Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wo_mask/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+wo_mask/checkpoint-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text

wo_mask/checkpoint-100/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "weqweasdas/RM-Gemma-2B",
+  "architectures": [
+    "GemmaForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 256000
+}

wo_mask/checkpoint-100/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc608c1b75d9796e36d487cf790216580129cc475cf8b4d2f67691ab3074b11
+size 4945242264

wo_mask/checkpoint-100/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec01c162bbd5857de73f9c8791a1ce44ea70e128efbbb83fdde2e3a634f749d
+size 67125784

wo_mask/checkpoint-100/model.safetensors.index.json

@@ -0,0 +1,172 @@
+{
+  "metadata": {
+    "total_size": 5012348928
+  },
+  "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-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-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.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",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

wo_mask/checkpoint-100/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

wo_mask/checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:298441ee7a12cf33d73f5d955d0c9eaf471d6acae1acb18e96bb33470ad8a49c
+size 34315571

wo_mask/checkpoint-100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

wo_mask/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "max_length": 2048,
+  "model_max_length": 2048,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "GemmaTokenizer",
+  "truncation_side": "left",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

wo_mask/checkpoint-100/trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8260196179659267,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008260196179659268,
+      "grad_norm": 6.151299127457545,
+      "learning_rate": 9.917355371900827e-07,
+      "loss": 0.8255,
+      "step": 1
+    },
+    {
+      "epoch": 0.016520392359318535,
+      "grad_norm": 5.780122487448709,
+      "learning_rate": 9.834710743801652e-07,
+      "loss": 0.8187,
+      "step": 2
+    },
+    {
+      "epoch": 0.0247805885389778,
+      "grad_norm": 5.284580545759994,
+      "learning_rate": 9.75206611570248e-07,
+      "loss": 0.8312,
+      "step": 3
+    },
+    {
+      "epoch": 0.03304078471863707,
+      "grad_norm": 5.276007202181103,
+      "learning_rate": 9.669421487603305e-07,
+      "loss": 0.8109,
+      "step": 4
+    },
+    {
+      "epoch": 0.041300980898296334,
+      "grad_norm": 5.183295459512783,
+      "learning_rate": 9.586776859504132e-07,
+      "loss": 0.7891,
+      "step": 5
+    },
+    {
+      "epoch": 0.0495611770779556,
+      "grad_norm": 5.332217660707675,
+      "learning_rate": 9.504132231404959e-07,
+      "loss": 0.7743,
+      "step": 6
+    },
+    {
+      "epoch": 0.05782137325761487,
+      "grad_norm": 5.730074140553302,
+      "learning_rate": 9.421487603305784e-07,
+      "loss": 0.7559,
+      "step": 7
+    },
+    {
+      "epoch": 0.06608156943727414,
+      "grad_norm": 5.293612302527298,
+      "learning_rate": 9.338842975206612e-07,
+      "loss": 0.7155,
+      "step": 8
+    },
+    {
+      "epoch": 0.0743417656169334,
+      "grad_norm": 5.085007745006763,
+      "learning_rate": 9.256198347107438e-07,
+      "loss": 0.7421,
+      "step": 9
+    },
+    {
+      "epoch": 0.08260196179659267,
+      "grad_norm": 5.098816875901866,
+      "learning_rate": 9.173553719008264e-07,
+      "loss": 0.7,
+      "step": 10
+    },
+    {
+      "epoch": 0.09086215797625194,
+      "grad_norm": 7.8680991633839765,
+      "learning_rate": 9.09090909090909e-07,
+      "loss": 0.6778,
+      "step": 11
+    },
+    {
+      "epoch": 0.0991223541559112,
+      "grad_norm": 7.957843903611215,
+      "learning_rate": 9.008264462809917e-07,
+      "loss": 0.6526,
+      "step": 12
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 7.059924617430371,
+      "learning_rate": 8.925619834710744e-07,
+      "loss": 0.621,
+      "step": 13
+    },
+    {
+      "epoch": 0.11564274651522974,
+      "grad_norm": 8.652197114711964,
+      "learning_rate": 8.84297520661157e-07,
+      "loss": 0.6319,
+      "step": 14
+    },
+    {
+      "epoch": 0.12390294269488901,
+      "grad_norm": 6.832187915211578,
+      "learning_rate": 8.760330578512396e-07,
+      "loss": 0.6022,
+      "step": 15
+    },
+    {
+      "epoch": 0.13216313887454828,
+      "grad_norm": 7.171557589862187,
+      "learning_rate": 8.677685950413223e-07,
+      "loss": 0.6056,
+      "step": 16
+    },
+    {
+      "epoch": 0.14042333505420754,
+      "grad_norm": 7.342397949784474,
+      "learning_rate": 8.595041322314049e-07,
+      "loss": 0.5822,
+      "step": 17
+    },
+    {
+      "epoch": 0.1486835312338668,
+      "grad_norm": 6.409864684511031,
+      "learning_rate": 8.512396694214876e-07,
