Upload Iran v1
Browse files- checkpoint-5000/config.json +29 -0
- checkpoint-5000/generation_config.json +6 -0
- checkpoint-5000/model.safetensors +3 -0
- checkpoint-5000/optimizer.pt +3 -0
- checkpoint-5000/rng_state.pth +3 -0
- checkpoint-5000/scaler.pt +3 -0
- checkpoint-5000/scheduler.pt +3 -0
- checkpoint-5000/trainer_state.json +384 -0
- checkpoint-5000/training_args.bin +3 -0
- config.json +29 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +23 -0
- vocab.json +0 -0
checkpoint-5000/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"YasinForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"max_position_embeddings": 1024,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "yasin",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"num_key_value_heads": 12,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"transformers_version": "4.57.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50257
|
| 29 |
+
}
|
checkpoint-5000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.57.1"
|
| 6 |
+
}
|
checkpoint-5000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07dcafeb1f764299f869599ed10509d9285437abaa407bb8ad2ce9b9c66765ae
|
| 3 |
+
size 761852960
|
checkpoint-5000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1d16624efef1ef1ea887e5bc6d8ab2d24516465bd7da011f0cb54d0b3be81bd
|
| 3 |
+
size 1523777035
|
checkpoint-5000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
|
| 3 |
+
size 14645
|
checkpoint-5000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82ad8990572ad11a824b7db276c8af49c179ca7e7724b4e6906cd0ae480a80a8
|
| 3 |
+
size 1383
|
checkpoint-5000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6f29c012492bc9d43a8cbe74689ae8d95f9b1c53e67e7acc8f79812e420f564
|
| 3 |
+
size 1465
|
checkpoint-5000/trainer_state.json
ADDED
|
@@ -0,0 +1,384 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 5000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.02,
|
| 14 |
+
"grad_norm": 1.9574642181396484,
|
| 15 |
+
"learning_rate": 4.901e-05,
|
| 16 |
+
"loss": 4.8716,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04,
|
| 21 |
+
"grad_norm": 1.562890648841858,
|
| 22 |
+
"learning_rate": 4.801e-05,
|
| 23 |
+
"loss": 2.5735,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06,
|
| 28 |
+
"grad_norm": 2.5503687858581543,
|
| 29 |
+
"learning_rate": 4.7010000000000006e-05,
|
| 30 |
+
"loss": 2.2182,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08,
|
| 35 |
+
"grad_norm": 1.3021109104156494,
|
| 36 |
+
"learning_rate": 4.601e-05,
|
| 37 |
+
"loss": 1.9191,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"grad_norm": 1.3246175050735474,
|
| 43 |
+
"learning_rate": 4.5010000000000004e-05,
|
| 44 |
+
"loss": 1.8126,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.12,
|
| 49 |
+
"grad_norm": 1.04691481590271,
|
| 50 |
+
"learning_rate": 4.401e-05,
|
| 51 |
+
"loss": 1.7728,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.14,
|
| 56 |
+
"grad_norm": 0.9935975670814514,
|
| 57 |
+
"learning_rate": 4.301e-05,
|
| 58 |
+
"loss": 1.6751,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.16,
|
| 63 |
+
"grad_norm": 1.1450852155685425,
|
| 64 |
+
"learning_rate": 4.201e-05,
|
| 65 |
+
"loss": 1.5686,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.18,
|
| 70 |
+
"grad_norm": 1.1858118772506714,
|
| 71 |
+
"learning_rate": 4.101e-05,
|
| 72 |
+
"loss": 1.6261,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.2,
|
| 77 |
+
"grad_norm": 1.2318594455718994,
|
| 78 |
+
"learning_rate": 4.0010000000000005e-05,
|
| 79 |
+
"loss": 1.6018,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.22,
|
| 84 |
+
"grad_norm": 1.0691641569137573,
|
| 85 |
+
"learning_rate": 3.901e-05,
|
| 86 |
+
"loss": 1.5865,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.24,
|
| 91 |
+
"grad_norm": 0.8661352396011353,
|
| 92 |
+
"learning_rate": 3.8010000000000004e-05,
|
| 93 |
+
"loss": 1.4648,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.26,
|
| 98 |
+
"grad_norm": 0.9778139591217041,
|
| 99 |
+
"learning_rate": 3.701e-05,
|
| 100 |
+
"loss": 1.4765,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.28,
|
| 105 |
+
"grad_norm": 1.3476413488388062,
|
| 106 |
+
"learning_rate": 3.601e-05,
|
| 107 |
+
"loss": 1.5541,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3,
|
| 112 |
+
"grad_norm": 0.7631675004959106,
|
| 113 |
+
"learning_rate": 3.5010000000000005e-05,
|
| 114 |
+
"loss": 1.5048,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.32,
|
| 119 |
+
