8000 of bart0-base

README.md

@@ -0,0 +1,52 @@
+---
+datasets:
+- bigscience/P3
+language: en
+license: apache-2.0
+widget:
+- text: "A is the son's of B's uncle. What is the family relationship between A and B?"
+- text: "Reorder the words in this sentence: justin and name bieber years is my am I 27 old."
+- text: "Task: copy but say the opposite.\n
+PSG won its match against Barca."
+- text: "Is this review positive or negative? Review: Best cast iron skillet you will every buy."
+  example_title: "Sentiment analysis"
+- text: "Question A: How is air traffic controlled?
+\nQuestion B: How do you become an air traffic controller?\nPick one: these questions are duplicates or not duplicates."
+- text: "Barack Obama nominated Hilary Clinton as his secretary of state on Monday. He chose her because she had foreign affairs experience as a former First Lady.
+\nIn the previous sentence, decide who 'her' is referring to."
+  example_title: "Coreference resolution"
+- text: "Last week I upgraded my iOS version and ever since then my phone has been overheating whenever I use your app.\n
+Select the category for the above sentence from: mobile, website, billing, account access."
+- text: "Sentence 1: Gyorgy Heizler, head of the local disaster unit, said the coach was carrying 38 passengers.\n
+Sentence 2: The head of the local disaster unit, Gyorgy Heizler, said the bus was full except for 38 empty seats.\n\n
+Do sentences 1 and 2 have the same meaning?"
+  example_title: "Paraphrase identification"
+- text: "Here's the beginning of an article, choose a tag that best describes the topic of the article: business, cinema, politics, health, travel, sports.\n\n
+The best and worst fo 007 as 'No time to die' marks Daniel Craig's exit.\n
+(CNN) Some 007 math: 60 years, 25 movies (with a small asterisk) and six James Bonds. For a Cold War creation, Ian Fleming's suave spy has certainly gotten around, but despite different guises in the tuxedo and occasional scuba gear, when it comes to Bond ratings, there really shouldn't be much argument about who wore it best."
+- text: "Max: Know any good websites to buy clothes from?\n
+Payton: Sure :) LINK 1, LINK 2, LINK 3\n
+Max: That's a lot of them!\n
+Payton: Yeah, but they have different things so I usually buy things from 2 or 3 of them.\n
+Max: I'll check them out. Thanks.\n\n
+Who or what are Payton and Max referring to when they say 'them'?"
+- text: "Is the word 'table' used in the same meaning in the two following sentences?\n\n
+Sentence A: you can leave the books on the table over there.\n
+Sentence B: the tables in this book are very hard to read."
+- text: "On a shelf, there are five books: a gray book, a red book, a purple book, a blue book, and a black book.\n
+The red book is to the right of the gray book. The black book is to the left of the blue book. The blue book is to the left of the gray book. The purple book is the second from the right.\n\n
+Which book is the leftmost book?"
+  example_title: "Logic puzzles"
+- text: "The two men running to become New York City's next mayor will face off in their first debate Wednesday night.\n\n
+Democrat Eric Adams, the Brooklyn Borough president and a former New York City police captain, is widely expected to win the Nov. 2 election against Republican Curtis Sliwa, the founder of the 1970s-era Guardian Angels anti-crime patril.\n\n
+Who are the men running for mayor?"
+  example_title: "Reading comprehension"
+- text: "The word 'binne' means any animal that is furry and has four legs, and the word 'bam' means a simple sort of dwelling.\n\n
+Which of the following best characterizes binne bams?\n
+- Sentence 1: Binne bams are for pets.\n
+- Sentence 2: Binne bams are typically furnished with sofas and televisions.\n
+- Sentence 3: Binne bams are luxurious apartments.\n
+- Sentence 4: Binne bams are places where people live."
