Upload folder using huggingface_hub
Browse files- outputs/tiny-50M/checkpoint-94/config.json +32 -0
- outputs/tiny-50M/checkpoint-94/generation_config.json +9 -0
- outputs/tiny-50M/checkpoint-94/model.safetensors +3 -0
- outputs/tiny-50M/checkpoint-94/optimizer.pt +3 -0
- outputs/tiny-50M/checkpoint-94/rng_state.pth +3 -0
- outputs/tiny-50M/checkpoint-94/scaler.pt +3 -0
- outputs/tiny-50M/checkpoint-94/scheduler.pt +3 -0
- outputs/tiny-50M/checkpoint-94/trainer_state.json +363 -0
- outputs/tiny-50M/model.safetensors +1 -1
outputs/tiny-50M/checkpoint-94/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 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": 512,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 1376,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 8,
|
| 19 |
+
"num_hidden_layers": 8,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"pad_token_id": null,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"rope_theta": 500000.0,
|
| 26 |
+
"rope_type": "default"
|
| 27 |
+
},
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"transformers_version": "5.17.0",
|
| 30 |
+
"use_cache": false,
|
| 31 |
+
"vocab_size": 32000
|
| 32 |
+
}
|
outputs/tiny-50M/checkpoint-94/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"transformers_version": "5.17.0",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
outputs/tiny-50M/checkpoint-94/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae96028076b6e140e06e513f753332301f0815540e99342614f848b0b5f0890a
|
| 3 |
+
size 223914096
|
outputs/tiny-50M/checkpoint-94/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7733ea084c434ec579f2f3cc4aee34b44190325f6f48362cfa246a0b6e81a92a
|
| 3 |
+
size 447876619
|
outputs/tiny-50M/checkpoint-94/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
|
| 3 |
+
size 14645
|
outputs/tiny-50M/checkpoint-94/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72c69b9ecccfbb663d97b378e5433389943067b42ff8fd466b6c215d4f67bcb4
|
| 3 |
+
size 1383
|
outputs/tiny-50M/checkpoint-94/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8e91a260695ec333361cb15989c494ddb7035f35f9b17c54bdc5581a2608474
|
| 3 |
+
size 1465
|
outputs/tiny-50M/checkpoint-94/trainer_state.json
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 94,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.021333333333333333,
|
| 14 |
+
"grad_norm": 19.857784271240234,
|
| 15 |
+
"learning_rate": 0.00029680851063829784,
|
| 16 |
+
"loss": 8.839614868164062,
|
| 17 |
+
"step": 2
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.042666666666666665,
|
| 21 |
+
"grad_norm": 8.053306579589844,
|
| 22 |
+
"learning_rate": 0.0002904255319148936,
|
| 23 |
+
"loss": 4.259130954742432,
|
| 24 |
+
"step": 4
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.064,
|
| 28 |
+
"grad_norm": 7.085880279541016,
|
| 29 |
+
"learning_rate": 0.00028404255319148934,
|
| 30 |
+
"loss": 4.260076999664307,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.08533333333333333,
|
| 35 |
+
"grad_norm": 5.618923664093018,
|
| 36 |
+
"learning_rate": 0.00027765957446808506,
|
| 37 |
+
"loss": 3.5047478675842285,
|
| 38 |
+
"step": 8
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.10666666666666667,
|
| 42 |
+
"grad_norm": 6.0084614753723145,
|
| 43 |
+
"learning_rate": 0.00027127659574468084,
|
| 44 |
+
"loss": 3.2548251152038574,
|
| 45 |
+
"step": 10
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.128,
|
| 49 |
+
