Training in progress, step 4000, checkpoint
Browse files- last-checkpoint/config.json +34 -0
- last-checkpoint/generation_config.json +9 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +17 -0
- last-checkpoint/trainer_state.json +346 -0
- last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridTimeScaleLM"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": 1,
|
| 6 |
+
"chunk_size": 128,
|
| 7 |
+
"dropout": 0.05,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"latent_dim": 768,
|
| 11 |
+
"layer_types": [
|
| 12 |
+
"linear",
|
| 13 |
+
"linear",
|
| 14 |
+
"linear",
|
| 15 |
+
"softmax",
|
| 16 |
+
"linear",
|
| 17 |
+
"linear",
|
| 18 |
+
"linear",
|
| 19 |
+
"softmax",
|
| 20 |
+
"linear",
|
| 21 |
+
"linear",
|
| 22 |
+
"linear",
|
| 23 |
+
"softmax"
|
| 24 |
+
],
|
| 25 |
+
"model_type": "hybrid_fourier_lm",
|
| 26 |
+
"num_layers": 12,
|
| 27 |
+
"num_modes": 64,
|
| 28 |
+
"pad_token_id": 2,
|
| 29 |
+
"tie_word_embeddings": true,
|
| 30 |
+
"time_scale": 128.0,
|
| 31 |
+
"transformers_version": "5.14.1",
|
| 32 |
+
"use_cache": false,
|
| 33 |
+
"vocab_size": 32768
|
| 34 |
+
}
|
last-checkpoint/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 |
+
"pad_token_id": 2,
|
| 8 |
+
"transformers_version": "5.14.1"
|
| 9 |
+
}
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95c73d234eccc64a09618013c53a92bc4a7c429ebfb1e2678f1bc84f054f04ca
|
| 3 |
+
size 234681136
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dde59450052d104d8238c08fc21017ca7929ea8c3847f36800fa1a9fca90e493
|
| 3 |
+
size 469516363
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f19cd3c4a3ac433efb0482e01f74c9bb46c2bbfbf5afed45038fc450ceaa5f6
|
| 3 |
+
size 14645
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b3af4aaa142e4a55ebe50a8d2db120dc2b7b23b5e6bb84de2f69f7d1627803e
|
| 3 |
+
size 1465
|
last-checkpoint/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"legacy": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 1000000000,
|
| 11 |
+
"pad_token": "</s>",
|
| 12 |
+
"sp_model_kwargs": {},
|
| 13 |
+
"spaces_between_special_tokens": false,
|
| 14 |
+
"tokenizer_class": "TokenizersBackend",
|
| 15 |
+
"unk_token": "<unk>",
|
| 16 |
+
"use_default_system_prompt": false
|
| 17 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.03636363636363636,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 4000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0009090909090909091,
|
| 14 |
+
"grad_norm": 0.25,
|
| 15 |
+
"learning_rate": 0.00066,
|
| 16 |
+
"loss": 2.65932861328125,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0018181818181818182,
|
| 21 |
+
"grad_norm": 0.193359375,
|
| 22 |
+
"learning_rate": 0.000999999509056267,
|
| 23 |
+
"loss": 2.663287353515625,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.0027272727272727275,
|
| 28 |
+
"grad_norm": 0.19140625,
|
| 29 |
+
"learning_rate": 0.0009999954604635122,
|
| 30 |
+
"loss": 2.6766876220703124,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0036363636363636364,
|
| 35 |
+
"grad_norm": 0.1630859375,
|
| 36 |
+
"learning_rate": 0.0009999873224161853,
|
| 37 |
+
"loss": 2.6875625610351563,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.004545454545454545,
|
| 42 |
+
"grad_norm": 0.1591796875,
|
| 43 |
+
"learning_rate": 0.000999975094980847,
|
| 44 |
+
"loss": 2.6895318603515626,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.005454545454545455,
|
| 49 |
+
"grad_norm": 0.16796875,
|
| 50 |
+
"learning_rate": 0.0009999587782575051,
|
| 51 |
+
"loss": 2.7013665771484376,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.006363636363636364,
|
| 56 |
+
"grad_norm": 0.162109375,
|
| 57 |
+
"learning_rate": 0.0009999383723796143,
|
| 58 |
+
"loss": 2.6975772094726564,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.007272727272727273,
|
| 63 |
+
"grad_norm": 0.17578125,
|
| 64 |
+
"learning_rate": 0.0009999138775140734,
|
| 65 |
+
"loss": 2.694542236328125,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.008181818181818182,
|
| 70 |
+
"grad_norm": 0.181640625,
|
| 71 |
+
"learning_rate": 0.000999885293861226,
|
| 72 |
+
"loss": 2.6991891479492187,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.00909090909090909,
|
| 77 |
+
"grad_norm": 0.1787109375,
|
| 78 |
+
