初始化项目，由ModelHub XC社区提供模型
Model: ericflo/Llama-3.1-8B-ContinuedTraining2-FFT Source: Original Platform
This commit is contained in:
ModelHub XC
35
checkpoint-100/config.json
Normal file
35
checkpoint-100/config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.44.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
9
checkpoint-100/generation_config.json
Normal file
9
checkpoint-100/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128001,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.44.2"
|
||||
}
|
||||
3
checkpoint-100/model-00001-of-00004.safetensors
Normal file
3
checkpoint-100/model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9f21285e9ba9b9b406f519f94ea0cd4d6447ffe06697fd555e640819483c5a6a
|
||||
size 4976698672
|
||||
3
checkpoint-100/model-00002-of-00004.safetensors
Normal file
3
checkpoint-100/model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:50905d52d17d83af0fb625c73afa64374c00992dcb0c5beaaa1fdf434637c25e
|
||||
size 4999802720
|
||||
3
checkpoint-100/model-00003-of-00004.safetensors
Normal file
3
checkpoint-100/model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:df2aee9dd8ddc925806d277a9ea6cd4674034f5dae9efe39747a32c2b9d7d15e
|
||||
size 4915916176
|
||||
3
checkpoint-100/model-00004-of-00004.safetensors
Normal file
3
checkpoint-100/model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:73dc8f83bd7c057cdd7fbff9d4c286d946cc250a7712608db22edda99f830827
|
||||
size 1168138808
|
||||
298
checkpoint-100/model.safetensors.index.json
Normal file
298
checkpoint-100/model.safetensors.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060522496
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
3
checkpoint-100/optimizer.pt
Normal file
3
checkpoint-100/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1e9042e67f1ef528141f4490e19b6e2fdf5b28198607530dccf9e8389e0e4179
|
||||
size 16092242760
|
||||
3
checkpoint-100/rng_state.pth
Normal file
3
checkpoint-100/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b258fab836746c851c9aecd3cb07de7b2180f764093531e44d01a68237843e91
|
||||
size 14180
|
||||
3
checkpoint-100/scheduler.pt
Normal file
3
checkpoint-100/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3f848b50e00d9d3d28b1b0722936422d53aabca64041474b5151a32afb758ef5
|
||||
size 1064
|
||||
17
checkpoint-100/special_tokens_map.json
Normal file
17
checkpoint-100/special_tokens_map.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|end_of_text|>"
|
||||
}
|
||||
410563
checkpoint-100/tokenizer.json
Normal file
410563
checkpoint-100/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2062
checkpoint-100/tokenizer_config.json
Normal file
2062
checkpoint-100/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
733
checkpoint-100/trainer_state.json
Normal file
733
checkpoint-100/trainer_state.json
Normal file
@@ -0,0 +1,733 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.001,
|
||||
"eval_steps": 500,
|
||||
"global_step": 100,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 1e-05,
|
||||
"grad_norm": 8.875,
|
||||
"learning_rate": 9.999999997532599e-06,
|
||||
"loss": 1.6459,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 2e-05,
|
||||
"grad_norm": 4.40625,
|
||||
"learning_rate": 9.999999990130395e-06,
|
||||
"loss": 1.6742,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 3e-05,