+      "loss": 0.5741,
+      "step": 18
+    },
+    {
+      "epoch": 0.15694372741352608,
+      "grad_norm": 5.90031720345188,
+      "learning_rate": 8.429752066115701e-07,
+      "loss": 0.5428,
+      "step": 19
+    },
+    {
+      "epoch": 0.16520392359318534,
+      "grad_norm": 5.721498192124633,
+      "learning_rate": 8.347107438016529e-07,
+      "loss": 0.5106,
+      "step": 20
+    },
+    {
+      "epoch": 0.1734641197728446,
+      "grad_norm": 5.393442254760478,
+      "learning_rate": 8.264462809917355e-07,
+      "loss": 0.4733,
+      "step": 21
+    },
+    {
+      "epoch": 0.18172431595250388,
+      "grad_norm": 5.474634077507737,
+      "learning_rate": 8.181818181818182e-07,
+      "loss": 0.4612,
+      "step": 22
+    },
+    {
+      "epoch": 0.18998451213216314,
+      "grad_norm": 5.75044582103474,
+      "learning_rate": 8.099173553719008e-07,
+      "loss": 0.4467,
+      "step": 23
+    },
+    {
+      "epoch": 0.1982447083118224,
+      "grad_norm": 5.364804428827895,
+      "learning_rate": 8.016528925619835e-07,
+      "loss": 0.4191,
+      "step": 24
+    },
+    {
+      "epoch": 0.20650490449148168,
+      "grad_norm": 5.48762563438622,
+      "learning_rate": 7.933884297520661e-07,
+      "loss": 0.3964,
+      "step": 25
+    },
+    {
+      "epoch": 0.21476510067114093,
+      "grad_norm": 5.721966438387265,
+      "learning_rate": 7.851239669421487e-07,
+      "loss": 0.3805,
+      "step": 26
+    },
+    {
+      "epoch": 0.22302529685080022,
+      "grad_norm": 5.637593244471927,
+      "learning_rate": 7.768595041322314e-07,
+      "loss": 0.357,
+      "step": 27
+    },
+    {
+      "epoch": 0.23128549303045948,
+      "grad_norm": 5.253127366512256,
+      "learning_rate": 7.68595041322314e-07,
+      "loss": 0.3176,
+      "step": 28
+    },
+    {
+      "epoch": 0.23954568921011873,
+      "grad_norm": 5.402262981848415,
+      "learning_rate": 7.603305785123967e-07,
+      "loss": 0.3344,
+      "step": 29
+    },
+    {
+      "epoch": 0.24780588538977802,
+      "grad_norm": 5.221833996297194,
+      "learning_rate": 7.520661157024793e-07,
+      "loss": 0.3157,
+      "step": 30
+    },
+    {
+      "epoch": 0.2560660815694373,
+      "grad_norm": 4.936826111971605,
+      "learning_rate": 7.43801652892562e-07,
+      "loss": 0.293,
+      "step": 31
+    },
+    {
+      "epoch": 0.26432627774909656,
+      "grad_norm": 5.467317249015266,
+      "learning_rate": 7.355371900826446e-07,
+      "loss": 0.2874,
+      "step": 32
+    },
+    {
+      "epoch": 0.2725864739287558,
+      "grad_norm": 5.731777293683918,
+      "learning_rate": 7.272727272727272e-07,
+      "loss": 0.2619,
+      "step": 33
+    },
+    {
+      "epoch": 0.2808466701084151,
+      "grad_norm": 5.007564269770195,
+      "learning_rate": 7.190082644628099e-07,
+      "loss": 0.2453,
+      "step": 34
+    },
+    {
+      "epoch": 0.28910686628807436,
+      "grad_norm": 5.129081210265052,
+      "learning_rate": 7.107438016528925e-07,
+      "loss": 0.2342,
+      "step": 35
+    },
+    {
+      "epoch": 0.2973670624677336,
+      "grad_norm": 5.615993298785848,
+      "learning_rate": 7.024793388429752e-07,
+      "loss": 0.2244,
+      "step": 36
+    },
+    {
+      "epoch": 0.3056272586473929,
+      "grad_norm": 5.92148008008197,
+      "learning_rate": 6.942148760330578e-07,
+      "loss": 0.2351,
+      "step": 37
+    },
+    {
+      "epoch": 0.31388745482705216,
+      "grad_norm": 5.235043676350482,
+      "learning_rate": 6.859504132231405e-07,
+      "loss": 0.2002,
+      "step": 38
+    },
+    {
+      "epoch": 0.3221476510067114,
+      "grad_norm": 4.845523937915667,
+      "learning_rate": 6.776859504132231e-07,
+      "loss": 0.1846,
+      "step": 39
+    },
+    {
+      "epoch": 0.3304078471863707,
+      "grad_norm": 5.453591513567315,
+      "learning_rate": 6.694214876033058e-07,
+      "loss": 0.1846,
+      "step": 40
+    },
+    {
+      "epoch": 0.33866804336602996,
+      "grad_norm": 5.406878125038352,
+      "learning_rate": 6.611570247933884e-07,
+      "loss": 0.1803,
+      "step": 41
+    },
+    {
+      "epoch": 0.3469282395456892,
+      "grad_norm": 5.720653857597168,
+      "learning_rate": 6.52892561983471e-07,
+      "loss": 0.1709,
+      "step": 42
+    },
+    {
+      "epoch": 0.3551884357253485,
+      "grad_norm": 4.7807197357380655,
+      "learning_rate": 6.446280991735537e-07,
+      "loss": 0.1535,
+      "step": 43
+    },
+    {
+      "epoch": 0.36344863190500776,
+      "grad_norm": 9.504234726479488,
+      "learning_rate": 6.363636363636363e-07,
+      "loss": 0.1492,
+      "step": 44
+    },
+    {
+      "epoch": 0.371708828084667,
+      "grad_norm": 5.4032075384453515,
+      "learning_rate": 6.28099173553719e-07,
+      "loss": 0.1352,
+      "step": 45
+    },
+    {
+      "epoch": 0.37996902426432627,
