Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* 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
+mask/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+mask/checkpoint-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text

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
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90945ad44b0326cfacb626ef380654f83b4d2c326e7933dd073f045c427c41e0
+size 4945242264

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4438e59e14e9ce61518c78ced42900df9af50febf1ddb5e7c345928b10a006a
+size 67125784

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"
+  }
+}

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
+  }
+}

mask/checkpoint-100/tokenizer.json

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

mask/checkpoint-100/tokenizer.model

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

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
+}

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": 8.833224831341008,
+      "learning_rate": 9.917355371900827e-07,
+      "loss": 0.6051,
+      "step": 1
+    },
+    {
+      "epoch": 0.016520392359318535,
+      "grad_norm": 8.28765409813015,
+      "learning_rate": 9.834710743801652e-07,
+      "loss": 0.5941,
+      "step": 2
+    },
+    {
+      "epoch": 0.0247805885389778,
+      "grad_norm": 7.7759780312342075,
+      "learning_rate": 9.75206611570248e-07,
+      "loss": 0.601,
+      "step": 3
+    },
+    {
+      "epoch": 0.03304078471863707,
+      "grad_norm": 6.331869804834741,
+      "learning_rate": 9.669421487603305e-07,
+      "loss": 0.5744,
+      "step": 4
+    },
+    {
+      "epoch": 0.041300980898296334,
+      "grad_norm": 6.82444805885506,
+      "learning_rate": 9.586776859504132e-07,
+      "loss": 0.5529,
+      "step": 5
+    },
+    {
+      "epoch": 0.0495611770779556,
+      "grad_norm": 7.2220736569961375,
+      "learning_rate": 9.504132231404959e-07,
+      "loss": 0.5283,
+      "step": 6
+    },
+    {
+      "epoch": 0.05782137325761487,
+      "grad_norm": 7.920339746711006,
+      "learning_rate": 9.421487603305784e-07,
+      "loss": 0.5128,
+      "step": 7
+    },
+    {
+      "epoch": 0.06608156943727414,
+      "grad_norm": 7.741933749943497,
+      "learning_rate": 9.338842975206612e-07,
+      "loss": 0.4731,
+      "step": 8
+    },
+    {
+      "epoch": 0.0743417656169334,
+      "grad_norm": 7.33305646635204,
+      "learning_rate": 9.256198347107438e-07,
+      "loss": 0.4889,
+      "step": 9
+    },
+    {
+      "epoch": 0.08260196179659267,
+      "grad_norm": 5.397722616120573,
+      "learning_rate": 9.173553719008264e-07,
+      "loss": 0.4445,
+      "step": 10
+    },
+    {
+      "epoch": 0.09086215797625194,
+      "grad_norm": 6.306346639937355,
+      "learning_rate": 9.09090909090909e-07,
+      "loss": 0.3776,
+      "step": 11
+    },
+    {
+      "epoch": 0.0991223541559112,
+      "grad_norm": 6.417179207932981,
+      "learning_rate": 9.008264462809917e-07,
+      "loss": 0.3639,
+      "step": 12
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 6.4453913869424095,
+      "learning_rate": 8.925619834710744e-07,
+      "loss": 0.3558,
+      "step": 13
+    },
+    {
+      "epoch": 0.11564274651522974,
+      "grad_norm": 7.114718937999426,
+      "learning_rate": 8.84297520661157e-07,
+      "loss": 0.3598,
+      "step": 14
+    },
+    {
+      "epoch": 0.12390294269488901,
+      "grad_norm": 6.547127744231474,
+      "learning_rate": 8.760330578512396e-07,
+      "loss": 0.3273,
+      "step": 15
+    },
+    {
+      "epoch": 0.13216313887454828,
+      "grad_norm": 7.307678912774062,
+      "learning_rate": 8.677685950413223e-07,
+      "loss": 0.3453,
+      "step": 16
+    },
+    {
+      "epoch": 0.14042333505420754,
+      "grad_norm": 7.466082653405334,
+      "learning_rate": 8.595041322314049e-07,
+      "loss": 0.3197,
+      "step": 17
+    },
+    {
+      "epoch": 0.1486835312338668,
+      "grad_norm": 6.58761708106512,
+      "learning_rate": 8.512396694214876e-07,
+      "loss": 0.2958,
+      "step": 18
+    },
+    {
+      "epoch": 0.15694372741352608,
+      "grad_norm": 6.3803321743795784,
+      "learning_rate": 8.429752066115701e-07,
+      "loss": 0.2863,
+      "step": 19
+    },
+    {
+      "epoch": 0.16520392359318534,
+      "grad_norm": 6.207348064176668,
+      "learning_rate": 8.347107438016529e-07,
+      "loss": 0.2693,
+      "step": 20
+    },
+    {
+      "epoch": 0.1734641197728446,
+      "grad_norm": 5.776604798851602,
+      "learning_rate": 8.264462809917355e-07,
+      "loss": 0.2314,
+      "step": 21
+    },
+    {
+      "epoch": 0.18172431595250388,