|
||||
"grad_norm": 4.3125,
|
||||
"learning_rate": 9.99999997779339e-06,
|
||||
"loss": 1.6223,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 4e-05,
|
||||
"grad_norm": 4.0625,
|
||||
"learning_rate": 9.999999960521582e-06,
|
||||
"loss": 1.5398,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"epoch": 5e-05,
|
||||
"grad_norm": 3.375,
|
||||
"learning_rate": 9.999999938314972e-06,
|
||||
"loss": 1.5666,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 6e-05,
|
||||
"grad_norm": 1.859375,
|
||||
"learning_rate": 9.999999911173561e-06,
|
||||
"loss": 1.5981,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 7e-05,
|
||||
"grad_norm": 1.734375,
|
||||
"learning_rate": 9.999999879097347e-06,
|
||||
"loss": 1.644,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 8e-05,
|
||||
"grad_norm": 1.796875,
|
||||
"learning_rate": 9.999999842086332e-06,
|
||||
"loss": 1.6331,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"epoch": 9e-05,
|
||||
"grad_norm": 1.3125,
|
||||
"learning_rate": 9.999999800140514e-06,
|
||||
"loss": 1.626,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 0.0001,
|
||||
"grad_norm": 1.9296875,
|
||||
"learning_rate": 9.999999753259893e-06,
|
||||
"loss": 1.5778,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.00011,
|
||||
"grad_norm": 1.34375,
|
||||
"learning_rate": 9.99999970144447e-06,
|
||||
"loss": 1.6286,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 0.00012,
|
||||
"grad_norm": 1.203125,
|
||||
"learning_rate": 9.999999644694247e-06,
|
||||
"loss": 1.5614,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"epoch": 0.00013,
|
||||
"grad_norm": 1.015625,
|
||||
"learning_rate": 9.999999583009221e-06,
|
||||
"loss": 1.6447,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 0.00014,
|
||||
"grad_norm": 1.3359375,
|
||||
"learning_rate": 9.999999516389394e-06,
|
||||
"loss": 1.5258,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 0.00015,
|
||||
"grad_norm": 1.25,
|
||||
"learning_rate": 9.999999444834763e-06,
|
||||
"loss": 1.6336,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.00016,
|
||||
"grad_norm": 1.5546875,
|
||||
"learning_rate": 9.999999368345333e-06,
|
||||
"loss": 1.6073,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"epoch": 0.00017,
|
||||
"grad_norm": 1.34375,
|
||||
"learning_rate": 9.999999286921101e-06,
|
||||
"loss": 1.5919,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 0.00018,
|
||||
"grad_norm": 0.96875,
|
||||
"learning_rate": 9.999999200562065e-06,
|
||||
"loss": 1.543,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 0.00019,
|
||||
"grad_norm": 1.6875,
|
||||
"learning_rate": 9.99999910926823e-06,
|
||||
"loss": 1.6101,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 0.0002,
|
||||
"grad_norm": 1.578125,
|
||||
"learning_rate": 9.999999013039593e-06,
|
||||
"loss": 1.5796,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.00021,
|
||||
"grad_norm": 2.578125,
|
||||
"learning_rate": 9.999998911876154e-06,
|
||||
"loss": 1.5748,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 0.00022,
|
||||
"grad_norm": 1.203125,
|
||||
"learning_rate": 9.999998805777915e-06,
|
||||
"loss": 1.5479,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 0.00023,
|
||||