+      "grad_norm": 4.957836295699517,
+      "learning_rate": 6.198347107438017e-07,
+      "loss": 0.1403,
+      "step": 46
+    },
+    {
+      "epoch": 0.38822922044398556,
+      "grad_norm": 4.821649080443891,
+      "learning_rate": 6.115702479338843e-07,
+      "loss": 0.1334,
+      "step": 47
+    },
+    {
+      "epoch": 0.3964894166236448,
+      "grad_norm": 6.078364579347982,
+      "learning_rate": 6.033057851239669e-07,
+      "loss": 0.1359,
+      "step": 48
+    },
+    {
+      "epoch": 0.40474961280330407,
+      "grad_norm": 4.920465068560464,
+      "learning_rate": 5.950413223140495e-07,
+      "loss": 0.1246,
+      "step": 49
+    },
+    {
+      "epoch": 0.41300980898296336,
+      "grad_norm": 4.9181285607981104,
+      "learning_rate": 5.867768595041323e-07,
+      "loss": 0.1176,
+      "step": 50
+    },
+    {
+      "epoch": 0.4212700051626226,
+      "grad_norm": 5.499139905865122,
+      "learning_rate": 5.785123966942148e-07,
+      "loss": 0.1189,
+      "step": 51
+    },
+    {
+      "epoch": 0.42953020134228187,
+      "grad_norm": 5.485462773630812,
+      "learning_rate": 5.702479338842975e-07,
+      "loss": 0.1125,
+      "step": 52
+    },
+    {
+      "epoch": 0.43779039752194115,
+      "grad_norm": 5.128741877444076,
+      "learning_rate": 5.619834710743801e-07,
+      "loss": 0.1088,
+      "step": 53
+    },
+    {
+      "epoch": 0.44605059370160044,
+      "grad_norm": 5.910794469376855,
+      "learning_rate": 5.537190082644629e-07,
+      "loss": 0.1053,
+      "step": 54
+    },
+    {
+      "epoch": 0.45431078988125967,
+      "grad_norm": 4.503146156347465,
+      "learning_rate": 5.454545454545454e-07,
+      "loss": 0.0906,
+      "step": 55
+    },
+    {
+      "epoch": 0.46257098606091895,
+      "grad_norm": 4.31143603563169,
+      "learning_rate": 5.371900826446281e-07,
+      "loss": 0.0922,
+      "step": 56
+    },
+    {
+      "epoch": 0.47083118224057824,
+      "grad_norm": 4.858551221277556,
+      "learning_rate": 5.289256198347107e-07,
+      "loss": 0.093,
+      "step": 57
+    },
+    {
+      "epoch": 0.47909137842023747,
+      "grad_norm": 4.395108974639106,
+      "learning_rate": 5.206611570247934e-07,
+      "loss": 0.0934,
+      "step": 58
+    },
+    {
+      "epoch": 0.48735157459989675,
+      "grad_norm": 4.748753031390499,
+      "learning_rate": 5.12396694214876e-07,
+      "loss": 0.0939,
+      "step": 59
+    },
+    {
+      "epoch": 0.49561177077955604,
+      "grad_norm": 5.165370234374591,
+      "learning_rate": 5.041322314049586e-07,
+      "loss": 0.0909,
+      "step": 60
+    },
+    {
+      "epoch": 0.5038719669592153,
+      "grad_norm": 4.780186488881603,
+      "learning_rate": 4.958677685950413e-07,
+      "loss": 0.0979,
+      "step": 61
+    },
+    {
+      "epoch": 0.5121321631388746,
+      "grad_norm": 4.526937392254728,
+      "learning_rate": 4.87603305785124e-07,
+      "loss": 0.089,
+      "step": 62
+    },
+    {
+      "epoch": 0.5203923593185338,
+      "grad_norm": 3.9484832227284037,
+      "learning_rate": 4.793388429752066e-07,
+      "loss": 0.0813,
+      "step": 63
+    },
+    {
+      "epoch": 0.5286525554981931,
+      "grad_norm": 4.626844473209987,
+      "learning_rate": 4.710743801652892e-07,
+      "loss": 0.0788,
+      "step": 64
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 4.111714528890263,
+      "learning_rate": 4.628099173553719e-07,
+      "loss": 0.0686,
+      "step": 65
+    },
+    {
+      "epoch": 0.5451729478575116,
+      "grad_norm": 3.847620812825054,
+      "learning_rate": 4.545454545454545e-07,
+      "loss": 0.0624,
+      "step": 66
+    },
+    {
+      "epoch": 0.5534331440371709,
+      "grad_norm": 4.014429221103349,
+      "learning_rate": 4.462809917355372e-07,
+      "loss": 0.0748,
+      "step": 67
+    },
+    {
+      "epoch": 0.5616933402168302,
+      "grad_norm": 5.410596858204166,
+      "learning_rate": 4.380165289256198e-07,
+      "loss": 0.0807,
+      "step": 68
+    },
+    {
+      "epoch": 0.5699535363964894,
+      "grad_norm": 5.060478727233313,
+      "learning_rate": 4.2975206611570245e-07,
+      "loss": 0.0814,
+      "step": 69
+    },
+    {
+      "epoch": 0.5782137325761487,
+      "grad_norm": 3.8693176106349663,
+      "learning_rate": 4.2148760330578507e-07,
+      "loss": 0.0708,
+      "step": 70
+    },
+    {
+      "epoch": 0.586473928755808,
+      "grad_norm": 3.6572429929976877,
+      "learning_rate": 4.1322314049586775e-07,
+      "loss": 0.0586,
+      "step": 71
+    },
+    {
+      "epoch": 0.5947341249354672,
+      "grad_norm": 4.291915714476109,
+      "learning_rate": 4.049586776859504e-07,
+      "loss": 0.0695,
+      "step": 72
+    },
+    {
+      "epoch": 0.6029943211151265,
+      "grad_norm": 6.79226277468724,
+      "learning_rate": 3.9669421487603305e-07,
+      "loss": 0.0683,
+      "step": 73
+    },
+    {
