Upload MacOS Terminal Assistant Model
Browse files- added_tokens.json +6 -0
- checkpoint-500/config.json +30 -0
- checkpoint-500/generation_config.json +7 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +383 -0
- checkpoint-500/training_args.bin +3 -0
- checkpoint-573/config.json +30 -0
- checkpoint-573/generation_config.json +7 -0
- checkpoint-573/model.safetensors +3 -0
- checkpoint-573/optimizer.pt +3 -0
- checkpoint-573/rng_state.pth +3 -0
- checkpoint-573/scheduler.pt +3 -0
- checkpoint-573/trainer_state.json +432 -0
- checkpoint-573/training_args.bin +3 -0
- config.json +30 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</terminal_command>": 32001,
|
| 3 |
+
"</user_input>": 32003,
|
| 4 |
+
"<terminal_command>": 32000,
|
| 5 |
+
"<user_input>": 32002
|
| 6 |
+
}
|
checkpoint-500/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5632,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 22,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.47.1",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 32004
|
| 30 |
+
}
|
checkpoint-500/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.47.1"
|
| 7 |
+
}
|
checkpoint-500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f2dd35e5dc291e0801a3ddb302a757834d18cef23acdce24e6e5f6f84134482
|
| 3 |
+
size 4400282072
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:300a5b01a304a55a51982ceb51ac8880889c01616f8bcf2e3615bd67b92a808c
|
| 3 |
+
size 8800692238
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
|
| 3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6198e44440094fdf1e4f1e63f5beb2d4f797b58de725c899ce67bb318d34ce3a
|
| 3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.6057441253263707,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05221932114882506,
|
| 13 |
+
"grad_norm": 5.394797325134277,
|
| 14 |
+
"learning_rate": 1.9650959860383945e-05,
|
| 15 |
+
"loss": 1.2108,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10443864229765012,
|
| 20 |
+
"grad_norm": 4.011317729949951,
|
| 21 |
+
"learning_rate": 1.930191972076789e-05,
|
| 22 |
+
"loss": 0.9376,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1566579634464752,
|
| 27 |
+
"grad_norm": 3.838289260864258,
|
| 28 |
+
"learning_rate": 1.895287958115183e-05,
|
| 29 |
+
"loss": 0.7876,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.20887728459530025,
|
| 34 |
+
"grad_norm": 4.1263933181762695,
|
| 35 |
+
"learning_rate": 1.8603839441535778e-05,
|
| 36 |
+
"loss": 0.7373,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.26109660574412535,
|
| 41 |
+
"grad_norm": 3.705490827560425,
|
| 42 |
+
"learning_rate": 1.825479930191972e-05,
|
| 43 |
+
"loss": 0.6564,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3133159268929504,
|
| 48 |
+
"grad_norm": 3.4956674575805664,
|
| 49 |
+
"learning_rate": 1.7905759162303668e-05,
|
| 50 |
+
"loss": 0.6102,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.36553524804177545,
|
| 55 |
+
"grad_norm": 3.823296308517456,
|
| 56 |
+
"learning_rate": 1.755671902268761e-05,
|
| 57 |
+
"loss": 0.4846,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4177545691906005,
|
| 62 |
+
"grad_norm": 2.9303112030029297,
|
| 63 |
+
"learning_rate": 1.7207678883071554e-05,
|
| 64 |
+
"loss": 0.447,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4699738903394256,
|
| 69 |
+
"grad_norm": 3.7392730712890625,
|
| 70 |
+
"learning_rate": 1.6858638743455497e-05,
|
| 71 |
+
"loss": 0.3669,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5221932114882507,
|
| 76 |
+
"grad_norm": 3.2671146392822266,
|
| 77 |
+
"learning_rate": 1.6509598603839444e-05,
|
| 78 |
+
"loss": 0.34,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5744125326370757,
|
| 83 |
+
"grad_norm": 3.2053961753845215,
|
| 84 |
+
