Training in progress, step 10
Browse files- config.json +74 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- runs/Oct07_10-54-21_5dc35bd65435/events.out.tfevents.1759834469.5dc35bd65435.21425.0 +3 -0
- runs/Oct07_11-03-20_5dc35bd65435/events.out.tfevents.1759835008.5dc35bd65435.23843.0 +3 -0
- runs/Oct07_11-10-03_5dc35bd65435/events.out.tfevents.1759835410.5dc35bd65435.25554.0 +3 -0
- runs/Oct07_11-14-10_5dc35bd65435/events.out.tfevents.1759835658.5dc35bd65435.26771.0 +3 -0
- runs/Oct07_11-21-35_5dc35bd65435/events.out.tfevents.1759836103.5dc35bd65435.28770.0 +3 -0
- runs/Oct07_11-35-15_5dc35bd65435/events.out.tfevents.1759836923.5dc35bd65435.32181.0 +3 -0
- runs/Oct07_11-42-44_5dc35bd65435/events.out.tfevents.1759837372.5dc35bd65435.34232.0 +3 -0
- runs/Oct07_11-49-19_5dc35bd65435/events.out.tfevents.1759837768.5dc35bd65435.35924.0 +3 -0
- runs/Oct07_12-02-21_5dc35bd65435/events.out.tfevents.1759838552.5dc35bd65435.39594.0 +3 -0
- runs/Oct07_12-08-20_5dc35bd65435/events.out.tfevents.1759838908.5dc35bd65435.41221.0 +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"DeepseekV3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoConfig": "configuration_deepseek.DeepseekV3Config",
|
| 9 |
+
"AutoModel": "modeling_deepseek.DeepseekV3Model",
|
| 10 |
+
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
|
| 11 |
+
},
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
+
"dtype": "bfloat16",
|
| 14 |
+
"eos_token_id": 1,
|
| 15 |
+
"ep_size": 1,
|
| 16 |
+
"first_k_dense_replace": 2,
|
| 17 |
+
"head_dim": 64,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 1012,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 4056,
|
| 22 |
+
"kv_lora_rank": 64,
|
| 23 |
+
"max_position_embeddings": 2048,
|
| 24 |
+
"model_type": "deepseek_v3",
|
| 25 |
+
"moe_intermediate_size": 2048,
|
| 26 |
+
"moe_layer_freq": 1,
|
| 27 |
+
"n_group": 8,
|
| 28 |
+
"n_routed_experts": 16,
|
| 29 |
+
"n_shared_experts": 1,
|
| 30 |
+
"norm_topk_prob": true,
|
| 31 |
+
"num_attention_heads": 16,
|
| 32 |
+
"num_experts_per_tok": 2,
|
| 33 |
+
"num_hidden_layers": 20,
|
| 34 |
+
"num_key_value_heads": 16,
|
| 35 |
+
"num_nextn_predict_layers": 1,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"pretraining_tp": 1,
|
| 38 |
+
"q_lora_rank": 128,
|
| 39 |
+
"qk_head_dim": 192,
|
| 40 |
+
"qk_nope_head_dim": 128,
|
| 41 |
+
"qk_rope_head_dim": 64,
|
| 42 |
+
"quantization_config": {
|
| 43 |
+
"activation_scheme": "dynamic",
|
| 44 |
+
"fmt": "e4m3",
|
| 45 |
+
"quant_method": "fp8",
|
| 46 |
+
"scale_fmt": "ue8m0",
|
| 47 |
+
"weight_block_size": [
|
| 48 |
+
128,
|
| 49 |
+
128
|
| 50 |
+
]
|
| 51 |
+
},
|
| 52 |
+
"rms_norm_eps": 1e-06,
|
| 53 |
+
"rope_interleave": true,
|
| 54 |
+
"rope_scaling": {
|
| 55 |
+
"beta_fast": 32.0,
|
| 56 |
+
"beta_slow": 1.0,
|
| 57 |
+
"factor": 40.0,
|
| 58 |
+
"mscale": 1.0,
|
| 59 |
+
"mscale_all_dim": 1.0,
|
| 60 |
+
"original_max_position_embeddings": 4096,
|
| 61 |
+
"rope_type": "yarn",
|