+      "grad_norm": 6.277376376848909,
+      "learning_rate": 8.181818181818182e-07,
+      "loss": 0.242,
+      "step": 22
+    },
+    {
+      "epoch": 0.18998451213216314,
+      "grad_norm": 6.590485185775048,
+      "learning_rate": 8.099173553719008e-07,
+      "loss": 0.2333,
+      "step": 23
+    },
+    {
+      "epoch": 0.1982447083118224,
+      "grad_norm": 6.094516363574539,
+      "learning_rate": 8.016528925619835e-07,
+      "loss": 0.2008,
+      "step": 24
+    },
+    {
+      "epoch": 0.20650490449148168,
+      "grad_norm": 6.010919592697381,
+      "learning_rate": 7.933884297520661e-07,
+      "loss": 0.1985,
+      "step": 25
+    },
+    {
+      "epoch": 0.21476510067114093,
+      "grad_norm": 5.948476311514442,
+      "learning_rate": 7.851239669421487e-07,
+      "loss": 0.1981,
+      "step": 26
+    },
+    {
+      "epoch": 0.22302529685080022,
+      "grad_norm": 5.657766604243092,
+      "learning_rate": 7.768595041322314e-07,
+      "loss": 0.1722,
+      "step": 27
+    },
+    {
+      "epoch": 0.23128549303045948,
+      "grad_norm": 5.3436389934314885,
+      "learning_rate": 7.68595041322314e-07,
+      "loss": 0.139,
+      "step": 28
+    },
+    {
+      "epoch": 0.23954568921011873,
+      "grad_norm": 6.050567759464481,
+      "learning_rate": 7.603305785123967e-07,
+      "loss": 0.1872,
+      "step": 29
+    },
+    {
+      "epoch": 0.24780588538977802,
+      "grad_norm": 5.888273604838657,
+      "learning_rate": 7.520661157024793e-07,
+      "loss": 0.182,
+      "step": 30
+    },
+    {
+      "epoch": 0.2560660815694373,
+      "grad_norm": 4.643340194462475,
+      "learning_rate": 7.43801652892562e-07,
+      "loss": 0.1337,
+      "step": 31
+    },
+    {
+      "epoch": 0.26432627774909656,
+      "grad_norm": 5.2982546245512445,
+      "learning_rate": 7.355371900826446e-07,
+      "loss": 0.1355,
+      "step": 32
+    },
+    {
+      "epoch": 0.2725864739287558,
+      "grad_norm": 5.444124845250493,
+      "learning_rate": 7.272727272727272e-07,
+      "loss": 0.1422,
+      "step": 33
+    },
+    {
+      "epoch": 0.2808466701084151,
+      "grad_norm": 5.305028072330304,
+      "learning_rate": 7.190082644628099e-07,
+      "loss": 0.1431,
+      "step": 34
+    },
+    {
+      "epoch": 0.28910686628807436,
+      "grad_norm": 4.64286696526394,
+      "learning_rate": 7.107438016528925e-07,
+      "loss": 0.1078,
+      "step": 35
+    },
+    {
+      "epoch": 0.2973670624677336,
+      "grad_norm": 5.077942838771361,
+      "learning_rate": 7.024793388429752e-07,
+      "loss": 0.1133,
+      "step": 36
+    },
+    {
+      "epoch": 0.3056272586473929,
+      "grad_norm": 5.827543683385444,
+      "learning_rate": 6.942148760330578e-07,
+      "loss": 0.1373,
+      "step": 37
+    },
+    {
+      "epoch": 0.31388745482705216,
+      "grad_norm": 4.619838338481372,
+      "learning_rate": 6.859504132231405e-07,
+      "loss": 0.0949,
+      "step": 38
+    },
+    {
+      "epoch": 0.3221476510067114,
+      "grad_norm": 4.877454362063687,
+      "learning_rate": 6.776859504132231e-07,
+      "loss": 0.106,
+      "step": 39
+    },
+    {
+      "epoch": 0.3304078471863707,
+      "grad_norm": 5.9983838979070185,
+      "learning_rate": 6.694214876033058e-07,
+      "loss": 0.1193,
+      "step": 40
+    },
+    {
+      "epoch": 0.33866804336602996,
+      "grad_norm": 4.857934673938672,
+      "learning_rate": 6.611570247933884e-07,
+      "loss": 0.1133,
+      "step": 41
+    },
+    {
+      "epoch": 0.3469282395456892,
+      "grad_norm": 4.972035576901775,
+      "learning_rate": 6.52892561983471e-07,
+      "loss": 0.1037,
+      "step": 42
+    },
+    {
+      "epoch": 0.3551884357253485,
+      "grad_norm": 3.9492698890695257,
+      "learning_rate": 6.446280991735537e-07,
+      "loss": 0.0887,
+      "step": 43
+    },
+    {
+      "epoch": 0.36344863190500776,
+      "grad_norm": 4.639663084480974,
+      "learning_rate": 6.363636363636363e-07,
+      "loss": 0.0964,
+      "step": 44
+    },
+    {
+      "epoch": 0.371708828084667,
+      "grad_norm": 4.238244774637056,
+      "learning_rate": 6.28099173553719e-07,
+      "loss": 0.0814,
+      "step": 45
+    },
+    {
+      "epoch": 0.37996902426432627,
+      "grad_norm": 4.317260522087231,
+      "learning_rate": 6.198347107438017e-07,
+      "loss": 0.0856,
+      "step": 46
+    },
+    {
+      "epoch": 0.38822922044398556,
+      "grad_norm": 5.008730972224478,
+      "learning_rate": 6.115702479338843e-07,
+      "loss": 0.0813,
+      "step": 47
+    },
+    {
+      "epoch": 0.3964894166236448,
+      "grad_norm": 4.572740643145854,
