Upload folder using huggingface_hub

checkpoint-25/relora/Untitled.ipynb

@@ -191,10 +191,138 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "Uploading...\n",
+      "Uploading...\n",
       "Uploading...\n",
       "Uploading...\n",
       "Uploading...\n"
      ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f580f9f773264ca89e3a57862f71bf96",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "adapter_model.bin:   0%|          | 0.00/125M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4a61ad7075bd48cd819b4ba1e3537a20",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "adapter_model.bin:   0%|          | 0.00/125M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "dcf3b328e6404d698284731b28d9c1b0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "optimizer.pt:   0%|          | 0.00/63.3M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "adf5465a701e4512997f3b559065ee11",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00001-of-00003.safetensors:   0%|          | 0.00/9.95G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a20511481ed64aaca9181d993e7c5310",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Upload 8 LFS files:   0%|          | 0/8 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b7d77a0cb87d42b4bc2ae42125078248",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00002-of-00003.safetensors:   0%|          | 0.00/9.90G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "713425b1389a4252a4f4eb1ccb1b2c31",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00003-of-00003.safetensors:   0%|          | 0.00/6.18G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a1c8ba5becc64a8e915872564cb041e0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "rng_state.pth:   0%|          | 0.00/14.6k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "01110336ada24188b41074deb18a915c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "scheduler.pt:   0%|          | 0.00/189M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
    "source": [

checkpoint-75/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-75/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Nous-Hermes-Llama2-13b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-75/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aabbca706cee7bc8845ede3cb2f4063e6acaf865c7feb6c900e4fa241ebd15bc
+size 125374989

checkpoint-75/adapter_model/README.md

@@ -0,0 +1,21 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+### Framework versions
+
+
+- PEFT 0.6.0.dev0

checkpoint-75/adapter_model/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "NousResearch/Nous-Hermes-Llama2-13b",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-75/adapter_model/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aabbca706cee7bc8845ede3cb2f4063e6acaf865c7feb6c900e4fa241ebd15bc
+size 125374989

checkpoint-75/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0723b07df5a587b5bd554bf5cb8ef0b277d3df8af5ef0d408b3e7a5997e5d13d
+size 63343327

checkpoint-75/relora/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623e51c48bbe2e9639b2977549296df6c0b8af3c15dfd8c09681ed3d1e726dd0
+size 9949019216

checkpoint-75/relora/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf94afb798eea616d9179e5299ca5b6908e954225cb44e1a2819a9161d8824a8
+size 9904127520

checkpoint-75/relora/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:190ec3ad229b7c1a6d9ef398509d60e7c3555d5710cad56cb7a58d09d1ecd501
+size 6179288912

checkpoint-75/relora/model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {}, "weight_map": {"lm_head.weight": "model-00003-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00003-of-00003.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00001-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors"}}

checkpoint-75/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301e84f805deb81664cec8dc0d5c2608f846e120dc9aa3226267bacdcfb2aa0e
+size 14575

checkpoint-75/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd302183551ea3929b0fa8429ab24fce454dcdfc7542975aacf23f46d9dfb24
+size 188692111

