Delete checkpoint-228

checkpoint-228/added_tokens.json

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

checkpoint-228/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-228/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-228/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-228/model-00001-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:90262fb12654cd0f0fa65c06486ad9ab261bfc8dfed43a6191fedbafd4189a67
-size 4983077832

checkpoint-228/model-00002-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:75672dfb25c87d01482b8ad04da1cb099a3d0b21a802f705cd574fd6448fa4d4
-size 3842234168

checkpoint-228/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-228/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:941af5b7b2b301f7de1f99119b4f89399bf3b35be2517cbb3a6d33bc6c750da2
-size 11466962878

checkpoint-228/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b1a97db8e41139aa1239ba7fb79ddeb0af5998c6305a440c1fe182e6ad02f2f5
-size 14244

checkpoint-228/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:09529ec298915bd02a86b1029ceb1b7af7fec86183593774d24da81d03b08254
-size 1064

checkpoint-228/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-228/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-228/trainer_state.json

@@ -1,1630 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.9868995633187772,
-  "eval_steps": 500,
-  "global_step": 228,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.008733624454148471,
-      "grad_norm": 2.234375,
-      "learning_rate": 0.0,
-      "loss": 2.578,
-      "step": 1
-    },
-    {
-      "epoch": 0.017467248908296942,
-      "grad_norm": 2.515625,
-      "learning_rate": 4.5454545454545457e-07,
-      "loss": 2.6324,
-      "step": 2
-    },
-    {
-      "epoch": 0.026200873362445413,
-      "grad_norm": 2.546875,
-      "learning_rate": 9.090909090909091e-07,
-      "loss": 2.6563,
-      "step": 3
-    },
-    {
-      "epoch": 0.034934497816593885,
-      "grad_norm": 2.21875,
-      "learning_rate": 1.3636363636363636e-06,
-      "loss": 2.5986,
-      "step": 4
-    },
-    {
-      "epoch": 0.043668122270742356,
-      "grad_norm": 2.40625,
-      "learning_rate": 1.8181818181818183e-06,
-      "loss": 2.6456,
-      "step": 5
-    },
-    {
-      "epoch": 0.05240174672489083,
-      "grad_norm": 2.28125,
-      "learning_rate": 2.2727272727272728e-06,
-      "loss": 2.638,
-      "step": 6
-    },
-    {
-      "epoch": 0.0611353711790393,
-      "grad_norm": 2.421875,
-      "learning_rate": 2.7272727272727272e-06,
-      "loss": 2.6678,
-      "step": 7
-    },
-    {
-      "epoch": 0.06986899563318777,
-      "grad_norm": 2.328125,
-      "learning_rate": 3.181818181818182e-06,
-      "loss": 2.6304,
-      "step": 8
-    },
-    {
-      "epoch": 0.07860262008733625,
-      "grad_norm": 2.046875,
-      "learning_rate": 3.6363636363636366e-06,
-      "loss": 2.6253,
-      "step": 9
-    },
-    {
-      "epoch": 0.08733624454148471,
-      "grad_norm": 2.109375,
-      "learning_rate": 4.0909090909090915e-06,
-      "loss": 2.6161,
-      "step": 10
-    },
-    {
-      "epoch": 0.09606986899563319,
-      "grad_norm": 2.015625,
-      "learning_rate": 4.5454545454545455e-06,
-      "loss": 2.6971,
-      "step": 11
-    },
-    {
-      "epoch": 0.10480349344978165,
-      "grad_norm": 1.75,
-      "learning_rate": 5e-06,
-      "loss": 2.5767,
-      "step": 12
-    },
-    {
-      "epoch": 0.11353711790393013,
-      "grad_norm": 1.703125,
-      "learning_rate": 5.4545454545454545e-06,
-      "loss": 2.5748,
-      "step": 13
-    },
-    {
-      "epoch": 0.1222707423580786,
-      "grad_norm": 1.6328125,
-      "learning_rate": 5.90909090909091e-06,
-      "loss": 2.5845,
-      "step": 14
-    },
-    {
-      "epoch": 0.13100436681222707,
-      "grad_norm": 1.5234375,
-      "learning_rate": 6.363636363636364e-06,
-      "loss": 2.6236,
-      "step": 15
-    },
-    {
-      "epoch": 0.13973799126637554,
-      "grad_norm": 1.3359375,
-      "learning_rate": 6.818181818181818e-06,
-      "loss": 2.6045,
-      "step": 16
-    },
-    {
-      "epoch": 0.14847161572052403,
-      "grad_norm": 1.296875,
-      "learning_rate": 7.272727272727273e-06,
-      "loss": 2.617,
-      "step": 17
-    },
-    {
-      "epoch": 0.1572052401746725,
-      "grad_norm": 1.15625,
-      "learning_rate": 7.727272727272727e-06,
-      "loss": 2.5447,
-      "step": 18
-    },
-    {
-      "epoch": 0.16593886462882096,
-      "grad_norm": 1.1796875,
-      "learning_rate": 8.181818181818183e-06,
-      "loss": 2.6597,
-      "step": 19
-    },
-    {
-      "epoch": 0.17467248908296942,
-      "grad_norm": 1.1328125,
-      "learning_rate": 8.636363636363637e-06,
-      "loss": 2.5515,
-      "step": 20
-    },
-    {
-      "epoch": 0.18340611353711792,
-      "grad_norm": 1.140625,
-      "learning_rate": 9.090909090909091e-06,
-      "loss": 2.5699,
-      "step": 21
-    },
-    {
-      "epoch": 0.19213973799126638,
-      "grad_norm": 1.1015625,
-      "learning_rate": 9.545454545454547e-06,
