Delete checkpoint-141

checkpoint-141/added_tokens.json

@@ -1,5 +0,0 @@
-{
-  "<|endofprompt|>": 100276,
-  "<|im_end|>": 100265,
-  "<|im_start|>": 100264
-}

checkpoint-141/chat_template.jinja

@@ -1,4 +0,0 @@
-{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
-' + message['content'] + '<|im_end|>' + '
-'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}

checkpoint-141/config.json

@@ -1,32 +0,0 @@
-{
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 100257,
-  "embd_pdrop": 0.0,
-  "eos_token_id": 100265,
-  "head_dim": 128,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 8192,
-  "max_position_embeddings": 262144,
-  "mlp_bias": false,
-  "model_type": "llama",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 8,
-  "pad_token_id": 100257,
-  "pretraining_tp": 1,
-  "resid_pdrop": 0.0,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 128000000,
-  "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.52.4",
-  "use_cache": false,
-  "vocab_size": 102400
-}

checkpoint-141/generation_config.json

@@ -1,9 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 100257,
-  "do_sample": true,
-  "eos_token_id": 100265,
-  "pad_token_id": 100257,
-  "transformers_version": "4.52.4",
-  "use_cache": false
-}

checkpoint-141/model-00001-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5fdd07bf5ce443f8e60d55a5b391253eed234f270782bac8b9c114e72e17f86d
-size 4983077832

checkpoint-141/model-00002-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:962c4cfabce6cd2afc02357983b04c8b474f30c79cfbae5384b281acb20a7795
-size 3842234168

checkpoint-141/model.safetensors.index.json

@@ -1,261 +0,0 @@
-{
-  "metadata": {
-    "total_size": 8825282560
-  },
-  "weight_map": {
-    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.norm.weight": "model-00002-of-00002.safetensors"
-  }
-}

checkpoint-141/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:40cd84cf6aa0350183d4bc0338c36f53416a4425c9dae3beee0c11c33cff2d61
-size 11466962878

checkpoint-141/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4b11a10749bfb1630d95eef94125f4590e8610c579d217d1f158e71ce518d72b
-size 14244

checkpoint-141/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:81d3b77a80be28ba7fd7bced065afe839678d65a68f497cb71e6167b4dfd4974
-size 1064

checkpoint-141/special_tokens_map.json

@@ -1,30 +0,0 @@
-{
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

checkpoint-141/tokenizer_config.json

@@ -1,69 +0,0 @@
-{
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "100257": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100258": {
-      "content": "<|fim_prefix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100259": {
-      "content": "<|fim_middle|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100260": {
-      "content": "<|fim_suffix|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100264": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "100265": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "100276": {
-      "content": "<|endofprompt|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "extra_special_tokens": {},
-  "model_max_length": 262144,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
-}