+---
+
+TBA

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec55770ac5772dacf707b630ddaa101a4a52d15c235ab4df1c0943d0ff2a0ec
+size 1115513717

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35bbfa70c58a9375d1eb22db049f8f84853dd7893937fb6d3201c63d54dedc6a
+size 557979193

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5291e3ed381afc496effc538f087f3918e3fe5352163cc27cefd75c0c948491e
+size 21515

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94018654b6c4468ad79069048e581fbbf5cc00e7f69c1bde948db425356d0796
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0ce319bb038aea3f3bf4993c8f9cb14dc0332875c74964501c4fabb01a1ecd
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}

trainer_state.json

@@ -0,0 +1,1616 @@
+{
+  "best_metric": 1.026070237159729,
+  "best_model_checkpoint": "./outputs/BART0-base/checkpoint-2000",
+  "epoch": 1.3402294999581206,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.979477299380131e-05,
+      "loss": 3.1968,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.958535768135366e-05,
+      "loss": 2.5802,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "eval_loss": 1.012151837348938,
+      "eval_runtime": 15.5603,
+      "eval_samples_per_second": 597.674,
+      "eval_steps_per_second": 2.378,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9375942368906014e-05,
+      "loss": 2.4448,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.916652705645837e-05,
+      "loss": 2.3684,
+      "step": 200
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 1.0450046062469482,
+      "eval_runtime": 15.8481,
+      "eval_samples_per_second": 586.822,
+      "eval_steps_per_second": 2.335,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.8957111744010725e-05,
+      "loss": 2.3267,
+      "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.874769643156308e-05,
+      "loss": 2.2764,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 1.0499160289764404,
+      "eval_runtime": 15.8218,
+      "eval_samples_per_second": 587.798,
+      "eval_steps_per_second": 2.339,
+      "step": 300
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.853828111911543e-05,
+      "loss": 2.2669,
+      "step": 350
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.8328865806667784e-05,
+      "loss": 2.2265,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 1.0236656665802002,
+      "eval_runtime": 15.7197,
+      "eval_samples_per_second": 591.616,
+      "eval_steps_per_second": 2.354,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.811945049422014e-05,
+      "loss": 2.2294,
+      "step": 450
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.7910035181772494e-05,
+      "loss": 2.1933,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 1.05411958694458,
+      "eval_runtime": 16.1405,
+      "eval_samples_per_second": 576.19,
+      "eval_steps_per_second": 2.292,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.770061986932485e-05,
+      "loss": 2.2091,
+      "step": 550
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.74912045568772e-05,
+      "loss": 2.2114,
+      "step": 600
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 1.0270859003067017,
+      "eval_runtime": 16.1225,
+      "eval_samples_per_second": 576.832,
+      "eval_steps_per_second": 2.295,
+      "step": 600
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.728178924442955e-05,
+      "loss": 2.1721,
+      "step": 650
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.707237393198191e-05,
+      "loss": 2.1518,
+      "step": 700
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.0103075504302979,
+      "eval_runtime": 15.7699,
+      "eval_samples_per_second": 589.729,
+      "eval_steps_per_second": 2.346,
+      "step": 700
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.6867146925783216e-05,
+      "loss": 2.1758,
+      "step": 750
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.665773161333557e-05,
+      "loss": 2.0953,
+      "step": 800
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 1.074766993522644,
+      "eval_runtime": 15.6532,
+      "eval_samples_per_second": 594.128,
+      "eval_steps_per_second": 2.364,
+      "step": 800
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.644831630088792e-05,
+      "loss": 2.097,
+      "step": 850
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.6238900988440275e-05,
+      "loss": 2.1284,
+      "step": 900
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 1.0292476415634155,
+      "eval_runtime": 15.7987,
+      "eval_samples_per_second": 588.655,
+      "eval_steps_per_second": 2.342,
+      "step": 900
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.602948567599263e-05,