-      "loss": 2.6027,
-      "step": 22
-    },
-    {
-      "epoch": 0.20087336244541484,
-      "grad_norm": 1.109375,
-      "learning_rate": 1e-05,
-      "loss": 2.5589,
-      "step": 23
-    },
-    {
-      "epoch": 0.2096069868995633,
-      "grad_norm": 1.0859375,
-      "learning_rate": 9.999869003890174e-06,
-      "loss": 2.5869,
-      "step": 24
-    },
-    {
-      "epoch": 0.2183406113537118,
-      "grad_norm": 1.078125,
-      "learning_rate": 9.999476022424688e-06,
-      "loss": 2.5414,
-      "step": 25
-    },
-    {
-      "epoch": 0.22707423580786026,
-      "grad_norm": 1.03125,
-      "learning_rate": 9.998821076195158e-06,
-      "loss": 2.6005,
-      "step": 26
-    },
-    {
-      "epoch": 0.23580786026200873,
-      "grad_norm": 1.078125,
-      "learning_rate": 9.997904199519748e-06,
-      "loss": 2.5769,
-      "step": 27
-    },
-    {
-      "epoch": 0.2445414847161572,
-      "grad_norm": 1.0703125,
-      "learning_rate": 9.996725440441368e-06,
-      "loss": 2.6084,
-      "step": 28
-    },
-    {
-      "epoch": 0.25327510917030566,
-      "grad_norm": 0.98828125,
-      "learning_rate": 9.995284860725162e-06,
-      "loss": 2.6237,
-      "step": 29
-    },
-    {
-      "epoch": 0.26200873362445415,
-      "grad_norm": 0.9453125,
-      "learning_rate": 9.993582535855265e-06,
-      "loss": 2.577,
-      "step": 30
-    },
-    {
-      "epoch": 0.27074235807860264,
-      "grad_norm": 0.953125,
-      "learning_rate": 9.991618555030848e-06,
-      "loss": 2.591,
-      "step": 31
-    },
-    {
-      "epoch": 0.2794759825327511,
-      "grad_norm": 0.94921875,
-      "learning_rate": 9.989393021161455e-06,
-      "loss": 2.5533,
-      "step": 32
-    },
-    {
-      "epoch": 0.28820960698689957,
-      "grad_norm": 0.99609375,
-      "learning_rate": 9.986906050861595e-06,
-      "loss": 2.5694,
-      "step": 33
-    },
-    {
-      "epoch": 0.29694323144104806,
-      "grad_norm": 0.9765625,
-      "learning_rate": 9.98415777444464e-06,
-      "loss": 2.53,
-      "step": 34
-    },
-    {
-      "epoch": 0.3056768558951965,
-      "grad_norm": 0.9296875,
-      "learning_rate": 9.981148335916e-06,
-      "loss": 2.5486,
-      "step": 35
-    },
-    {
-      "epoch": 0.314410480349345,
-      "grad_norm": 0.92578125,
-      "learning_rate": 9.977877892965572e-06,
-      "loss": 2.5649,
-      "step": 36
-    },
-    {
-      "epoch": 0.3231441048034934,
-      "grad_norm": 0.9609375,
-      "learning_rate": 9.974346616959476e-06,
-      "loss": 2.6342,
-      "step": 37
-    },
-    {
-      "epoch": 0.3318777292576419,
-      "grad_norm": 0.9140625,
-      "learning_rate": 9.970554692931081e-06,
-      "loss": 2.5869,
-      "step": 38
-    },
-    {
-      "epoch": 0.3406113537117904,
-      "grad_norm": 0.90234375,
-      "learning_rate": 9.966502319571303e-06,
-      "loss": 2.5639,
-      "step": 39
-    },
-    {
-      "epoch": 0.34934497816593885,
-      "grad_norm": 0.9375,
-      "learning_rate": 9.962189709218202e-06,
-      "loss": 2.5443,
-      "step": 40
-    },
-    {
-      "epoch": 0.35807860262008734,
-      "grad_norm": 0.9453125,
-      "learning_rate": 9.95761708784585e-06,
-      "loss": 2.5412,
-      "step": 41
-    },
-    {
-      "epoch": 0.36681222707423583,
-      "grad_norm": 0.8828125,
-      "learning_rate": 9.952784695052494e-06,
-      "loss": 2.5115,
-      "step": 42
-    },
-    {
-      "epoch": 0.37554585152838427,
-      "grad_norm": 0.99609375,
-      "learning_rate": 9.94769278404799e-06,
-      "loss": 2.4547,
-      "step": 43
-    },
-    {
-      "epoch": 0.38427947598253276,
-      "grad_norm": 0.90234375,
-      "learning_rate": 9.942341621640558e-06,
-      "loss": 2.5528,
-      "step": 44
-    },
-    {
-      "epoch": 0.3930131004366812,
-      "grad_norm": 0.96484375,
-      "learning_rate": 9.936731488222776e-06,
-      "loss": 2.5629,
-      "step": 45
-    },
-    {
-      "epoch": 0.4017467248908297,
-      "grad_norm": 0.89453125,
-      "learning_rate": 9.930862677756912e-06,
-      "loss": 2.5632,
-      "step": 46
-    },
-    {
-      "epoch": 0.4104803493449782,
-      "grad_norm": 0.890625,
-      "learning_rate": 9.924735497759497e-06,
-      "loss": 2.5625,
-      "step": 47
-    },
-    {
-      "epoch": 0.4192139737991266,
-      "grad_norm": 0.875,
-      "learning_rate": 9.918350269285228e-06,
-      "loss": 2.5522,
-      "step": 48
-    },
-    {
-      "epoch": 0.4279475982532751,
-      "grad_norm": 0.90234375,
-      "learning_rate": 9.911707326910145e-06,
-      "loss": 2.6349,
-      "step": 49
-    },
-    {
-      "epoch": 0.4366812227074236,
-      "grad_norm": 0.91015625,
-      "learning_rate": 9.904807018714088e-06,
-      "loss": 2.6174,
-      "step": 50
-    },
-    {
-      "epoch": 0.44541484716157204,
-      "grad_norm": 0.89453125,
-      "learning_rate": 9.897649706262474e-06,
-      "loss": 2.5732,
-      "step": 51
-    },
-    {
-      "epoch": 0.45414847161572053,
-      "grad_norm": 0.91796875,
-      "learning_rate": 9.890235764587332e-06,