checkpoint-141/trainer_state.json

@@ -1,1021 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.9964664310954063,
-  "eval_steps": 500,
-  "global_step": 141,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.007067137809187279,
-      "grad_norm": 1.2265625,
-      "learning_rate": 0.0,
-      "loss": 1.9174,
-      "step": 1
-    },
-    {
-      "epoch": 0.014134275618374558,
-      "grad_norm": 1.0234375,
-      "learning_rate": 3.5714285714285716e-07,
-      "loss": 2.2074,
-      "step": 2
-    },
-    {
-      "epoch": 0.02120141342756184,
-      "grad_norm": 1.2421875,
-      "learning_rate": 7.142857142857143e-07,
-      "loss": 1.7854,
-      "step": 3
-    },
-    {
-      "epoch": 0.028268551236749116,
-      "grad_norm": 1.1484375,
-      "learning_rate": 1.0714285714285714e-06,
-      "loss": 2.1768,
-      "step": 4
-    },
-    {
-      "epoch": 0.0353356890459364,
-      "grad_norm": 0.9375,
-      "learning_rate": 1.4285714285714286e-06,
-      "loss": 2.1438,
-      "step": 5
-    },
-    {
-      "epoch": 0.04240282685512368,
-      "grad_norm": 3.484375,
-      "learning_rate": 1.7857142857142859e-06,
-      "loss": 2.5976,
-      "step": 6
-    },
-    {
-      "epoch": 0.04946996466431095,
-      "grad_norm": 1.2265625,
-      "learning_rate": 2.1428571428571427e-06,
-      "loss": 2.2351,
-      "step": 7
-    },
-    {
-      "epoch": 0.05653710247349823,
-      "grad_norm": 0.984375,
-      "learning_rate": 2.5e-06,
-      "loss": 2.0092,
-      "step": 8
-    },
-    {
-      "epoch": 0.0636042402826855,
-      "grad_norm": 1.1015625,
-      "learning_rate": 2.8571428571428573e-06,
-      "loss": 2.1347,
-      "step": 9
-    },
-    {
-      "epoch": 0.0706713780918728,
-      "grad_norm": 1.03125,
-      "learning_rate": 3.2142857142857147e-06,
-      "loss": 2.0748,
-      "step": 10
-    },
-    {
-      "epoch": 0.07773851590106007,
-      "grad_norm": 0.9140625,
-      "learning_rate": 3.5714285714285718e-06,
-      "loss": 1.7444,
-      "step": 11
-    },
-    {
-      "epoch": 0.08480565371024736,
-      "grad_norm": 0.83984375,
-      "learning_rate": 3.928571428571429e-06,
-      "loss": 1.5372,
-      "step": 12
-    },
-    {
-      "epoch": 0.09187279151943463,
-      "grad_norm": 0.71484375,
-      "learning_rate": 4.2857142857142855e-06,
-      "loss": 1.4944,
-      "step": 13
-    },
-    {
-      "epoch": 0.0989399293286219,
-      "grad_norm": 0.8046875,
-      "learning_rate": 4.642857142857144e-06,
-      "loss": 1.8555,
-      "step": 14
-    },
-    {
-      "epoch": 0.10600706713780919,
-      "grad_norm": 0.92578125,
-      "learning_rate": 5e-06,
-      "loss": 1.5569,
-      "step": 15
-    },
-    {
-      "epoch": 0.11307420494699646,
-      "grad_norm": 1.34375,
-      "learning_rate": 5.357142857142857e-06,
-      "loss": 2.1602,
-      "step": 16
-    },
-    {
-      "epoch": 0.12014134275618374,
-      "grad_norm": 0.84375,
-      "learning_rate": 5.7142857142857145e-06,
-      "loss": 2.0495,
-      "step": 17
-    },
-    {
-      "epoch": 0.127208480565371,
-      "grad_norm": 2.9375,
-      "learning_rate": 6.071428571428571e-06,
-      "loss": 2.2094,
-      "step": 18
-    },
-    {
-      "epoch": 0.13427561837455831,
-      "grad_norm": 0.8046875,
-      "learning_rate": 6.4285714285714295e-06,
-      "loss": 1.3931,
-      "step": 19
-    },
-    {
-      "epoch": 0.1413427561837456,
-      "grad_norm": 0.71875,
-      "learning_rate": 6.785714285714287e-06,