+      "learning_rate": 6.033057851239669e-07,
+      "loss": 0.0861,
+      "step": 48
+    },
+    {
+      "epoch": 0.40474961280330407,
+      "grad_norm": 4.223394908610836,
+      "learning_rate": 5.950413223140495e-07,
+      "loss": 0.0851,
+      "step": 49
+    },
+    {
+      "epoch": 0.41300980898296336,
+      "grad_norm": 4.439883229699326,
+      "learning_rate": 5.867768595041323e-07,
+      "loss": 0.0758,
+      "step": 50
+    },
+    {
+      "epoch": 0.4212700051626226,
+      "grad_norm": 4.340441774291824,
+      "learning_rate": 5.785123966942148e-07,
+      "loss": 0.0732,
+      "step": 51
+    },
+    {
+      "epoch": 0.42953020134228187,
+      "grad_norm": 4.289070334443712,
+      "learning_rate": 5.702479338842975e-07,
+      "loss": 0.0732,
+      "step": 52
+    },
+    {
+      "epoch": 0.43779039752194115,
+      "grad_norm": 5.126081829105661,
+      "learning_rate": 5.619834710743801e-07,
+      "loss": 0.0832,
+      "step": 53
+    },
+    {
+      "epoch": 0.44605059370160044,
+      "grad_norm": 4.993834428920049,
+      "learning_rate": 5.537190082644629e-07,
+      "loss": 0.0848,
+      "step": 54
+    },
+    {
+      "epoch": 0.45431078988125967,
+      "grad_norm": 3.716478265572608,
+      "learning_rate": 5.454545454545454e-07,
+      "loss": 0.0604,
+      "step": 55
+    },
+    {
+      "epoch": 0.46257098606091895,
+      "grad_norm": 4.178642533290566,
+      "learning_rate": 5.371900826446281e-07,
+      "loss": 0.0681,
+      "step": 56
+    },
+    {
+      "epoch": 0.47083118224057824,
+      "grad_norm": 4.232442593100394,
+      "learning_rate": 5.289256198347107e-07,
+      "loss": 0.0599,
+      "step": 57
+    },
+    {
+      "epoch": 0.47909137842023747,
+      "grad_norm": 4.150222898652126,
+      "learning_rate": 5.206611570247934e-07,
+      "loss": 0.0703,
+      "step": 58
+    },
+    {
+      "epoch": 0.48735157459989675,
+      "grad_norm": 4.403051637850364,
+      "learning_rate": 5.12396694214876e-07,
+      "loss": 0.0713,
+      "step": 59
+    },
+    {
+      "epoch": 0.49561177077955604,
+      "grad_norm": 4.660075631992056,
+      "learning_rate": 5.041322314049586e-07,
+      "loss": 0.056,
+      "step": 60
+    },
+    {
+      "epoch": 0.5038719669592153,
+      "grad_norm": 4.694839170968639,
+      "learning_rate": 4.958677685950413e-07,
+      "loss": 0.079,
+      "step": 61
+    },
+    {
+      "epoch": 0.5121321631388746,
+      "grad_norm": 4.186240576925523,
+      "learning_rate": 4.87603305785124e-07,
+      "loss": 0.0674,
+      "step": 62
+    },
+    {
+      "epoch": 0.5203923593185338,
+      "grad_norm": 3.3199829625607955,
+      "learning_rate": 4.793388429752066e-07,
+      "loss": 0.0527,
+      "step": 63
+    },
+    {
+      "epoch": 0.5286525554981931,
+      "grad_norm": 4.997276223790548,
+      "learning_rate": 4.710743801652892e-07,
+      "loss": 0.0649,
+      "step": 64
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 4.376618807129675,
+      "learning_rate": 4.628099173553719e-07,
+      "loss": 0.0491,
+      "step": 65
+    },
+    {
+      "epoch": 0.5451729478575116,
+      "grad_norm": 3.822807868480414,
+      "learning_rate": 4.545454545454545e-07,
+      "loss": 0.0495,
+      "step": 66
+    },
+    {
+      "epoch": 0.5534331440371709,
+      "grad_norm": 4.396653504302493,
+      "learning_rate": 4.462809917355372e-07,
+      "loss": 0.0636,
+      "step": 67
+    },
+    {
+      "epoch": 0.5616933402168302,
+      "grad_norm": 4.2660235374858395,
+      "learning_rate": 4.380165289256198e-07,
+      "loss": 0.0613,
+      "step": 68
+    },
+    {
+      "epoch": 0.5699535363964894,
+      "grad_norm": 4.320113144784091,
+      "learning_rate": 4.2975206611570245e-07,
+      "loss": 0.0606,
+      "step": 69
+    },
+    {
+      "epoch": 0.5782137325761487,
+      "grad_norm": 3.489343597046561,
+      "learning_rate": 4.2148760330578507e-07,
+      "loss": 0.0488,
+      "step": 70
+    },
+    {
+      "epoch": 0.586473928755808,
+      "grad_norm": 4.202502491224329,
+      "learning_rate": 4.1322314049586775e-07,
+      "loss": 0.0461,
+      "step": 71
+    },
+    {
+      "epoch": 0.5947341249354672,
+      "grad_norm": 3.7979838261283447,
+      "learning_rate": 4.049586776859504e-07,
+      "loss": 0.0553,
+      "step": 72
+    },
+    {
+      "epoch": 0.6029943211151265,
+      "grad_norm": 3.670948905350722,
+      "learning_rate": 3.9669421487603305e-07,
+      "loss": 0.0508,
+      "step": 73
+    },
+    {
+      "epoch": 0.6112545172947857,
+      "grad_norm": 4.168891573097566,
+      "learning_rate": 3.884297520661157e-07,