-      "loss": 2.6071,
-      "step": 52
-    },
-    {
-      "epoch": 0.462882096069869,
-      "grad_norm": 0.89453125,
-      "learning_rate": 9.882565582167673e-06,
-      "loss": 2.5587,
-      "step": 53
-    },
-    {
-      "epoch": 0.47161572052401746,
-      "grad_norm": 0.88671875,
-      "learning_rate": 9.874639560909118e-06,
-      "loss": 2.5676,
-      "step": 54
-    },
-    {
-      "epoch": 0.48034934497816595,
-      "grad_norm": 0.890625,
-      "learning_rate": 9.866458116122852e-06,
-      "loss": 2.515,
-      "step": 55
-    },
-    {
-      "epoch": 0.4890829694323144,
-      "grad_norm": 0.8984375,
-      "learning_rate": 9.858021676503846e-06,
-      "loss": 2.5355,
-      "step": 56
-    },
-    {
-      "epoch": 0.4978165938864629,
-      "grad_norm": 0.90234375,
-      "learning_rate": 9.849330684108409e-06,
-      "loss": 2.5798,
-      "step": 57
-    },
-    {
-      "epoch": 0.5065502183406113,
-      "grad_norm": 0.87890625,
-      "learning_rate": 9.840385594331022e-06,
-      "loss": 2.5391,
-      "step": 58
-    },
-    {
-      "epoch": 0.5152838427947598,
-      "grad_norm": 0.90625,
-      "learning_rate": 9.831186875880467e-06,
-      "loss": 2.521,
-      "step": 59
-    },
-    {
-      "epoch": 0.5240174672489083,
-      "grad_norm": 0.91796875,
-      "learning_rate": 9.82173501075528e-06,
-      "loss": 2.5553,
-      "step": 60
-    },
-    {
-      "epoch": 0.5327510917030568,
-      "grad_norm": 0.890625,
-      "learning_rate": 9.812030494218484e-06,
-      "loss": 2.6096,
-      "step": 61
-    },
-    {
-      "epoch": 0.5414847161572053,
-      "grad_norm": 0.88671875,
-      "learning_rate": 9.802073834771642e-06,
-      "loss": 2.5513,
-      "step": 62
-    },
-    {
-      "epoch": 0.5502183406113537,
-      "grad_norm": 0.96484375,
-      "learning_rate": 9.79186555412822e-06,
-      "loss": 2.6127,
-      "step": 63
-    },
-    {
-      "epoch": 0.5589519650655022,
-      "grad_norm": 0.90234375,
-      "learning_rate": 9.781406187186237e-06,
-      "loss": 2.5172,
-      "step": 64
-    },
-    {
-      "epoch": 0.5676855895196506,
-      "grad_norm": 0.87890625,
-      "learning_rate": 9.770696282000245e-06,
-      "loss": 2.5562,
-      "step": 65
-    },
-    {
-      "epoch": 0.5764192139737991,
-      "grad_norm": 0.88671875,
-      "learning_rate": 9.759736399752611e-06,
-      "loss": 2.5538,
-      "step": 66
-    },
-    {
-      "epoch": 0.5851528384279476,
-      "grad_norm": 0.89453125,
-      "learning_rate": 9.748527114724111e-06,
-      "loss": 2.5661,
-      "step": 67
-    },
-    {
-      "epoch": 0.5938864628820961,
-      "grad_norm": 0.91796875,
-      "learning_rate": 9.737069014263837e-06,
-      "loss": 2.6247,
-      "step": 68
-    },
-    {
-      "epoch": 0.6026200873362445,
-      "grad_norm": 0.9296875,
-      "learning_rate": 9.725362698758425e-06,
-      "loss": 2.5432,
-      "step": 69
-    },
-    {
-      "epoch": 0.611353711790393,
-      "grad_norm": 0.890625,
-      "learning_rate": 9.713408781600588e-06,
-      "loss": 2.51,
-      "step": 70
-    },
-    {
-      "epoch": 0.6200873362445415,
-      "grad_norm": 0.8828125,
-      "learning_rate": 9.701207889156989e-06,
-      "loss": 2.5114,
-      "step": 71
-    },
-    {
-      "epoch": 0.62882096069869,
-      "grad_norm": 0.9296875,
-      "learning_rate": 9.688760660735403e-06,
-      "loss": 2.5707,
-      "step": 72
-    },
-    {
-      "epoch": 0.6375545851528385,
-      "grad_norm": 0.91015625,
-      "learning_rate": 9.676067748551232e-06,
-      "loss": 2.579,
-      "step": 73
-    },
-    {
-      "epoch": 0.6462882096069869,
-      "grad_norm": 0.91015625,
-      "learning_rate": 9.663129817693323e-06,
-      "loss": 2.5844,
-      "step": 74
-    },
-    {
-      "epoch": 0.6550218340611353,
-      "grad_norm": 0.9296875,
-      "learning_rate": 9.64994754608912e-06,
-      "loss": 2.5768,
-      "step": 75
-    },
-    {
-      "epoch": 0.6637554585152838,
-      "grad_norm": 0.890625,
-      "learning_rate": 9.636521624469144e-06,
-      "loss": 2.5568,
-      "step": 76
-    },
-    {
-      "epoch": 0.6724890829694323,
-      "grad_norm": 0.91796875,
-      "learning_rate": 9.622852756330797e-06,
-      "loss": 2.5348,
-      "step": 77
-    },
-    {
-      "epoch": 0.6812227074235808,
-      "grad_norm": 0.88671875,
-      "learning_rate": 9.608941657901496e-06,
-      "loss": 2.5221,
-      "step": 78
-    },
-    {
-      "epoch": 0.6899563318777293,
-      "grad_norm": 0.921875,
-      "learning_rate": 9.594789058101154e-06,
-      "loss": 2.6385,
-      "step": 79
-    },
-    {
-      "epoch": 0.6986899563318777,
-      "grad_norm": 0.91796875,
-      "learning_rate": 9.580395698503979e-06,
-      "loss": 2.5107,
-      "step": 80
-    },
-    {
-      "epoch": 0.7074235807860262,
-      "grad_norm": 0.953125,
-      "learning_rate": 9.565762333299616e-06,
-      "loss": 2.5751,
-      "step": 81
-    },
-    {
-      "epoch": 0.7161572052401747,
-      "grad_norm": 0.93359375,