-      "loss": 1.7009,
-      "step": 20
-    },
-    {
-      "epoch": 0.14840989399293286,
-      "grad_norm": 0.859375,
-      "learning_rate": 7.1428571428571436e-06,
-      "loss": 1.8362,
-      "step": 21
-    },
-    {
-      "epoch": 0.15547703180212014,
-      "grad_norm": 0.67578125,
-      "learning_rate": 7.500000000000001e-06,
-      "loss": 1.9375,
-      "step": 22
-    },
-    {
-      "epoch": 0.1625441696113074,
-      "grad_norm": 0.9765625,
-      "learning_rate": 7.857142857142858e-06,
-      "loss": 2.1988,
-      "step": 23
-    },
-    {
-      "epoch": 0.1696113074204947,
-      "grad_norm": 0.71484375,
-      "learning_rate": 8.214285714285714e-06,
-      "loss": 1.7918,
-      "step": 24
-    },
-    {
-      "epoch": 0.17667844522968199,
-      "grad_norm": 1.0234375,
-      "learning_rate": 8.571428571428571e-06,
-      "loss": 2.1915,
-      "step": 25
-    },
-    {
-      "epoch": 0.18374558303886926,
-      "grad_norm": 0.796875,
-      "learning_rate": 8.92857142857143e-06,
-      "loss": 2.3101,
-      "step": 26
-    },
-    {
-      "epoch": 0.19081272084805653,
-      "grad_norm": 0.71875,
-      "learning_rate": 9.285714285714288e-06,
-      "loss": 1.9351,
-      "step": 27
-    },
-    {
-      "epoch": 0.1978798586572438,
-      "grad_norm": 1.4296875,
-      "learning_rate": 9.642857142857144e-06,
-      "loss": 1.7059,
-      "step": 28
-    },
-    {
-      "epoch": 0.2049469964664311,
-      "grad_norm": 0.7734375,
-      "learning_rate": 1e-05,
-      "loss": 2.1424,
-      "step": 29
-    },
-    {
-      "epoch": 0.21201413427561838,
-      "grad_norm": 0.6328125,
-      "learning_rate": 9.999914116658896e-06,
-      "loss": 1.7643,
-      "step": 30
-    },
-    {
-      "epoch": 0.21908127208480566,
-      "grad_norm": 0.79296875,
-      "learning_rate": 9.999656469585957e-06,
-      "loss": 1.8743,
-      "step": 31
-    },
-    {
-      "epoch": 0.22614840989399293,
-      "grad_norm": 0.74609375,
-      "learning_rate": 9.999227067632223e-06,
-      "loss": 2.0273,
-      "step": 32
-    },
-    {
-      "epoch": 0.2332155477031802,
-      "grad_norm": 0.8359375,
-      "learning_rate": 9.99862592554908e-06,
-      "loss": 1.8072,
-      "step": 33
-    },
-    {
-      "epoch": 0.24028268551236748,
-      "grad_norm": 0.82421875,
-      "learning_rate": 9.997853063987768e-06,
-      "loss": 2.0589,
-      "step": 34
-    },
-    {
-      "epoch": 0.24734982332155478,
-      "grad_norm": 0.66796875,
-      "learning_rate": 9.996908509498662e-06,
-      "loss": 1.9282,
-      "step": 35
-    },
-    {
-      "epoch": 0.254416961130742,
-      "grad_norm": 1.046875,
-      "learning_rate": 9.995792294530356e-06,
-      "loss": 1.538,
-      "step": 36
-    },
-    {
-      "epoch": 0.26148409893992935,
-      "grad_norm": 0.81640625,
-      "learning_rate": 9.994504457428557e-06,
-      "loss": 1.9843,
-      "step": 37
-    },
-    {
-      "epoch": 0.26855123674911663,
-      "grad_norm": 1.84375,
-      "learning_rate": 9.993045042434772e-06,
-      "loss": 2.7539,
-      "step": 38
-    },
-    {
-      "epoch": 0.2756183745583039,
-      "grad_norm": 0.66796875,
-      "learning_rate": 9.99141409968477e-06,
-      "loss": 1.7211,
-      "step": 39
-    },
-    {
-      "epoch": 0.2826855123674912,
-      "grad_norm": 0.71875,
-      "learning_rate": 9.989611685206881e-06,
-      "loss": 2.1478,
-      "step": 40
-    },
-    {
-      "epoch": 0.28975265017667845,
-      "grad_norm": 0.65234375,