"learning_rate": 0.0009998526216548572,
|
| 79 |
+
"loss": 2.6621365356445312,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.00909090909090909,
|
| 84 |
+
"eval_loss": 3.092919111251831,
|
| 85 |
+
"eval_runtime": 5.3241,
|
| 86 |
+
"eval_samples_per_second": 112.132,
|
| 87 |
+
"eval_steps_per_second": 28.174,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.01,
|
| 92 |
+
"grad_norm": 0.1591796875,
|
| 93 |
+
"learning_rate": 0.0009998158611621922,
|
| 94 |
+
"loss": 2.6619110107421875,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.01090909090909091,
|
| 99 |
+
"grad_norm": 0.1669921875,
|
| 100 |
+
"learning_rate": 0.0009997750126838946,
|
| 101 |
+
"loss": 2.700511779785156,
|
| 102 |
+
"step": 1200
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.011818181818181818,
|
| 106 |
+
"grad_norm": 0.1591796875,
|
| 107 |
+
"learning_rate": 0.0009997300765540635,
|
| 108 |
+
"loss": 2.689774475097656,
|
| 109 |
+
"step": 1300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.012727272727272728,
|
| 113 |
+
"grad_norm": 0.171875,
|
| 114 |
+
"learning_rate": 0.0009996810531402306,
|
| 115 |
+
"loss": 2.69824462890625,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.013636363636363636,
|
| 120 |
+
"grad_norm": 0.166015625,
|
| 121 |
+
"learning_rate": 0.0009996279428433578,
|
| 122 |
+
"loss": 2.7036367797851564,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.014545454545454545,
|
| 127 |
+
"grad_norm": 0.1591796875,
|
| 128 |
+
"learning_rate": 0.000999570746097833,
|
| 129 |
+
"loss": 2.6719509887695314,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.015454545454545455,
|
| 134 |
+
"grad_norm": 0.16796875,
|
| 135 |
+
"learning_rate": 0.0009995094633714677,
|
| 136 |
+
"loss": 2.6892950439453127,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.016363636363636365,
|
| 141 |
+
"grad_norm": 0.23828125,
|
| 142 |
+
"learning_rate": 0.0009994440951654924,
|
| 143 |
+
"loss": 2.7064022827148437,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.017272727272727273,
|
| 148 |
+
"grad_norm": 0.169921875,
|
| 149 |
+
"learning_rate": 0.0009993746420145523,
|
| 150 |
+
"loss": 2.6744000244140627,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.01818181818181818,
|
| 155 |
+
"grad_norm": 0.1630859375,
|
| 156 |
+
"learning_rate": 0.0009993011044867038,
|
| 157 |
+
"loss": 2.69939453125,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.01818181818181818,
|
| 162 |
+
"eval_loss": 3.0854060649871826,
|
| 163 |
+
"eval_runtime": 5.237,
|
| 164 |
+
"eval_samples_per_second": 113.996,
|
| 165 |
+
"eval_steps_per_second": 28.642,
|
| 166 |
+
"step": 2000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.019090909090909092,
|
| 170 |
+
"grad_norm": 0.150390625,
|
| 171 |
+
"learning_rate": 0.000999223483183409,
|
| 172 |
+
"loss": 2.6586599731445313,
|
| 173 |
+
"step": 2100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.02,
|
| 177 |
+
"grad_norm": 0.1572265625,
|
| 178 |
+
"learning_rate": 0.000999141778739531,
|
| 179 |
+
"loss": 2.689534912109375,
|
| 180 |
+
"step": 2200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.02090909090909091,
|
| 184 |
+
"grad_norm": 0.177734375,
|
| 185 |
+
"learning_rate": 0.0009990559918233294,
|
| 186 |
+
"loss": 2.6719708251953125,
|
| 187 |
+
"step": 2300
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 0.02181818181818182,
|
| 191 |
+
"grad_norm": 0.20703125,
|
| 192 |
+
"learning_rate": 0.0009989661231364542,
|
| 193 |
+
"loss": 2.6797967529296876,
|
| 194 |
+
"step": 2400
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.022727272727272728,
|
| 198 |
+
"grad_norm": 0.173828125,
|
| 199 |
+
"learning_rate": 0.0009988721734139395,
|
| 200 |
+
"loss": 2.68374267578125,
|
| 201 |
+
"step": 2500
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.023636363636363636,
|
| 205 |
+
"grad_norm": 0.1748046875,
|
| 206 |
+
"learning_rate": 0.0009987741434241983,
|
| 207 |
+
"loss": 2.677032775878906,
|
| 208 |
+
"step": 2600
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.024545454545454544,
|
| 212 |
+
"grad_norm": 0.2119140625,
|
| 213 |
+
"learning_rate": 0.000998672033969017,
|
| 214 |
+
"loss": 2.7009921264648438,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.025454545454545455,
