upload checkpoint

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+optimizer.pt filter=lfs diff=lfs merge=lfs -text
+scheduler.pt filter=lfs diff=lfs merge=lfs -text
+49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58 filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83ab5c39e2b1c34a955136275ce0db068cb20d9643ead033d6b8124a73ab4f64
+size 15645492

config.json

@@ -0,0 +1,170 @@
+{
+  "_name_or_path": "checkpoints/clip-stage1-10240/checkpoint-6000",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "id2label": {
+    "0": "Entailment",
+    "1": "Neutral",
+    "2": "Contradiction"
+  },
+  "initializer_factor": 1.0,
+  "label2id": {
+    "Contradiction": 2,
+    "Entailment": 0,
+    "Neutral": 1
+  },
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 512,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 8,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.17.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "text_config_dict": null,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.17.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vision_config_dict": {
+    "patch_size": 16
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf44edbb240c29ceb52450f260a5dfdef4abb288008611bf5e8184f93fc97413
+size 689659578

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f42657547be587a9f5f6469da2b599442d0930c955ad6f5c113d7a84dbc95d1
+size 598642122

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c490da560183bd4d780a2290f9dbf9459789761b8216743996f2a5ea976ac4b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be843b940cbd307a44ae2d454806a7a3b5ccbefe61b63d347048e72a563c7207
+size 1064