-      "learning_rate": 9.987637860920053e-06,
-      "loss": 2.0103,
-      "step": 41
-    },
-    {
-      "epoch": 0.2968197879858657,
-      "grad_norm": 0.63671875,
-      "learning_rate": 9.985492694631733e-06,
-      "loss": 1.4481,
-      "step": 42
-    },
-    {
-      "epoch": 0.303886925795053,
-      "grad_norm": 0.80078125,
-      "learning_rate": 9.983176260035546e-06,
-      "loss": 1.7512,
-      "step": 43
-    },
-    {
-      "epoch": 0.31095406360424027,
-      "grad_norm": 0.71875,
-      "learning_rate": 9.980688636708744e-06,
-      "loss": 2.061,
-      "step": 44
-    },
-    {
-      "epoch": 0.31802120141342755,
-      "grad_norm": 0.59765625,
-      "learning_rate": 9.978029910109491e-06,
-      "loss": 1.572,
-      "step": 45
-    },
-    {
-      "epoch": 0.3250883392226148,
-      "grad_norm": 0.66015625,
-      "learning_rate": 9.975200171573917e-06,
-      "loss": 2.0828,
-      "step": 46
-    },
-    {
-      "epoch": 0.3321554770318021,
-      "grad_norm": 0.63671875,
-      "learning_rate": 9.972199518312979e-06,
-      "loss": 1.8459,
-      "step": 47
-    },
-    {
-      "epoch": 0.3392226148409894,
-      "grad_norm": 0.6796875,
-      "learning_rate": 9.969028053409131e-06,
-      "loss": 2.2307,
-      "step": 48
-    },
-    {
-      "epoch": 0.3462897526501767,
-      "grad_norm": 0.65625,
-      "learning_rate": 9.965685885812773e-06,
-      "loss": 1.5793,
-      "step": 49
-    },
-    {
-      "epoch": 0.35335689045936397,
-      "grad_norm": 0.75,
-      "learning_rate": 9.96217313033851e-06,
-      "loss": 2.1297,
-      "step": 50
-    },
-    {
-      "epoch": 0.36042402826855124,
-      "grad_norm": 1.0625,
-      "learning_rate": 9.958489907661217e-06,
-      "loss": 1.912,
-      "step": 51
-    },
-    {
-      "epoch": 0.3674911660777385,
-      "grad_norm": 0.72265625,
-      "learning_rate": 9.95463634431188e-06,
-      "loss": 2.122,
-      "step": 52
-    },
-    {
-      "epoch": 0.3745583038869258,
-      "grad_norm": 0.59375,
-      "learning_rate": 9.950612572673255e-06,
-      "loss": 1.9928,
-      "step": 53
-    },
-    {
-      "epoch": 0.38162544169611307,
-      "grad_norm": 0.8984375,
-      "learning_rate": 9.946418730975326e-06,
-      "loss": 1.9401,
-      "step": 54
-    },
-    {
-      "epoch": 0.38869257950530034,
-      "grad_norm": 0.578125,
-      "learning_rate": 9.942054963290549e-06,
-      "loss": 1.742,
-      "step": 55
-    },
-    {
-      "epoch": 0.3957597173144876,
-      "grad_norm": 0.70703125,
-      "learning_rate": 9.9375214195289e-06,
-      "loss": 1.775,
-      "step": 56
-    },
-    {
-      "epoch": 0.4028268551236749,
-      "grad_norm": 0.64453125,
-      "learning_rate": 9.932818255432733e-06,
-      "loss": 1.9486,
-      "step": 57
-    },
-    {
-      "epoch": 0.4098939929328622,
-      "grad_norm": 0.7265625,
-      "learning_rate": 9.92794563257143e-06,
-      "loss": 1.7127,
-      "step": 58
-    },
-    {
-      "epoch": 0.4169611307420495,
-      "grad_norm": 0.66796875,
-      "learning_rate": 9.92290371833584e-06,
-      "loss": 2.1642,
-      "step": 59
-    },
-    {
-      "epoch": 0.42402826855123676,
-      "grad_norm": 0.83984375,
-      "learning_rate": 9.91769268593254e-06,
-      "loss": 1.7884,
-      "step": 60
-    },
-    {
-      "epoch": 0.43109540636042404,
-      "grad_norm": 0.68359375,
-      "learning_rate": 9.91231271437788e-06,
-      "loss": 2.1369,
-      "step": 61
-    },