"grad_norm": 3.2026114463806152,
|
| 50 |
+
"learning_rate": 0.00026489361702127656,
|
| 51 |
+
"loss": 2.6681971549987793,
|
| 52 |
+
"step": 12
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.14933333333333335,
|
| 56 |
+
"grad_norm": 2.4880897998809814,
|
| 57 |
+
"learning_rate": 0.0002585106382978723,
|
| 58 |
+
"loss": 2.908954620361328,
|
| 59 |
+
"step": 14
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.17066666666666666,
|
| 63 |
+
"grad_norm": 2.081550121307373,
|
| 64 |
+
"learning_rate": 0.00025212765957446806,
|
| 65 |
+
"loss": 2.3955461978912354,
|
| 66 |
+
"step": 16
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.192,
|
| 70 |
+
"grad_norm": 2.23256254196167,
|
| 71 |
+
"learning_rate": 0.00024574468085106384,
|
| 72 |
+
"loss": 1.9950157403945923,
|
| 73 |
+
"step": 18
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.21333333333333335,
|
| 77 |
+
"grad_norm": 1.2642862796783447,
|
| 78 |
+
"learning_rate": 0.00023936170212765956,
|
| 79 |
+
"loss": 2.406209945678711,
|
| 80 |
+
"step": 20
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.23466666666666666,
|
| 84 |
+
"grad_norm": 1.0684170722961426,
|
| 85 |
+
"learning_rate": 0.00023297872340425529,
|
| 86 |
+
"loss": 1.4826658964157104,
|
| 87 |
+
"step": 22
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.256,
|
| 91 |
+
"grad_norm": 1.1620922088623047,
|
| 92 |
+
"learning_rate": 0.00022659574468085106,
|
| 93 |
+
"loss": 1.7480285167694092,
|
| 94 |
+
"step": 24
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2773333333333333,
|
| 98 |
+
"grad_norm": 1.057904839515686,
|
| 99 |
+
"learning_rate": 0.00022021276595744679,
|
| 100 |
+
"loss": 1.8112417459487915,
|
| 101 |
+
"step": 26
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2986666666666667,
|
| 105 |
+
"grad_norm": 1.139146327972412,
|
| 106 |
+
"learning_rate": 0.00021382978723404254,
|
| 107 |
+
"loss": 1.962647795677185,
|
| 108 |
+
"step": 28
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.32,
|
| 112 |
+
"grad_norm": 0.7921020984649658,
|
| 113 |
+
"learning_rate": 0.0002074468085106383,
|
| 114 |
+
"loss": 1.338681936264038,
|
| 115 |
+
"step": 30
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.3413333333333333,
|
| 119 |
+
"grad_norm": 0.5229901671409607,
|
| 120 |
+
"learning_rate": 0.00020106382978723404,
|
| 121 |
+
"loss": 1.2959659099578857,
|
| 122 |
+
"step": 32
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.3626666666666667,
|
| 126 |
+
"grad_norm": 0.5313481092453003,
|
| 127 |
+
"learning_rate": 0.00019468085106382976,
|
| 128 |
+
"loss": 1.3124475479125977,
|
| 129 |
+
"step": 34
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.384,
|
| 133 |
+
"grad_norm": 0.29172077775001526,
|
| 134 |
+
"learning_rate": 0.0001882978723404255,
|
| 135 |
+
"loss": 1.4122732877731323,
|
| 136 |
+
"step": 36
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4053333333333333,
|
| 140 |
+
"grad_norm": 0.4614223837852478,
|
| 141 |
+
"learning_rate": 0.00018191489361702126,
|
| 142 |
+
"loss": 1.14182710647583,
|
| 143 |
+
"step": 38
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.4266666666666667,
|
| 147 |
+
"grad_norm": 0.3804754912853241,
|
| 148 |
+
"learning_rate": 0.000175531914893617,
|
| 149 |
+
"loss": 1.2516833543777466,
|
| 150 |
+
"step": 40
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.448,
|
| 154 |
+
"grad_norm": 0.33474111557006836,
|
| 155 |
+
"learning_rate": 0.00016914893617021274,