+      "epoch": 0.6112545172947857,
+      "grad_norm": 4.49100451001806,
+      "learning_rate": 3.884297520661157e-07,
+      "loss": 0.0564,
+      "step": 74
+    },
+    {
+      "epoch": 0.619514713474445,
+      "grad_norm": 5.899350796294677,
+      "learning_rate": 3.8016528925619836e-07,
+      "loss": 0.0765,
+      "step": 75
+    },
+    {
+      "epoch": 0.6277749096541043,
+      "grad_norm": 4.515411657713084,
+      "learning_rate": 3.71900826446281e-07,
+      "loss": 0.0659,
+      "step": 76
+    },
+    {
+      "epoch": 0.6360351058337635,
+      "grad_norm": 4.177275599836179,
+      "learning_rate": 3.636363636363636e-07,
+      "loss": 0.0589,
+      "step": 77
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 4.52383547075553,
+      "learning_rate": 3.5537190082644623e-07,
+      "loss": 0.0676,
+      "step": 78
+    },
+    {
+      "epoch": 0.6525554981930821,
+      "grad_norm": 4.389273447724941,
+      "learning_rate": 3.471074380165289e-07,
+      "loss": 0.0569,
+      "step": 79
+    },
+    {
+      "epoch": 0.6608156943727413,
+      "grad_norm": 6.005106644541459,
+      "learning_rate": 3.3884297520661153e-07,
+      "loss": 0.0676,
+      "step": 80
+    },
+    {
+      "epoch": 0.6690758905524006,
+      "grad_norm": 4.143584995230645,
+      "learning_rate": 3.305785123966942e-07,
+      "loss": 0.0611,
+      "step": 81
+    },
+    {
+      "epoch": 0.6773360867320599,
+      "grad_norm": 4.636039389852911,
+      "learning_rate": 3.2231404958677684e-07,
+      "loss": 0.0547,
+      "step": 82
+    },
+    {
+      "epoch": 0.6855962829117191,
+      "grad_norm": 4.498379839418488,
+      "learning_rate": 3.140495867768595e-07,
+      "loss": 0.0541,
+      "step": 83
+    },
+    {
+      "epoch": 0.6938564790913784,
+      "grad_norm": 4.050771891202305,
+      "learning_rate": 3.0578512396694214e-07,
+      "loss": 0.0532,
+      "step": 84
+    },
+    {
+      "epoch": 0.7021166752710377,
+      "grad_norm": 4.957292939462247,
+      "learning_rate": 2.9752066115702476e-07,
+      "loss": 0.0625,
+      "step": 85
+    },
+    {
+      "epoch": 0.710376871450697,
+      "grad_norm": 7.434371068317916,
+      "learning_rate": 2.892561983471074e-07,
+      "loss": 0.0588,
+      "step": 86
+    },
+    {
+      "epoch": 0.7186370676303562,
+      "grad_norm": 4.395509690198425,
+      "learning_rate": 2.8099173553719007e-07,
+      "loss": 0.0581,
+      "step": 87
+    },
+    {
+      "epoch": 0.7268972638100155,
+      "grad_norm": 4.801912810444062,
+      "learning_rate": 2.727272727272727e-07,
+      "loss": 0.0486,
+      "step": 88
+    },
+    {
+      "epoch": 0.7351574599896747,
+      "grad_norm": 4.198285373551988,
+      "learning_rate": 2.6446280991735537e-07,
+      "loss": 0.0549,
+      "step": 89
+    },
+    {
+      "epoch": 0.743417656169334,
+      "grad_norm": 4.525973618695244,
+      "learning_rate": 2.56198347107438e-07,
+      "loss": 0.0513,
+      "step": 90
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 4.548856143122939,
+      "learning_rate": 2.4793388429752067e-07,
+      "loss": 0.0518,
+      "step": 91
+    },
+    {
+      "epoch": 0.7599380485286525,
+      "grad_norm": 4.491739317627872,
+      "learning_rate": 2.396694214876033e-07,
+      "loss": 0.0504,
+      "step": 92
+    },
+    {
+      "epoch": 0.7681982447083118,
+      "grad_norm": 5.507868276221893,
+      "learning_rate": 2.3140495867768595e-07,
+      "loss": 0.0525,
+      "step": 93
+    },
+    {
+      "epoch": 0.7764584408879711,
+      "grad_norm": 3.9085902511823125,
+      "learning_rate": 2.231404958677686e-07,
+      "loss": 0.0488,
+      "step": 94
+    },
+    {
+      "epoch": 0.7847186370676303,
+      "grad_norm": 4.748542698203251,
+      "learning_rate": 2.1487603305785122e-07,
+      "loss": 0.0546,
+      "step": 95
+    },
+    {
+      "epoch": 0.7929788332472896,
+      "grad_norm": 4.134593025394844,
+      "learning_rate": 2.0661157024793388e-07,
+      "loss": 0.041,
+      "step": 96
+    },
+    {
+      "epoch": 0.8012390294269489,
+      "grad_norm": 4.490686472752552,
+      "learning_rate": 1.9834710743801653e-07,
+      "loss": 0.0555,
+      "step": 97
+    },
+    {
+      "epoch": 0.8094992256066081,
+      "grad_norm": 4.16117453892463,
+      "learning_rate": 1.9008264462809918e-07,
+      "loss": 0.052,
+      "step": 98
+    },
+    {
+      "epoch": 0.8177594217862674,
+      "grad_norm": 4.204120951638181,
+      "learning_rate": 1.818181818181818e-07,
+      "loss": 0.0491,
+      "step": 99
+    },
+    {
+      "epoch": 0.8260196179659267,
+      "grad_norm": 3.6858721277315443,
+      "learning_rate": 1.7355371900826445e-07,
+      "loss": 0.0456,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 121,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 130229800009728.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