-    {
-      "epoch": 0.4381625441696113,
-      "grad_norm": 0.75390625,
-      "learning_rate": 9.906763988491834e-06,
-      "loss": 2.2394,
-      "step": 62
-    },
-    {
-      "epoch": 0.4452296819787986,
-      "grad_norm": 0.5859375,
-      "learning_rate": 9.901046698891648e-06,
-      "loss": 1.4972,
-      "step": 63
-    },
-    {
-      "epoch": 0.45229681978798586,
-      "grad_norm": 0.96875,
-      "learning_rate": 9.895161041985295e-06,
-      "loss": 1.8555,
-      "step": 64
-    },
-    {
-      "epoch": 0.45936395759717313,
-      "grad_norm": 0.74609375,
-      "learning_rate": 9.889107219964726e-06,
-      "loss": 2.2285,
-      "step": 65
-    },
-    {
-      "epoch": 0.4664310954063604,
-      "grad_norm": 0.6015625,
-      "learning_rate": 9.882885440798928e-06,
-      "loss": 1.6138,
-      "step": 66
-    },
-    {
-      "epoch": 0.4734982332155477,
-      "grad_norm": 0.6171875,
-      "learning_rate": 9.876495918226772e-06,
-      "loss": 1.7915,
-      "step": 67
-    },
-    {
-      "epoch": 0.48056537102473496,
-      "grad_norm": 0.56640625,
-      "learning_rate": 9.869938871749676e-06,
-      "loss": 1.6075,
-      "step": 68
-    },
-    {
-      "epoch": 0.4876325088339223,
-      "grad_norm": 0.6640625,
-      "learning_rate": 9.863214526624065e-06,
-      "loss": 1.9207,
-      "step": 69
-    },
-    {
-      "epoch": 0.49469964664310956,
-      "grad_norm": 0.703125,
-      "learning_rate": 9.856323113853632e-06,
-      "loss": 1.9285,
-      "step": 70
-    },
-    {
-      "epoch": 0.5017667844522968,
-      "grad_norm": 0.68359375,
-      "learning_rate": 9.849264870181393e-06,
-      "loss": 1.9508,
-      "step": 71
-    },
-    {
-      "epoch": 0.508833922261484,
-      "grad_norm": 0.6640625,
-      "learning_rate": 9.842040038081572e-06,
-      "loss": 1.9983,
-      "step": 72
-    },
-    {
-      "epoch": 0.5159010600706714,
-      "grad_norm": 0.5703125,
-      "learning_rate": 9.834648865751254e-06,
-      "loss": 1.6503,
-      "step": 73
-    },
-    {
-      "epoch": 0.5229681978798587,
-      "grad_norm": 1.046875,
-      "learning_rate": 9.827091607101871e-06,
-      "loss": 1.8562,
-      "step": 74
-    },
-    {
-      "epoch": 0.5300353356890459,
-      "grad_norm": 0.78515625,
-      "learning_rate": 9.81936852175047e-06,
-      "loss": 1.5611,
-      "step": 75
-    },
-    {
-      "epoch": 0.5371024734982333,
-      "grad_norm": 0.61328125,
-      "learning_rate": 9.811479875010801e-06,
-      "loss": 1.7828,
-      "step": 76
-    },
-    {
-      "epoch": 0.5441696113074205,
-      "grad_norm": 0.6015625,
-      "learning_rate": 9.803425937884202e-06,
-      "loss": 1.5878,
-      "step": 77
-    },
-    {
-      "epoch": 0.5512367491166078,
-      "grad_norm": 0.76171875,
-      "learning_rate": 9.79520698705028e-06,
-      "loss": 2.0218,
-      "step": 78
-    },
-    {
-      "epoch": 0.558303886925795,
-      "grad_norm": 0.640625,
-      "learning_rate": 9.786823304857424e-06,
-      "loss": 1.4419,
-      "step": 79
-    },
-    {
-      "epoch": 0.5653710247349824,
-      "grad_norm": 1.2265625,
-      "learning_rate": 9.778275179313084e-06,
-      "loss": 1.9871,
-      "step": 80
-    },
-    {
-      "epoch": 0.5724381625441696,
-      "grad_norm": 0.71875,
-      "learning_rate": 9.769562904073896e-06,
-      "loss": 1.9268,
-      "step": 81
-    },
-    {
-      "epoch": 0.5795053003533569,
-      "grad_norm": 0.57421875,
-      "learning_rate": 9.76068677843558e-06,