"learning_rate": 1.6160558464223387e-05,
|
| 85 |
+
"loss": 0.2791,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6266318537859008,
|
| 90 |
+
"grad_norm": 2.1108620166778564,
|
| 91 |
+
"learning_rate": 1.581151832460733e-05,
|
| 92 |
+
"loss": 0.2593,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6788511749347258,
|
| 97 |
+
"grad_norm": 3.154852867126465,
|
| 98 |
+
"learning_rate": 1.5462478184991274e-05,
|
| 99 |
+
"loss": 0.2308,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7310704960835509,
|
| 104 |
+
"grad_norm": 2.451120376586914,
|
| 105 |
+
"learning_rate": 1.511343804537522e-05,
|
| 106 |
+
"loss": 0.2126,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.783289817232376,
|
| 111 |
+
"grad_norm": 3.1815454959869385,
|
| 112 |
+
"learning_rate": 1.4764397905759162e-05,
|
| 113 |
+
"loss": 0.1987,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.835509138381201,
|
| 118 |
+
"grad_norm": 2.3058295249938965,
|
| 119 |
+
"learning_rate": 1.4415357766143108e-05,
|
| 120 |
+
"loss": 0.2129,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8877284595300261,
|
| 125 |
+
"grad_norm": 2.5228800773620605,
|
| 126 |
+
"learning_rate": 1.4066317626527052e-05,
|
| 127 |
+
"loss": 0.2154,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9399477806788512,
|
| 132 |
+
"grad_norm": 3.707547426223755,
|
| 133 |
+
"learning_rate": 1.3717277486910996e-05,
|
| 134 |
+
"loss": 0.1779,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.9921671018276762,
|
| 139 |
+
"grad_norm": 1.675297737121582,
|
| 140 |
+
"learning_rate": 1.336823734729494e-05,
|
| 141 |
+
"loss": 0.1925,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.04177545691906,
|
| 146 |
+
"grad_norm": 2.4128589630126953,
|
| 147 |
+
"learning_rate": 1.3019197207678885e-05,
|
| 148 |
+
"loss": 0.1193,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0939947780678851,
|
| 153 |
+
"grad_norm": 1.474452018737793,
|
| 154 |
+
"learning_rate": 1.2670157068062828e-05,
|
| 155 |
+
"loss": 0.1135,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.1462140992167102,
|
| 160 |
+
"grad_norm": 1.6879887580871582,
|
| 161 |
+
"learning_rate": 1.2321116928446773e-05,
|
| 162 |
+
"loss": 0.1064,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.1984334203655354,
|
| 167 |
+
"grad_norm": 1.3061121702194214,
|
| 168 |
+
"learning_rate": 1.1972076788830716e-05,
|
| 169 |
+
"loss": 0.1125,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.2506527415143602,
|
| 174 |
+
"grad_norm": 1.8820029497146606,
|
| 175 |
+
"learning_rate": 1.162303664921466e-05,
|
| 176 |
+
"loss": 0.1156,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.3028720626631853,
|
| 181 |
+
"grad_norm": 2.1106035709381104,
|
| 182 |
+
"learning_rate": 1.1273996509598604e-05,
|
| 183 |
+
"loss": 0.1112,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.3550913838120104,
|
| 188 |
+
"grad_norm": 1.6610087156295776,
|
| 189 |
+
"learning_rate": 1.0924956369982549e-05,
|
| 190 |
+
"loss": 0.1147,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.4073107049608355,
|
| 195 |
+
"grad_norm": 1.0979489088058472,
|
| 196 |
+
"learning_rate": 1.0575916230366492e-05,
|
| 197 |
+
"loss": 0.0959,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.4595300261096606,
|
| 202 |
+
"grad_norm": 1.7349355220794678,
|
| 203 |
+
"learning_rate": 1.0226876090750437e-05,
|
| 204 |
+
"loss": 0.0959,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.5117493472584855,
|
| 209 |
+
"grad_norm": 1.3557089567184448,
|
| 210 |
+
"learning_rate": 9.877835951134382e-06,
|
| 211 |
+
"loss": 0.0961,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.5639686684073109,
|
| 216 |
+
"grad_norm": 2.409390687942505,
|
| 217 |
+
"learning_rate": 9.528795811518325e-06,
|
| 218 |
+