wo_mask/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a943c37879ea5b2eba7c8c19841021854d026ad3191b08d9027eb53ab168d64
+size 7096

wo_mask/checkpoint-121/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "weqweasdas/RM-Gemma-2B",
+  "architectures": [
+    "GemmaForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 256000
+}

wo_mask/checkpoint-121/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf0cdb9fc2e1452fedb8bc99465db5ed69732cd063165bd6936509c70143316
+size 4945242264

wo_mask/checkpoint-121/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc6b7e091f8f47258d3261726a441a56724748a3e77b80548773d95e0f965ef
+size 67125784

wo_mask/checkpoint-121/model.safetensors.index.json

@@ -0,0 +1,172 @@
+{
+  "metadata": {
+    "total_size": 5012348928
+  },
+  "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-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-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.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",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

wo_mask/checkpoint-121/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

wo_mask/checkpoint-121/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:298441ee7a12cf33d73f5d955d0c9eaf471d6acae1acb18e96bb33470ad8a49c
+size 34315571

wo_mask/checkpoint-121/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

wo_mask/checkpoint-121/tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "max_length": 2048,
+  "model_max_length": 2048,
+  "pad_token": "<eos>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "GemmaTokenizer",
+  "truncation_side": "left",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

wo_mask/checkpoint-121/trainer_state.json

@@ -0,0 +1,880 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9994837377387713,
+  "eval_steps": 500,
+  "global_step": 121,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008260196179659268,
+      "grad_norm": 6.151299127457545,
+      "learning_rate": 9.917355371900827e-07,
+      "loss": 0.8255,
+      "step": 1
+    },
+    {
+      "epoch": 0.016520392359318535,
+      "grad_norm": 5.780122487448709,
+      "learning_rate": 9.834710743801652e-07,
+      "loss": 0.8187,
+      "step": 2
+    },
+    {
+      "epoch": 0.0247805885389778,
+      "grad_norm": 5.284580545759994,
+      "learning_rate": 9.75206611570248e-07,
+      "loss": 0.8312,
+      "step": 3
+    },
+    {
+      "epoch": 0.03304078471863707,
+      "grad_norm": 5.276007202181103,
+      "learning_rate": 9.669421487603305e-07,
+      "loss": 0.8109,
+      "step": 4
+    },
+    {
+      "epoch": 0.041300980898296334,
+      "grad_norm": 5.183295459512783,
+      "learning_rate": 9.586776859504132e-07,
+      "loss": 0.7891,
+      "step": 5
+    },
+    {
+      "epoch": 0.0495611770779556,
+      "grad_norm": 5.332217660707675,
+      "learning_rate": 9.504132231404959e-07,
+      "loss": 0.7743,
+      "step": 6
+    },
+    {
+      "epoch": 0.05782137325761487,
+      "grad_norm": 5.730074140553302,
+      "learning_rate": 9.421487603305784e-07,
+      "loss": 0.7559,
+      "step": 7
+    },
+    {
+      "epoch": 0.06608156943727414,
+      "grad_norm": 5.293612302527298,
+      "learning_rate": 9.338842975206612e-07,
+      "loss": 0.7155,
+      "step": 8
+    },
+    {
+      "epoch": 0.0743417656169334,
+      "grad_norm": 5.085007745006763,
+      "learning_rate": 9.256198347107438e-07,
+      "loss": 0.7421,
+      "step": 9
+    },
+    {
+      "epoch": 0.08260196179659267,
+      "grad_norm": 5.098816875901866,
+      "learning_rate": 9.173553719008264e-07,
+      "loss": 0.7,
+      "step": 10
+    },
+    {
+      "epoch": 0.09086215797625194,
+      "grad_norm": 7.8680991633839765,
+      "learning_rate": 9.09090909090909e-07,
+      "loss": 0.6778,
+      "step": 11
+    },
+    {
+      "epoch": 0.0991223541559112,
+      "grad_norm": 7.957843903611215,
+      "learning_rate": 9.008264462809917e-07,
+      "loss": 0.6526,
+      "step": 12
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 7.059924617430371,
+      "learning_rate": 8.925619834710744e-07,
+      "loss": 0.621,
+      "step": 13
+    },
+    {
+      "epoch": 0.11564274651522974,
+      "grad_norm": 8.652197114711964,
+      "learning_rate": 8.84297520661157e-07,
+      "loss": 0.6319,
+      "step": 14
+    },
+    {
+      "epoch": 0.12390294269488901,
+      "grad_norm": 6.832187915211578,
+      "learning_rate": 8.760330578512396e-07,
+      "loss": 0.6022,
+      "step": 15
+    },
+    {
+      "epoch": 0.13216313887454828,
+      "grad_norm": 7.171557589862187,
+      "learning_rate": 8.677685950413223e-07,
+      "loss": 0.6056,
+      "step": 16
+    },
+    {
+      "epoch": 0.14042333505420754,
+      "grad_norm": 7.342397949784474,
+      "learning_rate": 8.595041322314049e-07,
+      "loss": 0.5822,
+      "step": 17
+    },
+    {
+      "epoch": 0.1486835312338668,
+      "grad_norm": 6.409864684511031,
+      "learning_rate": 8.512396694214876e-07,
+      "loss": 0.5741,
+      "step": 18
+    },
+    {
+      "epoch": 0.15694372741352608,
+      "grad_norm": 5.90031720345188,
+      "learning_rate": 8.429752066115701e-07,
+      "loss": 0.5428,
+      "step": 19
+    },
+    {
+      "epoch": 0.16520392359318534,
+      "grad_norm": 5.721498192124633,
+      "learning_rate": 8.347107438016529e-07,
+      "loss": 0.5106,
+      "step": 20
+    },
+    {
+      "epoch": 0.1734641197728446,
+      "grad_norm": 5.393442254760478,
+      "learning_rate": 8.264462809917355e-07,
+      "loss": 0.4733,
+      "step": 21
+    },
+    {
+      "epoch": 0.18172431595250388,
+      "grad_norm": 5.474634077507737,
+      "learning_rate": 8.181818181818182e-07,
+      "loss": 0.4612,
+      "step": 22
+    },
+    {
+      "epoch": 0.18998451213216314,
+      "grad_norm": 5.75044582103474,
+      "learning_rate": 8.099173553719008e-07,
+      "loss": 0.4467,