-      "loss": 1.4848,
-      "step": 82
-    },
-    {
-      "epoch": 0.5865724381625441,
-      "grad_norm": 0.65234375,
-      "learning_rate": 9.751647107322668e-06,
-      "loss": 2.0959,
-      "step": 83
-    },
-    {
-      "epoch": 0.5936395759717314,
-      "grad_norm": 0.74609375,
-      "learning_rate": 9.742444201278022e-06,
-      "loss": 2.3728,
-      "step": 84
-    },
-    {
-      "epoch": 0.6007067137809188,
-      "grad_norm": 0.671875,
-      "learning_rate": 9.733078376452172e-06,
-      "loss": 1.3637,
-      "step": 85
-    },
-    {
-      "epoch": 0.607773851590106,
-      "grad_norm": 0.671875,
-      "learning_rate": 9.723549954592447e-06,
-      "loss": 1.8211,
-      "step": 86
-    },
-    {
-      "epoch": 0.6148409893992933,
-      "grad_norm": 0.64453125,
-      "learning_rate": 9.713859263031928e-06,
-      "loss": 1.9919,
-      "step": 87
-    },
-    {
-      "epoch": 0.6219081272084805,
-      "grad_norm": 0.6015625,
-      "learning_rate": 9.704006634678205e-06,
-      "loss": 1.5786,
-      "step": 88
-    },
-    {
-      "epoch": 0.6289752650176679,
-      "grad_norm": 0.6640625,
-      "learning_rate": 9.693992408001934e-06,
-      "loss": 1.9939,
-      "step": 89
-    },
-    {
-      "epoch": 0.6360424028268551,
-      "grad_norm": 0.60546875,
-      "learning_rate": 9.683816927025212e-06,
-      "loss": 2.1518,
-      "step": 90
-    },
-    {
-      "epoch": 0.6431095406360424,
-      "grad_norm": 0.7578125,
-      "learning_rate": 9.673480541309761e-06,
-      "loss": 2.2444,
-      "step": 91
-    },
-    {
-      "epoch": 0.6501766784452296,
-      "grad_norm": 0.609375,
-      "learning_rate": 9.662983605944918e-06,
-      "loss": 1.9037,
-      "step": 92
-    },
-    {
-      "epoch": 0.657243816254417,
-      "grad_norm": 1.5625,
-      "learning_rate": 9.652326481535434e-06,
-      "loss": 2.3459,
-      "step": 93
-    },
-    {
-      "epoch": 0.6643109540636042,
-      "grad_norm": 0.609375,
-      "learning_rate": 9.64150953418909e-06,
-      "loss": 1.7578,
-      "step": 94
-    },
-    {
-      "epoch": 0.6713780918727915,
-      "grad_norm": 0.6328125,
-      "learning_rate": 9.630533135504118e-06,
-      "loss": 1.5717,
-      "step": 95
-    },
-    {
-      "epoch": 0.6784452296819788,
-      "grad_norm": 0.7109375,
-      "learning_rate": 9.619397662556434e-06,
-      "loss": 1.7722,
-      "step": 96
-    },
-    {
-      "epoch": 0.6855123674911661,
-      "grad_norm": 0.6796875,
-      "learning_rate": 9.608103497886687e-06,
-      "loss": 1.8594,
-      "step": 97
-    },
-    {
-      "epoch": 0.6925795053003534,
-      "grad_norm": 0.66796875,
-      "learning_rate": 9.596651029487116e-06,
-      "loss": 2.1158,
-      "step": 98
-    },
-    {
-      "epoch": 0.6996466431095406,
-      "grad_norm": 0.75,
-      "learning_rate": 9.585040650788222e-06,
-      "loss": 1.2966,
-      "step": 99
-    },
-    {
-      "epoch": 0.7067137809187279,
-      "grad_norm": 1.2890625,
-      "learning_rate": 9.573272760645248e-06,
-      "loss": 2.3551,
-      "step": 100
-    },
-    {
-      "epoch": 0.7137809187279152,
-      "grad_norm": 0.61328125,
-      "learning_rate": 9.561347763324484e-06,
-      "loss": 2.0097,
-      "step": 101
-    },
-    {
-      "epoch": 0.7208480565371025,
-      "grad_norm": 0.6640625,
-      "learning_rate": 9.549266068489377e-06,
-      "loss": 1.7785,
-      "step": 102
-    },
-    {
-      "epoch": 0.7279151943462897,