+      "loss": 2.1503,
+      "step": 950
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.5820070363544986e-05,
+      "loss": 2.1173,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 1.0330989360809326,
+      "eval_runtime": 16.1941,
+      "eval_samples_per_second": 574.283,
+      "eval_steps_per_second": 2.285,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.561065505109734e-05,
+      "loss": 2.064,
+      "step": 1050
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.54096163511476e-05,
+      "loss": 2.1102,
+      "step": 1100
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 1.0028032064437866,
+      "eval_runtime": 15.6866,
+      "eval_samples_per_second": 592.862,
+      "eval_steps_per_second": 2.359,
+      "step": 1100
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.520020103869995e-05,
+      "loss": 2.0906,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.4990785726252305e-05,
+      "loss": 2.0648,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.0790895223617554,
+      "eval_runtime": 15.8769,
+      "eval_samples_per_second": 585.758,
+      "eval_steps_per_second": 2.33,
+      "step": 1200
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.478137041380466e-05,
+      "loss": 2.0613,
+      "step": 1250
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.4571955101357016e-05,
+      "loss": 2.0785,
+      "step": 1300
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 1.0282424688339233,
+      "eval_runtime": 15.9134,
+      "eval_samples_per_second": 584.414,
+      "eval_steps_per_second": 2.325,
+      "step": 1300
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.436253978890937e-05,
+      "loss": 2.0786,
+      "step": 1350
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.415312447646172e-05,
+      "loss": 2.0748,
+      "step": 1400
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 1.0269650220870972,
+      "eval_runtime": 16.1388,
+      "eval_samples_per_second": 576.252,
+      "eval_steps_per_second": 2.293,
+      "step": 1400
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.3943709164014075e-05,
+      "loss": 2.05,
+      "step": 1450
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.373429385156643e-05,
+      "loss": 2.0797,
+      "step": 1500
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.0267333984375,
+      "eval_runtime": 16.2393,
+      "eval_samples_per_second": 572.684,
+      "eval_steps_per_second": 2.278,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.3524878539118785e-05,
+      "loss": 2.0736,
+      "step": 1550
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.331546322667114e-05,
+      "loss": 2.0734,
+      "step": 1600
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.0247018337249756,
+      "eval_runtime": 15.6292,
+      "eval_samples_per_second": 595.039,
+      "eval_steps_per_second": 2.367,
+      "step": 1600
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.310604791422349e-05,
+      "loss": 2.0417,
+      "step": 1650
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.2896632601775844e-05,
+      "loss": 2.0529,
+      "step": 1700
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.0378021001815796,
+      "eval_runtime": 16.0607,
+      "eval_samples_per_second": 579.055,
+      "eval_steps_per_second": 2.304,
+      "step": 1700
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.26872172893282e-05,
+      "loss": 2.0452,
+      "step": 1750
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.247780197688055e-05,
+      "loss": 2.0267,
+      "step": 1800
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 1.0441969633102417,
+      "eval_runtime": 16.1723,
+      "eval_samples_per_second": 575.058,
+      "eval_steps_per_second": 2.288,
+      "step": 1800
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.226838666443291e-05,
+      "loss": 2.0142,
+      "step": 1850
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.205897135198526e-05,
+      "loss": 2.0266,
+      "step": 1900
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 1.0151029825210571,
+      "eval_runtime": 16.1156,
+      "eval_samples_per_second": 577.082,
+      "eval_steps_per_second": 2.296,
+      "step": 1900
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.1849556039537614e-05,
+      "loss": 2.0295,
+      "step": 1950
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.164014072708997e-05,
+      "loss": 2.0069,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 1.026070237159729,
+      "eval_runtime": 16.0479,
+      "eval_samples_per_second": 579.515,
+      "eval_steps_per_second": 2.306,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.143072541464232e-05,
