Delete checkpoint-200

checkpoint-200/added_tokens.json

@@ -1,3 +0,0 @@
-{
-  "[PAD]": 32000
-}

checkpoint-200/config.json

@@ -1,23 +0,0 @@
-{
-  "_name_or_path": "/workspace/llama-7b-hf",
-  "architectures": [
-    "LLaMAForCausalLM"
-  ],
-  "bos_token_id": 0,
-  "eos_token_id": 1,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 11008,
-  "max_sequence_length": 2048,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "pad_token_id": -1,
-  "rms_norm_eps": 1e-06,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.27.0.dev0",
-  "use_cache": true,
-  "vocab_size": 32001
-}

checkpoint-200/generation_config.json

@@ -1,7 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 1,
-  "pad_token_id": 0,
-  "transformers_version": "4.27.0.dev0"
-}

checkpoint-200/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c8718b817f3e7fec342d528ca98c05641adbb53dbef0fc71cdf401173e58b0e9
-size 13476876030

checkpoint-200/pytorch_model-00001-of-00003.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7888575d8c9f96b618f55a43d1173376cabfba125ceea6efda6da199caec5755
-size 9878006034

checkpoint-200/pytorch_model-00002-of-00003.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:94e0a309ad393c80e5ad26eefda46108c1925752ede92b99578788b0679d0c25
-size 9894801206

checkpoint-200/pytorch_model-00003-of-00003.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b4cd55918c46c532e4fd978ce30cc131009ab76a064ce9d9082f196d7c5288dc
-size 7181007225

checkpoint-200/pytorch_model.bin.index.json

@@ -1,330 +0,0 @@
-{
-  "metadata": {
-    "total_size": 26953699328
-  },
-  "weight_map": {
-    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
-    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
-  }
-}

checkpoint-200/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e75c96f06b249e57a701db73ce821398e69672027a86d3a44063830602a29ab4
-size 14583

checkpoint-200/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6dae7f45b6bac644ac207a61f43cba6d4b919a4cac22022bbb02907914422f5d
-size 14583

checkpoint-200/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e53c770fe48635faad7fa341007d771781f1397cd47daab5b58f879ffb65f178
-size 14583

checkpoint-200/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:68692af1001e65d02e07ac9974ccf4c332cfb23bc8f89566e1a908b1f2c4a1ed
-size 14583

checkpoint-200/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:101d17cf5b9805d0a0ac406a7e2e9097fbcc4cc6400262383a2f1907249b7bca
-size 627

checkpoint-200/special_tokens_map.json

@@ -1,6 +0,0 @@
-{
-  "bos_token": "</s>",
-  "eos_token": "</s>",
-  "pad_token": "[PAD]",
-  "unk_token": "</s>"
-}

checkpoint-200/tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723

checkpoint-200/tokenizer_config.json

@@ -1,9 +0,0 @@
-{
-  "bos_token": "",
-  "eos_token": "",
-  "model_max_length": 512,
-  "padding_side": "right",
-  "special_tokens_map_file": "/workspace/llama-7b-hf/special_tokens_map.json",
-  "tokenizer_class": "LLaMATokenizer",
-  "unk_token": ""
-}