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}

text_renderer_config.json

@@ -0,0 +1,253 @@
+{
+  "background_color": "white",
+  "dpi": 120,
+  "font_color": "black",
+  "font_file": "49e6dc219d1a1a1c9236acaf05a48b542002016a6dc877ee72baab085a84257b.3f28e7f4b38e1efe1b6da4a3732404c19d4c6a614ff32dce90a251e293d4ce58",
+  "font_size": 8,
+  "fonts_list": [
+    "Apple Color Emoji",
+    "DejaVu Sans",
+    "DejaVu Sans Mono",
+    "DejaVu Serif",
+    "FontAwesome",
+    "GLYPHICONS Halflings",
+    "Go Noto Current",
+    "Inconsolata",
+    "Lato",
+    "MathJax_AMS",
+    "MathJax_Caligraphic",
+    "MathJax_Fraktur",
+    "MathJax_Main",
+    "MathJax_Math",
+    "MathJax_SansSerif",
+    "MathJax_Script",
+    "MathJax_Size1",
+    "MathJax_Size2",
+    "MathJax_Size3",
+    "MathJax_Size4",
+    "MathJax_Typewriter",
+    "MathJax_Vector",
+    "MathJax_Vector-Bold",
+    "MathJax_WinChrome",
+    "MathJax_WinIE6",
+    "Monospace",
+    "Noto Fangsong KSS Rotated",
+    "Noto Fangsong KSS Vertical",
+    "Noto Kufi Arabic",
+    "Noto Music",
+    "Noto Naskh Arabic UI",
+    "Noto Nastaliq Urdu",
+    "Noto Rashi Hebrew",
+    "Noto Sans",
+    "Noto Sans Adlam",
+    "Noto Sans Adlam Unjoined",
+    "Noto Sans Anatolian Hieroglyphs",
+    "Noto Sans Arabic",
+    "Noto Sans Armenian",
+    "Noto Sans Avestan",
+    "Noto Sans Balinese",
+    "Noto Sans Bamum",
+    "Noto Sans Bassa Vah",
+    "Noto Sans Batak",
+    "Noto Sans Bhaiksuki",
+    "Noto Sans Brahmi",
+    "Noto Sans Buginese",
+    "Noto Sans Buhid",
+    "Noto Sans CJK HK",
+    "Noto Sans CJK JP",
+    "Noto Sans CJK KR",
+    "Noto Sans CJK SC",
+    "Noto Sans CJK TC",
+    "Noto Sans Canadian Aboriginal",
+    "Noto Sans Carian",
+    "Noto Sans Caucasian Albanian",
+    "Noto Sans Chakma",
+    "Noto Sans Cham",
+    "Noto Sans Cherokee",
+    "Noto Sans Chorasmian",
+    "Noto Sans Coptic",
+    "Noto Sans Cuneiform",
+    "Noto Sans Cypriot",
+    "Noto Sans Cypro Minoan",
+    "Noto Sans Deseret",
+    "Noto Sans Devanagari",
+    "Noto Sans Devanagari UI",
+    "Noto Sans Duployan",
+    "Noto Sans Egyptian Hieroglyphs",
+    "Noto Sans Elbasan",
+    "Noto Sans Elymaic",
+    "Noto Sans Ethiopic",
+    "Noto Sans Georgian",
+    "Noto Sans Glagolitic",
+    "Noto Sans Gothic",
+    "Noto Sans Grantha",
+    "Noto Sans Gujarati",
+    "Noto Sans Gujarati UI",
+    "Noto Sans Gunjala Gondi",
+    "Noto Sans Gurmukhi",
+    "Noto Sans Gurmukhi UI",
+    "Noto Sans Hanifi Rohingya",
+    "Noto Sans Hanunoo",
+    "Noto Sans Hatran",
+    "Noto Sans Hebrew",
+    "Noto Sans Hebrew Droid",
+    "Noto Sans Imperial Aramaic",
+    "Noto Sans Indic Siyaq Numbers",
+    "Noto Sans Inscriptional Pahlavi",
+    "Noto Sans Inscriptional Parthian",
+    "Noto Sans Javanese",
+    "Noto Sans Kaithi",
+    "Noto Sans Kannada",
+    "Noto Sans Kannada UI",
+    "Noto Sans Kawi",
+    "Noto Sans Kayah Li",
+    "Noto Sans Kharoshthi",
+    "Noto Sans Khmer",
+    "Noto Sans Khmer UI",
+    "Noto Sans Khojki",
+    "Noto Sans Khudawadi",
+    "Noto Sans Lao",
+    "Noto Sans Lao Looped",
+    "Noto Sans Lao Looped UI",
+    "Noto Sans Lao UI",
+    "Noto Sans Lepcha",
+    "Noto Sans Limbu",
+    "Noto Sans Linear A",
+    "Noto Sans Linear B",
+    "Noto Sans Lisu",
+    "Noto Sans Lycian",
+    "Noto Sans Lydian",
+    "Noto Sans Mahajani",
+    "Noto Sans Malayalam",
+    "Noto Sans Malayalam UI",
+    "Noto Sans Mandaic",
+    "Noto Sans Manichaean",
+    "Noto Sans Marchen",
+    "Noto Sans Masaram Gondi",
+    "Noto Sans Math",
+    "Noto Sans Mayan Numerals",
+    "Noto Sans Medefaidrin",
+    "Noto Sans Meetei Mayek",
+    "Noto Sans Mende Kikakui",
+    "Noto Sans Meroitic",
+    "Noto Sans Miao",
+    "Noto Sans Modi",
+    "Noto Sans Mongolian",