-      "learning_rate": 9.550889729253631e-06,
-      "loss": 2.6106,
-      "step": 82
-    },
-    {
-      "epoch": 0.7248908296943232,
-      "grad_norm": 0.921875,
-      "learning_rate": 9.535778665667334e-06,
-      "loss": 2.6177,
-      "step": 83
-    },
-    {
-      "epoch": 0.7336244541484717,
-      "grad_norm": 1.0,
-      "learning_rate": 9.520429934336944e-06,
-      "loss": 2.5421,
-      "step": 84
-    },
-    {
-      "epoch": 0.74235807860262,
-      "grad_norm": 0.90234375,
-      "learning_rate": 9.504844339512096e-06,
-      "loss": 2.6234,
-      "step": 85
-    },
-    {
-      "epoch": 0.7510917030567685,
-      "grad_norm": 0.91015625,
-      "learning_rate": 9.48902269785371e-06,
-      "loss": 2.5791,
-      "step": 86
-    },
-    {
-      "epoch": 0.759825327510917,
-      "grad_norm": 0.8671875,
-      "learning_rate": 9.472965838391187e-06,
-      "loss": 2.5052,
-      "step": 87
-    },
-    {
-      "epoch": 0.7685589519650655,
-      "grad_norm": 0.984375,
-      "learning_rate": 9.456674602478975e-06,
-      "loss": 2.5445,
-      "step": 88
-    },
-    {
-      "epoch": 0.777292576419214,
-      "grad_norm": 1.1953125,
-      "learning_rate": 9.44014984375249e-06,
-      "loss": 2.5956,
-      "step": 89
-    },
-    {
-      "epoch": 0.7860262008733624,
-      "grad_norm": 0.87109375,
-      "learning_rate": 9.423392428083374e-06,
-      "loss": 2.5261,
-      "step": 90
-    },
-    {
-      "epoch": 0.7947598253275109,
-      "grad_norm": 0.89453125,
-      "learning_rate": 9.406403233534134e-06,
-      "loss": 2.5626,
-      "step": 91
-    },
-    {
-      "epoch": 0.8034934497816594,
-      "grad_norm": 0.89453125,
-      "learning_rate": 9.389183150312124e-06,
-      "loss": 2.5228,
-      "step": 92
-    },
-    {
-      "epoch": 0.8122270742358079,
-      "grad_norm": 0.875,
-      "learning_rate": 9.371733080722911e-06,
-      "loss": 2.5494,
-      "step": 93
-    },
-    {
-      "epoch": 0.8209606986899564,
-      "grad_norm": 0.93359375,
-      "learning_rate": 9.354053939122988e-06,
-      "loss": 2.6738,
-      "step": 94
-    },
-    {
-      "epoch": 0.8296943231441049,
-      "grad_norm": 0.91015625,
-      "learning_rate": 9.33614665187187e-06,
-      "loss": 2.5862,
-      "step": 95
-    },
-    {
-      "epoch": 0.8384279475982532,
-      "grad_norm": 0.91015625,
-      "learning_rate": 9.318012157283533e-06,
-      "loss": 2.57,
-      "step": 96
-    },
-    {
-      "epoch": 0.8471615720524017,
-      "grad_norm": 0.96875,
-      "learning_rate": 9.299651405577286e-06,
-      "loss": 2.6046,
-      "step": 97
-    },
-    {
-      "epoch": 0.8558951965065502,
-      "grad_norm": 0.9140625,
-      "learning_rate": 9.28106535882794e-06,
-      "loss": 2.5911,
-      "step": 98
-    },
-    {
-      "epoch": 0.8646288209606987,
-      "grad_norm": 0.90234375,
-      "learning_rate": 9.262254990915427e-06,
-      "loss": 2.5898,
-      "step": 99
-    },
-    {
-      "epoch": 0.8733624454148472,
-      "grad_norm": 0.93359375,
-      "learning_rate": 9.243221287473755e-06,
-      "loss": 2.6268,
-      "step": 100
-    },
-    {
-      "epoch": 0.8820960698689956,
-      "grad_norm": 0.91015625,
-      "learning_rate": 9.223965245839367e-06,
-      "loss": 2.5823,
-      "step": 101
-    },
-    {
-      "epoch": 0.8908296943231441,
-      "grad_norm": 0.91796875,
-      "learning_rate": 9.20448787499888e-06,
-      "loss": 2.6937,
-      "step": 102
-    },
-    {
-      "epoch": 0.8995633187772926,
-      "grad_norm": 0.9296875,
-      "learning_rate": 9.184790195536217e-06,
-      "loss": 2.5609,
-      "step": 103
-    },
-    {
-      "epoch": 0.9082969432314411,
-      "grad_norm": 0.91015625,
-      "learning_rate": 9.164873239579133e-06,
-      "loss": 2.5716,
-      "step": 104
-    },
-    {
-      "epoch": 0.9170305676855895,
-      "grad_norm": 0.99609375,
-      "learning_rate": 9.144738050745129e-06,
-      "loss": 2.5099,
-      "step": 105
-    },
-    {
-      "epoch": 0.925764192139738,
-      "grad_norm": 0.91015625,
-      "learning_rate": 9.124385684086762e-06,
-      "loss": 2.5131,
-      "step": 106
-    },
-    {
-      "epoch": 0.9344978165938864,
-      "grad_norm": 1.015625,
-      "learning_rate": 9.103817206036383e-06,
-      "loss": 2.5407,
-      "step": 107
-    },
-    {
-      "epoch": 0.9432314410480349,
-      "grad_norm": 0.9609375,
-      "learning_rate": 9.08303369435023e-06,
-      "loss": 2.5364,
-      "step": 108
-    },
-    {
-      "epoch": 0.9519650655021834,
-      "grad_norm": 0.9296875,
-      "learning_rate": 9.062036238051978e-06,
-      "loss": 2.6053,
-      "step": 109
-    },
-    {
-      "epoch": 0.9606986899563319,
-      "grad_norm": 0.9296875,
-      "learning_rate": 9.040825937375664e-06,
-      "loss": 2.563,
-      "step": 110
-    },
-    {
-      "epoch": 0.9694323144104804,
-      "grad_norm": 0.9375,
-      "learning_rate": 9.019403903708036e-06,
-      "loss": 2.5744,
-      "step": 111
-    },
-    {
-      "epoch": 0.9781659388646288,