+      "step": 23
+    },
+    {
+      "epoch": 0.1982447083118224,
+      "grad_norm": 5.364804428827895,
+      "learning_rate": 8.016528925619835e-07,
+      "loss": 0.4191,
+      "step": 24
+    },
+    {
+      "epoch": 0.20650490449148168,
+      "grad_norm": 5.48762563438622,
+      "learning_rate": 7.933884297520661e-07,
+      "loss": 0.3964,
+      "step": 25
+    },
+    {
+      "epoch": 0.21476510067114093,
+      "grad_norm": 5.721966438387265,
+      "learning_rate": 7.851239669421487e-07,
+      "loss": 0.3805,
+      "step": 26
+    },
+    {
+      "epoch": 0.22302529685080022,
+      "grad_norm": 5.637593244471927,
+      "learning_rate": 7.768595041322314e-07,
+      "loss": 0.357,
+      "step": 27
+    },
+    {
+      "epoch": 0.23128549303045948,
+      "grad_norm": 5.253127366512256,
+      "learning_rate": 7.68595041322314e-07,
+      "loss": 0.3176,
+      "step": 28
+    },
+    {
+      "epoch": 0.23954568921011873,
+      "grad_norm": 5.402262981848415,
+      "learning_rate": 7.603305785123967e-07,
+      "loss": 0.3344,
+      "step": 29
+    },
+    {
+      "epoch": 0.24780588538977802,
+      "grad_norm": 5.221833996297194,
+      "learning_rate": 7.520661157024793e-07,
+      "loss": 0.3157,
+      "step": 30
+    },
+    {
+      "epoch": 0.2560660815694373,
+      "grad_norm": 4.936826111971605,
+      "learning_rate": 7.43801652892562e-07,
+      "loss": 0.293,
+      "step": 31
+    },
+    {
+      "epoch": 0.26432627774909656,
+      "grad_norm": 5.467317249015266,
+      "learning_rate": 7.355371900826446e-07,
+      "loss": 0.2874,
+      "step": 32
+    },
+    {
+      "epoch": 0.2725864739287558,
+      "grad_norm": 5.731777293683918,
+      "learning_rate": 7.272727272727272e-07,
+      "loss": 0.2619,
+      "step": 33
+    },
+    {
+      "epoch": 0.2808466701084151,
+      "grad_norm": 5.007564269770195,
+      "learning_rate": 7.190082644628099e-07,
+      "loss": 0.2453,
+      "step": 34
+    },
+    {
+      "epoch": 0.28910686628807436,
+      "grad_norm": 5.129081210265052,
+      "learning_rate": 7.107438016528925e-07,
+      "loss": 0.2342,
+      "step": 35
+    },
+    {
+      "epoch": 0.2973670624677336,
+      "grad_norm": 5.615993298785848,
+      "learning_rate": 7.024793388429752e-07,
+      "loss": 0.2244,
+      "step": 36
+    },
+    {
+      "epoch": 0.3056272586473929,
+      "grad_norm": 5.92148008008197,
+      "learning_rate": 6.942148760330578e-07,
+      "loss": 0.2351,
+      "step": 37
+    },
+    {
+      "epoch": 0.31388745482705216,
+      "grad_norm": 5.235043676350482,
+      "learning_rate": 6.859504132231405e-07,
+      "loss": 0.2002,
+      "step": 38
+    },
+    {
+      "epoch": 0.3221476510067114,
+      "grad_norm": 4.845523937915667,
+      "learning_rate": 6.776859504132231e-07,
+      "loss": 0.1846,
+      "step": 39
+    },
+    {
+      "epoch": 0.3304078471863707,
+      "grad_norm": 5.453591513567315,
+      "learning_rate": 6.694214876033058e-07,
+      "loss": 0.1846,
+      "step": 40
+    },
+    {
+      "epoch": 0.33866804336602996,
+      "grad_norm": 5.406878125038352,
+      "learning_rate": 6.611570247933884e-07,
+      "loss": 0.1803,
+      "step": 41
+    },
+    {
+      "epoch": 0.3469282395456892,
+      "grad_norm": 5.720653857597168,
+      "learning_rate": 6.52892561983471e-07,
+      "loss": 0.1709,
+      "step": 42
+    },
+    {
+      "epoch": 0.3551884357253485,
+      "grad_norm": 4.7807197357380655,
+      "learning_rate": 6.446280991735537e-07,
+      "loss": 0.1535,
+      "step": 43
+    },
+    {
+      "epoch": 0.36344863190500776,
+      "grad_norm": 9.504234726479488,
+      "learning_rate": 6.363636363636363e-07,
+      "loss": 0.1492,
+      "step": 44
+    },
+    {
+      "epoch": 0.371708828084667,
+      "grad_norm": 5.4032075384453515,
+      "learning_rate": 6.28099173553719e-07,
+      "loss": 0.1352,
+      "step": 45
+    },
+    {
+      "epoch": 0.37996902426432627,
+      "grad_norm": 4.957836295699517,
+      "learning_rate": 6.198347107438017e-07,
+      "loss": 0.1403,
+      "step": 46
+    },
+    {
+      "epoch": 0.38822922044398556,
+      "grad_norm": 4.821649080443891,
+      "learning_rate": 6.115702479338843e-07,
+      "loss": 0.1334,
+      "step": 47
+    },
+    {
+      "epoch": 0.3964894166236448,
+      "grad_norm": 6.078364579347982,
+      "learning_rate": 6.033057851239669e-07,
+      "loss": 0.1359,
+      "step": 48
+    },
+    {
+      "epoch": 0.40474961280330407,
+      "grad_norm": 4.920465068560464,
+      "learning_rate": 5.950413223140495e-07,
+      "loss": 0.1246,
+      "step": 49
+    },
+    {
+      "epoch": 0.41300980898296336,
+      "grad_norm": 4.9181285607981104,
+      "learning_rate": 5.867768595041323e-07,
+      "loss": 0.1176,
+      "step": 50
+    },
+    {
+      "epoch": 0.4212700051626226,
+      "grad_norm": 5.499139905865122,
+      "learning_rate": 5.785123966942148e-07,
+      "loss": 0.1189,
+      "step": 51
+    },
+    {
+      "epoch": 0.42953020134228187,
+      "grad_norm": 5.485462773630812,
+      "learning_rate": 5.702479338842975e-07,
+      "loss": 0.1125,
+      "step": 52
+    },
+    {
+      "epoch": 0.43779039752194115,
+      "grad_norm": 5.128741877444076,
+      "learning_rate": 5.619834710743801e-07,
+      "loss": 0.1088,
+      "step": 53
+    },
+    {
+      "epoch": 0.44605059370160044,
+      "grad_norm": 5.910794469376855,
+      "learning_rate": 5.537190082644629e-07,
+      "loss": 0.1053,
+      "step": 54
+    },
+    {
+      "epoch": 0.45431078988125967,
+      "grad_norm": 4.503146156347465,
+      "learning_rate": 5.454545454545454e-07,
+      "loss": 0.0906,
+      "step": 55
+    },
+    {
+      "epoch": 0.46257098606091895,
+      "grad_norm": 4.31143603563169,
+      "learning_rate": 5.371900826446281e-07,
+      "loss": 0.0922,
+      "step": 56
+    },
+    {
