rate": 5.195154777927323e-06,
|
| 196 |
+
"loss": 0.0522,
|
| 197 |
+
"step": 11000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 7.74,
|
| 201 |
+
"learning_rate": 4.522207267833109e-06,
|
| 202 |
+
"loss": 0.0542,
|
| 203 |
+
"step": 11500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 8.0,
|
| 207 |
+
"eval_loss": 0.13295996189117432,
|
| 208 |
+
"eval_runtime": 122.4378,
|
| 209 |
+
"eval_samples_per_second": 12.145,
|
| 210 |
+
"eval_steps_per_second": 3.038,
|
| 211 |
+
"step": 11888
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 8.08,
|
| 215 |
+
"learning_rate": 3.849259757738897e-06,
|
| 216 |
+
"loss": 0.0545,
|
| 217 |
+
"step": 12000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 8.41,
|
| 221 |
+
"learning_rate": 3.176312247644684e-06,
|
| 222 |
+
"loss": 0.0391,
|
| 223 |
+
"step": 12500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 8.75,
|
| 227 |
+
"learning_rate": 2.503364737550471e-06,
|
| 228 |
+
"loss": 0.0418,
|
| 229 |
+
"step": 13000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 9.0,
|
| 233 |
+
"eval_loss": 0.1395300030708313,
|
| 234 |
+
"eval_runtime": 122.4262,
|
| 235 |
+
"eval_samples_per_second": 12.146,
|
| 236 |
+
"eval_steps_per_second": 3.039,
|
| 237 |
+
"step": 13374
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.08,
|
| 241 |
+
"learning_rate": 1.8304172274562585e-06,
|
| 242 |
+
"loss": 0.0385,
|
| 243 |
+
"step": 13500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 9.42,
|
| 247 |
+
"learning_rate": 1.157469717362046e-06,
|
| 248 |
+
"loss": 0.0434,
|
| 249 |
+
"step": 14000
|
| 250 |
+
}
|
| 251 |
+
],
|
| 252 |
+
"logging_steps": 500,
|
| 253 |
+
"max_steps": 14860,
|
| 254 |
+
"num_train_epochs": 10,
|
| 255 |
+
"save_steps": 500,
|
| 256 |
+
"total_flos": 2.52083994624e+17,
|
| 257 |
+
"trial_name": null,
|
| 258 |
+
"trial_params": null
|
| 259 |
+
}
|
checkpoint-14000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe0e860512f8469e428abf5b40149ed383475cb1fb119ba3f4a814c039cc7eba
|
| 3 |
+
size 4536
|
checkpoint-14500/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 24,
|
| 22 |
+
"num_heads": 16,
|
| 23 |
+
"num_layers": 24,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.35.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32128
|
| 33 |
+
}
|
checkpoint-14500/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.35.2"
|
| 7 |
+
}
|
checkpoint-14500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5c9f43b43f47473764bc2a266439e5428b780e6eeb8cb2f10eb6498f8da1d54
|
| 3 |
+
size 3132668808
|
checkpoint-14500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65b5200dfb72e46ffb40baa1cd436e6832b792611f4dfd7ed8b6f928ed04d529
|
| 3 |
+
size 6265677800
|
checkpoint-14500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d108c9f568f5e26cf17e4ac5b761737cf91a74592fca3a3d6dbcb3394a2c8568
|
| 3 |
+
size 14244
|
checkpoint-14500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7c3ed9d025cc361b79e46fefb4550bc2fb96c392b7005751052c4e8418be02c
|
| 3 |
+
size 1064
|
checkpoint-14500/trainer_state.json
ADDED
|
@@ -0,0 +1,265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.757738896366083,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 14500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.34,
|
| 13 |
+
"learning_rate": 1.932705248990579e-05,
|
| 14 |
+
"loss": 0.2243,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.67,
|
| 19 |
+
"learning_rate": 1.8654104979811575e-05,
|
| 20 |
+
"loss": 0.1513,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.0,
|
| 25 |
+
"eval_loss": 0.15557065606117249,
|
| 26 |
+
"eval_runtime": 122.4795,
|
| 27 |
+
"eval_samples_per_second": 12.141,
|
| 28 |
+
"eval_steps_per_second": 3.037,
|
| 29 |
+
"step": 1486
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.01,
|