-      "grad_norm": 0.93359375,
-      "learning_rate": 8.997771259530324e-06,
-      "loss": 2.5768,
-      "step": 112
-    },
-    {
-      "epoch": 0.9868995633187773,
-      "grad_norm": 0.96484375,
-      "learning_rate": 8.975929138359423e-06,
-      "loss": 2.577,
-      "step": 113
-    },
-    {
-      "epoch": 0.9956331877729258,
-      "grad_norm": 0.92578125,
-      "learning_rate": 8.953878684688492e-06,
-      "loss": 2.6206,
-      "step": 114
-    },
-    {
-      "epoch": 1.0,
-      "grad_norm": 1.8828125,
-      "learning_rate": 8.931621053926998e-06,
-      "loss": 2.5724,
-      "step": 115
-    },
-    {
-      "epoch": 1.0087336244541485,
-      "grad_norm": 0.87890625,
-      "learning_rate": 8.90915741234015e-06,
-      "loss": 2.4993,
-      "step": 116
-    },
-    {
-      "epoch": 1.017467248908297,
-      "grad_norm": 0.9296875,
-      "learning_rate": 8.886488936987817e-06,
-      "loss": 2.5537,
-      "step": 117
-    },
-    {
-      "epoch": 1.0262008733624455,
-      "grad_norm": 0.93359375,
-      "learning_rate": 8.863616815662833e-06,
-      "loss": 2.6468,
-      "step": 118
-    },
-    {
-      "epoch": 1.034934497816594,
-      "grad_norm": 0.91796875,
-      "learning_rate": 8.840542246828763e-06,
-      "loss": 2.5739,
-      "step": 119
-    },
-    {
-      "epoch": 1.0436681222707425,
-      "grad_norm": 0.96484375,
-      "learning_rate": 8.817266439557109e-06,
-      "loss": 2.5705,
-      "step": 120
-    },
-    {
-      "epoch": 1.0524017467248907,
-      "grad_norm": 0.89453125,
-      "learning_rate": 8.793790613463956e-06,
-      "loss": 2.587,
-      "step": 121
-    },
-    {
-      "epoch": 1.0611353711790392,
-      "grad_norm": 0.88671875,
-      "learning_rate": 8.770115998646057e-06,
-      "loss": 2.522,
-      "step": 122
-    },
-    {
-      "epoch": 1.0698689956331877,
-      "grad_norm": 0.91015625,
-      "learning_rate": 8.746243835616392e-06,
-      "loss": 2.5717,
-      "step": 123
-    },
-    {
-      "epoch": 1.0786026200873362,
-      "grad_norm": 0.92578125,
-      "learning_rate": 8.722175375239157e-06,
-      "loss": 2.5287,
-      "step": 124
-    },
-    {
-      "epoch": 1.0873362445414847,
-      "grad_norm": 0.8828125,
-      "learning_rate": 8.697911878664222e-06,
-      "loss": 2.4822,
-      "step": 125
-    },
-    {
-      "epoch": 1.0960698689956332,
-      "grad_norm": 0.9296875,
-      "learning_rate": 8.673454617261054e-06,
-      "loss": 2.5232,
-      "step": 126
-    },
-    {
-      "epoch": 1.1048034934497817,
-      "grad_norm": 0.87890625,
-      "learning_rate": 8.648804872552092e-06,
-      "loss": 2.5506,
-      "step": 127
-    },
-    {
-      "epoch": 1.1135371179039302,
-      "grad_norm": 0.8984375,
-      "learning_rate": 8.6239639361456e-06,
-      "loss": 2.6104,
-      "step": 128
-    },
-    {
-      "epoch": 1.1222707423580787,
-      "grad_norm": 0.95703125,
-      "learning_rate": 8.598933109667995e-06,
-      "loss": 2.642,
-      "step": 129
-    },
-    {
-      "epoch": 1.1310043668122272,
-      "grad_norm": 0.90625,
-      "learning_rate": 8.573713704695633e-06,
-      "loss": 2.5569,
-      "step": 130
-    },
-    {
-      "epoch": 1.1397379912663754,
-      "grad_norm": 0.91796875,
-      "learning_rate": 8.548307042686093e-06,
-      "loss": 2.567,
-      "step": 131
-    },
-    {
-      "epoch": 1.1484716157205241,
-      "grad_norm": 0.90625,
-      "learning_rate": 8.522714454908926e-06,
-      "loss": 2.5177,
-      "step": 132
-    },
-    {
-      "epoch": 1.1572052401746724,
-      "grad_norm": 0.91796875,
-      "learning_rate": 8.496937282375912e-06,
-      "loss": 2.5793,
-      "step": 133
-    },
-    {
-      "epoch": 1.165938864628821,
-      "grad_norm": 0.8984375,
-      "learning_rate": 8.470976875770776e-06,
-      "loss": 2.543,
-      "step": 134
-    },
-    {
-      "epoch": 1.1746724890829694,
-      "grad_norm": 0.90625,
-      "learning_rate": 8.444834595378434e-06,
-      "loss": 2.5375,
-      "step": 135
-    },
-    {
-      "epoch": 1.1834061135371179,
-      "grad_norm": 0.92578125,
-      "learning_rate": 8.418511811013694e-06,
-      "loss": 2.5851,
-      "step": 136
-    },
-    {
-      "epoch": 1.1921397379912664,
-      "grad_norm": 0.91796875,
-      "learning_rate": 8.3920099019495e-06,
-      "loss": 2.6014,
-      "step": 137
-    },
-    {
-      "epoch": 1.2008733624454149,
-      "grad_norm": 1.0078125,
-      "learning_rate": 8.365330256844647e-06,
-      "loss": 2.5553,
-      "step": 138
-    },
-    {
-      "epoch": 1.2096069868995634,
-      "grad_norm": 0.91796875,
-      "learning_rate": 8.33847427367102e-06,
-      "loss": 2.5817,
-      "step": 139
-    },
-    {
-      "epoch": 1.2183406113537119,
-      "grad_norm": 0.9609375,
-      "learning_rate": 8.311443359640353e-06,
-      "loss": 2.5187,
-      "step": 140
-    },
-    {
-      "epoch": 1.2270742358078603,
-      "grad_norm": 0.921875,
-      "learning_rate": 8.284238931130476e-06,
-      "loss": 2.5306,
-      "step": 141
-    },
-    {
