Upload 12 files

reficr base test version

checkpoint-28712/config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "GritLM/GritLM-7B",
+  "architectures": [
+    "ReFICRTrainModel"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoModel": "GritLM/GritLM-7B--modeling_gritlm7b.MistralModel",
+    "AutoModelForCausalLM": "GritLM/GritLM-7B--modeling_gritlm7b.MistralForCausalLM",
+    "AutoModelForSequenceClassification": "GritLM/GritLM-7B--modeling_gritlm7b.MistralForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

checkpoint-28712/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46173caadc95a301d231b30e950d24017cc9ef45617b269ffe61b477ee2cc453
+size 1342555602

checkpoint-28712/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51bd72868f2617a544f51296b48e87a0993f1aa59b927b73c207e9b2de90d7bb
+size 4797876230

checkpoint-28712/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25744784d7f3a6e93c904a92ccb2d89867bcdd6afe29fbae705230b8902e98b
+size 524289413

checkpoint-28712/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae065185b393342d43bd3f56a07b675353c33667950d14d417a20a8e171e9218
+size 14244

checkpoint-28712/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74f0e4a638e06bb4361fe1343bfdaa9eb56865557aeaf26e2457521f467ab7a2
+size 1064

checkpoint-28712/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-28712/tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-28712/trainer_state.json