+      "loss": 0.0528,
+      "step": 74
+    },
+    {
+      "epoch": 0.619514713474445,
+      "grad_norm": 5.573251173467056,
+      "learning_rate": 3.8016528925619836e-07,
+      "loss": 0.0624,
+      "step": 75
+    },
+    {
+      "epoch": 0.6277749096541043,
+      "grad_norm": 4.171764571534108,
+      "learning_rate": 3.71900826446281e-07,
+      "loss": 0.0591,
+      "step": 76
+    },
+    {
+      "epoch": 0.6360351058337635,
+      "grad_norm": 3.927683207188494,
+      "learning_rate": 3.636363636363636e-07,
+      "loss": 0.0505,
+      "step": 77
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 4.507087595945348,
+      "learning_rate": 3.5537190082644623e-07,
+      "loss": 0.0563,
+      "step": 78
+    },
+    {
+      "epoch": 0.6525554981930821,
+      "grad_norm": 4.147902238392531,
+      "learning_rate": 3.471074380165289e-07,
+      "loss": 0.0454,
+      "step": 79
+    },
+    {
+      "epoch": 0.6608156943727413,
+      "grad_norm": 5.190554517507134,
+      "learning_rate": 3.3884297520661153e-07,
+      "loss": 0.0616,
+      "step": 80
+    },
+    {
+      "epoch": 0.6690758905524006,
+      "grad_norm": 3.655024717222077,
+      "learning_rate": 3.305785123966942e-07,
+      "loss": 0.0507,
+      "step": 81
+    },
+    {
+      "epoch": 0.6773360867320599,
+      "grad_norm": 4.157714544531685,
+      "learning_rate": 3.2231404958677684e-07,
+      "loss": 0.0402,
+      "step": 82
+    },
+    {
+      "epoch": 0.6855962829117191,
+      "grad_norm": 4.341916585620508,
+      "learning_rate": 3.140495867768595e-07,
+      "loss": 0.0521,
+      "step": 83
+    },
+    {
+      "epoch": 0.6938564790913784,
+      "grad_norm": 4.110840470674744,
+      "learning_rate": 3.0578512396694214e-07,
+      "loss": 0.0454,
+      "step": 84
+    },
+    {
+      "epoch": 0.7021166752710377,
+      "grad_norm": 5.172930642801743,
+      "learning_rate": 2.9752066115702476e-07,
+      "loss": 0.0598,
+      "step": 85
+    },
+    {
+      "epoch": 0.710376871450697,
+      "grad_norm": 4.015284333455354,
+      "learning_rate": 2.892561983471074e-07,
+      "loss": 0.0534,
+      "step": 86
+    },
+    {
+      "epoch": 0.7186370676303562,
+      "grad_norm": 5.219043400469888,
+      "learning_rate": 2.8099173553719007e-07,
+      "loss": 0.0635,
+      "step": 87
+    },
+    {
+      "epoch": 0.7268972638100155,
+      "grad_norm": 3.801053158376501,
+      "learning_rate": 2.727272727272727e-07,
+      "loss": 0.04,
+      "step": 88
+    },
+    {
+      "epoch": 0.7351574599896747,
+      "grad_norm": 3.590260348342961,
+      "learning_rate": 2.6446280991735537e-07,
+      "loss": 0.0449,
+      "step": 89
+    },
+    {
+      "epoch": 0.743417656169334,
+      "grad_norm": 3.9090379662096733,
+      "learning_rate": 2.56198347107438e-07,
+      "loss": 0.0456,
+      "step": 90
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 3.544469232478435,
+      "learning_rate": 2.4793388429752067e-07,
+      "loss": 0.0445,
+      "step": 91
+    },
+    {
+      "epoch": 0.7599380485286525,
+      "grad_norm": 4.302834475508462,
+      "learning_rate": 2.396694214876033e-07,
+      "loss": 0.0457,
+      "step": 92
+    },
+    {
+      "epoch": 0.7681982447083118,
+      "grad_norm": 3.6622022266692644,
+      "learning_rate": 2.3140495867768595e-07,
+      "loss": 0.0446,
+      "step": 93
+    },
+    {
+      "epoch": 0.7764584408879711,
+      "grad_norm": 2.8029493422652005,
+      "learning_rate": 2.231404958677686e-07,
+      "loss": 0.0307,
+      "step": 94
+    },
+    {
+      "epoch": 0.7847186370676303,
+      "grad_norm": 4.408520384921988,
+      "learning_rate": 2.1487603305785122e-07,
+      "loss": 0.0479,
+      "step": 95
+    },
+    {
+      "epoch": 0.7929788332472896,
+      "grad_norm": 4.360677288902582,
+      "learning_rate": 2.0661157024793388e-07,
+      "loss": 0.0473,
+      "step": 96
+    },
+    {
+      "epoch": 0.8012390294269489,
+      "grad_norm": 4.577659670729056,
+      "learning_rate": 1.9834710743801653e-07,
+      "loss": 0.0636,
+      "step": 97
+    },
+    {
+      "epoch": 0.8094992256066081,
+      "grad_norm": 3.439295481239559,
+      "learning_rate": 1.9008264462809918e-07,
+      "loss": 0.0405,
+      "step": 98
+    },
+    {
+      "epoch": 0.8177594217862674,
+      "grad_norm": 3.5257606444607577,
+      "learning_rate": 1.818181818181818e-07,
+      "loss": 0.0416,
+      "step": 99
+    },
+    {
+      "epoch": 0.8260196179659267,
+      "grad_norm": 4.363970112200522,
+      "learning_rate": 1.7355371900826445e-07,
+      "loss": 0.048,
+      "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
+}