-      "epoch": 1.2358078602620086,
-      "grad_norm": 0.91796875,
-      "learning_rate": 8.256862413611113e-06,
-      "loss": 2.56,
-      "step": 142
-    },
-    {
-      "epoch": 1.244541484716157,
-      "grad_norm": 0.953125,
-      "learning_rate": 8.229315241569177e-06,
-      "loss": 2.5076,
-      "step": 143
-    },
-    {
-      "epoch": 1.2532751091703056,
-      "grad_norm": 0.94921875,
-      "learning_rate": 8.201598858433625e-06,
-      "loss": 2.5798,
-      "step": 144
-    },
-    {
-      "epoch": 1.262008733624454,
-      "grad_norm": 0.8671875,
-      "learning_rate": 8.173714716499801e-06,
-      "loss": 2.4532,
-      "step": 145
-    },
-    {
-      "epoch": 1.2707423580786026,
-      "grad_norm": 0.94140625,
-      "learning_rate": 8.145664276853353e-06,
-      "loss": 2.4997,
-      "step": 146
-    },
-    {
-      "epoch": 1.279475982532751,
-      "grad_norm": 0.94140625,
-      "learning_rate": 8.117449009293668e-06,
-      "loss": 2.5093,
-      "step": 147
-    },
-    {
-      "epoch": 1.2882096069868996,
-      "grad_norm": 0.94140625,
-      "learning_rate": 8.089070392256866e-06,
-      "loss": 2.5558,
-      "step": 148
-    },
-    {
-      "epoch": 1.296943231441048,
-      "grad_norm": 0.984375,
-      "learning_rate": 8.060529912738316e-06,
-      "loss": 2.5583,
-      "step": 149
-    },
-    {
-      "epoch": 1.3056768558951966,
-      "grad_norm": 1.0,
-      "learning_rate": 8.031829066214735e-06,
-      "loss": 2.5477,
-      "step": 150
-    },
-    {
-      "epoch": 1.314410480349345,
-      "grad_norm": 0.953125,
-      "learning_rate": 8.002969356565822e-06,
-      "loss": 2.56,
-      "step": 151
-    },
-    {
-      "epoch": 1.3231441048034935,
-      "grad_norm": 0.97265625,
-      "learning_rate": 7.973952295995452e-06,
-      "loss": 2.5918,
-      "step": 152
-    },
-    {
-      "epoch": 1.3318777292576418,
-      "grad_norm": 0.94140625,
-      "learning_rate": 7.94477940495245e-06,
-      "loss": 2.5883,
-      "step": 153
-    },
-    {
-      "epoch": 1.3406113537117905,
-      "grad_norm": 0.9765625,
-      "learning_rate": 7.91545221205091e-06,
-      "loss": 2.557,
-      "step": 154
-    },
-    {
-      "epoch": 1.3493449781659388,
-      "grad_norm": 0.921875,
-      "learning_rate": 7.885972253990104e-06,
-      "loss": 2.5619,
-      "step": 155
-    },
-    {
-      "epoch": 1.3580786026200873,
-      "grad_norm": 0.93359375,
-      "learning_rate": 7.856341075473963e-06,
-      "loss": 2.6278,
-      "step": 156
-    },
-    {
-      "epoch": 1.3668122270742358,
-      "grad_norm": 0.9453125,
-      "learning_rate": 7.826560229130132e-06,
-      "loss": 2.5959,
-      "step": 157
-    },
-    {
-      "epoch": 1.3755458515283843,
-      "grad_norm": 0.94140625,
-      "learning_rate": 7.796631275428617e-06,
-      "loss": 2.529,
-      "step": 158
-    },
-    {
-      "epoch": 1.3842794759825328,
-      "grad_norm": 0.91015625,
-      "learning_rate": 7.766555782600023e-06,
-      "loss": 2.5481,
-      "step": 159
-    },
-    {
-      "epoch": 1.3930131004366813,
-      "grad_norm": 0.99609375,
-      "learning_rate": 7.736335326553373e-06,
-      "loss": 2.4771,
-      "step": 160
-    },
-    {
-      "epoch": 1.4017467248908297,
-      "grad_norm": 0.98046875,
-      "learning_rate": 7.70597149079354e-06,
-      "loss": 2.5304,
-      "step": 161
-    },
-    {
-      "epoch": 1.4104803493449782,
-      "grad_norm": 0.9140625,
-      "learning_rate": 7.67546586633827e-06,
-      "loss": 2.47,
-      "step": 162
-    },
-    {
-      "epoch": 1.4192139737991267,
-      "grad_norm": 0.921875,
-      "learning_rate": 7.644820051634813e-06,
-      "loss": 2.5756,
-      "step": 163
-    },
-    {
-      "epoch": 1.427947598253275,
-      "grad_norm": 0.9375,
-      "learning_rate": 7.614035652476175e-06,
-      "loss": 2.5157,
-      "step": 164
-    },
-    {
-      "epoch": 1.4366812227074237,
-      "grad_norm": 0.9453125,
-      "learning_rate": 7.5831142819169664e-06,
-      "loss": 2.5364,
-      "step": 165
-    },
-    {
-      "epoch": 1.445414847161572,
-      "grad_norm": 0.93359375,
-      "learning_rate": 7.552057560188892e-06,
-      "loss": 2.5279,
-      "step": 166
-    },
-    {
-      "epoch": 1.4541484716157205,
-      "grad_norm": 0.90234375,
-      "learning_rate": 7.520867114615844e-06,
-      "loss": 2.491,
-      "step": 167
-    },
-    {
-      "epoch": 1.462882096069869,
-      "grad_norm": 0.9140625,
-      "learning_rate": 7.4895445795286325e-06,
-      "loss": 2.5906,
-      "step": 168
-    },
-    {
-      "epoch": 1.4716157205240175,
-      "grad_norm": 0.953125,
-      "learning_rate": 7.458091596179359e-06,
-      "loss": 2.5283,
-      "step": 169
-    },
-    {
-      "epoch": 1.480349344978166,
-      "grad_norm": 1.0078125,
-      "learning_rate": 7.4265098126554065e-06,
-      "loss": 2.5956,
-      "step": 170
-    },
-    {
-      "epoch": 1.4890829694323144,
-      "grad_norm": 0.93359375,
-      "learning_rate": 7.394800883793087e-06,
-      "loss": 2.5629,