checkpoint-200/trainer_state.json

@@ -1,1216 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.4921562596124269,
-  "global_step": 200,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0,
-      "learning_rate": 5.405405405405406e-07,
-      "loss": 1.5039,
-      "step": 1
-    },
-    {
-      "epoch": 0.0,
-      "learning_rate": 1.0810810810810812e-06,
-      "loss": 1.5785,
-      "step": 2
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 1.6216216216216219e-06,
-      "loss": 1.2981,
-      "step": 3
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 2.1621621621621623e-06,
-      "loss": 1.1631,
-      "step": 4
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 2.702702702702703e-06,
-      "loss": 1.2493,
-      "step": 5
-    },
-    {
-      "epoch": 0.01,
-      "learning_rate": 3.2432432432432437e-06,
-      "loss": 1.2413,
-      "step": 6
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 3.7837837837837844e-06,
-      "loss": 1.2368,
-      "step": 7
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 4.324324324324325e-06,
-      "loss": 1.2152,
-      "step": 8
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 4.864864864864866e-06,
-      "loss": 1.1487,
-      "step": 9
-    },
-    {
-      "epoch": 0.02,
-      "learning_rate": 5.405405405405406e-06,
-      "loss": 1.116,
-      "step": 10
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 5.945945945945947e-06,
-      "loss": 1.179,
-      "step": 11
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 6.486486486486487e-06,
-      "loss": 1.2134,
-      "step": 12
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 7.027027027027028e-06,
-      "loss": 1.1641,
-      "step": 13
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 7.567567567567569e-06,
-      "loss": 1.0623,
-      "step": 14
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 8.108108108108109e-06,
-      "loss": 1.0922,
-      "step": 15
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 8.64864864864865e-06,
-      "loss": 1.0979,
-      "step": 16
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 9.189189189189191e-06,
-      "loss": 1.1572,
-      "step": 17
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 9.729729729729732e-06,
-      "loss": 1.0788,
-      "step": 18
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 1.027027027027027e-05,
-      "loss": 1.1467,
-      "step": 19
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 1.0810810810810812e-05,
-      "loss": 1.0852,
-      "step": 20
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 1.1351351351351352e-05,
-      "loss": 1.1176,
-      "step": 21
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 1.1891891891891894e-05,
-      "loss": 1.1049,
-      "step": 22
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 1.2432432432432433e-05,
-      "loss": 1.0972,
-      "step": 23
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 1.2972972972972975e-05,
-      "loss": 1.1404,
-      "step": 24
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 1.3513513513513515e-05,
-      "loss": 1.1416,
-      "step": 25
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 1.4054054054054055e-05,
-      "loss": 1.1458,
-      "step": 26
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 1.4594594594594596e-05,
-      "loss": 1.1497,
-      "step": 27
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 1.5135135135135138e-05,
-      "loss": 1.14,
-      "step": 28
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 1.5675675675675676e-05,
-      "loss": 1.0808,
-      "step": 29
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 1.6216216216216218e-05,
-      "loss": 1.0996,
-      "step": 30
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 1.6756756756756757e-05,
-      "loss": 1.1064,
-      "step": 31
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 1.72972972972973e-05,
-      "loss": 1.1823,
-      "step": 32
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 1.783783783783784e-05,
-      "loss": 1.0483,
-      "step": 33
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 1.8378378378378383e-05,
-      "loss": 1.1019,
-      "step": 34
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 1.891891891891892e-05,
-      "loss": 1.0325,
-      "step": 35
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 1.9459459459459463e-05,
-      "loss": 1.1006,
-      "step": 36
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 2e-05,
-      "loss": 1.0715,
-      "step": 37
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 1.999996461903301e-05,
-      "loss": 1.1542,
-      "step": 38
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 1.9999858476382388e-05,
-      "loss": 1.1402,
-      "step": 39
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 1.9999681572799226e-05,
-      "loss": 1.0163,
-      "step": 40
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 1.9999433909535333e-05,
-      "loss": 1.0851,
-      "step": 41
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 1.9999115488343213e-05,
-      "loss": 1.1119,
-      "step": 42
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 1.999872631147608e-05,
-      "loss": 1.0726,
-      "step": 43
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 1.999826638168783e-05,
-      "loss": 1.0927,
-      "step": 44
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 1.9997735702233006e-05,
-      "loss": 1.0697,
-      "step": 45
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 1.99971342768668e-05,
-      "loss": 1.0363,
-      "step": 46
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 1.999646210984502e-05,
-      "loss": 1.1251,
-      "step": 47
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 1.999571920592405e-05,
-      "loss": 1.127,
-      "step": 48
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 1.9994905570360817e-05,
-      "loss": 1.0994,
-      "step": 49
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 1.999402120891276e-05,
-      "loss": 1.0688,