"loss": 0.1122,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.6161879895561357,
|
| 223 |
+
"grad_norm": 2.6092705726623535,
|
| 224 |
+
"learning_rate": 9.17975567190227e-06,
|
| 225 |
+
"loss": 0.1012,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.6684073107049608,
|
| 230 |
+
"grad_norm": 0.9906852841377258,
|
| 231 |
+
"learning_rate": 8.830715532286213e-06,
|
| 232 |
+
"loss": 0.0949,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.720626631853786,
|
| 237 |
+
"grad_norm": 1.7950801849365234,
|
| 238 |
+
"learning_rate": 8.481675392670158e-06,
|
| 239 |
+
"loss": 0.108,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.7728459530026108,
|
| 244 |
+
"grad_norm": 5.53033971786499,
|
| 245 |
+
"learning_rate": 8.132635253054101e-06,
|
| 246 |
+
"loss": 0.0999,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.8250652741514362,
|
| 251 |
+
"grad_norm": 1.3689807653427124,
|
| 252 |
+
"learning_rate": 7.783595113438046e-06,
|
| 253 |
+
"loss": 0.0848,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.877284595300261,
|
| 258 |
+
"grad_norm": 0.9605047702789307,
|
| 259 |
+
"learning_rate": 7.43455497382199e-06,
|
| 260 |
+
"loss": 0.0889,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.9295039164490861,
|
| 265 |
+
"grad_norm": 2.4679007530212402,
|
| 266 |
+
"learning_rate": 7.0855148342059345e-06,
|
| 267 |
+
"loss": 0.0942,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.9817232375979112,
|
| 272 |
+
"grad_norm": 1.0207858085632324,
|
| 273 |
+
"learning_rate": 6.7364746945898785e-06,
|
| 274 |
+
"loss": 0.0897,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.031331592689295,
|
| 279 |
+
"grad_norm": 0.7235077023506165,
|
| 280 |
+
"learning_rate": 6.3874345549738226e-06,
|
| 281 |
+
"loss": 0.0767,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.08355091383812,
|
| 286 |
+
"grad_norm": 1.5406379699707031,
|
| 287 |
+
"learning_rate": 6.038394415357767e-06,
|
| 288 |
+
"loss": 0.064,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.1357702349869454,
|
| 293 |
+
"grad_norm": 1.5837807655334473,
|
| 294 |
+
"learning_rate": 5.689354275741711e-06,
|
| 295 |
+
"loss": 0.0624,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.1879895561357703,
|
| 300 |
+
"grad_norm": 0.8071414828300476,
|
| 301 |
+
"learning_rate": 5.340314136125655e-06,
|
| 302 |
+
"loss": 0.0618,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.240208877284595,
|
| 307 |
+
"grad_norm": 1.0322142839431763,
|
| 308 |
+
"learning_rate": 4.991273996509599e-06,
|
| 309 |
+
"loss": 0.0626,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.2924281984334205,
|
| 314 |
+
"grad_norm": 0.9583885073661804,
|
| 315 |
+
"learning_rate": 4.642233856893543e-06,
|
| 316 |
+
"loss": 0.0588,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.3446475195822454,
|
| 321 |
+
"grad_norm": 1.3839960098266602,
|
| 322 |
+
"learning_rate": 4.293193717277487e-06,
|
| 323 |
+
"loss": 0.0609,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.3968668407310707,
|
| 328 |
+
"grad_norm": 1.018333911895752,
|
| 329 |
+
"learning_rate": 3.944153577661432e-06,
|
| 330 |
+
"loss": 0.0627,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.4490861618798956,
|
| 335 |
+
"grad_norm": 0.6483064889907837,
|
| 336 |
+
"learning_rate": 3.5951134380453755e-06,
|
| 337 |
+
"loss": 0.0635,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.5013054830287205,
|
| 342 |
+
"grad_norm": 1.3443909883499146,
|
| 343 |
+
"learning_rate": 3.2460732984293196e-06,
|
| 344 |
+
"loss": 0.0599,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.553524804177546,
|
| 349 |
+
"grad_norm": 0.8122425675392151,
|
| 350 |
+
"learning_rate": 2.897033158813264e-06,
|
| 351 |
+
"loss": 0.0606,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.6057441253263707,