mask/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b9ad627d34be3ceeeeace87bbbc374e6a9b91294fa89a8c81f0ed1e5b03c52
+size 7096

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
+}

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9733557345655ebd94dd27531071ce48034530c508c53fb84b64cfad0290460
+size 4945242264

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87908a19ea031d703e1eace60be6bb754ac1a68d2fd15f9fafae8c6e91182168
+size 67125784

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"
+  }
+}

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
+  }
+}

mask/checkpoint-121/tokenizer.json

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

mask/checkpoint-121/tokenizer.model

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

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
+}

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": 8.833224831341008,
+      "learning_rate": 9.917355371900827e-07,
+      "loss": 0.6051,
+      "step": 1
+    },
+    {
+      "epoch": 0.016520392359318535,
+      "grad_norm": 8.28765409813015,
+      "learning_rate": 9.834710743801652e-07,
+      "loss": 0.5941,
+      "step": 2
+    },
+    {
+      "epoch": 0.0247805885389778,
+      "grad_norm": 7.7759780312342075,
+      "learning_rate": 9.75206611570248e-07,
+      "loss": 0.601,
+      "step": 3
+    },
+    {
+      "epoch": 0.03304078471863707,
+      "grad_norm": 6.331869804834741,
+      "learning_rate": 9.669421487603305e-07,
+      "loss": 0.5744,
+      "step": 4
+    },
+    {
+      "epoch": 0.041300980898296334,
+      "grad_norm": 6.82444805885506,
+      "learning_rate": 9.586776859504132e-07,
+      "loss": 0.5529,
+      "step": 5
+    },
+    {
+      "epoch": 0.0495611770779556,
+      "grad_norm": 7.2220736569961375,
+      "learning_rate": 9.504132231404959e-07,
+      "loss": 0.5283,
+      "step": 6
+    },
+    {
+      "epoch": 0.05782137325761487,
+      "grad_norm": 7.920339746711006,
+      "learning_rate": 9.421487603305784e-07,
+      "loss": 0.5128,
+      "step": 7
+    },
+    {
+      "epoch": 0.06608156943727414,
+      "grad_norm": 7.741933749943497,
+      "learning_rate": 9.338842975206612e-07,
+      "loss": 0.4731,
+      "step": 8
+    },
+    {
+      "epoch": 0.0743417656169334,
+      "grad_norm": 7.33305646635204,
+      "learning_rate": 9.256198347107438e-07,
+      "loss": 0.4889,
+      "step": 9
+    },
+    {
+      "epoch": 0.08260196179659267,
+      "grad_norm": 5.397722616120573,
+      "learning_rate": 9.173553719008264e-07,
+      "loss": 0.4445,
+      "step": 10
+    },
+    {
+      "epoch": 0.09086215797625194,
+      "grad_norm": 6.306346639937355,
+      "learning_rate": 9.09090909090909e-07,
+      "loss": 0.3776,
+      "step": 11
+    },
+    {
+      "epoch": 0.0991223541559112,
+      "grad_norm": 6.417179207932981,
+      "learning_rate": 9.008264462809917e-07,
+      "loss": 0.3639,
+      "step": 12
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 6.4453913869424095,
+      "learning_rate": 8.925619834710744e-07,
+      "loss": 0.3558,
+      "step": 13
+    },
+    {
+      "epoch": 0.11564274651522974,
+      "grad_norm": 7.114718937999426,
+      "learning_rate": 8.84297520661157e-07,
+      "loss": 0.3598,
+      "step": 14
+    },
+    {
+      "epoch": 0.12390294269488901,
+      "grad_norm": 6.547127744231474,
+      "learning_rate": 8.760330578512396e-07,
+      "loss": 0.3273,
+      "step": 15
+    },
+    {
+      "epoch": 0.13216313887454828,
+      "grad_norm": 7.307678912774062,
+      "learning_rate": 8.677685950413223e-07,
+      "loss": 0.3453,
+      "step": 16
+    },
+    {
+      "epoch": 0.14042333505420754,
+      "grad_norm": 7.466082653405334,
+      "learning_rate": 8.595041322314049e-07,
+      "loss": 0.3197,
+      "step": 17
+    },
+    {
+      "epoch": 0.1486835312338668,
+      "grad_norm": 6.58761708106512,
+      "learning_rate": 8.512396694214876e-07,
+      "loss": 0.2958,
+      "step": 18
+    },
+    {
+      "epoch": 0.15694372741352608,
+      "grad_norm": 6.3803321743795784,
+      "learning_rate": 8.429752066115701e-07,
+      "loss": 0.2863,
+      "step": 19
+    },
+    {
+      "epoch": 0.16520392359318534,
+      "grad_norm": 6.207348064176668,
+      "learning_rate": 8.347107438016529e-07,
+      "loss": 0.2693,
+      "step": 20
+    },
+    {
+      "epoch": 0.1734641197728446,
+      "grad_norm": 5.776604798851602,
+      "learning_rate": 8.264462809917355e-07,
+      "loss": 0.2314,
+      "step": 21
+    },
+    {
+      "epoch": 0.18172431595250388,
+      "grad_norm": 6.277376376848909,
+      "learning_rate": 8.181818181818182e-07,
+      "loss": 0.242,
+      "step": 22
+    },
+    {
+      "epoch": 0.18998451213216314,
+      "grad_norm": 6.590485185775048,
+      "learning_rate": 8.099173553719008e-07,
+      "loss": 0.2333,
+      "step": 23
+    },
+    {
+      "epoch": 0.1982447083118224,
+      "grad_norm": 6.094516363574539,
+      "learning_rate": 8.016528925619835e-07,
+      "loss": 0.2008,
+      "step": 24
+    },
+    {
+      "epoch": 0.20650490449148168,
+      "grad_norm": 6.010919592697381,
+      "learning_rate": 7.933884297520661e-07,
+      "loss": 0.1985,
+      "step": 25
+    },
+    {
+      "epoch": 0.21476510067114093,
+      "grad_norm": 5.948476311514442,
+      "learning_rate": 7.851239669421487e-07,
+      "loss": 0.1981,
+      "step": 26
+    },
+    {
+      "epoch": 0.22302529685080022,
+      "grad_norm": 5.657766604243092,
+      "learning_rate": 7.768595041322314e-07,
+      "loss": 0.1722,
+      "step": 27
+    },
+    {