"grad_norm": 1.4921875,
|
||||
"learning_rate": 9.999998694744875e-06,
|
||||
"loss": 1.5318,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 0.00024,
|
||||
"grad_norm": 1.125,
|
||||
"learning_rate": 9.999998578777036e-06,
|
||||
"loss": 1.6259,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"epoch": 0.00025,
|
||||
"grad_norm": 2.21875,
|
||||
"learning_rate": 9.999998457874392e-06,
|
||||
"loss": 1.5525,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.00026,
|
||||
"grad_norm": 3.234375,
|
||||
"learning_rate": 9.99999833203695e-06,
|
||||
"loss": 1.5576,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 0.00027,
|
||||
"grad_norm": 2.046875,
|
||||
"learning_rate": 9.999998201264707e-06,
|
||||
"loss": 1.3934,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 0.00028,
|
||||
"grad_norm": 3.15625,
|
||||
"learning_rate": 9.999998065557664e-06,
|
||||
"loss": 1.5423,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"epoch": 0.00029,
|
||||
"grad_norm": 1.2734375,
|
||||
"learning_rate": 9.999997924915818e-06,
|
||||
"loss": 1.5679,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 0.0003,
|
||||
"grad_norm": 1.625,
|
||||
"learning_rate": 9.999997779339175e-06,
|
||||
"loss": 1.5329,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.00031,
|
||||
"grad_norm": 1.2421875,
|
||||
"learning_rate": 9.999997628827732e-06,
|
||||
"loss": 1.4603,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 0.00032,
|
||||
"grad_norm": 1.46875,
|
||||
"learning_rate": 9.999997473381487e-06,
|
||||
"loss": 1.5774,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"epoch": 0.00033,
|
||||
"grad_norm": 2.0625,
|
||||
"learning_rate": 9.999997313000444e-06,
|
||||
"loss": 1.5522,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 0.00034,
|
||||
"grad_norm": 1.421875,
|
||||
"learning_rate": 9.9999971476846e-06,
|
||||
"loss": 1.5964,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 0.00035,
|
||||
"grad_norm": 1.59375,
|
||||
"learning_rate": 9.999996977433957e-06,
|
||||
"loss": 1.6129,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.00036,
|
||||
"grad_norm": 1.78125,
|
||||
"learning_rate": 9.999996802248514e-06,
|
||||
"loss": 1.548,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"epoch": 0.00037,
|
||||
"grad_norm": 0.94140625,
|
||||
"learning_rate": 9.999996622128274e-06,
|
||||
"loss": 1.5662,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 0.00038,
|
||||
"grad_norm": 4.84375,
|
||||
"learning_rate": 9.999996437073236e-06,
|
||||
"loss": 1.6197,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 0.00039,
|
||||
"grad_norm": 3.234375,
|
||||
"learning_rate": 9.999996247083397e-06,
|
||||
"loss": 1.5308,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 0.0004,
|
||||
"grad_norm": 1.375,
|
||||
"learning_rate": 9.99999605215876e-06,
|
||||
"loss": 1.5846,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.00041,
|
||||
"grad_norm": 1.34375,
|
||||
"learning_rate": 9.999995852299324e-06,
|
||||
"loss": 1.4274,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 0.00042,
|
||||
"grad_norm": 1.15625,
|
||||
"learning_rate": 9.999995647505092e-06,
|
||||
"loss": 1.4986,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 0.00043,
|
||||
"grad_norm": 0.94140625,
|
||||