|
| 356 |
+
"grad_norm": 0.841248631477356,
|
| 357 |
+
"learning_rate": 2.547993019197208e-06,
|
| 358 |
+
"loss": 0.0583,
|
| 359 |
+
"step": 500
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 10,
|
| 363 |
+
"max_steps": 573,
|
| 364 |
+
"num_input_tokens_seen": 0,
|
| 365 |
+
"num_train_epochs": 3,
|
| 366 |
+
"save_steps": 500,
|
| 367 |
+
"stateful_callbacks": {
|
| 368 |
+
"TrainerControl": {
|
| 369 |
+
"args": {
|
| 370 |
+
"should_epoch_stop": false,
|
| 371 |
+
"should_evaluate": false,
|
| 372 |
+
"should_log": false,
|
| 373 |
+
"should_save": true,
|
| 374 |
+
"should_training_stop": false
|
| 375 |
+
},
|
| 376 |
+
"attributes": {}
|
| 377 |
+
}
|
| 378 |
+
},
|
| 379 |
+
"total_flos": 1.2686764460212224e+16,
|
| 380 |
+
"train_batch_size": 2,
|
| 381 |
+
"trial_name": null,
|
| 382 |
+
"trial_params": null
|
| 383 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbbef71d3b925143ec349b161b942747741b3b33f420196cc047b0e6e77360f7
|
| 3 |
+
size 5240
|
checkpoint-573/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5632,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 22,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.47.1",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 32004
|
| 30 |
+
}
|
checkpoint-573/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.47.1"
|
| 7 |
+
}
|
checkpoint-573/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31bb1ecc419fc7939271d0c47cce77c9a2b74cfc73f1c3dbc15fda9ea16f31ee
|
| 3 |
+
size 4400282072
|
checkpoint-573/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26ec5baf1336523b08eb93a88a0e1150cd3c69ceaf0591b7200afbcc1836095a
|
| 3 |
+
size 8800692238
|
checkpoint-573/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf9097d4513154245c48236b6ec5137b7ee2a21c9f58f2cba798ea275c6026f
|
| 3 |
+
size 14244
|
checkpoint-573/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:306e6ecf5d1b9604a8c5379ba25452e630f5259d81eb7857fcf240061f89a9fc
|
| 3 |
+
size 1064
|
checkpoint-573/trainer_state.json
ADDED
|
@@ -0,0 +1,432 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9869451697127936,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 573,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05221932114882506,
|
| 13 |
+
"grad_norm": 5.394797325134277,
|
| 14 |
+
"learning_rate": 1.9650959860383945e-05,
|
| 15 |
+
"loss": 1.2108,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10443864229765012,
|
| 20 |
+
"grad_norm": 4.011317729949951,
|
| 21 |
+
"learning_rate": 1.930191972076789e-05,
|
| 22 |
+
"loss": 0.9376,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1566579634464752,
|
| 27 |
+
"grad_norm": 3.838289260864258,
|
| 28 |
+
"learning_rate": 1.895287958115183e-05,
|
| 29 |
+
"loss": 0.7876,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.20887728459530025,
|
| 34 |
+
"grad_norm": 4.1263933181762695,
|
| 35 |
+
"learning_rate": 1.8603839441535778e-05,
|
| 36 |
+
"loss": 0.7373,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.26109660574412535,
|
| 41 |
+
"grad_norm": 3.705490827560425,
|
| 42 |
+
"learning_rate": 1.825479930191972e-05,
|
| 43 |
+
"loss": 0.6564,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3133159268929504,
|
| 48 |
+
"grad_norm": 3.4956674575805664,
|
| 49 |
+
"learning_rate": 1.7905759162303668e-05,
|
| 50 |
+
"loss": 0.6102,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.36553524804177545,
|
| 55 |
+
"grad_norm": 3.823296308517456,
|
| 56 |
+
"learning_rate": 1.755671902268761e-05,
|
| 57 |
+
"loss": 0.4846,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4177545691906005,
|
| 62 |
+
"grad_norm": 2.9303112030029297,
|
| 63 |
+
"learning_rate": 1.7207678883071554e-05,
|
| 64 |
+
"loss": 0.447,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4699738903394256,