"grad_norm": 1.1490070819854736,
|
| 120 |
+
"learning_rate": 3.401e-05,
|
| 121 |
+
"loss": 1.5052,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.34,
|
| 126 |
+
"grad_norm": 1.077760934829712,
|
| 127 |
+
"learning_rate": 3.3010000000000004e-05,
|
| 128 |
+
"loss": 1.5638,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.36,
|
| 133 |
+
"grad_norm": 0.8567506670951843,
|
| 134 |
+
"learning_rate": 3.201e-05,
|
| 135 |
+
"loss": 1.5387,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.38,
|
| 140 |
+
"grad_norm": 0.842096209526062,
|
| 141 |
+
"learning_rate": 3.101e-05,
|
| 142 |
+
"loss": 1.5037,
|
| 143 |
+
"step": 1900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4,
|
| 147 |
+
"grad_norm": 0.8851768374443054,
|
| 148 |
+
"learning_rate": 3.001e-05,
|
| 149 |
+
"loss": 1.5145,
|
| 150 |
+
"step": 2000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.42,
|
| 154 |
+
"grad_norm": 0.7667313814163208,
|
| 155 |
+
"learning_rate": 2.9010000000000005e-05,
|
| 156 |
+
"loss": 1.526,
|
| 157 |
+
"step": 2100
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.44,
|
| 161 |
+
"grad_norm": 1.079816460609436,
|
| 162 |
+
"learning_rate": 2.8010000000000005e-05,
|
| 163 |
+
"loss": 1.5332,
|
| 164 |
+
"step": 2200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.46,
|
| 168 |
+
"grad_norm": 0.9301439523696899,
|
| 169 |
+
"learning_rate": 2.701e-05,
|
| 170 |
+
"loss": 1.4011,
|
| 171 |
+
"step": 2300
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.48,
|
| 175 |
+
"grad_norm": 0.9722267985343933,
|
| 176 |
+
"learning_rate": 2.601e-05,
|
| 177 |
+
"loss": 1.4697,
|
| 178 |
+
"step": 2400
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5,
|
| 182 |
+
"grad_norm": 0.8725349307060242,
|
| 183 |
+
"learning_rate": 2.501e-05,
|
| 184 |
+
"loss": 1.4873,
|
| 185 |
+
"step": 2500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.52,
|
| 189 |
+
"grad_norm": 1.0267070531845093,
|
| 190 |
+
"learning_rate": 2.4010000000000002e-05,
|
| 191 |
+
"loss": 1.4103,
|
| 192 |
+
"step": 2600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.54,
|
| 196 |
+
"grad_norm": 0.70062655210495,
|
| 197 |
+
"learning_rate": 2.301e-05,
|
| 198 |
+
"loss": 1.3659,
|
| 199 |
+
"step": 2700
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.56,
|
| 203 |
+
"grad_norm": 0.8035644888877869,
|
| 204 |
+
"learning_rate": 2.201e-05,
|
| 205 |
+
"loss": 1.4009,
|
| 206 |
+
"step": 2800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.58,
|
| 210 |
+
"grad_norm": 0.8089845776557922,
|
| 211 |
+
"learning_rate": 2.101e-05,
|
| 212 |
+
"loss": 1.4293,
|
| 213 |
+
"step": 2900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.6,
|
| 217 |
+
"grad_norm": 0.8427271246910095,
|
| 218 |
+
"learning_rate": 2.001e-05,
|
| 219 |
+
"loss": 1.4011,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.62,
|
| 224 |
+
"grad_norm": 0.994111180305481,
|
| 225 |
+
"learning_rate": 1.901e-05,
|
| 226 |
+
"loss": 1.3785,
|
| 227 |
+
"step": 3100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.64,
|
| 231 |
+
"grad_norm": 1.0096153020858765,
|
| 232 |
+
"learning_rate": 1.8010000000000002e-05,
|
| 233 |
+
"loss": 1.4122,
|
| 234 |
+
"step": 3200
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.66,
|
| 238 |
+
"grad_norm": 0.7762922644615173,
|
| 239 |
+
"learning_rate": 1.701e-05,
|
| 240 |
+
"loss": 1.3849,
|
| 241 |
+
"step": 3300
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.68,
|
| 245 |
+
"grad_norm": 1.1585968732833862,
|
| 246 |
+
"learning_rate": 1.601e-05,
|
| 247 |
+
"loss": 1.3961,
|
| 248 |
+
"step": 3400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7,
|
| 252 |
+
"grad_norm": 0.9618488550186157,
|
| 253 |
+
"learning_rate": 1.5010000000000002e-05,
|
| 254 |
+
"loss": 1.3458,
|
| 255 |
+
"step": 3500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.72,
|
| 259 |
+
"grad_norm": 1.007106065750122,
|
| 260 |
+
"learning_rate": 1.4010000000000001e-05,
|
| 261 |
+
"loss": 1.3952,
|
| 262 |
+
"step": 3600
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.74,
|
| 266 |
+
"grad_norm": 0.9712181091308594,
|
| 267 |
+
"learning_rate": 1.301e-05,
|
| 268 |
+
"loss": 1.3275,
|
| 269 |
+
"step": 3700
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.76,
|
| 273 |
+
"grad_norm": 0.9360325336456299,
|
| 274 |
+
"learning_rate": 1.201e-05,
|
| 275 |
+
"loss": 1.3479,
|
| 276 |
+
"step": 3800
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.78,
|
| 280 |
+
"grad_norm": 0.889412522315979,