-      "step": 50
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 1.99930661278378e-05,
-      "loss": 1.0544,
-      "step": 51
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 1.9992040333894273e-05,
-      "loss": 1.0908,
-      "step": 52
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 1.9990943834340893e-05,
-      "loss": 1.1394,
-      "step": 53
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 1.9989776636936705e-05,
-      "loss": 1.1065,
-      "step": 54
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 1.9988538749941024e-05,
-      "loss": 1.0752,
-      "step": 55
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 1.9987230182113374e-05,
-      "loss": 1.076,
-      "step": 56
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 1.998585094271344e-05,
-      "loss": 1.0504,
-      "step": 57
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 1.998440104150098e-05,
-      "loss": 1.0934,
-      "step": 58
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 1.998288048873578e-05,
-      "loss": 1.1355,
-      "step": 59
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 1.9981289295177566e-05,
-      "loss": 1.1693,
-      "step": 60
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 1.9979627472085927e-05,
-      "loss": 1.0514,
-      "step": 61
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 1.997789503122025e-05,
-      "loss": 1.119,
-      "step": 62
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 1.9976091984839616e-05,
-      "loss": 1.0635,
-      "step": 63
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 1.9974218345702733e-05,
-      "loss": 1.1111,
-      "step": 64
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 1.9972274127067838e-05,
-      "loss": 1.1732,
-      "step": 65
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 1.997025934269259e-05,
-      "loss": 1.149,
-      "step": 66
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 1.9968174006833996e-05,
-      "loss": 1.1011,
-      "step": 67
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 1.9966018134248296e-05,
-      "loss": 1.1367,
-      "step": 68
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 1.9963791740190863e-05,
-      "loss": 1.1354,
-      "step": 69
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 1.996149484041609e-05,
-      "loss": 1.0343,
-      "step": 70
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 1.9959127451177287e-05,
-      "loss": 1.1997,
-      "step": 71
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 1.9956689589226555e-05,
-      "loss": 1.1131,
-      "step": 72
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 1.9954181271814673e-05,
-      "loss": 1.0335,
-      "step": 73
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 1.9951602516690988e-05,
-      "loss": 1.0786,
-      "step": 74
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 1.9948953342103268e-05,
-      "loss": 1.0926,
-      "step": 75
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 1.994623376679758e-05,
-      "loss": 1.1353,
-      "step": 76
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 1.9943443810018174e-05,
-      "loss": 1.0605,
-      "step": 77
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 1.9940583491507314e-05,
-      "loss": 1.1255,
-      "step": 78
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 1.993765283150517e-05,
-      "loss": 1.0541,
-      "step": 79
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 1.9934651850749663e-05,
-      "loss": 1.1197,
-      "step": 80
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 1.9931580570476306e-05,
-      "loss": 1.1297,
-      "step": 81
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 1.9928439012418076e-05,
-      "loss": 1.1324,
-      "step": 82
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 1.9925227198805247e-05,
-      "loss": 1.0846,
-      "step": 83
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 1.9921945152365235e-05,
-      "loss": 1.1831,
-      "step": 84
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 1.9918592896322432e-05,
-      "loss": 1.0921,
-      "step": 85
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 1.9915170454398045e-05,
-      "loss": 1.1037,
-      "step": 86
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 1.9911677850809943e-05,
-      "loss": 1.125,
-      "step": 87
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 1.9908115110272463e-05,
-      "loss": 1.1279,
-      "step": 88
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 1.9904482257996244e-05,
-      "loss": 1.1427,
-      "step": 89
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 1.990077931968805e-05,
-      "loss": 1.1475,
-      "step": 90
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 1.9897006321550592e-05,
-      "loss": 1.136,
-      "step": 91
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 1.9893163290282335e-05,
-      "loss": 1.0469,
-      "step": 92
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 1.9889250253077306e-05,
-      "loss": 1.1028,
-      "step": 93
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 1.9885267237624923e-05,
-      "loss": 1.1775,
-      "step": 94
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 1.988121427210976e-05,
-      "loss": 1.1744,
-      "step": 95
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 1.98770913852114e-05,
-      "loss": 1.1049,
-      "step": 96
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 1.9872898606104175e-05,
-      "loss": 1.1085,
-      "step": 97
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 1.9868635964457007e-05,
-      "loss": 1.1153,
-      "step": 98
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 1.986430349043317e-05,
-      "loss": 1.1637,
-      "step": 99
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 1.9859901214690094e-05,
-      "loss": 1.0971,
-      "step": 100
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 1.9855429168379127e-05,
-      "loss": 1.1537,
-      "step": 101