@@ -0,0 +1,432 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 28712,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01741432153803288,
+      "grad_norm": 6.671968936920166,
+      "learning_rate": 1.160092807424594e-05,
+      "loss": 3.4084,
+      "step": 500
+    },
+    {
+      "epoch": 0.03482864307606576,
+      "grad_norm": 4.760310173034668,
+      "learning_rate": 1.9900897666068224e-05,
+      "loss": 2.8756,
+      "step": 1000
+    },
+    {
+      "epoch": 0.052242964614098636,
+      "grad_norm": 10.023279190063477,
+      "learning_rate": 1.9541831238779175e-05,
+      "loss": 2.7465,
+      "step": 1500
+    },
+    {
+      "epoch": 0.06965728615213151,
+      "grad_norm": 13.3428316116333,
+      "learning_rate": 1.9182764811490127e-05,
+      "loss": 2.8027,
+      "step": 2000
+    },
+    {
+      "epoch": 0.0870716076901644,
+      "grad_norm": 10.00976276397705,
+      "learning_rate": 1.882369838420108e-05,
+      "loss": 2.5838,
+      "step": 2500
+    },
+    {
+      "epoch": 0.10448592922819727,
+      "grad_norm": 9.512397766113281,
+      "learning_rate": 1.846463195691203e-05,
+      "loss": 2.5855,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12190025076623015,
+      "grad_norm": 7.561283588409424,
+      "learning_rate": 1.8105565529622982e-05,
+      "loss": 2.5998,
+      "step": 3500
+    },
+    {
+      "epoch": 0.13931457230426303,
+      "grad_norm": 5.637691497802734,
+      "learning_rate": 1.7746499102333934e-05,
+      "loss": 2.6146,
+      "step": 4000
+    },
+    {
+      "epoch": 0.1567288938422959,
+      "grad_norm": 5.674258232116699,
+      "learning_rate": 1.7387432675044886e-05,
+      "loss": 2.5343,
+      "step": 4500
+    },
+    {
+      "epoch": 0.1741432153803288,
+      "grad_norm": 6.290276527404785,
+      "learning_rate": 1.7028366247755838e-05,
+      "loss": 2.5986,
+      "step": 5000
+    },
+    {
+      "epoch": 0.19155753691836166,
+      "grad_norm": 9.24161148071289,
+      "learning_rate": 1.6669299820466786e-05,
+      "loss": 2.5192,
+      "step": 5500
+    },
+    {
+      "epoch": 0.20897185845639454,
+      "grad_norm": 5.9918413162231445,
+      "learning_rate": 1.6310233393177738e-05,
+      "loss": 2.44,
+      "step": 6000
+    },
+    {
+      "epoch": 0.22638617999442742,
+      "grad_norm": 5.031735420227051,
+      "learning_rate": 1.5951166965888693e-05,
+      "loss": 2.5443,
+      "step": 6500
+    },
+    {
+      "epoch": 0.2438005015324603,
+      "grad_norm": 8.406722068786621,
+      "learning_rate": 1.559210053859964e-05,
+      "loss": 2.4336,
+      "step": 7000
+    },
+    {
+      "epoch": 0.26121482307049315,
+      "grad_norm": 5.958395957946777,
+      "learning_rate": 1.5233034111310595e-05,
+      "loss": 2.5202,
+      "step": 7500
+    },
+    {
+      "epoch": 0.27862914460852606,
+      "grad_norm": 6.343221187591553,
+      "learning_rate": 1.4873967684021545e-05,
+      "loss": 2.4703,
+      "step": 8000
+    },
+    {
+      "epoch": 0.2960434661465589,
+      "grad_norm": 6.622114181518555,
+      "learning_rate": 1.4514901256732496e-05,
+      "loss": 2.4571,
+      "step": 8500
+    },
+    {
+      "epoch": 0.3134577876845918,
+      "grad_norm": 7.682774543762207,
+      "learning_rate": 1.4155834829443448e-05,
+      "loss": 2.3446,
+      "step": 9000
+    },
+    {
+      "epoch": 0.33087210922262467,
+      "grad_norm": 12.083649635314941,
+      "learning_rate": 1.37967684021544e-05,
+      "loss": 2.4335,
+      "step": 9500
+    },
+    {
+      "epoch": 0.3482864307606576,
+      "grad_norm": 15.165790557861328,
+      "learning_rate": 1.3437701974865352e-05,
+      "loss": 2.4165,
+      "step": 10000
+    },
+    {
+      "epoch": 0.3657007522986904,
+      "grad_norm": 4.316242694854736,
+      "learning_rate": 1.3078635547576302e-05,
+      "loss": 2.3593,
+      "step": 10500
+    },
+    {
+      "epoch": 0.38311507383672333,
+      "grad_norm": 13.665470123291016,
+      "learning_rate": 1.2719569120287253e-05,
+      "loss": 2.3966,
+      "step": 11000
+    },
+    {
+      "epoch": 0.4005293953747562,
+      "grad_norm": 7.673960208892822,
+      "learning_rate": 1.2360502692998207e-05,
+      "loss": 2.3842,
+      "step": 11500
+    },
+    {
+      "epoch": 0.4179437169127891,
+      "grad_norm": 6.637418746948242,
+      "learning_rate": 1.2001436265709157e-05,
+      "loss": 2.333,
+      "step": 12000
+    },
+    {
+      "epoch": 0.43535803845082194,
+      "grad_norm": 12.264994621276855,
+      "learning_rate": 1.1642369838420109e-05,
+      "loss": 2.4412,
+      "step": 12500
+    },
+    {
+      "epoch": 0.45277235998885484,
+      "grad_norm": 8.014012336730957,
+      "learning_rate": 1.1283303411131059e-05,
+      "loss": 2.4107,
+      "step": 13000
+    },
+    {
+      "epoch": 0.4701866815268877,
+      "grad_norm": 5.616372585296631,
+      "learning_rate": 1.0924236983842012e-05,
+      "loss": 2.3865,
+      "step": 13500
+    },
+    {
+      "epoch": 0.4876010030649206,
+      "grad_norm": 12.474315643310547,
+      "learning_rate": 1.0565170556552964e-05,
+      "loss": 2.4172,
+      "step": 14000
+    },
+    {
+      "epoch": 0.5050153246029535,
+      "grad_norm": 4.360251426696777,
+      "learning_rate": 1.0206104129263914e-05,
+      "loss": 2.3679,