+    "Noto Sans Mono",
+    "Noto Sans Mro",
+    "Noto Sans Multani",
+    "Noto Sans Myanmar",
+    "Noto Sans Myanmar UI",
+    "Noto Sans NKo",
+    "Noto Sans NKo Unjoined",
+    "Noto Sans Nabataean",
+    "Noto Sans Nag Mundari",
+    "Noto Sans Nandinagari",
+    "Noto Sans New Tai Lue",
+    "Noto Sans Newa",
+    "Noto Sans Nushu",
+    "Noto Sans Ogham",
+    "Noto Sans Ol Chiki",
+    "Noto Sans Old Hungarian",
+    "Noto Sans Old Italic",
+    "Noto Sans Old North Arabian",
+    "Noto Sans Old Permic",
+    "Noto Sans Old Persian",
+    "Noto Sans Old Sogdian",
+    "Noto Sans Old South Arabian",
+    "Noto Sans Old Turkic",
+    "Noto Sans Oriya",
+    "Noto Sans Osage",
+    "Noto Sans Osmanya",
+    "Noto Sans Pahawh Hmong",
+    "Noto Sans Palmyrene",
+    "Noto Sans Pau Cin Hau",
+    "Noto Sans PhagsPa",
+    "Noto Sans Phoenician",
+    "Noto Sans Psalter Pahlavi",
+    "Noto Sans Rejang",
+    "Noto Sans Runic",
+    "Noto Sans Samaritan",
+    "Noto Sans Saurashtra",
+    "Noto Sans Sharada",
+    "Noto Sans Shavian",
+    "Noto Sans Siddham",
+    "Noto Sans SignWriting",
+    "Noto Sans Sinhala",
+    "Noto Sans Sinhala UI",
+    "Noto Sans Sogdian",
+    "Noto Sans Sora Sompeng",
+    "Noto Sans Soyombo",
+    "Noto Sans Sundanese",
+    "Noto Sans Syloti Nagri",
+    "Noto Sans Symbols",
+    "Noto Sans Symbols 2",
+    "Noto Sans Syriac",
+    "Noto Sans Syriac Eastern",
+    "Noto Sans Syriac Western",
+    "Noto Sans Tagalog",
+    "Noto Sans Tagbanwa",
+    "Noto Sans Tai Le",
+    "Noto Sans Tai Tham",
+    "Noto Sans Tai Viet",
+    "Noto Sans Takri",
+    "Noto Sans Tamil",
+    "Noto Sans Tamil Supplement",
+    "Noto Sans Tamil UI",
+    "Noto Sans Tangsa",
+    "Noto Sans Telugu",
+    "Noto Sans Telugu UI",
+    "Noto Sans Test",
+    "Noto Sans Thaana",
+    "Noto Sans Thai",
+    "Noto Sans Thai Looped",
+    "Noto Sans Thai Looped UI",
+    "Noto Sans Thai UI",
+    "Noto Sans Tifinagh",
+    "Noto Sans Tifinagh APT",
+    "Noto Sans Tifinagh Adrar",
+    "Noto Sans Tifinagh Agraw Imazighen",
+    "Noto Sans Tifinagh Ahaggar",
+    "Noto Sans Tifinagh Air",
+    "Noto Sans Tifinagh Azawagh",
+    "Noto Sans Tifinagh Ghat",
+    "Noto Sans Tifinagh Hawad",
+    "Noto Sans Tifinagh Rhissa Ixa",
+    "Noto Sans Tifinagh SIL",
+    "Noto Sans Tifinagh Tawellemmet",
+    "Noto Sans Tirhuta",
+    "Noto Sans Ugaritic",
+    "Noto Sans Vai",
+    "Noto Sans Vithkuqi",
+    "Noto Sans Wancho",
+    "Noto Sans Warang Citi",
+    "Noto Sans Yi",
+    "Noto Sans Zanabazar Square",
+    "Noto Traditional Nushu",
+    "NotoSansOldHungarianUI",
+    "Sans",
+    "Serif",
+    "Source Code Pro",
+    "System-ui",
+    "Ubuntu",
+    "Ubuntu Condensed",
+    "Ubuntu Mono",
+    "cmex10",
+    "cmmi10",
+    "cmr10",
+    "cmsy10",
+    "dsrom10",
+    "esint10",
+    "eufm10",
+    "msam10",
+    "msbm10",
+    "rsfs10",
+    "stmary10",
+    "wasy10"
+  ],
+  "max_seq_length": 196,
+  "pad_size": 3,
+  "pixels_per_patch": 16,
+  "rgb": false,
+  "text_renderer_type": "PangoCairoTextRenderer"
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+    "unk_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "bos_token": {
+        "content": "<|startoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "eos_token": {
+        "content": "<|endoftext|>",
+        "single_word": false,
+        "lstrip": false,
+        "rstrip": false,
+        "normalized": true,
+        "__type": "AddedToken"
+    },
+    "pad_token": "<|endoftext|>",
+    "errors": "replace",
+    "add_prefix_space": false,
+    "do_lower_case": true,
+    "name_or_path": "openai/clip-vit-base-patch16",
+    "model_max_length": 77,
+    "special_tokens_map_file": "./special_tokens_map.json",
+    "tokenizer_class": "CLIPTokenizer"
+}