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 1.985088738314534e-05,
-      "loss": 1.0882,
-      "step": 102
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 1.9846275891127275e-05,
-      "loss": 1.128,
-      "step": 103
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 1.9841594724956746e-05,
-      "loss": 1.14,
-      "step": 104
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 1.9836843917758593e-05,
-      "loss": 1.0273,
-      "step": 105
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 1.983202350315044e-05,
-      "loss": 1.0891,
-      "step": 106
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 1.982713351524248e-05,
-      "loss": 1.106,
-      "step": 107
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 1.982217398863721e-05,
-      "loss": 1.0599,
-      "step": 108
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 1.98171449584292e-05,
-      "loss": 1.0396,
-      "step": 109
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 1.9812046460204837e-05,
-      "loss": 1.0767,
-      "step": 110
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 1.9806878530042083e-05,
-      "loss": 1.1568,
-      "step": 111
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 1.9801641204510216e-05,
-      "loss": 1.1534,
-      "step": 112
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 1.9796334520669555e-05,
-      "loss": 1.0332,
-      "step": 113
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 1.9790958516071228e-05,
-      "loss": 1.1018,
-      "step": 114
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 1.978551322875688e-05,
-      "loss": 1.0634,
-      "step": 115
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 1.977999869725842e-05,
-      "loss": 1.0766,
-      "step": 116
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 1.977441496059774e-05,
-      "loss": 1.0456,
-      "step": 117
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 1.9768762058286433e-05,
-      "loss": 1.0047,
-      "step": 118
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 1.976304003032554e-05,
-      "loss": 1.0798,
-      "step": 119
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 1.9757248917205228e-05,
-      "loss": 1.1055,
-      "step": 120
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 1.975138875990454e-05,
-      "loss": 1.1921,
-      "step": 121
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 1.974545959989108e-05,
-      "loss": 1.0465,
-      "step": 122
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 1.9739461479120727e-05,
-      "loss": 1.129,
-      "step": 123
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 1.973339444003735e-05,
-      "loss": 1.0773,
-      "step": 124
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 1.9727258525572487e-05,
-      "loss": 1.0955,
-      "step": 125
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 1.9721053779145057e-05,
-      "loss": 1.0941,
-      "step": 126
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 1.9714780244661044e-05,
-      "loss": 1.1672,
-      "step": 127
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 1.9708437966513196e-05,
-      "loss": 1.1014,
-      "step": 128
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 1.9702026989580694e-05,
-      "loss": 1.1272,
-      "step": 129
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 1.969554735922885e-05,
-      "loss": 1.0398,
-      "step": 130
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 1.968899912130879e-05,
-      "loss": 1.106,
-      "step": 131
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 1.9682382322157103e-05,
-      "loss": 1.1033,
-      "step": 132
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 1.9675697008595545e-05,
-      "loss": 1.0154,
-      "step": 133
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 1.9668943227930686e-05,
-      "loss": 1.1219,
-      "step": 134
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 1.966212102795358e-05,
-      "loss": 1.0824,
-      "step": 135
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 1.965523045693944e-05,
-      "loss": 1.0581,
-      "step": 136
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 1.964827156364728e-05,
-      "loss": 1.1327,
-      "step": 137
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 1.964124439731957e-05,
-      "loss": 1.1144,
-      "step": 138
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 1.9634149007681894e-05,
-      "loss": 1.1436,
-      "step": 139
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 1.962698544494261e-05,
-      "loss": 1.0457,
-      "step": 140
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 1.9619753759792466e-05,
-      "loss": 1.1053,
-      "step": 141
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 1.961245400340427e-05,
-      "loss": 1.0881,
-      "step": 142
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 1.9605086227432512e-05,
-      "loss": 1.1058,
-      "step": 143
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 1.9597650484012997e-05,
-      "loss": 1.1418,
-      "step": 144
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 1.9590146825762476e-05,
-      "loss": 1.0623,
-      "step": 145
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 1.9582575305778297e-05,
-      "loss": 1.0987,
-      "step": 146
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 1.9574935977637994e-05,
-      "loss": 1.0764,
-      "step": 147
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 1.9567228895398936e-05,
-      "loss": 1.153,
-      "step": 148
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 1.955945411359792e-05,
-      "loss": 1.1233,
-      "step": 149
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 1.9551611687250808e-05,
-      "loss": 1.0827,
-      "step": 150
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 1.9543701671852127e-05,
-      "loss": 1.0487,
-      "step": 151
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 1.9535724123374674e-05,