"learning_rate": 9.99999543777606e-06,
|
||||
"loss": 1.5135,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 0.00044,
|
||||
"grad_norm": 0.8125,
|
||||
"learning_rate": 9.999995223112231e-06,
|
||||
"loss": 1.5472,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"epoch": 0.00045,
|
||||
"grad_norm": 1.5703125,
|
||||
"learning_rate": 9.999995003513605e-06,
|
||||
"loss": 1.5635,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.00046,
|
||||
"grad_norm": 3.34375,
|
||||
"learning_rate": 9.999994778980182e-06,
|
||||
"loss": 1.5506,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 0.00047,
|
||||
"grad_norm": 5.4375,
|
||||
"learning_rate": 9.99999454951196e-06,
|
||||
"loss": 1.5071,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 0.00048,
|
||||
"grad_norm": 1.578125,
|
||||
"learning_rate": 9.999994315108943e-06,
|
||||
"loss": 1.5532,
|
||||
"step": 48
|
||||
},
|
||||
{
|
||||
"epoch": 0.00049,
|
||||
"grad_norm": 1.828125,
|
||||
"learning_rate": 9.999994075771128e-06,
|
||||
"loss": 1.6061,
|
||||
"step": 49
|
||||
},
|
||||
{
|
||||
"epoch": 0.0005,
|
||||
"grad_norm": 1.4453125,
|
||||
"learning_rate": 9.999993831498517e-06,
|
||||
"loss": 1.5629,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.00051,
|
||||
"grad_norm": 1.109375,
|
||||
"learning_rate": 9.999993582291112e-06,
|
||||
"loss": 1.5536,
|
||||
"step": 51
|
||||
},
|
||||
{
|
||||
"epoch": 0.00052,
|
||||
"grad_norm": 1.0078125,
|
||||
"learning_rate": 9.999993328148909e-06,
|
||||
"loss": 1.5013,
|
||||
"step": 52
|
||||
},
|
||||
{
|
||||
"epoch": 0.00053,
|
||||
"grad_norm": 1.171875,
|
||||
"learning_rate": 9.999993069071912e-06,
|
||||
"loss": 1.4943,
|
||||
"step": 53
|
||||
},
|
||||
{
|
||||
"epoch": 0.00054,
|
||||
"grad_norm": 1.8203125,
|
||||
"learning_rate": 9.999992805060117e-06,
|
||||
"loss": 1.5057,
|
||||
"step": 54
|
||||
},
|
||||
{
|
||||
"epoch": 0.00055,
|
||||
"grad_norm": 0.97265625,
|
||||
"learning_rate": 9.99999253611353e-06,
|
||||
"loss": 1.6486,
|
||||
"step": 55
|
||||
},
|
||||
{
|
||||
"epoch": 0.00056,
|
||||
"grad_norm": 3.765625,
|
||||
"learning_rate": 9.999992262232145e-06,
|
||||
"loss": 1.4421,
|
||||
"step": 56
|
||||
},
|
||||
{
|
||||
"epoch": 0.00057,
|
||||
"grad_norm": 2.21875,
|
||||
"learning_rate": 9.999991983415968e-06,
|
||||
"loss": 1.5346,
|
||||
"step": 57
|
||||
},
|
||||
{
|
||||
"epoch": 0.00058,
|
||||
"grad_norm": 0.953125,
|
||||
"learning_rate": 9.999991699664996e-06,
|
||||
"loss": 1.5433,
|
||||
"step": 58
|
||||
},
|
||||
{
|
||||
"epoch": 0.00059,
|
||||
"grad_norm": 3.171875,
|
||||
"learning_rate": 9.99999141097923e-06,
|
||||
"loss": 1.5306,
|
||||
"step": 59
|
||||
},
|
||||
{
|
||||
"epoch": 0.0006,
|
||||
"grad_norm": 1.0546875,
|
||||
"learning_rate": 9.99999111735867e-06,
|
||||
"loss": 1.4453,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.00061,
|
||||
"grad_norm": 0.796875,
|
||||
"learning_rate": 9.999990818803316e-06,
|
||||
"loss": 1.6219,
|
||||
"step": 61
|
||||
},
|
||||
{
|
||||
"epoch": 0.00062,
|
||||
"grad_norm": 1.078125,
|
||||
"learning_rate": 9.99999051531317e-06,
|
||||
"loss": 1.5296,
|
||||
"step": 62
|
||||
},
|
||||
{
|
||||
"epoch": 0.00063,
|
||||
"grad_norm": 1.2109375,
|
||||
"learning_rate": 9.999990206888231e-06,
|
||||