+      "epoch": 0.47083118224057824,
+      "grad_norm": 4.858551221277556,
+      "learning_rate": 5.289256198347107e-07,
+      "loss": 0.093,
+      "step": 57
+    },
+    {
+      "epoch": 0.47909137842023747,
+      "grad_norm": 4.395108974639106,
+      "learning_rate": 5.206611570247934e-07,
+      "loss": 0.0934,
+      "step": 58
+    },
+    {
+      "epoch": 0.48735157459989675,
+      "grad_norm": 4.748753031390499,
+      "learning_rate": 5.12396694214876e-07,
+      "loss": 0.0939,
+      "step": 59
+    },
+    {
+      "epoch": 0.49561177077955604,
+      "grad_norm": 5.165370234374591,
+      "learning_rate": 5.041322314049586e-07,
+      "loss": 0.0909,
+      "step": 60
+    },
+    {
+      "epoch": 0.5038719669592153,
+      "grad_norm": 4.780186488881603,
+      "learning_rate": 4.958677685950413e-07,
+      "loss": 0.0979,
+      "step": 61
+    },
+    {
+      "epoch": 0.5121321631388746,
+      "grad_norm": 4.526937392254728,
+      "learning_rate": 4.87603305785124e-07,
+      "loss": 0.089,
+      "step": 62
+    },
+    {
+      "epoch": 0.5203923593185338,
+      "grad_norm": 3.9484832227284037,
+      "learning_rate": 4.793388429752066e-07,
+      "loss": 0.0813,
+      "step": 63
+    },
+    {
+      "epoch": 0.5286525554981931,
+      "grad_norm": 4.626844473209987,
+      "learning_rate": 4.710743801652892e-07,
+      "loss": 0.0788,
+      "step": 64
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 4.111714528890263,
+      "learning_rate": 4.628099173553719e-07,
+      "loss": 0.0686,
+      "step": 65
+    },
+    {
+      "epoch": 0.5451729478575116,
+      "grad_norm": 3.847620812825054,
+      "learning_rate": 4.545454545454545e-07,
+      "loss": 0.0624,
+      "step": 66
+    },
+    {
+      "epoch": 0.5534331440371709,
+      "grad_norm": 4.014429221103349,
+      "learning_rate": 4.462809917355372e-07,
+      "loss": 0.0748,
+      "step": 67
+    },
+    {
+      "epoch": 0.5616933402168302,
+      "grad_norm": 5.410596858204166,
+      "learning_rate": 4.380165289256198e-07,
+      "loss": 0.0807,
+      "step": 68
+    },
+    {
+      "epoch": 0.5699535363964894,
+      "grad_norm": 5.060478727233313,
+      "learning_rate": 4.2975206611570245e-07,
+      "loss": 0.0814,
+      "step": 69
+    },
+    {
+      "epoch": 0.5782137325761487,
+      "grad_norm": 3.8693176106349663,
+      "learning_rate": 4.2148760330578507e-07,
+      "loss": 0.0708,
+      "step": 70
+    },
+    {
+      "epoch": 0.586473928755808,
+      "grad_norm": 3.6572429929976877,
+      "learning_rate": 4.1322314049586775e-07,
+      "loss": 0.0586,
+      "step": 71
+    },
+    {
+      "epoch": 0.5947341249354672,
+      "grad_norm": 4.291915714476109,
+      "learning_rate": 4.049586776859504e-07,
+      "loss": 0.0695,
+      "step": 72
+    },
+    {
+      "epoch": 0.6029943211151265,
+      "grad_norm": 6.79226277468724,
+      "learning_rate": 3.9669421487603305e-07,
+      "loss": 0.0683,
+      "step": 73
+    },
+    {
+      "epoch": 0.6112545172947857,
+      "grad_norm": 4.49100451001806,
+      "learning_rate": 3.884297520661157e-07,
+      "loss": 0.0564,
+      "step": 74
+    },
+    {
+      "epoch": 0.619514713474445,
+      "grad_norm": 5.899350796294677,
+      "learning_rate": 3.8016528925619836e-07,
+      "loss": 0.0765,
+      "step": 75
+    },
+    {
+      "epoch": 0.6277749096541043,
+      "grad_norm": 4.515411657713084,
+      "learning_rate": 3.71900826446281e-07,
+      "loss": 0.0659,
+      "step": 76
+    },
+    {
+      "epoch": 0.6360351058337635,
+      "grad_norm": 4.177275599836179,
+      "learning_rate": 3.636363636363636e-07,
+      "loss": 0.0589,
+      "step": 77
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 4.52383547075553,
+      "learning_rate": 3.5537190082644623e-07,
+      "loss": 0.0676,
+      "step": 78
+    },
+    {
+      "epoch": 0.6525554981930821,
+      "grad_norm": 4.389273447724941,
+      "learning_rate": 3.471074380165289e-07,
+      "loss": 0.0569,
+      "step": 79
+    },
+    {
+      "epoch": 0.6608156943727413,
+      "grad_norm": 6.005106644541459,
+      "learning_rate": 3.3884297520661153e-07,
+      "loss": 0.0676,
+      "step": 80
+    },
+    {
+      "epoch": 0.6690758905524006,
+      "grad_norm": 4.143584995230645,
+      "learning_rate": 3.305785123966942e-07,
+      "loss": 0.0611,
+      "step": 81
+    },
+    {
+      "epoch": 0.6773360867320599,
+      "grad_norm": 4.636039389852911,
+      "learning_rate": 3.2231404958677684e-07,
+      "loss": 0.0547,
+      "step": 82
+    },
+    {
+      "epoch": 0.6855962829117191,
+      "grad_norm": 4.498379839418488,
+      "learning_rate": 3.140495867768595e-07,
+      "loss": 0.0541,
+      "step": 83
+    },
+    {
+      "epoch": 0.6938564790913784,
+      "grad_norm": 4.050771891202305,
+      "learning_rate": 3.0578512396694214e-07,
+      "loss": 0.0532,
+      "step": 84
+    },
+    {
+      "epoch": 0.7021166752710377,
+      "grad_norm": 4.957292939462247,
+      "learning_rate": 2.9752066115702476e-07,
+      "loss": 0.0625,
+      "step": 85
+    },
+    {
+      "epoch": 0.710376871450697,
+      "grad_norm": 7.434371068317916,
+      "learning_rate": 2.892561983471074e-07,
+      "loss": 0.0588,
+      "step": 86
+    },
+    {
+      "epoch": 0.7186370676303562,
+      "grad_norm": 4.395509690198425,
+      "learning_rate": 2.8099173553719007e-07,
+      "loss": 0.0581,
+      "step": 87
+    },
+    {
+      "epoch": 0.7268972638100155,
+      "grad_norm": 4.801912810444062,
+      "learning_rate": 2.727272727272727e-07,
+      "loss": 0.0486,
+      "step": 88
+    },
+    {
+      "epoch": 0.7351574599896747,
+      "grad_norm": 4.198285373551988,
+      "learning_rate": 2.6446280991735537e-07,
+      "loss": 0.0549,
+      "step": 89
+    },
+    {
+      "epoch": 0.743417656169334,
+      "grad_norm": 4.525973618695244,