|
| 219 |
+
"grad_norm": 0.189453125,
|
| 220 |
+
"learning_rate": 0.0009985658458835465,
|
| 221 |
+
"loss": 2.66544677734375,
|
| 222 |
+
"step": 2800
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.026363636363636363,
|
| 226 |
+
"grad_norm": 0.16796875,
|
| 227 |
+
"learning_rate": 0.0009984555800362977,
|
| 228 |
+
"loss": 2.6626568603515626,
|
| 229 |
+
"step": 2900
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.02727272727272727,
|
| 233 |
+
"grad_norm": 0.1689453125,
|
| 234 |
+
"learning_rate": 0.0009983412373291332,
|
| 235 |
+
"loss": 2.708771057128906,
|
| 236 |
+
"step": 3000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.02727272727272727,
|
| 240 |
+
"eval_loss": 3.0887579917907715,
|
| 241 |
+
"eval_runtime": 5.2307,
|
| 242 |
+
"eval_samples_per_second": 114.134,
|
| 243 |
+
"eval_steps_per_second": 28.677,
|
| 244 |
+
"step": 3000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.028181818181818183,
|
| 248 |
+
"grad_norm": 0.169921875,
|
| 249 |
+
"learning_rate": 0.0009982228186972597,
|
| 250 |
+
"loss": 2.6861444091796876,
|
| 251 |
+
"step": 3100
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.02909090909090909,
|
| 255 |
+
"grad_norm": 0.19921875,
|
| 256 |
+
"learning_rate": 0.0009981003251092215,
|
| 257 |
+
"loss": 2.706370544433594,
|
| 258 |
+
"step": 3200
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.03,
|
| 262 |
+
"grad_norm": 0.1708984375,
|
| 263 |
+
"learning_rate": 0.0009979737575668917,
|
| 264 |
+
"loss": 2.6617535400390624,
|
| 265 |
+
"step": 3300
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.03090909090909091,
|
| 269 |
+
"grad_norm": 0.162109375,
|
| 270 |
+
"learning_rate": 0.000997843117105464,
|
| 271 |
+
"loss": 2.673968505859375,
|
| 272 |
+
"step": 3400
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.031818181818181815,
|
| 276 |
+
"grad_norm": 0.1533203125,
|
| 277 |
+
"learning_rate": 0.0009977084047934448,
|
| 278 |
+
"loss": 2.6613540649414062,
|
| 279 |
+
"step": 3500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.03272727272727273,
|
| 283 |
+
"grad_norm": 0.1640625,
|
| 284 |
+
"learning_rate": 0.0009975696217326435,
|
| 285 |
+
"loss": 2.6789846801757813,
|
| 286 |
+
"step": 3600
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.03363636363636364,
|
| 290 |
+
"grad_norm": 0.1787109375,
|
| 291 |
+
"learning_rate": 0.0009974267690581644,
|
| 292 |
+
"loss": 2.664853210449219,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.034545454545454546,
|
| 297 |
+
"grad_norm": 0.1787109375,
|
| 298 |
+
"learning_rate": 0.0009972798479383977,
|
| 299 |
+
"loss": 2.685954284667969,
|
| 300 |
+
"step": 3800
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.035454545454545454,
|
| 304 |
+
"grad_norm": 0.205078125,
|
| 305 |
+
"learning_rate": 0.0009971288595750083,
|
| 306 |
+
"loss": 2.677633056640625,
|
| 307 |
+
"step": 3900
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.03636363636363636,
|
| 311 |
+
"grad_norm": 0.1630859375,
|
| 312 |
+
"learning_rate": 0.0009969738052029277,
|
| 313 |
+
"loss": 2.6985595703125,
|
| 314 |
+
"step": 4000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.03636363636363636,
|
| 318 |
+
"eval_loss": 3.0944459438323975,
|
| 319 |
+
"eval_runtime": 5.3684,
|
| 320 |
+
"eval_samples_per_second": 111.206,
|
| 321 |
+
"eval_steps_per_second": 27.941,
|
| 322 |
+
"step": 4000
|
| 323 |
+
}
|
| 324 |
+
],
|
| 325 |
+
"logging_steps": 100,
|
| 326 |
+
"max_steps": 110000,
|
| 327 |
+
"num_input_tokens_seen": 0,
|
| 328 |
+
"num_train_epochs": 9223372036854775807,
|
| 329 |
+
"save_steps": 4000,
|
| 330 |
+
"stateful_callbacks": {
|
| 331 |
+
"TrainerControl": {
|
| 332 |
+
"args": {
|
| 333 |
+
"should_epoch_stop": false,
|
| 334 |
+
"should_evaluate": false,
|
| 335 |
+
"should_log": false,
|
| 336 |
+
"should_save": true,
|
| 337 |
+
"should_training_stop": false
|
| 338 |
+
},
|
| 339 |
+
"attributes": {}
|
| 340 |
+
}
|
| 341 |
+
},
|
| 342 |
+
"total_flos": 9.9658323984384e+16,
|
| 343 |
+
"train_batch_size": 22,
|
| 344 |
+
"trial_name": null,
|
| 345 |
+
"trial_params": null
|
| 346 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e603921b5fe0b842c30ab2079e7b2171b7aa484c50ff53b17a53468fcd71ca0
|
| 3 |
+
size 5201
|