|
| 156 |
+
"loss": 1.2273238897323608,
|
| 157 |
+
"step": 42
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.4693333333333333,
|
| 161 |
+
"grad_norm": 0.39935603737831116,
|
| 162 |
+
"learning_rate": 0.00016276595744680849,
|
| 163 |
+
"loss": 0.9951828122138977,
|
| 164 |
+
"step": 44
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.49066666666666664,
|
| 168 |
+
"grad_norm": 0.23251356184482574,
|
| 169 |
+
"learning_rate": 0.00015638297872340426,
|
| 170 |
+
"loss": 1.0770968198776245,
|
| 171 |
+
"step": 46
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.512,
|
| 175 |
+
"grad_norm": 0.262003093957901,
|
| 176 |
+
"learning_rate": 0.00015,
|
| 177 |
+
"loss": 1.340306043624878,
|
| 178 |
+
"step": 48
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.5333333333333333,
|
| 182 |
+
"grad_norm": 0.3379991352558136,
|
| 183 |
+
"learning_rate": 0.00014361702127659574,
|
| 184 |
+
"loss": 1.1250380277633667,
|
| 185 |
+
"step": 50
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.5546666666666666,
|
| 189 |
+
"grad_norm": 0.25868967175483704,
|
| 190 |
+
"learning_rate": 0.0001372340425531915,
|
| 191 |
+
"loss": 1.2347091436386108,
|
| 192 |
+
"step": 52
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.576,
|
| 196 |
+
"grad_norm": 0.2983493506908417,
|
| 197 |
+
"learning_rate": 0.00013085106382978724,
|
| 198 |
+
"loss": 1.0739911794662476,
|
| 199 |
+
"step": 54
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.5973333333333334,
|
| 203 |
+
"grad_norm": 0.3253922760486603,
|
| 204 |
+
"learning_rate": 0.00012446808510638296,
|
| 205 |
+
"loss": 0.986941397190094,
|
| 206 |
+
"step": 56
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.6186666666666667,
|
| 210 |
+
"grad_norm": 0.32209739089012146,
|
| 211 |
+
"learning_rate": 0.00011808510638297871,
|
| 212 |
+
"loss": 1.1307929754257202,
|
| 213 |
+
"step": 58
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.64,
|
| 217 |
+
"grad_norm": 0.2041606307029724,
|
| 218 |
+
"learning_rate": 0.00011170212765957445,
|
| 219 |
+
"loss": 0.9198997616767883,
|
| 220 |
+
"step": 60
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.6613333333333333,
|
| 224 |
+
"grad_norm": 0.20420902967453003,
|
| 225 |
+
"learning_rate": 0.0001053191489361702,
|
| 226 |
+
"loss": 0.7641400694847107,
|
| 227 |
+
"step": 62
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.6826666666666666,
|
| 231 |
+
"grad_norm": 0.3539799451828003,
|
| 232 |
+
"learning_rate": 9.893617021276594e-05,
|
| 233 |
+
"loss": 1.109285593032837,
|
| 234 |
+
"step": 64
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.704,
|
| 238 |
+
"grad_norm": 0.3249659836292267,
|
| 239 |
+
"learning_rate": 9.25531914893617e-05,
|
| 240 |
+
"loss": 1.0656695365905762,
|
| 241 |
+
"step": 66
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.7253333333333334,
|
| 245 |
+
"grad_norm": 0.283320814371109,
|
| 246 |
+
"learning_rate": 8.617021276595745e-05,
|
| 247 |
+
"loss": 1.0882402658462524,
|
| 248 |
+
"step": 68
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.7466666666666667,
|
| 252 |
+
"grad_norm": 0.4081163704395294,
|
| 253 |
+
"learning_rate": 7.978723404255319e-05,
|
| 254 |
+
"loss": 0.8739507794380188,
|
| 255 |
+
"step": 70
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.768,
|
| 259 |
+
"grad_norm": 0.4886767864227295,
|
| 260 |
+
"learning_rate": 7.340425531914892e-05,
|
| 261 |
+
"loss": 1.099593162536621,