+      "learning_rate": 2.56198347107438e-07,
+      "loss": 0.0513,
+      "step": 90
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 4.548856143122939,
+      "learning_rate": 2.4793388429752067e-07,
+      "loss": 0.0518,
+      "step": 91
+    },
+    {
+      "epoch": 0.7599380485286525,
+      "grad_norm": 4.491739317627872,
+      "learning_rate": 2.396694214876033e-07,
+      "loss": 0.0504,
+      "step": 92
+    },
+    {
+      "epoch": 0.7681982447083118,
+      "grad_norm": 5.507868276221893,
+      "learning_rate": 2.3140495867768595e-07,
+      "loss": 0.0525,
+      "step": 93
+    },
+    {
+      "epoch": 0.7764584408879711,
+      "grad_norm": 3.9085902511823125,
+      "learning_rate": 2.231404958677686e-07,
+      "loss": 0.0488,
+      "step": 94
+    },
+    {
+      "epoch": 0.7847186370676303,
+      "grad_norm": 4.748542698203251,
+      "learning_rate": 2.1487603305785122e-07,
+      "loss": 0.0546,
+      "step": 95
+    },
+    {
+      "epoch": 0.7929788332472896,
+      "grad_norm": 4.134593025394844,
+      "learning_rate": 2.0661157024793388e-07,
+      "loss": 0.041,
+      "step": 96
+    },
+    {
+      "epoch": 0.8012390294269489,
+      "grad_norm": 4.490686472752552,
+      "learning_rate": 1.9834710743801653e-07,
+      "loss": 0.0555,
+      "step": 97
+    },
+    {
+      "epoch": 0.8094992256066081,
+      "grad_norm": 4.16117453892463,
+      "learning_rate": 1.9008264462809918e-07,
+      "loss": 0.052,
+      "step": 98
+    },
+    {
+      "epoch": 0.8177594217862674,
+      "grad_norm": 4.204120951638181,
+      "learning_rate": 1.818181818181818e-07,
+      "loss": 0.0491,
+      "step": 99
+    },
+    {
+      "epoch": 0.8260196179659267,
+      "grad_norm": 3.6858721277315443,
+      "learning_rate": 1.7355371900826445e-07,
+      "loss": 0.0456,
+      "step": 100
+    },
+    {
+      "epoch": 0.8342798141455859,
+      "grad_norm": 4.882005579520836,
+      "learning_rate": 1.652892561983471e-07,
+      "loss": 0.0483,
+      "step": 101
+    },
+    {
+      "epoch": 0.8425400103252452,
+      "grad_norm": 5.420086119834582,
+      "learning_rate": 1.5702479338842976e-07,
+      "loss": 0.045,
+      "step": 102
+    },
+    {
+      "epoch": 0.8508002065049045,
+      "grad_norm": 4.299574765950468,
+      "learning_rate": 1.4876033057851238e-07,
+      "loss": 0.0431,
+      "step": 103
+    },
+    {
+      "epoch": 0.8590604026845637,
+      "grad_norm": 5.412657060787109,
+      "learning_rate": 1.4049586776859503e-07,
+      "loss": 0.0449,
+      "step": 104
+    },
+    {
+      "epoch": 0.8673205988642231,
+      "grad_norm": 4.358066967612829,
+      "learning_rate": 1.3223140495867768e-07,
+      "loss": 0.0463,
+      "step": 105
+    },
+    {
+      "epoch": 0.8755807950438823,
+      "grad_norm": 4.2546611824159095,
+      "learning_rate": 1.2396694214876034e-07,
+      "loss": 0.0407,
+      "step": 106
+    },
+    {
+      "epoch": 0.8838409912235415,
+      "grad_norm": 3.9158572221460766,
+      "learning_rate": 1.1570247933884297e-07,
+      "loss": 0.0407,
+      "step": 107
+    },
+    {
+      "epoch": 0.8921011874032009,
+      "grad_norm": 5.5309953405728125,
+      "learning_rate": 1.0743801652892561e-07,
+      "loss": 0.0487,
+      "step": 108
+    },
+    {
+      "epoch": 0.9003613835828601,
+      "grad_norm": 3.2852480193433604,
+      "learning_rate": 9.917355371900826e-08,
+      "loss": 0.0408,
+      "step": 109
+    },
+    {
+      "epoch": 0.9086215797625193,
+      "grad_norm": 3.67113768716039,
+      "learning_rate": 9.09090909090909e-08,
+      "loss": 0.0436,
+      "step": 110
+    },
+    {
+      "epoch": 0.9168817759421787,
+      "grad_norm": 3.573260793363699,
+      "learning_rate": 8.264462809917355e-08,
+      "loss": 0.0399,
+      "step": 111
+    },
+    {
+      "epoch": 0.9251419721218379,
+      "grad_norm": 4.452647993157429,
+      "learning_rate": 7.438016528925619e-08,
+      "loss": 0.0464,
+      "step": 112
+    },
+    {
+      "epoch": 0.9334021683014971,
+      "grad_norm": 3.8497858085693353,
+      "learning_rate": 6.611570247933884e-08,
+      "loss": 0.04,
+      "step": 113
+    },
+    {
+      "epoch": 0.9416623644811565,
+      "grad_norm": 5.172088209506264,
+      "learning_rate": 5.785123966942149e-08,
+      "loss": 0.0413,
+      "step": 114
+    },
+    {
+      "epoch": 0.9499225606608157,
+      "grad_norm": 3.674285708196009,
+      "learning_rate": 4.958677685950413e-08,
+      "loss": 0.0406,
+      "step": 115
+    },
+    {
+      "epoch": 0.9581827568404749,
+      "grad_norm": 3.5948562795658723,
+      "learning_rate": 4.1322314049586776e-08,
+      "loss": 0.0353,
+      "step": 116
+    },
+    {
+      "epoch": 0.9664429530201343,
+      "grad_norm": 3.662645188403965,
+      "learning_rate": 3.305785123966942e-08,
+      "loss": 0.0416,
+      "step": 117
+    },
+    {
+      "epoch": 0.9747031491997935,
+      "grad_norm": 3.766802533629169,
+      "learning_rate": 2.4793388429752066e-08,
+      "loss": 0.0395,
+      "step": 118
+    },
+    {
+      "epoch": 0.9829633453794527,
+      "grad_norm": 3.0783880440297775,
+      "learning_rate": 1.652892561983471e-08,
+      "loss": 0.0355,
+      "step": 119
+    },
+    {
+      "epoch": 0.9912235415591121,
+      "grad_norm": 4.411105484316595,
+      "learning_rate": 8.264462809917355e-09,
+      "loss": 0.0448,
+      "step": 120
+    },
+    {
+      "epoch": 0.9994837377387713,
+      "grad_norm": 3.734016171700682,
+      "learning_rate": 0.0,
+      "loss": 0.0423,
+      "step": 121
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 121,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 157230967554048.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

wo_mask/checkpoint-121/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a943c37879ea5b2eba7c8c19841021854d026ad3191b08d9027eb53ab168d64
+size 7096