|
| 281 |
+
"learning_rate": 1.1010000000000001e-05,
|
| 282 |
+
"loss": 1.4002,
|
| 283 |
+
"step": 3900
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.8,
|
| 287 |
+
"grad_norm": 1.4792468547821045,
|
| 288 |
+
"learning_rate": 1.001e-05,
|
| 289 |
+
"loss": 1.2896,
|
| 290 |
+
"step": 4000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.82,
|
| 294 |
+
"grad_norm": 0.8564038276672363,
|
| 295 |
+
"learning_rate": 9.01e-06,
|
| 296 |
+
"loss": 1.3501,
|
| 297 |
+
"step": 4100
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.84,
|
| 301 |
+
"grad_norm": 0.8316518664360046,
|
| 302 |
+
"learning_rate": 8.010000000000001e-06,
|
| 303 |
+
"loss": 1.3673,
|
| 304 |
+
"step": 4200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.86,
|
| 308 |
+
"grad_norm": 0.8671555519104004,
|
| 309 |
+
"learning_rate": 7.01e-06,
|
| 310 |
+
"loss": 1.328,
|
| 311 |
+
"step": 4300
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.88,
|
| 315 |
+
"grad_norm": 0.9001341462135315,
|
| 316 |
+
"learning_rate": 6.01e-06,
|
| 317 |
+
"loss": 1.3363,
|
| 318 |
+
"step": 4400
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.9,
|
| 322 |
+
"grad_norm": 0.8028829097747803,
|
| 323 |
+
"learning_rate": 5.01e-06,
|
| 324 |
+
"loss": 1.3272,
|
| 325 |
+
"step": 4500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.92,
|
| 329 |
+
"grad_norm": 0.923729419708252,
|
| 330 |
+
"learning_rate": 4.01e-06,
|
| 331 |
+
"loss": 1.3645,
|
| 332 |
+
"step": 4600
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.94,
|
| 336 |
+
"grad_norm": 1.2373661994934082,
|
| 337 |
+
"learning_rate": 3.01e-06,
|
| 338 |
+
"loss": 1.3762,
|
| 339 |
+
"step": 4700
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.96,
|
| 343 |
+
"grad_norm": 1.1914544105529785,
|
| 344 |
+
"learning_rate": 2.0100000000000002e-06,
|
| 345 |
+
"loss": 1.2622,
|
| 346 |
+
"step": 4800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.98,
|
| 350 |
+
"grad_norm": 0.8515170216560364,
|
| 351 |
+
"learning_rate": 1.01e-06,
|
| 352 |
+
"loss": 1.3327,
|
| 353 |
+
"step": 4900
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.0,
|
| 357 |
+
"grad_norm": 0.9752984046936035,
|
| 358 |
+
"learning_rate": 1e-08,
|
| 359 |
+
"loss": 1.2896,
|
| 360 |
+
"step": 5000
|
| 361 |
+
}
|
| 362 |
+
],
|
| 363 |
+
"logging_steps": 100,
|
| 364 |
+
"max_steps": 5000,
|
| 365 |
+
"num_input_tokens_seen": 0,
|
| 366 |
+
"num_train_epochs": 9223372036854775807,
|
| 367 |
+
"save_steps": 5000,
|
| 368 |
+
"stateful_callbacks": {
|
| 369 |
+
"TrainerControl": {
|
| 370 |
+
"args": {
|
| 371 |
+
"should_epoch_stop": false,
|
| 372 |
+
"should_evaluate": false,
|
| 373 |
+
"should_log": false,
|
| 374 |
+
"should_save": true,
|
| 375 |
+
"should_training_stop": true
|
| 376 |
+
},
|
| 377 |
+
"attributes": {}
|
| 378 |
+
}
|
| 379 |
+
},
|
| 380 |
+
"total_flos": 7.464359559168e+16,
|
| 381 |
+
"train_batch_size": 4,
|
| 382 |
+
"trial_name": null,
|
| 383 |
+
"trial_params": null
|
| 384 |
+
}
|
checkpoint-5000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7107d9f95e5277c9bd038a1736d06d2f2137a0fa0774b1bba3084f3aaa129b9e
|
| 3 |
+
size 5841
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"YasinForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"max_position_embeddings": 1024,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "yasin",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"num_key_value_heads": 12,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-06,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"transformers_version": "4.57.1",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50257
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.57.1"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07dcafeb1f764299f869599ed10509d9285437abaa407bb8ad2ce9b9c66765ae
|
| 3 |
+
size 761852960
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|endoftext|>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"50256": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
}
|
| 13 |
+
},
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
+
"clean_up_tokenization_spaces": false,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"errors": "replace",
|
| 18 |
+
"extra_special_tokens": {},
|
| 19 |
+
"model_max_length": 1024,
|
| 20 |
+
"pad_token": "<|endoftext|>",
|
| 21 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 22 |
+
"unk_token": "<|endoftext|>"
|
| 23 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|