+      "step": 14500
+    },
+    {
+      "epoch": 0.5224296461409863,
+      "grad_norm": 11.085514068603516,
+      "learning_rate": 9.847037701974866e-06,
+      "loss": 2.2899,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5398439676790192,
+      "grad_norm": 8.206655502319336,
+      "learning_rate": 9.487971274685817e-06,
+      "loss": 2.396,
+      "step": 15500
+    },
+    {
+      "epoch": 0.5572582892170521,
+      "grad_norm": 8.702625274658203,
+      "learning_rate": 9.128904847396769e-06,
+      "loss": 2.4141,
+      "step": 16000
+    },
+    {
+      "epoch": 0.574672610755085,
+      "grad_norm": 5.285048007965088,
+      "learning_rate": 8.769838420107721e-06,
+      "loss": 2.386,
+      "step": 16500
+    },
+    {
+      "epoch": 0.5920869322931178,
+      "grad_norm": 12.492161750793457,
+      "learning_rate": 8.410771992818673e-06,
+      "loss": 2.3857,
+      "step": 17000
+    },
+    {
+      "epoch": 0.6095012538311507,
+      "grad_norm": 6.360340595245361,
+      "learning_rate": 8.051705565529624e-06,
+      "loss": 2.3265,
+      "step": 17500
+    },
+    {
+      "epoch": 0.6269155753691836,
+      "grad_norm": 9.026312828063965,
+      "learning_rate": 7.692639138240574e-06,
+      "loss": 2.2468,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6443298969072165,
+      "grad_norm": 15.688992500305176,
+      "learning_rate": 7.333572710951526e-06,
+      "loss": 2.416,
+      "step": 18500
+    },
+    {
+      "epoch": 0.6617442184452493,
+      "grad_norm": 14.925408363342285,
+      "learning_rate": 6.974506283662478e-06,
+      "loss": 2.3618,
+      "step": 19000
+    },
+    {
+      "epoch": 0.6791585399832822,
+      "grad_norm": 6.57327127456665,
+      "learning_rate": 6.6154398563734305e-06,
+      "loss": 2.3216,
+      "step": 19500
+    },
+    {
+      "epoch": 0.6965728615213151,
+      "grad_norm": 4.341097831726074,
+      "learning_rate": 6.2563734290843814e-06,
+      "loss": 2.2302,
+      "step": 20000
+    },
+    {
+      "epoch": 0.713987183059348,
+      "grad_norm": 6.36518669128418,
+      "learning_rate": 5.897307001795332e-06,
+      "loss": 2.3242,
+      "step": 20500
+    },
+    {
+      "epoch": 0.7314015045973808,
+      "grad_norm": 5.405521869659424,
+      "learning_rate": 5.538240574506284e-06,
+      "loss": 2.1918,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7488158261354138,
+      "grad_norm": 11.361534118652344,
+      "learning_rate": 5.179174147217235e-06,
+      "loss": 2.2957,
+      "step": 21500
+    },
+    {
+      "epoch": 0.7662301476734467,
+      "grad_norm": 12.7646484375,
+      "learning_rate": 4.820107719928187e-06,
+      "loss": 2.3009,
+      "step": 22000
+    },
+    {
+      "epoch": 0.7836444692114796,
+      "grad_norm": 7.689826488494873,
+      "learning_rate": 4.4610412926391385e-06,
+      "loss": 2.2011,
+      "step": 22500
+    },
+    {
+      "epoch": 0.8010587907495124,
+      "grad_norm": 12.123157501220703,
+      "learning_rate": 4.10197486535009e-06,
+      "loss": 2.3082,
+      "step": 23000
+    },
+    {
+      "epoch": 0.8184731122875453,
+      "grad_norm": 7.985175132751465,
+      "learning_rate": 3.7429084380610415e-06,
+      "loss": 2.2633,
+      "step": 23500
+    },
+    {
+      "epoch": 0.8358874338255782,
+      "grad_norm": 7.724106311798096,
+      "learning_rate": 3.3838420107719933e-06,
+      "loss": 2.3609,
+      "step": 24000
+    },
+    {
+      "epoch": 0.8533017553636111,
+      "grad_norm": 11.675145149230957,
+      "learning_rate": 3.0247755834829446e-06,
+      "loss": 2.2966,
+      "step": 24500
+    },
+    {
+      "epoch": 0.8707160769016439,
+      "grad_norm": 10.773253440856934,
+      "learning_rate": 2.6657091561938963e-06,
+      "loss": 2.3305,
+      "step": 25000
+    },
+    {
+      "epoch": 0.8881303984396768,
+      "grad_norm": 13.044085502624512,
+      "learning_rate": 2.3066427289048477e-06,
+      "loss": 2.2828,
+      "step": 25500
+    },
+    {
+      "epoch": 0.9055447199777097,
+      "grad_norm": 7.912332534790039,
+      "learning_rate": 1.947576301615799e-06,
+      "loss": 2.2439,
+      "step": 26000
+    },
+    {
+      "epoch": 0.9229590415157426,
+      "grad_norm": 13.101786613464355,
+      "learning_rate": 1.5885098743267505e-06,
+      "loss": 2.289,
+      "step": 26500
+    },
+    {
+      "epoch": 0.9403733630537754,
+      "grad_norm": 5.365452766418457,
+      "learning_rate": 1.229443447037702e-06,
+      "loss": 2.302,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9577876845918083,
+      "grad_norm": 11.440293312072754,
+      "learning_rate": 8.703770197486536e-07,
+      "loss": 2.2542,
+      "step": 27500
+    },
+    {
+      "epoch": 0.9752020061298412,
+      "grad_norm": 23.63568115234375,
+      "learning_rate": 5.11310592459605e-07,
+      "loss": 2.2199,
+      "step": 28000
+    },
+    {
+      "epoch": 0.9926163276678741,
+      "grad_norm": 14.987226486206055,
+      "learning_rate": 1.5224416517055656e-07,
+      "loss": 2.2635,
+      "step": 28500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 28712,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-28712/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00534653f4d305635409811af1c0c1e311e6bd928afe44a6c0abac6c19c943cb
+size 5688