checkpoint-75/trainer_state.json

@@ -0,0 +1,469 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.348314606741573,
+  "eval_steps": 500,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1e-05,
+      "loss": 1.6702,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.5e-05,
+      "loss": 1.5262,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2e-05,
+      "loss": 1.8831,
+      "step": 3
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.5e-05,
+      "loss": 1.6531,
+      "step": 4
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3e-05,
+      "loss": 1.6833,
+      "step": 5
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.5e-05,
+      "loss": 1.7288,
+      "step": 6
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4e-05,
+      "loss": 1.5015,
+      "step": 7
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.5e-05,
+      "loss": 1.6876,
+      "step": 8
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 5e-05,
+      "loss": 1.6648,
+      "step": 9
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.998766400914329e-05,
+      "loss": 1.8044,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.995066821070679e-05,
+      "loss": 1.6566,
+      "step": 11
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.9889049115077005e-05,
+      "loss": 1.6917,
+      "step": 12
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.980286753286195e-05,
+      "loss": 1.6271,
+      "step": 13
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 1.7478,
+      "step": 14
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.9557181268217227e-05,
+      "loss": 1.606,
+      "step": 15
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.939791904846869e-05,
+      "loss": 1.6176,
+      "step": 16
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.9214579028215776e-05,
+      "loss": 1.7205,
+      "step": 17
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.900734214192358e-05,
+      "loss": 1.5682,
+      "step": 18
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 1.6807,
+      "step": 19
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.852201922385564e-05,
+      "loss": 1.6137,
+      "step": 20
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.8244412147206284e-05,
+      "loss": 1.6352,
+      "step": 21
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.794386564209953e-05,
+      "loss": 1.5979,
+      "step": 22
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.762067631165049e-05,
+      "loss": 1.6163,
+      "step": 23
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.72751631047092e-08,
+      "loss": 1.6513,
+      "step": 24
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.5667160778366258e-05,
+      "loss": 1.5181,
+      "step": 25
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.102787330029076e-05,
+      "loss": 1.544,
+      "step": 26
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.610819813755038e-05,
+      "loss": 1.4473,
+      "step": 27
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.567701435686404e-05,
+      "loss": 1.6461,
+      "step": 28
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 1.519,
+      "step": 29
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.4753875309392266e-05,
+      "loss": 1.5967,
+      "step": 30
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.426283106939474e-05,
+      "loss": 1.6351,
+      "step": 31
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.375277674076149e-05,
+      "loss": 1.5408,
+      "step": 32
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.3224215685535294e-05,
+      "loss": 1.6087,
+      "step": 33
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 1.5753,
+      "step": 34
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.211367764821722e-05,
+      "loss": 1.6771,
+      "step": 35
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.1532796633091296e-05,
+      "loss": 1.5738,
+      "step": 36
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 1.5405,
+      "step": 37
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.0322676341324415e-05,
+      "loss": 1.614,
+      "step": 38
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 1.6264,
+      "step": 39
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.905208444630327e-05,
+      "loss": 1.5959,
+      "step": 40
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.8395669874474915e-05,
+      "loss": 1.5935,
+      "step": 41
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.7726035393759285e-05,
+      "loss": 1.502,
+      "step": 42
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.704384185254288e-05,
+      "loss": 1.6214,
+      "step": 43
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 1.5852,
+      "step": 44
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.564448228912682e-05,
+      "loss": 1.7603,
+      "step": 45
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.4928697265869515e-05,
+      "loss": 1.4935,
+      "step": 46
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.4203113817116957e-05,
+      "loss": 1.5517,
+      "step": 47
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.346844800613229e-05,
+      "loss": 1.6087,
+      "step": 48
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.2725424859373694e-08,
+      "loss": 1.5613,
+      "step": 49
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.0679575735427564e-05,
+      "loss": 1.597,
+      "step": 50
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.0821903868473956e-05,
+      "loss": 1.5146,
+      "step": 51
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.045358103491357e-05,
+      "loss": 1.5927,
+      "step": 52
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.9684532864643122e-05,
+      "loss": 1.6061,
+      "step": 53
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 1.5321,
+      "step": 54
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.8133330839107608e-05,
+      "loss": 1.4788,
+      "step": 55
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.7352707832962865e-05,
+      "loss": 1.499,
+      "step": 56
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.656976298823284e-05,
+      "loss": 1.5762,
+      "step": 57
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.578526897695321e-05,
+      "loss": 1.5178,
+      "step": 58
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.5e-05,
+      "loss": 1.5249,
+      "step": 59
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.4214731023046793e-05,
+      "loss": 1.5864,
+      "step": 60
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.3430237011767167e-05,
+      "loss": 1.4421,
+      "step": 61
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.2647292167037144e-05,
+      "loss": 1.6576,
+      "step": 62
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.186666916089239e-05,
+      "loss": 1.5909,
+      "step": 63
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 1.6872,
+      "step": 64
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.031546713535688e-05,
+      "loss": 1.5855,
+      "step": 65
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.9546418965086442e-05,
+      "loss": 1.4649,
+      "step": 66
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.8782752820878634e-05,
+      "loss": 1.5359,
+      "step": 67
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.802522234901927e-05,
+      "loss": 1.5669,
+      "step": 68
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 1.5668,
+      "step": 69
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.6531551993867717e-05,
+      "loss": 1.5836,
+      "step": 70
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.5796886182883053e-05,
+      "loss": 1.6105,
+      "step": 71
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.5071302734130489e-05,
+      "loss": 1.7016,
+      "step": 72
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.4355517710873184e-05,
+      "loss": 1.5267,
+      "step": 73
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3650237506511332e-08,
+      "loss": 1.5548,
+      "step": 74
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.327356821250675e-06,
+      "loss": 1.4613,
+      "step": 75
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 110,
+  "num_train_epochs": 2,
+  "save_steps": 25,
+  "total_flos": 2.6572405131313152e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-75/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac1807a3dad2a889f8270df29e23d2a109745612aa45d4ed5932877dca4b399
+size 4411