|
| 69 |
+
"grad_norm": 3.7392730712890625,
|
| 70 |
+
"learning_rate": 1.6858638743455497e-05,
|
| 71 |
+
"loss": 0.3669,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5221932114882507,
|
| 76 |
+
"grad_norm": 3.2671146392822266,
|
| 77 |
+
"learning_rate": 1.6509598603839444e-05,
|
| 78 |
+
"loss": 0.34,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5744125326370757,
|
| 83 |
+
"grad_norm": 3.2053961753845215,
|
| 84 |
+
"learning_rate": 1.6160558464223387e-05,
|
| 85 |
+
"loss": 0.2791,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6266318537859008,
|
| 90 |
+
"grad_norm": 2.1108620166778564,
|
| 91 |
+
"learning_rate": 1.581151832460733e-05,
|
| 92 |
+
"loss": 0.2593,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.6788511749347258,
|
| 97 |
+
"grad_norm": 3.154852867126465,
|
| 98 |
+
"learning_rate": 1.5462478184991274e-05,
|
| 99 |
+
"loss": 0.2308,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7310704960835509,
|
| 104 |
+
"grad_norm": 2.451120376586914,
|
| 105 |
+
"learning_rate": 1.511343804537522e-05,
|
| 106 |
+
"loss": 0.2126,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.783289817232376,
|
| 111 |
+
"grad_norm": 3.1815454959869385,
|
| 112 |
+
"learning_rate": 1.4764397905759162e-05,
|
| 113 |
+
"loss": 0.1987,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.835509138381201,
|
| 118 |
+
"grad_norm": 2.3058295249938965,
|
| 119 |
+
"learning_rate": 1.4415357766143108e-05,
|
| 120 |
+
"loss": 0.2129,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.8877284595300261,
|
| 125 |
+
"grad_norm": 2.5228800773620605,
|
| 126 |
+
"learning_rate": 1.4066317626527052e-05,
|
| 127 |
+
"loss": 0.2154,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9399477806788512,
|
| 132 |
+
"grad_norm": 3.707547426223755,
|
| 133 |
+
"learning_rate": 1.3717277486910996e-05,
|
| 134 |
+
"loss": 0.1779,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.9921671018276762,
|
| 139 |
+
"grad_norm": 1.675297737121582,
|
| 140 |
+
"learning_rate": 1.336823734729494e-05,
|
| 141 |
+
"loss": 0.1925,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.04177545691906,
|
| 146 |
+
"grad_norm": 2.4128589630126953,
|
| 147 |
+
"learning_rate": 1.3019197207678885e-05,
|
| 148 |
+
"loss": 0.1193,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0939947780678851,
|
| 153 |
+
"grad_norm": 1.474452018737793,
|
| 154 |
+
"learning_rate": 1.2670157068062828e-05,
|
| 155 |
+
"loss": 0.1135,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.1462140992167102,
|
| 160 |
+
"grad_norm": 1.6879887580871582,
|
| 161 |
+
"learning_rate": 1.2321116928446773e-05,
|
| 162 |
+
"loss": 0.1064,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.1984334203655354,
|
| 167 |
+
"grad_norm": 1.3061121702194214,
|
| 168 |
+
"learning_rate": 1.1972076788830716e-05,
|
| 169 |
+
"loss": 0.1125,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.2506527415143602,
|
| 174 |
+
"grad_norm": 1.8820029497146606,
|
| 175 |
+
"learning_rate": 1.162303664921466e-05,
|
| 176 |
+
"loss": 0.1156,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.3028720626631853,
|
| 181 |
+
"grad_norm": 2.1106035709381104,
|
| 182 |
+
"learning_rate": 1.1273996509598604e-05,
|
| 183 |
+
"loss": 0.1112,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.3550913838120104,
|
| 188 |
+
"grad_norm": 1.6610087156295776,
|
| 189 |
+
"learning_rate": 1.0924956369982549e-05,
|
| 190 |
+
"loss": 0.1147,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.4073107049608355,
|
| 195 |
+
"grad_norm": 1.0979489088058472,
|
| 196 |
+
"learning_rate": 1.0575916230366492e-05,
|
| 197 |
+
"loss": 0.0959,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.4595300261096606,
|
| 202 |
+
"grad_norm": 1.7349355220794678,