-      "step": 171
-    },
-    {
-      "epoch": 1.497816593886463,
-      "grad_norm": 1.0390625,
-      "learning_rate": 7.3629664710909354e-06,
-      "loss": 2.5138,
-      "step": 172
-    },
-    {
-      "epoch": 1.5065502183406112,
-      "grad_norm": 1.0625,
-      "learning_rate": 7.331008242622637e-06,
-      "loss": 2.5712,
-      "step": 173
-    },
-    {
-      "epoch": 1.51528384279476,
-      "grad_norm": 0.96484375,
-      "learning_rate": 7.2989278729496374e-06,
-      "loss": 2.6415,
-      "step": 174
-    },
-    {
-      "epoch": 1.5240174672489082,
-      "grad_norm": 1.03125,
-      "learning_rate": 7.266727043033386e-06,
-      "loss": 2.5236,
-      "step": 175
-    },
-    {
-      "epoch": 1.532751091703057,
-      "grad_norm": 0.96875,
-      "learning_rate": 7.234407440147266e-06,
-      "loss": 2.5656,
-      "step": 176
-    },
-    {
-      "epoch": 1.5414847161572052,
-      "grad_norm": 0.98828125,
-      "learning_rate": 7.201970757788172e-06,
-      "loss": 2.5682,
-      "step": 177
-    },
-    {
-      "epoch": 1.5502183406113537,
-      "grad_norm": 0.96484375,
-      "learning_rate": 7.169418695587791e-06,
-      "loss": 2.5356,
-      "step": 178
-    },
-    {
-      "epoch": 1.5589519650655022,
-      "grad_norm": 0.96875,
-      "learning_rate": 7.136752959223527e-06,
-      "loss": 2.6174,
-      "step": 179
-    },
-    {
-      "epoch": 1.5676855895196506,
-      "grad_norm": 0.93359375,
-      "learning_rate": 7.103975260329136e-06,
-      "loss": 2.6003,
-      "step": 180
-    },
-    {
-      "epoch": 1.5764192139737991,
-      "grad_norm": 0.9140625,
-      "learning_rate": 7.071087316405037e-06,
-      "loss": 2.5504,
-      "step": 181
-    },
-    {
-      "epoch": 1.5851528384279476,
-      "grad_norm": 0.93359375,
-      "learning_rate": 7.038090850728312e-06,
-      "loss": 2.5491,
-      "step": 182
-    },
-    {
-      "epoch": 1.5938864628820961,
-      "grad_norm": 0.9296875,
-      "learning_rate": 7.00498759226242e-06,
-      "loss": 2.5331,
-      "step": 183
-    },
-    {
-      "epoch": 1.6026200873362444,
-      "grad_norm": 0.921875,
-      "learning_rate": 6.971779275566593e-06,
-      "loss": 2.537,
-      "step": 184
-    },
-    {
-      "epoch": 1.611353711790393,
-      "grad_norm": 0.94140625,
-      "learning_rate": 6.938467640704953e-06,
-      "loss": 2.5117,
-      "step": 185
-    },
-    {
-      "epoch": 1.6200873362445414,
-      "grad_norm": 0.93359375,
-      "learning_rate": 6.90505443315533e-06,
-      "loss": 2.6398,
-      "step": 186
-    },
-    {
-      "epoch": 1.62882096069869,
-      "grad_norm": 0.9609375,
-      "learning_rate": 6.871541403717808e-06,
-      "loss": 2.5182,
-      "step": 187
-    },
-    {
-      "epoch": 1.6375545851528384,
-      "grad_norm": 0.9296875,
-      "learning_rate": 6.8379303084229765e-06,
-      "loss": 2.6042,
-      "step": 188
-    },
-    {
-      "epoch": 1.6462882096069869,
-      "grad_norm": 0.953125,
-      "learning_rate": 6.8042229084399325e-06,
-      "loss": 2.5974,
-      "step": 189
-    },
-    {
-      "epoch": 1.6550218340611353,
-      "grad_norm": 0.98828125,
-      "learning_rate": 6.770420969983982e-06,
-      "loss": 2.5706,
-      "step": 190
-    },
-    {
-      "epoch": 1.6637554585152838,
-      "grad_norm": 1.0,
-      "learning_rate": 6.736526264224101e-06,
-      "loss": 2.4622,
-      "step": 191
-    },
-    {
-      "epoch": 1.6724890829694323,
-      "grad_norm": 0.9375,
-      "learning_rate": 6.702540567190132e-06,
-      "loss": 2.5172,
-      "step": 192
-    },
-    {
-      "epoch": 1.6812227074235808,
-      "grad_norm": 0.9453125,
-      "learning_rate": 6.668465659679714e-06,
-      "loss": 2.5317,
-      "step": 193
-    },
-    {
-      "epoch": 1.6899563318777293,
-      "grad_norm": 1.046875,
-      "learning_rate": 6.634303327164976e-06,
-      "loss": 2.5942,
-      "step": 194
-    },
-    {
-      "epoch": 1.6986899563318776,
-      "grad_norm": 0.9765625,
-      "learning_rate": 6.600055359698984e-06,
-      "loss": 2.5432,
-      "step": 195
-    },
-    {
-      "epoch": 1.7074235807860263,
-      "grad_norm": 1.0234375,
-      "learning_rate": 6.565723551821943e-06,
-      "loss": 2.532,
-      "step": 196
-    },
-    {
-      "epoch": 1.7161572052401746,
-      "grad_norm": 0.9609375,
-      "learning_rate": 6.531309702467159e-06,
-      "loss": 2.4832,
-      "step": 197
-    },
-    {
-      "epoch": 1.7248908296943233,
-      "grad_norm": 0.9296875,
-      "learning_rate": 6.496815614866792e-06,
-      "loss": 2.5488,
-      "step": 198
-    },
-    {
-      "epoch": 1.7336244541484715,
-      "grad_norm": 0.9296875,
-      "learning_rate": 6.462243096457352e-06,
-      "loss": 2.6082,
-      "step": 199
-    },
-    {
-      "epoch": 1.74235807860262,
-      "grad_norm": 0.9609375,
-      "learning_rate": 6.42759395878501e-06,
-      "loss": 2.5815,
-      "step": 200
-    },
-    {
-      "epoch": 1.7510917030567685,
-      "grad_norm": 0.9609375,
-      "learning_rate": 6.392870017410665e-06,