+      "epoch": 0.23128549303045948,
+      "grad_norm": 5.3436389934314885,
+      "learning_rate": 7.68595041322314e-07,
+      "loss": 0.139,
+      "step": 28
+    },
+    {
+      "epoch": 0.23954568921011873,
+      "grad_norm": 6.050567759464481,
+      "learning_rate": 7.603305785123967e-07,
+      "loss": 0.1872,
+      "step": 29
+    },
+    {
+      "epoch": 0.24780588538977802,
+      "grad_norm": 5.888273604838657,
+      "learning_rate": 7.520661157024793e-07,
+      "loss": 0.182,
+      "step": 30
+    },
+    {
+      "epoch": 0.2560660815694373,
+      "grad_norm": 4.643340194462475,
+      "learning_rate": 7.43801652892562e-07,
+      "loss": 0.1337,
+      "step": 31
+    },
+    {
+      "epoch": 0.26432627774909656,
+      "grad_norm": 5.2982546245512445,
+      "learning_rate": 7.355371900826446e-07,
+      "loss": 0.1355,
+      "step": 32
+    },
+    {
+      "epoch": 0.2725864739287558,
+      "grad_norm": 5.444124845250493,
+      "learning_rate": 7.272727272727272e-07,
+      "loss": 0.1422,
+      "step": 33
+    },
+    {
+      "epoch": 0.2808466701084151,
+      "grad_norm": 5.305028072330304,
+      "learning_rate": 7.190082644628099e-07,
+      "loss": 0.1431,
+      "step": 34
+    },
+    {
+      "epoch": 0.28910686628807436,
+      "grad_norm": 4.64286696526394,
+      "learning_rate": 7.107438016528925e-07,
+      "loss": 0.1078,
+      "step": 35
+    },
+    {
+      "epoch": 0.2973670624677336,
+      "grad_norm": 5.077942838771361,
+      "learning_rate": 7.024793388429752e-07,
+      "loss": 0.1133,
+      "step": 36
+    },
+    {
+      "epoch": 0.3056272586473929,
+      "grad_norm": 5.827543683385444,
+      "learning_rate": 6.942148760330578e-07,
+      "loss": 0.1373,
+      "step": 37
+    },
+    {
+      "epoch": 0.31388745482705216,
+      "grad_norm": 4.619838338481372,
+      "learning_rate": 6.859504132231405e-07,
+      "loss": 0.0949,
+      "step": 38
+    },
+    {
+      "epoch": 0.3221476510067114,
+      "grad_norm": 4.877454362063687,
+      "learning_rate": 6.776859504132231e-07,
+      "loss": 0.106,
+      "step": 39
+    },
+    {
+      "epoch": 0.3304078471863707,
+      "grad_norm": 5.9983838979070185,
+      "learning_rate": 6.694214876033058e-07,
+      "loss": 0.1193,
+      "step": 40
+    },
+    {
+      "epoch": 0.33866804336602996,
+      "grad_norm": 4.857934673938672,
+      "learning_rate": 6.611570247933884e-07,
+      "loss": 0.1133,
+      "step": 41
+    },
+    {
+      "epoch": 0.3469282395456892,
+      "grad_norm": 4.972035576901775,
+      "learning_rate": 6.52892561983471e-07,
+      "loss": 0.1037,
+      "step": 42
+    },
+    {
+      "epoch": 0.3551884357253485,
+      "grad_norm": 3.9492698890695257,
+      "learning_rate": 6.446280991735537e-07,
+      "loss": 0.0887,
+      "step": 43
+    },
+    {
+      "epoch": 0.36344863190500776,
+      "grad_norm": 4.639663084480974,
+      "learning_rate": 6.363636363636363e-07,
+      "loss": 0.0964,
+      "step": 44
+    },
+    {
+      "epoch": 0.371708828084667,
+      "grad_norm": 4.238244774637056,
+      "learning_rate": 6.28099173553719e-07,
+      "loss": 0.0814,
+      "step": 45
+    },
+    {
+      "epoch": 0.37996902426432627,
+      "grad_norm": 4.317260522087231,
+      "learning_rate": 6.198347107438017e-07,
+      "loss": 0.0856,
+      "step": 46
+    },
+    {
+      "epoch": 0.38822922044398556,
+      "grad_norm": 5.008730972224478,
+      "learning_rate": 6.115702479338843e-07,
+      "loss": 0.0813,
+      "step": 47
+    },
+    {
+      "epoch": 0.3964894166236448,
+      "grad_norm": 4.572740643145854,
+      "learning_rate": 6.033057851239669e-07,
+      "loss": 0.0861,
+      "step": 48
+    },
+    {
+      "epoch": 0.40474961280330407,
+      "grad_norm": 4.223394908610836,
+      "learning_rate": 5.950413223140495e-07,
+      "loss": 0.0851,
+      "step": 49
+    },
+    {
+      "epoch": 0.41300980898296336,
+      "grad_norm": 4.439883229699326,
+      "learning_rate": 5.867768595041323e-07,
+      "loss": 0.0758,
+      "step": 50
+    },
+    {
+      "epoch": 0.4212700051626226,
+      "grad_norm": 4.340441774291824,
+      "learning_rate": 5.785123966942148e-07,
+      "loss": 0.0732,
+      "step": 51
+    },
+    {
+      "epoch": 0.42953020134228187,
+      "grad_norm": 4.289070334443712,
+      "learning_rate": 5.702479338842975e-07,
+      "loss": 0.0732,
+      "step": 52
+    },
+    {
+      "epoch": 0.43779039752194115,
+      "grad_norm": 5.126081829105661,
+      "learning_rate": 5.619834710743801e-07,
+      "loss": 0.0832,
+      "step": 53
+    },
+    {
+      "epoch": 0.44605059370160044,
+      "grad_norm": 4.993834428920049,
+      "learning_rate": 5.537190082644629e-07,
+      "loss": 0.0848,
+      "step": 54
+    },
+    {
+      "epoch": 0.45431078988125967,
+      "grad_norm": 3.716478265572608,
+      "learning_rate": 5.454545454545454e-07,
+      "loss": 0.0604,
+      "step": 55
+    },
+    {
+      "epoch": 0.46257098606091895,
+      "grad_norm": 4.178642533290566,
+      "learning_rate": 5.371900826446281e-07,
+      "loss": 0.0681,
+      "step": 56
+    },
+    {
+      "epoch": 0.47083118224057824,
+      "grad_norm": 4.232442593100394,
+      "learning_rate": 5.289256198347107e-07,
+      "loss": 0.0599,
+      "step": 57
+    },
+    {
+      "epoch": 0.47909137842023747,
+      "grad_norm": 4.150222898652126,
+      "learning_rate": 5.206611570247934e-07,
+      "loss": 0.0703,
+      "step": 58
+    },
+    {
+      "epoch": 0.48735157459989675,
+      "grad_norm": 4.403051637850364,
+      "learning_rate": 5.12396694214876e-07,