-      "grad_norm": 0.59765625,
-      "learning_rate": 9.537028091186453e-06,
-      "loss": 1.7432,
-      "step": 103
-    },
-    {
-      "epoch": 0.734982332155477,
-      "grad_norm": 0.57421875,
-      "learning_rate": 9.524634251831064e-06,
-      "loss": 1.9585,
-      "step": 104
-    },
-    {
-      "epoch": 0.7420494699646644,
-      "grad_norm": 0.7890625,
-      "learning_rate": 9.512084976192944e-06,
-      "loss": 1.8571,
-      "step": 105
-    },
-    {
-      "epoch": 0.7491166077738516,
-      "grad_norm": 0.62890625,
-      "learning_rate": 9.499380695381577e-06,
-      "loss": 1.8799,
-      "step": 106
-    },
-    {
-      "epoch": 0.7561837455830389,
-      "grad_norm": 0.7421875,
-      "learning_rate": 9.486521845831403e-06,
-      "loss": 1.8795,
-      "step": 107
-    },
-    {
-      "epoch": 0.7632508833922261,
-      "grad_norm": 0.69140625,
-      "learning_rate": 9.4735088692868e-06,
-      "loss": 1.8043,
-      "step": 108
-    },
-    {
-      "epoch": 0.7703180212014135,
-      "grad_norm": 0.8125,
-      "learning_rate": 9.460342212786933e-06,
-      "loss": 2.1479,
-      "step": 109
-    },
-    {
-      "epoch": 0.7773851590106007,
-      "grad_norm": 0.7890625,
-      "learning_rate": 9.447022328650382e-06,
-      "loss": 1.7199,
-      "step": 110
-    },
-    {
-      "epoch": 0.784452296819788,
-      "grad_norm": 0.80078125,
-      "learning_rate": 9.43354967445961e-06,
-      "loss": 2.1058,
-      "step": 111
-    },
-    {
-      "epoch": 0.7915194346289752,
-      "grad_norm": 0.828125,
-      "learning_rate": 9.419924713045234e-06,
-      "loss": 1.9554,
-      "step": 112
-    },
-    {
-      "epoch": 0.7985865724381626,
-      "grad_norm": 0.64453125,
-      "learning_rate": 9.406147912470142e-06,
-      "loss": 1.3284,
-      "step": 113
-    },
-    {
-      "epoch": 0.8056537102473498,
-      "grad_norm": 0.66015625,
-      "learning_rate": 9.392219746013399e-06,
-      "loss": 1.8721,
-      "step": 114
-    },
-    {
-      "epoch": 0.8127208480565371,
-      "grad_norm": 0.5703125,
-      "learning_rate": 9.378140692153991e-06,
-      "loss": 1.8162,
-      "step": 115
-    },
-    {
-      "epoch": 0.8197879858657244,
-      "grad_norm": 0.6171875,
-      "learning_rate": 9.363911234554394e-06,
-      "loss": 2.1554,
-      "step": 116
-    },
-    {
-      "epoch": 0.8268551236749117,
-      "grad_norm": 0.703125,
-      "learning_rate": 9.349531862043952e-06,
-      "loss": 2.1176,
-      "step": 117
-    },
-    {
-      "epoch": 0.833922261484099,
-      "grad_norm": 0.609375,
-      "learning_rate": 9.335003068602087e-06,
-      "loss": 1.7494,
-      "step": 118
-    },
-    {
-      "epoch": 0.8409893992932862,
-      "grad_norm": 0.62109375,
-      "learning_rate": 9.320325353341325e-06,
-      "loss": 1.8479,
-      "step": 119
-    },
-    {
-      "epoch": 0.8480565371024735,
-      "grad_norm": 0.6328125,
-      "learning_rate": 9.305499220490162e-06,
-      "loss": 1.5816,
-      "step": 120
-    },
-    {
-      "epoch": 0.8551236749116607,
-      "grad_norm": 0.70703125,
-      "learning_rate": 9.290525179375722e-06,
-      "loss": 2.1121,
-      "step": 121
-    },
-    {
-      "epoch": 0.8621908127208481,
-      "grad_norm": 0.67578125,
-      "learning_rate": 9.275403744406282e-06,
-      "loss": 1.9516,
-      "step": 122
-    },
-    {
-      "epoch": 0.8692579505300353,
-      "grad_norm": 0.609375,
-      "learning_rate": 9.260135435053583e-06,