|
| 262 |
+
"step": 72
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.7893333333333333,
|
| 266 |
+
"grad_norm": 0.38340282440185547,
|
| 267 |
+
"learning_rate": 6.702127659574467e-05,
|
| 268 |
+
"loss": 1.378351092338562,
|
| 269 |
+
"step": 74
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.8106666666666666,
|
| 273 |
+
"grad_norm": 0.39620906114578247,
|
| 274 |
+
"learning_rate": 6.063829787234042e-05,
|
| 275 |
+
"loss": 1.1076319217681885,
|
| 276 |
+
"step": 76
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.832,
|
| 280 |
+
"grad_norm": 0.30094316601753235,
|
| 281 |
+
"learning_rate": 5.425531914893617e-05,
|
| 282 |
+
"loss": 0.768018901348114,
|
| 283 |
+
"step": 78
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.8533333333333334,
|
| 287 |
+
"grad_norm": 0.4080992639064789,
|
| 288 |
+
"learning_rate": 4.787234042553191e-05,
|
| 289 |
+
"loss": 0.9190238118171692,
|
| 290 |
+
"step": 80
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.8746666666666667,
|
| 294 |
+
"grad_norm": 0.22875891625881195,
|
| 295 |
+
"learning_rate": 4.1489361702127656e-05,
|
| 296 |
+
"loss": 0.6930217146873474,
|
| 297 |
+
"step": 82
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.896,
|
| 301 |
+
"grad_norm": 0.4183938801288605,
|
| 302 |
+
"learning_rate": 3.51063829787234e-05,
|
| 303 |
+
"loss": 0.9895132780075073,
|
| 304 |
+
"step": 84
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.9173333333333333,
|
| 308 |
+
"grad_norm": 0.5136104822158813,
|
| 309 |
+
"learning_rate": 2.8723404255319147e-05,
|
| 310 |
+
"loss": 0.9970792531967163,
|
| 311 |
+
"step": 86
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.9386666666666666,
|
| 315 |
+
"grad_norm": 0.39408519864082336,
|
| 316 |
+
"learning_rate": 2.234042553191489e-05,
|
| 317 |
+
"loss": 0.8527765870094299,
|
| 318 |
+
"step": 88
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.96,
|
| 322 |
+
"grad_norm": 0.3212464153766632,
|
| 323 |
+
"learning_rate": 1.5957446808510637e-05,
|
| 324 |
+
"loss": 1.1280995607376099,
|
| 325 |
+
"step": 90
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.9813333333333333,
|
| 329 |
+
"grad_norm": 0.37641191482543945,
|
| 330 |
+
"learning_rate": 9.574468085106381e-06,
|
| 331 |
+
"loss": 1.1669095754623413,
|
| 332 |
+
"step": 92
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.0,
|
| 336 |
+
"grad_norm": 0.3149685263633728,
|
| 337 |
+
"learning_rate": 3.1914893617021273e-06,
|
| 338 |
+
"loss": 0.982663631439209,
|
| 339 |
+
"step": 94
|
| 340 |
+
}
|
| 341 |
+
],
|
| 342 |
+
"logging_steps": 2,
|
| 343 |
+
"max_steps": 94,
|
| 344 |
+
"num_input_tokens_seen": 0,
|
| 345 |
+
"num_train_epochs": 1,
|
| 346 |
+
"save_steps": 50,
|
| 347 |
+
"stateful_callbacks": {
|
| 348 |
+
"TrainerControl": {
|
| 349 |
+
"args": {
|
| 350 |
+
"should_epoch_stop": false,
|
| 351 |
+
"should_evaluate": false,
|
| 352 |
+
"should_log": false,
|
| 353 |
+
"should_save": true,
|
| 354 |
+
"should_training_stop": true
|
| 355 |
+
},
|
| 356 |
+
"attributes": {}
|
| 357 |
+
}
|
| 358 |
+
},
|
| 359 |
+
"total_flos": 729768001536000.0,
|
| 360 |
+
"train_batch_size": 2,
|
| 361 |
+
"trial_name": null,
|
| 362 |
+
"trial_params": null
|
| 363 |
+
}
|
outputs/tiny-50M/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 223914096
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae96028076b6e140e06e513f753332301f0815540e99342614f848b0b5f0890a
|
| 3 |
size 223914096
|