"loss": 1.5165,
|
||||
"step": 63
|
||||
},
|
||||
{
|
||||
"epoch": 0.00064,
|
||||
"grad_norm": 1.0234375,
|
||||
"learning_rate": 9.999989893528499e-06,
|
||||
"loss": 1.5697,
|
||||
"step": 64
|
||||
},
|
||||
{
|
||||
"epoch": 0.00065,
|
||||
"grad_norm": 3.0625,
|
||||
"learning_rate": 9.999989575233975e-06,
|
||||
"loss": 1.5121,
|
||||
"step": 65
|
||||
},
|
||||
{
|
||||
"epoch": 0.00066,
|
||||
"grad_norm": 0.9296875,
|
||||
"learning_rate": 9.999989252004657e-06,
|
||||
"loss": 1.4815,
|
||||
"step": 66
|
||||
},
|
||||
{
|
||||
"epoch": 0.00067,
|
||||
"grad_norm": 1.53125,
|
||||
"learning_rate": 9.999988923840551e-06,
|
||||
"loss": 1.4624,
|
||||
"step": 67
|
||||
},
|
||||
{
|
||||
"epoch": 0.00068,
|
||||
"grad_norm": 0.80859375,
|
||||
"learning_rate": 9.999988590741651e-06,
|
||||
"loss": 1.5089,
|
||||
"step": 68
|
||||
},
|
||||
{
|
||||
"epoch": 0.00069,
|
||||
"grad_norm": 1.4453125,
|
||||
"learning_rate": 9.999988252707961e-06,
|
||||
"loss": 1.4864,
|
||||
"step": 69
|
||||
},
|
||||
{
|
||||
"epoch": 0.0007,
|
||||
"grad_norm": 2.328125,
|
||||
"learning_rate": 9.999987909739481e-06,
|
||||
"loss": 1.5284,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.00071,
|
||||
"grad_norm": 1.4296875,
|
||||
"learning_rate": 9.99998756183621e-06,
|
||||
"loss": 1.4759,
|
||||
"step": 71
|
||||
},
|
||||
{
|
||||
"epoch": 0.00072,
|
||||
"grad_norm": 1.2890625,
|
||||
"learning_rate": 9.999987208998151e-06,
|
||||
"loss": 1.5659,
|
||||
"step": 72
|
||||
},
|
||||
{
|
||||
"epoch": 0.00073,
|
||||
"grad_norm": 3.1875,
|
||||
"learning_rate": 9.9999868512253e-06,
|
||||
"loss": 1.6112,
|
||||
"step": 73
|
||||
},
|
||||
{
|
||||
"epoch": 0.00074,
|
||||
"grad_norm": 1.09375,
|
||||
"learning_rate": 9.999986488517661e-06,
|
||||
"loss": 1.503,
|
||||
"step": 74
|
||||
},
|
||||
{
|
||||
"epoch": 0.00075,
|
||||
"grad_norm": 0.80078125,
|
||||
"learning_rate": 9.999986120875233e-06,
|
||||
"loss": 1.4688,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.00076,
|
||||
"grad_norm": 2.09375,
|
||||
"learning_rate": 9.999985748298016e-06,
|
||||
"loss": 1.543,
|
||||
"step": 76
|
||||
},
|
||||
{
|
||||
"epoch": 0.00077,
|
||||
"grad_norm": 0.89453125,
|
||||
"learning_rate": 9.999985370786011e-06,
|
||||
"loss": 1.5166,
|
||||
"step": 77
|
||||
},
|
||||
{
|
||||
"epoch": 0.00078,
|
||||
"grad_norm": 1.859375,
|
||||
"learning_rate": 9.999984988339219e-06,
|
||||
"loss": 1.5451,
|
||||
"step": 78
|
||||
},
|
||||
{
|
||||
"epoch": 0.00079,
|
||||
"grad_norm": 1.6640625,
|
||||
"learning_rate": 9.999984600957639e-06,
|
||||
"loss": 1.5026,
|
||||
"step": 79
|
||||
},
|
||||
{
|
||||
"epoch": 0.0008,
|
||||
"grad_norm": 1.5234375,
|
||||
"learning_rate": 9.999984208641271e-06,
|
||||
"loss": 1.4629,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.00081,
|
||||
"grad_norm": 1.0,
|
||||
"learning_rate": 9.999983811390117e-06,
|
||||
"loss": 1.5866,
|
||||
"step": 81
|
||||
},
|
||||
{
|
||||
"epoch": 0.00082,
|
||||
"grad_norm": 1.2734375,
|
||||
"learning_rate": 9.999983409204178e-06,
|
||||
"loss": 1.4361,
|
||||
"step": 82
|
||||
},
|
||||
{
|
||||
"epoch": 0.00083,
|
||||
"grad_norm": 1.9609375,
|
||||
"learning_rate": 9.999983002083451e-06,
|
||||
"loss": 1.5498,
|
||||
"step": 83
|
||||
},
|