+      "loss": 2.0349,
+      "step": 2050
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.122131010219468e-05,
+      "loss": 2.0565,
+      "step": 2100
+    },
+    {
+      "epoch": 0.35,
+      "eval_loss": 1.0249441862106323,
+      "eval_runtime": 16.4225,
+      "eval_samples_per_second": 566.297,
+      "eval_steps_per_second": 2.253,
+      "step": 2100
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.101189478974703e-05,
+      "loss": 2.0196,
+      "step": 2150
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.080247947729938e-05,
+      "loss": 2.0251,
+      "step": 2200
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 1.0202720165252686,
+      "eval_runtime": 16.1636,
+      "eval_samples_per_second": 575.367,
+      "eval_steps_per_second": 2.289,
+      "step": 2200
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.059306416485174e-05,
+      "loss": 2.0122,
+      "step": 2250
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.038364885240409e-05,
+      "loss": 2.0046,
+      "step": 2300
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 1.0397460460662842,
+      "eval_runtime": 16.2098,
+      "eval_samples_per_second": 573.726,
+      "eval_steps_per_second": 2.283,
+      "step": 2300
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.017423353995645e-05,
+      "loss": 1.9894,
+      "step": 2350
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.99648182275088e-05,
+      "loss": 1.9869,
+      "step": 2400
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.05420982837677,
+      "eval_runtime": 16.4921,
+      "eval_samples_per_second": 563.906,
+      "eval_steps_per_second": 2.243,
+      "step": 2400
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.975540291506115e-05,
+      "loss": 2.022,
+      "step": 2450
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.954598760261351e-05,
+      "loss": 1.9956,
+      "step": 2500
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 1.031363844871521,
+      "eval_runtime": 16.1444,
+      "eval_samples_per_second": 576.052,
+      "eval_steps_per_second": 2.292,
+      "step": 2500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.9336572290165856e-05,
+      "loss": 1.9659,
+      "step": 2550
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.912715697771821e-05,
+      "loss": 2.0078,
+      "step": 2600
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 1.0604513883590698,
+      "eval_runtime": 16.0399,
+      "eval_samples_per_second": 579.804,
+      "eval_steps_per_second": 2.307,
+      "step": 2600
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 3.891774166527057e-05,
+      "loss": 1.9656,
+      "step": 2650
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.870832635282292e-05,
+      "loss": 1.9977,
+      "step": 2700
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 1.0340880155563354,
+      "eval_runtime": 16.1614,
+      "eval_samples_per_second": 575.444,
+      "eval_steps_per_second": 2.289,
+      "step": 2700
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 3.849891104037528e-05,
+      "loss": 2.0003,
+      "step": 2750
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 3.8289495727927626e-05,
+      "loss": 1.9757,
+      "step": 2800
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 1.0368785858154297,
+      "eval_runtime": 16.3593,
+      "eval_samples_per_second": 568.482,
+      "eval_steps_per_second": 2.262,
+      "step": 2800
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 3.808008041547998e-05,
+      "loss": 1.9215,
+      "step": 2850
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.7870665103032336e-05,
+      "loss": 1.975,
+      "step": 2900
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 1.026584267616272,
+      "eval_runtime": 16.0597,
+      "eval_samples_per_second": 579.091,
+      "eval_steps_per_second": 2.304,
+      "step": 2900
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 3.766124979058469e-05,
+      "loss": 1.9971,
+      "step": 2950
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 3.745183447813705e-05,
+      "loss": 1.9633,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 1.0441828966140747,
+      "eval_runtime": 15.8581,
+      "eval_samples_per_second": 586.449,
+      "eval_steps_per_second": 2.333,
+      "step": 3000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 3.7242419165689395e-05,
+      "loss": 1.9569,
+      "step": 3050
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 3.703300385324175e-05,
+      "loss": 1.9916,
+      "step": 3100
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 1.0376336574554443,