+      "loss": 0.0713,
+      "step": 59
+    },
+    {
+      "epoch": 0.49561177077955604,
+      "grad_norm": 4.660075631992056,
+      "learning_rate": 5.041322314049586e-07,
+      "loss": 0.056,
+      "step": 60
+    },
+    {
+      "epoch": 0.5038719669592153,
+      "grad_norm": 4.694839170968639,
+      "learning_rate": 4.958677685950413e-07,
+      "loss": 0.079,
+      "step": 61
+    },
+    {
+      "epoch": 0.5121321631388746,
+      "grad_norm": 4.186240576925523,
+      "learning_rate": 4.87603305785124e-07,
+      "loss": 0.0674,
+      "step": 62
+    },
+    {
+      "epoch": 0.5203923593185338,
+      "grad_norm": 3.3199829625607955,
+      "learning_rate": 4.793388429752066e-07,
+      "loss": 0.0527,
+      "step": 63
+    },
+    {
+      "epoch": 0.5286525554981931,
+      "grad_norm": 4.997276223790548,
+      "learning_rate": 4.710743801652892e-07,
+      "loss": 0.0649,
+      "step": 64
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 4.376618807129675,
+      "learning_rate": 4.628099173553719e-07,
+      "loss": 0.0491,
+      "step": 65
+    },
+    {
+      "epoch": 0.5451729478575116,
+      "grad_norm": 3.822807868480414,
+      "learning_rate": 4.545454545454545e-07,
+      "loss": 0.0495,
+      "step": 66
+    },
+    {
+      "epoch": 0.5534331440371709,
+      "grad_norm": 4.396653504302493,
+      "learning_rate": 4.462809917355372e-07,
+      "loss": 0.0636,
+      "step": 67
+    },
+    {
+      "epoch": 0.5616933402168302,
+      "grad_norm": 4.2660235374858395,
+      "learning_rate": 4.380165289256198e-07,
+      "loss": 0.0613,
+      "step": 68
+    },
+    {
+      "epoch": 0.5699535363964894,
+      "grad_norm": 4.320113144784091,
+      "learning_rate": 4.2975206611570245e-07,
+      "loss": 0.0606,
+      "step": 69
+    },
+    {
+      "epoch": 0.5782137325761487,
+      "grad_norm": 3.489343597046561,
+      "learning_rate": 4.2148760330578507e-07,
+      "loss": 0.0488,
+      "step": 70
+    },
+    {
+      "epoch": 0.586473928755808,
+      "grad_norm": 4.202502491224329,
+      "learning_rate": 4.1322314049586775e-07,
+      "loss": 0.0461,
+      "step": 71
+    },
+    {
+      "epoch": 0.5947341249354672,
+      "grad_norm": 3.7979838261283447,
+      "learning_rate": 4.049586776859504e-07,
+      "loss": 0.0553,
+      "step": 72
+    },
+    {
+      "epoch": 0.6029943211151265,
+      "grad_norm": 3.670948905350722,
+      "learning_rate": 3.9669421487603305e-07,
+      "loss": 0.0508,
+      "step": 73
+    },
+    {
+      "epoch": 0.6112545172947857,
+      "grad_norm": 4.168891573097566,
+      "learning_rate": 3.884297520661157e-07,
+      "loss": 0.0528,
+      "step": 74
+    },
+    {
+      "epoch": 0.619514713474445,
+      "grad_norm": 5.573251173467056,
+      "learning_rate": 3.8016528925619836e-07,
+      "loss": 0.0624,
+      "step": 75
+    },
+    {
+      "epoch": 0.6277749096541043,
+      "grad_norm": 4.171764571534108,
+      "learning_rate": 3.71900826446281e-07,
+      "loss": 0.0591,
+      "step": 76
+    },
+    {
+      "epoch": 0.6360351058337635,
+      "grad_norm": 3.927683207188494,
+      "learning_rate": 3.636363636363636e-07,
+      "loss": 0.0505,
+      "step": 77
+    },
+    {
+      "epoch": 0.6442953020134228,
+      "grad_norm": 4.507087595945348,
+      "learning_rate": 3.5537190082644623e-07,
+      "loss": 0.0563,
+      "step": 78
+    },
+    {
+      "epoch": 0.6525554981930821,
+      "grad_norm": 4.147902238392531,
+      "learning_rate": 3.471074380165289e-07,
+      "loss": 0.0454,
+      "step": 79
+    },
+    {
+      "epoch": 0.6608156943727413,
+      "grad_norm": 5.190554517507134,
+      "learning_rate": 3.3884297520661153e-07,
+      "loss": 0.0616,
+      "step": 80
+    },
+    {
+      "epoch": 0.6690758905524006,
+      "grad_norm": 3.655024717222077,
+      "learning_rate": 3.305785123966942e-07,
+      "loss": 0.0507,
+      "step": 81
+    },
+    {
+      "epoch": 0.6773360867320599,
+      "grad_norm": 4.157714544531685,
+      "learning_rate": 3.2231404958677684e-07,
+      "loss": 0.0402,
+      "step": 82
+    },
+    {
+      "epoch": 0.6855962829117191,
+      "grad_norm": 4.341916585620508,
+      "learning_rate": 3.140495867768595e-07,
+      "loss": 0.0521,
+      "step": 83
+    },
+    {
+      "epoch": 0.6938564790913784,
+      "grad_norm": 4.110840470674744,
+      "learning_rate": 3.0578512396694214e-07,
+      "loss": 0.0454,
+      "step": 84
+    },
+    {
+      "epoch": 0.7021166752710377,
+      "grad_norm": 5.172930642801743,
+      "learning_rate": 2.9752066115702476e-07,
+      "loss": 0.0598,
+      "step": 85
+    },
+    {
+      "epoch": 0.710376871450697,
+      "grad_norm": 4.015284333455354,
+      "learning_rate": 2.892561983471074e-07,
+      "loss": 0.0534,
+      "step": 86
+    },
+    {
+      "epoch": 0.7186370676303562,
+      "grad_norm": 5.219043400469888,
+      "learning_rate": 2.8099173553719007e-07,
+      "loss": 0.0635,
+      "step": 87
+    },
+    {
+      "epoch": 0.7268972638100155,
+      "grad_norm": 3.801053158376501,
+      "learning_rate": 2.727272727272727e-07,
+      "loss": 0.04,
+      "step": 88
+    },
+    {
+      "epoch": 0.7351574599896747,
+      "grad_norm": 3.590260348342961,
+      "learning_rate": 2.6446280991735537e-07,
+      "loss": 0.0449,
+      "step": 89
+    },
+    {
+      "epoch": 0.743417656169334,
+      "grad_norm": 3.9090379662096733,
+      "learning_rate": 2.56198347107438e-07,
+      "loss": 0.0456,
+      "step": 90
+    },
+    {
+      "epoch": 0.7516778523489933,
+      "grad_norm": 3.544469232478435,