||||
{
|
||||
"epoch": 0.00084,
|
||||
"grad_norm": 3.125,
|
||||
"learning_rate": 9.999982590027942e-06,
|
||||
"loss": 1.5787,
|
||||
"step": 84
|
||||
},
|
||||
{
|
||||
"epoch": 0.00085,
|
||||
"grad_norm": 0.9453125,
|
||||
"learning_rate": 9.999982173037645e-06,
|
||||
"loss": 1.5674,
|
||||
"step": 85
|
||||
},
|
||||
{
|
||||
"epoch": 0.00086,
|
||||
"grad_norm": 0.91015625,
|
||||
"learning_rate": 9.999981751112563e-06,
|
||||
"loss": 1.5676,
|
||||
"step": 86
|
||||
},
|
||||
{
|
||||
"epoch": 0.00087,
|
||||
"grad_norm": 1.3203125,
|
||||
"learning_rate": 9.999981324252698e-06,
|
||||
"loss": 1.5031,
|
||||
"step": 87
|
||||
},
|
||||
{
|
||||
"epoch": 0.00088,
|
||||
"grad_norm": 1.40625,
|
||||
"learning_rate": 9.99998089245805e-06,
|
||||
"loss": 1.5127,
|
||||
"step": 88
|
||||
},
|
||||
{
|
||||
"epoch": 0.00089,
|
||||
"grad_norm": 0.92578125,
|
||||
"learning_rate": 9.999980455728618e-06,
|
||||
"loss": 1.5867,
|
||||
"step": 89
|
||||
},
|
||||
{
|
||||
"epoch": 0.0009,
|
||||
"grad_norm": 1.0078125,
|
||||
"learning_rate": 9.999980014064404e-06,
|
||||
"loss": 1.4413,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.00091,
|
||||
"grad_norm": 0.93359375,
|
||||
"learning_rate": 9.999979567465405e-06,
|
||||
"loss": 1.3676,
|
||||
"step": 91
|
||||
},
|
||||
{
|
||||
"epoch": 0.00092,
|
||||
"grad_norm": 0.9609375,
|
||||
"learning_rate": 9.999979115931626e-06,
|
||||
"loss": 1.5553,
|
||||
"step": 92
|
||||
},
|
||||
{
|
||||
"epoch": 0.00093,
|
||||
"grad_norm": 0.75,
|
||||
"learning_rate": 9.999978659463065e-06,
|
||||
"loss": 1.4763,
|
||||
"step": 93
|
||||
},
|
||||
{
|
||||
"epoch": 0.00094,
|
||||
"grad_norm": 0.6796875,
|
||||
"learning_rate": 9.999978198059722e-06,
|
||||
"loss": 1.4483,
|
||||
"step": 94
|
||||
},
|
||||
{
|
||||
"epoch": 0.00095,
|
||||
"grad_norm": 0.8046875,
|
||||
"learning_rate": 9.9999777317216e-06,
|
||||
"loss": 1.5449,
|
||||
"step": 95
|
||||
},
|
||||
{
|
||||
"epoch": 0.00096,
|
||||
"grad_norm": 1.0859375,
|
||||
"learning_rate": 9.999977260448697e-06,
|
||||
"loss": 1.4965,
|
||||
"step": 96
|
||||
},
|
||||
{
|
||||
"epoch": 0.00097,
|
||||
"grad_norm": 1.0,
|
||||
"learning_rate": 9.999976784241014e-06,
|
||||
"loss": 1.596,
|
||||
"step": 97
|
||||
},
|
||||
{
|
||||
"epoch": 0.00098,
|
||||
"grad_norm": 0.94921875,
|
||||
"learning_rate": 9.999976303098552e-06,
|
||||
"loss": 1.5585,
|
||||
"step": 98
|
||||
},
|
||||
{
|
||||
"epoch": 0.00099,
|
||||
"grad_norm": 0.921875,
|
||||
"learning_rate": 9.99997581702131e-06,
|
||||
"loss": 1.501,
|
||||
"step": 99
|
||||
},
|
||||
{
|
||||
"epoch": 0.001,
|
||||
"grad_norm": 1.8984375,
|
||||
"learning_rate": 9.999975326009292e-06,
|
||||
"loss": 1.4553,
|
||||
"step": 100
|
||||
}
|
||||
],
|
||||
"logging_steps": 1.0,
|
||||
"max_steps": 100000,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 9223372036854775807,
|
||||
"save_steps": 50,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 2.3055128592384e+18,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
checkpoint-100/training_args.bin
Normal file
3
checkpoint-100/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:489201d0ef80ec44754ed9b7096bc634ab56fa8d1c361078d73aa8493edb9c66
|
||||
size 5752
|
||||
Reference in New Issue
Block a user