+      "eval_runtime": 15.252,
+      "eval_samples_per_second": 609.754,
+      "eval_steps_per_second": 2.426,
+      "step": 3100
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.682777684704306e-05,
+      "loss": 1.9359,
+      "step": 3150
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3.6618361534595414e-05,
+      "loss": 1.9447,
+      "step": 3200
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.9997221231460571,
+      "eval_runtime": 16.6296,
+      "eval_samples_per_second": 559.243,
+      "eval_steps_per_second": 2.225,
+      "step": 3200
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3.640894622214777e-05,
+      "loss": 1.9436,
+      "step": 3250
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 3.619953090970012e-05,
+      "loss": 1.9924,
+      "step": 3300
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 1.0513906478881836,
+      "eval_runtime": 16.0136,
+      "eval_samples_per_second": 580.755,
+      "eval_steps_per_second": 2.311,
+      "step": 3300
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.599011559725247e-05,
+      "loss": 1.9793,
+      "step": 3350
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 3.578070028480482e-05,
+      "loss": 1.9409,
+      "step": 3400
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 1.056003212928772,
+      "eval_runtime": 16.6238,
+      "eval_samples_per_second": 559.44,
+      "eval_steps_per_second": 2.226,
+      "step": 3400
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 3.557128497235718e-05,
+      "loss": 1.9694,
+      "step": 3450
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.536186965990954e-05,
+      "loss": 1.9751,
+      "step": 3500
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 1.035875678062439,
+      "eval_runtime": 15.8522,
+      "eval_samples_per_second": 586.668,
+      "eval_steps_per_second": 2.334,
+      "step": 3500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 3.515245434746189e-05,
+      "loss": 1.9504,
+      "step": 3550
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3.494303903501424e-05,
+      "loss": 1.9421,
+      "step": 3600
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 1.0627715587615967,
+      "eval_runtime": 15.8545,
+      "eval_samples_per_second": 586.583,
+      "eval_steps_per_second": 2.334,
+      "step": 3600
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.473362372256659e-05,
+      "loss": 1.9026,
+      "step": 3650
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.452420841011895e-05,
+      "loss": 1.9501,
+      "step": 3700
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 1.049263596534729,
+      "eval_runtime": 16.1043,
+      "eval_samples_per_second": 577.486,
+      "eval_steps_per_second": 2.298,
+      "step": 3700
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.431479309767131e-05,
+      "loss": 1.9331,
+      "step": 3750
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.4105377785223656e-05,
+      "loss": 1.9362,
+      "step": 3800
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.039939045906067,
+      "eval_runtime": 16.1428,
+      "eval_samples_per_second": 576.107,
+      "eval_steps_per_second": 2.292,
+      "step": 3800
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.389596247277601e-05,
+      "loss": 1.9174,
+      "step": 3850
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.368654716032836e-05,
+      "loss": 1.94,
+      "step": 3900
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 1.0347034931182861,
+      "eval_runtime": 16.2615,
+      "eval_samples_per_second": 571.902,
+      "eval_steps_per_second": 2.275,
+      "step": 3900
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.3477131847880715e-05,
+      "loss": 1.9182,
+      "step": 3950
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.326771653543308e-05,
+      "loss": 1.9499,
+      "step": 4000
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.0576939582824707,
+      "eval_runtime": 16.282,
+      "eval_samples_per_second": 571.183,
+      "eval_steps_per_second": 2.272,
+      "step": 4000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.3058301222985426e-05,
+      "loss": 1.9325,
+      "step": 4050
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.284888591053778e-05,
+      "loss": 1.9062,
+      "step": 4100
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 1.0423039197921753,
+      "eval_runtime": 15.965,
+      "eval_samples_per_second": 582.524,
+      "eval_steps_per_second": 2.318,
+      "step": 4100
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.263947059809013e-05,
+      "loss": 1.9215,
+      "step": 4150