|
| 203 |
+
"learning_rate": 1.0226876090750437e-05,
|
| 204 |
+
"loss": 0.0959,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.5117493472584855,
|
| 209 |
+
"grad_norm": 1.3557089567184448,
|
| 210 |
+
"learning_rate": 9.877835951134382e-06,
|
| 211 |
+
"loss": 0.0961,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.5639686684073109,
|
| 216 |
+
"grad_norm": 2.409390687942505,
|
| 217 |
+
"learning_rate": 9.528795811518325e-06,
|
| 218 |
+
"loss": 0.1122,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.6161879895561357,
|
| 223 |
+
"grad_norm": 2.6092705726623535,
|
| 224 |
+
"learning_rate": 9.17975567190227e-06,
|
| 225 |
+
"loss": 0.1012,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.6684073107049608,
|
| 230 |
+
"grad_norm": 0.9906852841377258,
|
| 231 |
+
"learning_rate": 8.830715532286213e-06,
|
| 232 |
+
"loss": 0.0949,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.720626631853786,
|
| 237 |
+
"grad_norm": 1.7950801849365234,
|
| 238 |
+
"learning_rate": 8.481675392670158e-06,
|
| 239 |
+
"loss": 0.108,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.7728459530026108,
|
| 244 |
+
"grad_norm": 5.53033971786499,
|
| 245 |
+
"learning_rate": 8.132635253054101e-06,
|
| 246 |
+
"loss": 0.0999,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.8250652741514362,
|
| 251 |
+
"grad_norm": 1.3689807653427124,
|
| 252 |
+
"learning_rate": 7.783595113438046e-06,
|
| 253 |
+
"loss": 0.0848,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.877284595300261,
|
| 258 |
+
"grad_norm": 0.9605047702789307,
|
| 259 |
+
"learning_rate": 7.43455497382199e-06,
|
| 260 |
+
"loss": 0.0889,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.9295039164490861,
|
| 265 |
+
"grad_norm": 2.4679007530212402,
|
| 266 |
+
"learning_rate": 7.0855148342059345e-06,
|
| 267 |
+
"loss": 0.0942,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.9817232375979112,
|
| 272 |
+
"grad_norm": 1.0207858085632324,
|
| 273 |
+
"learning_rate": 6.7364746945898785e-06,
|
| 274 |
+
"loss": 0.0897,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.031331592689295,
|
| 279 |
+
"grad_norm": 0.7235077023506165,
|
| 280 |
+
"learning_rate": 6.3874345549738226e-06,
|
| 281 |
+
"loss": 0.0767,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.08355091383812,
|
| 286 |
+
"grad_norm": 1.5406379699707031,
|
| 287 |
+
"learning_rate": 6.038394415357767e-06,
|
| 288 |
+
"loss": 0.064,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.1357702349869454,
|
| 293 |
+
"grad_norm": 1.5837807655334473,
|
| 294 |
+
"learning_rate": 5.689354275741711e-06,
|
| 295 |
+
"loss": 0.0624,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.1879895561357703,
|
| 300 |
+
"grad_norm": 0.8071414828300476,
|
| 301 |
+
"learning_rate": 5.340314136125655e-06,
|
| 302 |
+
"loss": 0.0618,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.240208877284595,
|
| 307 |
+
"grad_norm": 1.0322142839431763,
|
| 308 |
+
"learning_rate": 4.991273996509599e-06,
|
| 309 |
+
"loss": 0.0626,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.2924281984334205,
|
| 314 |
+
"grad_norm": 0.9583885073661804,
|
| 315 |
+
"learning_rate": 4.642233856893543e-06,
|
| 316 |
+
"loss": 0.0588,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.3446475195822454,
|
| 321 |
+
"grad_norm": 1.3839960098266602,
|
| 322 |
+
"learning_rate": 4.293193717277487e-06,
|
| 323 |
+
"loss": 0.0609,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.3968668407310707,
|
| 328 |
+
"grad_norm": 1.018333911895752,
|
| 329 |
+
"learning_rate": 3.944153577661432e-06,
|
| 330 |
+
"loss": 0.0627,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.4490861618798956,
|
| 335 |
+
"grad_norm": 0.6483064889907837,
|
| 336 |
+
"learning_rate": 3.5951134380453755e-06,