-      "loss": 1.8081,
-      "step": 123
-    },
-    {
-      "epoch": 0.8763250883392226,
-      "grad_norm": 0.62890625,
-      "learning_rate": 9.244720775834993e-06,
-      "loss": 2.2066,
-      "step": 124
-    },
-    {
-      "epoch": 0.8833922261484098,
-      "grad_norm": 0.80859375,
-      "learning_rate": 9.229160296295488e-06,
-      "loss": 2.0408,
-      "step": 125
-    },
-    {
-      "epoch": 0.8904593639575972,
-      "grad_norm": 0.6875,
-      "learning_rate": 9.213454530989454e-06,
-      "loss": 1.7211,
-      "step": 126
-    },
-    {
-      "epoch": 0.8975265017667845,
-      "grad_norm": 0.58984375,
-      "learning_rate": 9.197604019462334e-06,
-      "loss": 0.905,
-      "step": 127
-    },
-    {
-      "epoch": 0.9045936395759717,
-      "grad_norm": 0.65234375,
-      "learning_rate": 9.18160930623208e-06,
-      "loss": 1.4443,
-      "step": 128
-    },
-    {
-      "epoch": 0.911660777385159,
-      "grad_norm": 0.72265625,
-      "learning_rate": 9.165470940770458e-06,
-      "loss": 1.8498,
-      "step": 129
-    },
-    {
-      "epoch": 0.9187279151943463,
-      "grad_norm": 0.6875,
-      "learning_rate": 9.149189477484169e-06,
-      "loss": 1.7645,
-      "step": 130
-    },
-    {
-      "epoch": 0.9257950530035336,
-      "grad_norm": 0.59375,
-      "learning_rate": 9.132765475695795e-06,
-      "loss": 1.7509,
-      "step": 131
-    },
-    {
-      "epoch": 0.9328621908127208,
-      "grad_norm": 0.61328125,
-      "learning_rate": 9.116199499624596e-06,
-      "loss": 2.2509,
-      "step": 132
-    },
-    {
-      "epoch": 0.9399293286219081,
-      "grad_norm": 0.765625,
-      "learning_rate": 9.099492118367123e-06,
-      "loss": 1.5412,
-      "step": 133
-    },
-    {
-      "epoch": 0.9469964664310954,
-      "grad_norm": 0.609375,
-      "learning_rate": 9.082643905877665e-06,
-      "loss": 1.5065,
-      "step": 134
-    },
-    {
-      "epoch": 0.9540636042402827,
-      "grad_norm": 0.625,
-      "learning_rate": 9.065655440948536e-06,
-      "loss": 1.8347,
-      "step": 135
-    },
-    {
-      "epoch": 0.9611307420494699,
-      "grad_norm": 0.765625,
-      "learning_rate": 9.048527307190182e-06,
-      "loss": 2.1884,
-      "step": 136
-    },
-    {
-      "epoch": 0.9681978798586572,
-      "grad_norm": 0.62109375,
-      "learning_rate": 9.03126009301115e-06,
-      "loss": 1.7727,
-      "step": 137
-    },
-    {
-      "epoch": 0.9752650176678446,
-      "grad_norm": 0.61328125,
-      "learning_rate": 9.013854391597856e-06,
-      "loss": 1.7151,
-      "step": 138
-    },
-    {
-      "epoch": 0.9823321554770318,
-      "grad_norm": 0.66796875,
-      "learning_rate": 8.996310800894215e-06,
-      "loss": 1.992,
-      "step": 139
-    },
-    {
-      "epoch": 0.9893992932862191,
-      "grad_norm": 0.69140625,
-      "learning_rate": 8.978629923581104e-06,
-      "loss": 2.2281,
-      "step": 140
-    },
-    {
-      "epoch": 0.9964664310954063,
-      "grad_norm": 1.15625,
-      "learning_rate": 8.960812367055646e-06,
-      "loss": 2.874,
-      "step": 141
-    }
-  ],
-  "logging_steps": 1,
-  "max_steps": 564,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
-  "save_steps": 141,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 4.4279482344800256e+17,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-141/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:406982d99a22da9752c26535cc9f5894b29792d701bc3fe309a0db5d133444df
-size 6840