-      "loss": 2.4902,
-      "step": 201
-    },
-    {
-      "epoch": 1.759825327510917,
-      "grad_norm": 0.9375,
-      "learning_rate": 6.358073091814809e-06,
-      "loss": 2.4882,
-      "step": 202
-    },
-    {
-      "epoch": 1.7685589519650655,
-      "grad_norm": 1.0,
-      "learning_rate": 6.323205005302199e-06,
-      "loss": 2.5042,
-      "step": 203
-    },
-    {
-      "epoch": 1.777292576419214,
-      "grad_norm": 0.953125,
-      "learning_rate": 6.288267584906308e-06,
-      "loss": 2.5471,
-      "step": 204
-    },
-    {
-      "epoch": 1.7860262008733625,
-      "grad_norm": 0.91796875,
-      "learning_rate": 6.2532626612936035e-06,
-      "loss": 2.5491,
-      "step": 205
-    },
-    {
-      "epoch": 1.7947598253275108,
-      "grad_norm": 0.93359375,
-      "learning_rate": 6.21819206866761e-06,
-      "loss": 2.5086,
-      "step": 206
-    },
-    {
-      "epoch": 1.8034934497816595,
-      "grad_norm": 1.1484375,
-      "learning_rate": 6.18305764467281e-06,
-      "loss": 2.585,
-      "step": 207
-    },
-    {
-      "epoch": 1.8122270742358078,
-      "grad_norm": 0.99609375,
-      "learning_rate": 6.147861230298349e-06,
-      "loss": 2.564,
-      "step": 208
-    },
-    {
-      "epoch": 1.8209606986899565,
-      "grad_norm": 1.0859375,
-      "learning_rate": 6.112604669781572e-06,
-      "loss": 2.5534,
-      "step": 209
-    },
-    {
-      "epoch": 1.8296943231441047,
-      "grad_norm": 1.0234375,
-      "learning_rate": 6.077289810511389e-06,
-      "loss": 2.5989,
-      "step": 210
-    },
-    {
-      "epoch": 1.8384279475982532,
-      "grad_norm": 1.0078125,
-      "learning_rate": 6.041918502931473e-06,
-      "loss": 2.5781,
-      "step": 211
-    },
-    {
-      "epoch": 1.8471615720524017,
-      "grad_norm": 1.1171875,
-      "learning_rate": 6.006492600443301e-06,
-      "loss": 2.4495,
-      "step": 212
-    },
-    {
-      "epoch": 1.8558951965065502,
-      "grad_norm": 1.0,
-      "learning_rate": 5.971013959309038e-06,
-      "loss": 2.4965,
-      "step": 213
-    },
-    {
-      "epoch": 1.8646288209606987,
-      "grad_norm": 0.96875,
-      "learning_rate": 5.935484438554273e-06,
-      "loss": 2.5466,
-      "step": 214
-    },
-    {
-      "epoch": 1.8733624454148472,
-      "grad_norm": 0.94140625,
-      "learning_rate": 5.8999058998706046e-06,
-      "loss": 2.447,
-      "step": 215
-    },
-    {
-      "epoch": 1.8820960698689957,
-      "grad_norm": 0.98828125,
-      "learning_rate": 5.8642802075181e-06,
-      "loss": 2.5911,
-      "step": 216
-    },
-    {
-      "epoch": 1.890829694323144,
-      "grad_norm": 1.1015625,
-      "learning_rate": 5.828609228227603e-06,
-      "loss": 2.5723,
-      "step": 217
-    },
-    {
-      "epoch": 1.8995633187772927,
-      "grad_norm": 1.015625,
-      "learning_rate": 5.7928948311029175e-06,
-      "loss": 2.6029,
-      "step": 218
-    },
-    {
-      "epoch": 1.908296943231441,
-      "grad_norm": 1.0078125,
-      "learning_rate": 5.757138887522884e-06,
-      "loss": 2.5432,
-      "step": 219
-    },
-    {
-      "epoch": 1.9170305676855897,
-      "grad_norm": 0.94140625,
-      "learning_rate": 5.721343271043305e-06,
-      "loss": 2.5273,
-      "step": 220
-    },
-    {
-      "epoch": 1.925764192139738,
-      "grad_norm": 0.93359375,
-      "learning_rate": 5.685509857298781e-06,
-      "loss": 2.5822,
-      "step": 221
-    },
-    {
-      "epoch": 1.9344978165938864,
-      "grad_norm": 0.97265625,
-      "learning_rate": 5.649640523904438e-06,
-      "loss": 2.4545,
-      "step": 222
-    },
-    {
-      "epoch": 1.943231441048035,
-      "grad_norm": 0.95703125,
-      "learning_rate": 5.613737150357528e-06,
-      "loss": 2.6138,
-      "step": 223
-    },
-    {
-      "epoch": 1.9519650655021834,
-      "grad_norm": 0.984375,
-      "learning_rate": 5.577801617938956e-06,
-      "loss": 2.5428,
-      "step": 224
-    },
-    {
-      "epoch": 1.960698689956332,
-      "grad_norm": 0.96875,
-      "learning_rate": 5.541835809614704e-06,
-      "loss": 2.4883,
-      "step": 225
-    },
-    {
-      "epoch": 1.9694323144104804,
-      "grad_norm": 0.97265625,
-      "learning_rate": 5.505841609937162e-06,
-      "loss": 2.5128,
-      "step": 226
-    },
-    {
-      "epoch": 1.9781659388646289,
-      "grad_norm": 0.9375,
-      "learning_rate": 5.469820904946383e-06,
-      "loss": 2.5452,
-      "step": 227
-    },
-    {
-      "epoch": 1.9868995633187772,
-      "grad_norm": 0.98828125,
-      "learning_rate": 5.43377558207126e-06,
-      "loss": 2.5695,
-      "step": 228
-    }
-  ],
-  "logging_steps": 1,
-  "max_steps": 456,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
-  "save_steps": 114,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 7.136533590677914e+17,
-  "train_batch_size": 2,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-228/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae0592bc0dda5ec7f7a3ef05f7a468bec687ffdab3262199ff4c718485bd04da
-size 6520