trainer_state.json

@@ -0,0 +1,376 @@
+{
+  "best_metric": 0.7677604385680659,
+  "best_model_checkpoint": "./checkpoints/clip-stage2-10240/checkpoint-860",
+  "epoch": 0.6259780907668232,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 6e-06,
+      "loss": 4.375,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.2e-05,
+      "loss": 2.2072,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8e-05,
+      "loss": 1.7421,
+      "step": 60
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 2.4e-05,
+      "loss": 1.5179,
+      "step": 80
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 3e-05,
+      "loss": 1.3767,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 2.9670329670329673e-05,
+      "loss": 1.2672,
+      "step": 120
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 2.934065934065934e-05,
+      "loss": 1.1824,
+      "step": 140
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.9010989010989013e-05,
+      "loss": 1.1082,
+      "step": 160
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.8681318681318685e-05,
+      "loss": 1.0627,
+      "step": 180
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.8351648351648353e-05,
+      "loss": 1.0224,
+      "step": 200
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.802197802197802e-05,
+      "loss": 0.991,
+      "step": 220
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.7692307692307694e-05,
+      "loss": 0.9595,
+      "step": 240
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.7362637362637362e-05,
+      "loss": 0.9364,
+      "step": 260
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.7032967032967034e-05,
+      "loss": 0.9123,
+      "step": 280
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.6703296703296702e-05,
+      "loss": 0.8941,
+      "step": 300
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.6373626373626374e-05,
+      "loss": 0.8776,
+      "step": 320
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.6043956043956046e-05,
+      "loss": 0.8598,
+      "step": 340
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.8323,
+      "step": 360
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.5384615384615386e-05,
+      "loss": 0.8301,
+      "step": 380
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.5054945054945058e-05,
+      "loss": 0.8138,
+      "step": 400
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 2.4725274725274723e-05,
+      "loss": 0.8084,
+      "step": 420
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.4395604395604395e-05,
+      "loss": 0.7964,
+      "step": 440
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.4065934065934067e-05,
+      "loss": 0.7846,
+      "step": 460
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.3736263736263735e-05,
+      "loss": 0.7686,
+      "step": 480
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.3406593406593407e-05,
+      "loss": 0.7574,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 0.7542,
+      "step": 520
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.2747252747252748e-05,
+      "loss": 0.7474,
+      "step": 540
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 2.241758241758242e-05,
+      "loss": 0.7369,
+      "step": 560
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.208791208791209e-05,
+      "loss": 0.7296,
+      "step": 580
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 2.175824175824176e-05,
+      "loss": 0.7167,
+      "step": 600
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.7155,
+      "step": 620
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.10989010989011e-05,
+      "loss": 0.7052,
+      "step": 640
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.076923076923077e-05,
+      "loss": 0.6997,
+      "step": 660
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.043956043956044e-05,
+      "loss": 0.6944,
+      "step": 680
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 2.010989010989011e-05,
+      "loss": 0.6896,
+      "step": 700
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.978021978021978e-05,
+      "loss": 0.6802,
+      "step": 720
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.9450549450549452e-05,
+      "loss": 0.6777,
+      "step": 740
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.912087912087912e-05,
+      "loss": 0.6707,
+      "step": 760
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8791208791208793e-05,
+      "loss": 0.6679,
+      "step": 780
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.6575,
+      "step": 800
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.813186813186813e-05,
+      "loss": 0.6589,
+      "step": 820
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.78021978021978e-05,
+      "loss": 0.6514,
+      "step": 840
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.7472527472527473e-05,
+      "loss": 0.6494,
+      "step": 860
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.6441,
+      "step": 880
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.6813186813186814e-05,
+      "loss": 0.6364,
+      "step": 900
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.6483516483516486e-05,
+      "loss": 0.6335,
+      "step": 920
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 0.63,
+      "step": 940
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.5824175824175826e-05,
+      "loss": 0.6278,
+      "step": 960
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5494505494505498e-05,
+      "loss": 0.6214,
+      "step": 980
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.5164835164835164e-05,
+      "loss": 0.6174,
+      "step": 1000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.4835164835164836e-05,
+      "loss": 0.6184,
+      "step": 1020
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.4505494505494506e-05,
+      "loss": 0.6128,
+      "step": 1040
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.4175824175824177e-05,
+      "loss": 0.6146,
+      "step": 1060
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 0.6073,
+      "step": 1080
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.3516483516483517e-05,
+      "loss": 0.6037,
+      "step": 1100
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.3186813186813187e-05,
+      "loss": 0.594,
+      "step": 1120
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.597,
+      "step": 1140
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.2527472527472529e-05,
+      "loss": 0.5906,
+      "step": 1160
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.2197802197802198e-05,
+      "loss": 0.5941,
+      "step": 1180
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.1868131868131868e-05,
+      "loss": 0.591,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1920,
+  "num_train_epochs": 2,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be052f75c1ffd4073657164e7b19c5b1cfad83baa28ac02f4e36a7f9485dcfbc
+size 3640