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.2430055285642485e-05,
+      "loss": 1.9026,
+      "step": 4200
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 1.0391933917999268,
+      "eval_runtime": 14.8765,
+      "eval_samples_per_second": 625.146,
+      "eval_steps_per_second": 2.487,
+      "step": 4200
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.222063997319485e-05,
+      "loss": 1.9491,
+      "step": 4250
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.2011224660747195e-05,
+      "loss": 1.9152,
+      "step": 4300
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 1.0235393047332764,
+      "eval_runtime": 15.2908,
+      "eval_samples_per_second": 608.21,
+      "eval_steps_per_second": 2.42,
+      "step": 4300
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.180180934829955e-05,
+      "loss": 1.9233,
+      "step": 4350
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.15923940358519e-05,
+      "loss": 1.9279,
+      "step": 4400
+    },
+    {
+      "epoch": 0.74,
+      "eval_loss": 1.028559923171997,
+      "eval_runtime": 14.9232,
+      "eval_samples_per_second": 623.192,
+      "eval_steps_per_second": 2.479,
+      "step": 4400
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1382978723404254e-05,
+      "loss": 1.9025,
+      "step": 4450
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.1173563410956616e-05,
+      "loss": 1.9195,
+      "step": 4500
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.025765061378479,
+      "eval_runtime": 14.9794,
+      "eval_samples_per_second": 620.854,
+      "eval_steps_per_second": 2.47,
+      "step": 4500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.0964148098508965e-05,
+      "loss": 1.9,
+      "step": 4550
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.075473278606132e-05,
+      "loss": 1.9079,
+      "step": 4600
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 1.0234707593917847,
+      "eval_runtime": 15.1735,
+      "eval_samples_per_second": 612.912,
+      "eval_steps_per_second": 2.438,
+      "step": 4600
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.054531747361367e-05,
+      "loss": 1.8868,
+      "step": 4650
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.0335902161166024e-05,
+      "loss": 1.9096,
+      "step": 4700
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 1.0209083557128906,
+      "eval_runtime": 15.0076,
+      "eval_samples_per_second": 619.685,
+      "eval_steps_per_second": 2.465,
+      "step": 4700
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.0126486848718375e-05,
+      "loss": 1.8942,
+      "step": 4750
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.9917071536270734e-05,
+      "loss": 1.9036,
+      "step": 4800
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.0443929433822632,
+      "eval_runtime": 14.8431,
+      "eval_samples_per_second": 626.553,
+      "eval_steps_per_second": 2.493,
+      "step": 4800
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.970765622382309e-05,
+      "loss": 1.892,
+      "step": 4850
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.949824091137544e-05,
+      "loss": 1.926,
+      "step": 4900
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 1.041871190071106,
+      "eval_runtime": 15.1234,
+      "eval_samples_per_second": 614.939,
+      "eval_steps_per_second": 2.447,
+      "step": 4900
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.9288825598927793e-05,
+      "loss": 1.8894,
+      "step": 4950
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.9079410286480145e-05,
+      "loss": 1.9163,
+      "step": 5000
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 1.0646345615386963,
+      "eval_runtime": 14.6224,
+      "eval_samples_per_second": 636.01,
+      "eval_steps_per_second": 2.53,
+      "step": 5000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.8869994974032504e-05,
+      "loss": 1.9106,
+      "step": 5050
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.866057966158486e-05,
+      "loss": 1.8973,
+      "step": 5100
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.0399593114852905,
+      "eval_runtime": 14.8746,
+      "eval_samples_per_second": 625.228,
+      "eval_steps_per_second": 2.487,
+      "step": 5100
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.845116434913721e-05,
+      "loss": 1.9107,
+      "step": 5150
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.8241749036689562e-05,
+      "loss": 1.9189,
+      "step": 5200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 1.0655252933502197,
+      "eval_runtime": 15.0739,
+      "eval_samples_per_second": 616.962,
+      "eval_steps_per_second": 2.455,