| 33 |
+
"learning_rate": 1.7981157469717363e-05,
|
| 34 |
+
"loss": 0.1319,
|
| 35 |
+
"step": 1500
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.35,
|
| 39 |
+
"learning_rate": 1.730820995962315e-05,
|
| 40 |
+
"loss": 0.1161,
|
| 41 |
+
"step": 2000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.68,
|
| 45 |
+
"learning_rate": 1.6635262449528936e-05,
|
| 46 |
+
"loss": 0.1161,
|
| 47 |
+
"step": 2500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_loss": 0.09562207758426666,
|
| 52 |
+
"eval_runtime": 122.4632,
|
| 53 |
+
"eval_samples_per_second": 12.142,
|
| 54 |
+
"eval_steps_per_second": 3.038,
|
| 55 |
+
"step": 2972
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.02,
|
| 59 |
+
"learning_rate": 1.5962314939434724e-05,
|
| 60 |
+
"loss": 0.1072,
|
| 61 |
+
"step": 3000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.36,
|
| 65 |
+
"learning_rate": 1.5289367429340512e-05,
|
| 66 |
+
"loss": 0.0999,
|
| 67 |
+
"step": 3500
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.69,
|
| 71 |
+
"learning_rate": 1.46164199192463e-05,
|
| 72 |
+
"loss": 0.0765,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 3.0,
|
| 77 |
+
"eval_loss": 0.11794405430555344,
|
| 78 |
+
"eval_runtime": 122.4644,
|
| 79 |
+
"eval_samples_per_second": 12.142,
|
| 80 |
+
"eval_steps_per_second": 3.038,
|
| 81 |
+
"step": 4458
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.03,
|
| 85 |
+
"learning_rate": 1.3943472409152087e-05,
|
| 86 |
+
"loss": 0.0886,
|
| 87 |
+
"step": 4500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.36,
|
| 91 |
+
"learning_rate": 1.3270524899057875e-05,
|
| 92 |
+
"loss": 0.0793,
|
| 93 |
+
"step": 5000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.7,
|
| 97 |
+
"learning_rate": 1.2597577388963662e-05,
|
| 98 |
+
"loss": 0.0798,
|
| 99 |
+
"step": 5500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.0,
|
| 103 |
+
"eval_loss": 0.11743835359811783,
|
| 104 |
+
"eval_runtime": 122.4332,
|
| 105 |
+
"eval_samples_per_second": 12.145,
|
| 106 |
+
"eval_steps_per_second": 3.038,
|
| 107 |
+
"step": 5944
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 4.04,
|
| 111 |
+
"learning_rate": 1.192462987886945e-05,
|
| 112 |
+
"loss": 0.0737,
|
| 113 |
+
"step": 6000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 4.37,
|
| 117 |
+
"learning_rate": 1.1251682368775237e-05,
|
| 118 |
+
"loss": 0.0739,
|
| 119 |
+
"step": 6500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.71,
|
| 123 |
+
"learning_rate": 1.0578734858681023e-05,
|
| 124 |
+
"loss": 0.0705,
|
| 125 |
+
"step": 7000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 5.0,
|
| 129 |
+
"eval_loss": 0.09409211575984955,
|
| 130 |
+
"eval_runtime": 122.4407,
|
| 131 |
+
"eval_samples_per_second": 12.145,
|
| 132 |
+
"eval_steps_per_second": 3.038,
|
| 133 |
+
"step": 7430
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 5.05,
|
| 137 |
+
"learning_rate": 9.905787348586811e-06,
|
| 138 |
+
"loss": 0.0668,
|
| 139 |
+
"step": 7500
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 5.38,
|
| 143 |
+
"learning_rate": 9.2328398384926e-06,
|
| 144 |
+
"loss": 0.0558,
|
| 145 |
+
"step": 8000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 5.72,
|
| 149 |
+
"learning_rate": 8.559892328398386e-06,
|
| 150 |
+
"loss": 0.0609,
|
| 151 |
+
"step": 8500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 6.0,
|
| 155 |
+
"eval_loss": 0.12117910385131836,
|
| 156 |
+
"eval_runtime": 122.4449,
|
| 157 |
+
"eval_samples_per_second": 12.144,
|
| 158 |
+
"eval_steps_per_second": 3.038,
|
| 159 |
+
"step": 8916
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 6.06,
|
| 163 |
+
"learning_rate": 7.886944818304172e-06,
|
| 164 |
+
"loss": 0.0617,
|
| 165 |
+
"step": 9000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 6.39,