| 62 |
+
"type": "yarn"
|
| 63 |
+
},
|
| 64 |
+
"rope_theta": 10000,
|
| 65 |
+
"routed_scaling_factor": 2.5,
|
| 66 |
+
"scoring_func": "sigmoid",
|
| 67 |
+
"tie_word_embeddings": false,
|
| 68 |
+
"topk_group": 1,
|
| 69 |
+
"topk_method": "noaux_tc",
|
| 70 |
+
"transformers_version": "4.57.0.dev0",
|
| 71 |
+
"use_cache": false,
|
| 72 |
+
"v_head_dim": 16,
|
| 73 |
+
"vocab_size": 64000
|
| 74 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.57.0.dev0",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c926480da0d9471c7b339a0ecd629e0fdd763b453e0ce511bbd2fa82eb53f8a3
|
| 3 |
+
size 4156744752
|
runs/Oct07_10-54-21_5dc35bd65435/events.out.tfevents.1759834469.5dc35bd65435.21425.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2305f575abe3e490fe283bcac1845735cbac0b13ca06e0dcfded4ef5ace71d
|
| 3 |
+
size 5927
|
runs/Oct07_11-03-20_5dc35bd65435/events.out.tfevents.1759835008.5dc35bd65435.23843.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d19805628b56cd38d519ad3d64d9a136fa0b4805aa3ca16f6aca4ca1e84b9ff
|
| 3 |
+
size 6134
|
runs/Oct07_11-10-03_5dc35bd65435/events.out.tfevents.1759835410.5dc35bd65435.25554.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18adda3adef7b518d45e5fc20f0eea2025cdc845750b94128af05cb3a9e200ac
|
| 3 |
+
size 4184
|
runs/Oct07_11-14-10_5dc35bd65435/events.out.tfevents.1759835658.5dc35bd65435.26771.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bc6f221129895774aa2979fb4603ef58c18a500ffcec1b828712e82e66cf40e
|
| 3 |
+
size 6134
|
runs/Oct07_11-21-35_5dc35bd65435/events.out.tfevents.1759836103.5dc35bd65435.28770.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df83174a1d336b08936babb4cc757f3463f9ba42fb8b5db03ba7c64a4d59bcdc
|
| 3 |
+
size 6134
|
runs/Oct07_11-35-15_5dc35bd65435/events.out.tfevents.1759836923.5dc35bd65435.32181.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62fc8a9d53a1bfb05f3f33cd51299a8516c00fc30b4af47f2f2b6883b20220d8
|
| 3 |
+
size 6133
|
runs/Oct07_11-42-44_5dc35bd65435/events.out.tfevents.1759837372.5dc35bd65435.34232.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:138b0158abeaa3436286eb295efb2586e63fb7ee48cc174f866438f2cd023c29
|
| 3 |
+
size 6133
|
runs/Oct07_11-49-19_5dc35bd65435/events.out.tfevents.1759837768.5dc35bd65435.35924.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d041d021f517d7d052aa51eda2409214c2b652531d08e435c22c5c631236547
|
| 3 |
+
size 6133
|
runs/Oct07_12-02-21_5dc35bd65435/events.out.tfevents.1759838552.5dc35bd65435.39594.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2119f4f140d9c19d65f147d28285c658c716c6fd12f8cc07c8a8412e1d6253d9
|
| 3 |
+
size 5927
|
runs/Oct07_12-08-20_5dc35bd65435/events.out.tfevents.1759838908.5dc35bd65435.41221.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af30947ddcbaf31f0e5cf7aac280113c94a8bdc08feca99a75b4f4047f468acc
|
| 3 |
+
size 7997
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb08b65ddf8cfe9535a7296485be97b38a5d3726d26656631c74af48caeb158c
|
| 3 |
+
size 5649
|