+      "learning_rate": 2.4793388429752067e-07,
+      "loss": 0.0445,
+      "step": 91
+    },
+    {
+      "epoch": 0.7599380485286525,
+      "grad_norm": 4.302834475508462,
+      "learning_rate": 2.396694214876033e-07,
+      "loss": 0.0457,
+      "step": 92
+    },
+    {
+      "epoch": 0.7681982447083118,
+      "grad_norm": 3.6622022266692644,
+      "learning_rate": 2.3140495867768595e-07,
+      "loss": 0.0446,
+      "step": 93
+    },
+    {
+      "epoch": 0.7764584408879711,
+      "grad_norm": 2.8029493422652005,
+      "learning_rate": 2.231404958677686e-07,
+      "loss": 0.0307,
+      "step": 94
+    },
+    {
+      "epoch": 0.7847186370676303,
+      "grad_norm": 4.408520384921988,
+      "learning_rate": 2.1487603305785122e-07,
+      "loss": 0.0479,
+      "step": 95
+    },
+    {
+      "epoch": 0.7929788332472896,
+      "grad_norm": 4.360677288902582,
+      "learning_rate": 2.0661157024793388e-07,
+      "loss": 0.0473,
+      "step": 96
+    },
+    {
+      "epoch": 0.8012390294269489,
+      "grad_norm": 4.577659670729056,
+      "learning_rate": 1.9834710743801653e-07,
+      "loss": 0.0636,
+      "step": 97
+    },
+    {
+      "epoch": 0.8094992256066081,
+      "grad_norm": 3.439295481239559,
+      "learning_rate": 1.9008264462809918e-07,
+      "loss": 0.0405,
+      "step": 98
+    },
+    {
+      "epoch": 0.8177594217862674,
+      "grad_norm": 3.5257606444607577,
+      "learning_rate": 1.818181818181818e-07,
+      "loss": 0.0416,
+      "step": 99
+    },
+    {
+      "epoch": 0.8260196179659267,
+      "grad_norm": 4.363970112200522,
+      "learning_rate": 1.7355371900826445e-07,
+      "loss": 0.048,
+      "step": 100
+    },
+    {
+      "epoch": 0.8342798141455859,
+      "grad_norm": 4.445157388889456,
+      "learning_rate": 1.652892561983471e-07,
+      "loss": 0.0584,
+      "step": 101
+    },
+    {
+      "epoch": 0.8425400103252452,
+      "grad_norm": 3.345934561704921,
+      "learning_rate": 1.5702479338842976e-07,
+      "loss": 0.0386,
+      "step": 102
+    },
+    {
+      "epoch": 0.8508002065049045,
+      "grad_norm": 3.189653818572567,
+      "learning_rate": 1.4876033057851238e-07,
+      "loss": 0.0337,
+      "step": 103
+    },
+    {
+      "epoch": 0.8590604026845637,
+      "grad_norm": 3.836047647097417,
+      "learning_rate": 1.4049586776859503e-07,
+      "loss": 0.0361,
+      "step": 104
+    },
+    {
+      "epoch": 0.8673205988642231,
+      "grad_norm": 4.953048703242531,
+      "learning_rate": 1.3223140495867768e-07,
+      "loss": 0.0522,
+      "step": 105
+    },
+    {
+      "epoch": 0.8755807950438823,
+      "grad_norm": 4.568389351728364,
+      "learning_rate": 1.2396694214876034e-07,
+      "loss": 0.045,
+      "step": 106
+    },
+    {
+      "epoch": 0.8838409912235415,
+      "grad_norm": 4.361223344634253,
+      "learning_rate": 1.1570247933884297e-07,
+      "loss": 0.0483,
+      "step": 107
+    },
+    {
+      "epoch": 0.8921011874032009,
+      "grad_norm": 5.251590021158591,
+      "learning_rate": 1.0743801652892561e-07,
+      "loss": 0.0491,
+      "step": 108
+    },
+    {
+      "epoch": 0.9003613835828601,
+      "grad_norm": 4.121232283320186,
+      "learning_rate": 9.917355371900826e-08,
+      "loss": 0.0504,
+      "step": 109
+    },
+    {
+      "epoch": 0.9086215797625193,
+      "grad_norm": 3.731644677845439,
+      "learning_rate": 9.09090909090909e-08,
+      "loss": 0.0454,
+      "step": 110
+    },
+    {
+      "epoch": 0.9168817759421787,
+      "grad_norm": 2.984892140413037,
+      "learning_rate": 8.264462809917355e-08,
+      "loss": 0.037,
+      "step": 111
+    },
+    {
+      "epoch": 0.9251419721218379,
+      "grad_norm": 3.3942896522087245,
+      "learning_rate": 7.438016528925619e-08,
+      "loss": 0.0442,
+      "step": 112
+    },
+    {
+      "epoch": 0.9334021683014971,
+      "grad_norm": 4.030385386610412,
+      "learning_rate": 6.611570247933884e-08,
+      "loss": 0.0363,
+      "step": 113
+    },
+    {
+      "epoch": 0.9416623644811565,
+      "grad_norm": 4.330930465464469,
+      "learning_rate": 5.785123966942149e-08,
+      "loss": 0.048,
+      "step": 114
+    },
+    {
+      "epoch": 0.9499225606608157,
+      "grad_norm": 3.5173484874636376,
+      "learning_rate": 4.958677685950413e-08,
+      "loss": 0.032,
+      "step": 115
+    },
+    {
+      "epoch": 0.9581827568404749,
+      "grad_norm": 3.295585869681872,
+      "learning_rate": 4.1322314049586776e-08,
+      "loss": 0.0345,
+      "step": 116
+    },
+    {
+      "epoch": 0.9664429530201343,
+      "grad_norm": 4.397751162974457,
+      "learning_rate": 3.305785123966942e-08,
+      "loss": 0.0461,
+      "step": 117
+    },
+    {
+      "epoch": 0.9747031491997935,
+      "grad_norm": 3.005067928394933,
+      "learning_rate": 2.4793388429752066e-08,
+      "loss": 0.0346,
+      "step": 118
+    },
+    {
+      "epoch": 0.9829633453794527,
+      "grad_norm": 3.823617625749292,
+      "learning_rate": 1.652892561983471e-08,
+      "loss": 0.0432,
+      "step": 119
+    },
+    {
+      "epoch": 0.9912235415591121,
+      "grad_norm": 3.870748801218549,
+      "learning_rate": 8.264462809917355e-09,
+      "loss": 0.0498,
+      "step": 120
+    },
+    {
+      "epoch": 0.9994837377387713,
+      "grad_norm": 5.076388336876707,
+      "learning_rate": 0.0,
+      "loss": 0.0459,
+      "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
+}

mask/checkpoint-121/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b9ad627d34be3ceeeeace87bbbc374e6a9b91294fa89a8c81f0ed1e5b03c52
+size 7096