-      "loss": 1.0795,
-      "step": 152
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 1.952767909826913e-05,
-      "loss": 1.15,
-      "step": 153
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 1.951956665346364e-05,
-      "loss": 1.0645,
-      "step": 154
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 1.951138684636344e-05,
-      "loss": 1.0764,
-      "step": 155
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 1.9503139734850426e-05,
-      "loss": 1.1185,
-      "step": 156
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 1.9494825377282746e-05,
-      "loss": 1.0879,
-      "step": 157
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 1.9486443832494414e-05,
-      "loss": 1.0558,
-      "step": 158
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 1.9477995159794854e-05,
-      "loss": 1.1042,
-      "step": 159
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 1.9469479418968506e-05,
-      "loss": 1.1029,
-      "step": 160
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 1.9460896670274408e-05,
-      "loss": 0.9836,
-      "step": 161
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 1.9452246974445743e-05,
-      "loss": 1.1325,
-      "step": 162
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 1.9443530392689434e-05,
-      "loss": 1.1018,
-      "step": 163
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 1.94347469866857e-05,
-      "loss": 1.1525,
-      "step": 164
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 1.9425896818587615e-05,
-      "loss": 1.0719,
-      "step": 165
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 1.941697995102069e-05,
-      "loss": 1.1595,
-      "step": 166
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 1.9407996447082394e-05,
-      "loss": 1.1698,
-      "step": 167
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 1.939894637034174e-05,
-      "loss": 1.131,
-      "step": 168
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 1.9389829784838833e-05,
-      "loss": 1.0604,
-      "step": 169
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 1.938064675508438e-05,
-      "loss": 1.0422,
-      "step": 170
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 1.9371397346059286e-05,
-      "loss": 1.1098,
-      "step": 171
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 1.936208162321415e-05,
-      "loss": 1.0682,
-      "step": 172
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 1.9352699652468835e-05,
-      "loss": 1.0763,
-      "step": 173
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 1.9343251500211977e-05,
-      "loss": 1.1038,
-      "step": 174
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 1.933373723330053e-05,
-      "loss": 1.0613,
-      "step": 175
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 1.9324156919059286e-05,
-      "loss": 1.1157,
-      "step": 176
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 1.93145106252804e-05,
-      "loss": 1.1264,
-      "step": 177
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 1.9304798420222918e-05,
-      "loss": 1.0787,
-      "step": 178
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 1.9295020372612276e-05,
-      "loss": 1.1298,
-      "step": 179
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 1.9285176551639826e-05,
-      "loss": 1.1175,
-      "step": 180
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 1.9275267026962358e-05,
-      "loss": 1.1686,
-      "step": 181
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 1.9265291868701584e-05,
-      "loss": 1.0939,
-      "step": 182
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 1.9255251147443646e-05,
-      "loss": 1.1674,
-      "step": 183
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 1.924514493423864e-05,
-      "loss": 1.0747,
-      "step": 184
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 1.9234973300600074e-05,
-      "loss": 1.1085,
-      "step": 185
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 1.92247363185044e-05,
-      "loss": 1.1157,
-      "step": 186
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 1.9214434060390484e-05,
-      "loss": 1.1827,
-      "step": 187
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 1.9204066599159094e-05,
-      "loss": 1.1126,
-      "step": 188
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 1.9193634008172396e-05,
-      "loss": 1.1158,
-      "step": 189
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 1.9183136361253417e-05,
-      "loss": 1.0609,
-      "step": 190
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 1.917257373268554e-05,
-      "loss": 1.0617,
-      "step": 191
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 1.916194619721196e-05,
-      "loss": 1.0724,
-      "step": 192
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 1.915125383003518e-05,
-      "loss": 1.0784,
-      "step": 193
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 1.914049670681646e-05,
-      "loss": 1.1141,
-      "step": 194
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 1.912967490367528e-05,
-      "loss": 1.0305,
-      "step": 195
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 1.9118788497188815e-05,
-      "loss": 1.026,
-      "step": 196
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 1.9107837564391376e-05,
-      "loss": 1.0663,
-      "step": 197
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 1.9096822182773887e-05,
-      "loss": 1.0368,
-      "step": 198
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 1.9085742430283322e-05,
-      "loss": 1.1052,
-      "step": 199
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 1.907459838532215e-05,
-      "loss": 1.0834,
-      "step": 200
-    }
-  ],
-  "max_steps": 1218,
-  "num_train_epochs": 3,
-  "total_flos": 4.842042281898803e+16,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-200/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:489a2c2f2f6410389af7de61eb98d5f872555fc9d4010f24177144678ba20982
-size 3707