|
| 337 |
+
"loss": 0.0635,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.5013054830287205,
|
| 342 |
+
"grad_norm": 1.3443909883499146,
|
| 343 |
+
"learning_rate": 3.2460732984293196e-06,
|
| 344 |
+
"loss": 0.0599,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.553524804177546,
|
| 349 |
+
"grad_norm": 0.8122425675392151,
|
| 350 |
+
"learning_rate": 2.897033158813264e-06,
|
| 351 |
+
"loss": 0.0606,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.6057441253263707,
|
| 356 |
+
"grad_norm": 0.841248631477356,
|
| 357 |
+
"learning_rate": 2.547993019197208e-06,
|
| 358 |
+
"loss": 0.0583,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.657963446475196,
|
| 363 |
+
"grad_norm": 0.8031327128410339,
|
| 364 |
+
"learning_rate": 2.198952879581152e-06,
|
| 365 |
+
"loss": 0.0601,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.710182767624021,
|
| 370 |
+
"grad_norm": 0.9310224056243896,
|
| 371 |
+
"learning_rate": 1.8499127399650962e-06,
|
| 372 |
+
"loss": 0.0605,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.7624020887728458,
|
| 377 |
+
"grad_norm": 0.9988183379173279,
|
| 378 |
+
"learning_rate": 1.5008726003490403e-06,
|
| 379 |
+
"loss": 0.0607,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.814621409921671,
|
| 384 |
+
"grad_norm": 0.6764442920684814,
|
| 385 |
+
"learning_rate": 1.1518324607329843e-06,
|
| 386 |
+
"loss": 0.0577,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.866840731070496,
|
| 391 |
+
"grad_norm": 0.7667761445045471,
|
| 392 |
+
"learning_rate": 8.027923211169285e-07,
|
| 393 |
+
"loss": 0.0605,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.9190600522193213,
|
| 398 |
+
"grad_norm": 1.5497705936431885,
|
| 399 |
+
"learning_rate": 4.537521815008726e-07,
|
| 400 |
+
"loss": 0.059,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.971279373368146,
|
| 405 |
+
"grad_norm": 0.8243622779846191,
|
| 406 |
+
"learning_rate": 1.0471204188481677e-07,
|
| 407 |
+
"loss": 0.055,
|
| 408 |
+
"step": 570
|
| 409 |
+
}
|
| 410 |
+
],
|
| 411 |
+
"logging_steps": 10,
|
| 412 |
+
"max_steps": 573,
|
| 413 |
+
"num_input_tokens_seen": 0,
|
| 414 |
+
"num_train_epochs": 3,
|
| 415 |
+
"save_steps": 500,
|
| 416 |
+
"stateful_callbacks": {
|
| 417 |
+
"TrainerControl": {
|
| 418 |
+
"args": {
|
| 419 |
+
"should_epoch_stop": false,
|
| 420 |
+
"should_evaluate": false,
|
| 421 |
+
"should_log": false,
|
| 422 |
+
"should_save": true,
|
| 423 |
+
"should_training_stop": true
|
| 424 |
+
},
|
| 425 |
+
"attributes": {}
|
| 426 |
+
}
|
| 427 |
+
},
|
| 428 |
+
"total_flos": 1.4542744030543872e+16,
|
| 429 |
+
"train_batch_size": 2,
|
| 430 |
+
"trial_name": null,
|
| 431 |
+
"trial_params": null
|
| 432 |
+
}
|
checkpoint-573/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbbef71d3b925143ec349b161b942747741b3b33f420196cc047b0e6e77360f7
|
| 3 |
+
size 5240
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5632,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 22,
|
| 20 |
+
"num_key_value_heads": 4,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.47.1",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 32000
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.47.1"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9dc1c1a8c6b29e153dea7aaf2ed6c4d242163489add0e7c14c23889745437be4
|
| 3 |
+
size 4400216536
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"extra_special_tokens": {},
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": null,
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 41 |
+
"unk_token": "<unk>",
|
| 42 |
+
"use_default_system_prompt": false
|
| 43 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbbef71d3b925143ec349b161b942747741b3b33f420196cc047b0e6e77360f7
|
| 3 |
+
size 5240
|