|
| 169 |
+
"learning_rate": 7.21399730820996e-06,
|
| 170 |
+
"loss": 0.0537,
|
| 171 |
+
"step": 9500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 6.73,
|
| 175 |
+
"learning_rate": 6.541049798115747e-06,
|
| 176 |
+
"loss": 0.0542,
|
| 177 |
+
"step": 10000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 7.0,
|
| 181 |
+
"eval_loss": 0.10626289248466492,
|
| 182 |
+
"eval_runtime": 122.4232,
|
| 183 |
+
"eval_samples_per_second": 12.146,
|
| 184 |
+
"eval_steps_per_second": 3.039,
|
| 185 |
+
"step": 10402
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 7.07,
|
| 189 |
+
"learning_rate": 5.8681022880215346e-06,
|
| 190 |
+
"loss": 0.0485,
|
| 191 |
+
"step": 10500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 7.4,
|
| 195 |
+
"learning_rate": 5.195154777927323e-06,
|
| 196 |
+
"loss": 0.0522,
|
| 197 |
+
"step": 11000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 7.74,
|
| 201 |
+
"learning_rate": 4.522207267833109e-06,
|
| 202 |
+
"loss": 0.0542,
|
| 203 |
+
"step": 11500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 8.0,
|
| 207 |
+
"eval_loss": 0.13295996189117432,
|
| 208 |
+
"eval_runtime": 122.4378,
|
| 209 |
+
"eval_samples_per_second": 12.145,
|
| 210 |
+
"eval_steps_per_second": 3.038,
|
| 211 |
+
"step": 11888
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 8.08,
|
| 215 |
+
"learning_rate": 3.849259757738897e-06,
|
| 216 |
+
"loss": 0.0545,
|
| 217 |
+
"step": 12000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 8.41,
|
| 221 |
+
"learning_rate": 3.176312247644684e-06,
|
| 222 |
+
"loss": 0.0391,
|
| 223 |
+
"step": 12500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 8.75,
|
| 227 |
+
"learning_rate": 2.503364737550471e-06,
|
| 228 |
+
"loss": 0.0418,
|
| 229 |
+
"step": 13000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 9.0,
|
| 233 |
+
"eval_loss": 0.1395300030708313,
|
| 234 |
+
"eval_runtime": 122.4262,
|
| 235 |
+
"eval_samples_per_second": 12.146,
|
| 236 |
+
"eval_steps_per_second": 3.039,
|
| 237 |
+
"step": 13374
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.08,
|
| 241 |
+
"learning_rate": 1.8304172274562585e-06,
|
| 242 |
+
"loss": 0.0385,
|
| 243 |
+
"step": 13500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 9.42,
|
| 247 |
+
"learning_rate": 1.157469717362046e-06,
|
| 248 |
+
"loss": 0.0434,
|
| 249 |
+
"step": 14000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 9.76,
|
| 253 |
+
"learning_rate": 4.845222072678332e-07,
|
| 254 |
+
"loss": 0.0494,
|
| 255 |
+
"step": 14500
|
| 256 |
+
}
|
| 257 |
+
],
|
| 258 |
+
"logging_steps": 500,
|
| 259 |
+
"max_steps": 14860,
|
| 260 |
+
"num_train_epochs": 10,
|
| 261 |
+
"save_steps": 500,
|
| 262 |
+
"total_flos": 2.61086994432e+17,
|
| 263 |
+
"trial_name": null,
|
| 264 |
+
"trial_params": null
|
| 265 |
+
}
|
checkpoint-14500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe0e860512f8469e428abf5b40149ed383475cb1fb119ba3f4a814c039cc7eba
|
| 3 |
+
size 4536
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 24,
|
| 22 |
+
"num_heads": 16,
|
| 23 |
+
"num_layers": 24,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.35.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32128
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.35.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bdead01fd8f943755ef93798510534d6362cf6f02a1c3c6872ccf6b3ca1347e
|
| 3 |
+
size 3132668808
|
runs/Nov29_19-42-21_ea2ffa840b9b/events.out.tfevents.1701286949.ea2ffa840b9b.184.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:025af226f7786de677e4902a1abc8c20496ee68730d5b5fddc0c11d523ed297a
|
| 3 |
+
size 11948
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe0e860512f8469e428abf5b40149ed383475cb1fb119ba3f4a814c039cc7eba
|
| 3 |
+
size 4536
|