+      "step": 5200
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2.8032333724241914e-05,
+      "loss": 1.9153,
+      "step": 5250
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.7822918411794273e-05,
+      "loss": 1.9365,
+      "step": 5300
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 1.0276598930358887,
+      "eval_runtime": 15.0216,
+      "eval_samples_per_second": 619.109,
+      "eval_steps_per_second": 2.463,
+      "step": 5300
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.7613503099346628e-05,
+      "loss": 1.8813,
+      "step": 5350
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.740408778689898e-05,
+      "loss": 1.8907,
+      "step": 5400
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 1.0385425090789795,
+      "eval_runtime": 15.1648,
+      "eval_samples_per_second": 613.264,
+      "eval_steps_per_second": 2.44,
+      "step": 5400
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.7194672474451332e-05,
+      "loss": 1.9187,
+      "step": 5450
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.6985257162003684e-05,
+      "loss": 1.8917,
+      "step": 5500
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 1.0304224491119385,
+      "eval_runtime": 14.8782,
+      "eval_samples_per_second": 625.077,
+      "eval_steps_per_second": 2.487,
+      "step": 5500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.6780030155804992e-05,
+      "loss": 1.8612,
+      "step": 5550
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.657061484335735e-05,
+      "loss": 1.9204,
+      "step": 5600
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 1.0601547956466675,
+      "eval_runtime": 14.8806,
+      "eval_samples_per_second": 624.975,
+      "eval_steps_per_second": 2.486,
+      "step": 5600
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.6361199530909702e-05,
+      "loss": 1.8942,
+      "step": 5650
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.6151784218462054e-05,
+      "loss": 1.9072,
+      "step": 5700
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 1.0364910364151,
+      "eval_runtime": 14.8508,
+      "eval_samples_per_second": 626.23,
+      "eval_steps_per_second": 2.491,
+      "step": 5700
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.594236890601441e-05,
+      "loss": 1.904,
+      "step": 5750
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.573295359356676e-05,
+      "loss": 1.8952,
+      "step": 5800
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 1.0579551458358765,
+      "eval_runtime": 15.8601,
+      "eval_samples_per_second": 586.376,
+      "eval_steps_per_second": 2.333,
+      "step": 5800
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.552353828111912e-05,
+      "loss": 1.8922,
+      "step": 5850
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.5314122968671472e-05,
+      "loss": 1.9074,
+      "step": 5900
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 1.0638257265090942,
+      "eval_runtime": 14.9183,
+      "eval_samples_per_second": 623.397,
+      "eval_steps_per_second": 2.48,
+      "step": 5900
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5104707656223824e-05,
+      "loss": 1.8948,
+      "step": 5950
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.489529234377618e-05,
+      "loss": 1.8758,
+      "step": 6000
+    },
+    {
+      "epoch": 1.01,
+      "eval_loss": 1.0558853149414062,
+      "eval_runtime": 14.5514,
+      "eval_samples_per_second": 639.112,
+      "eval_steps_per_second": 2.543,
+      "step": 6000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.4685877031328534e-05,
+      "loss": 1.8458,
+      "step": 6050
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 2.4476461718880886e-05,
+      "loss": 1.8118,
+      "step": 6100
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 1.0648460388183594,
+      "eval_runtime": 14.9731,
+      "eval_samples_per_second": 621.114,
+      "eval_steps_per_second": 2.471,
+      "step": 6100
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 2.4267046406433238e-05,
+      "loss": 1.8216,
+      "step": 6150
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2.4057631093985593e-05,
+      "loss": 1.8181,
+      "step": 6200
+    },
+    {
+      "epoch": 1.04,
+      "eval_loss": 1.0505411624908447,
+      "eval_runtime": 14.9571,
+      "eval_samples_per_second": 621.78,
+      "eval_steps_per_second": 2.474,
+      "step": 6200
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 2.3848215781537948e-05,
+      "loss": 1.8426,
+      "step": 6250
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.36388004690903e-05,
+      "loss": 1.8481,
+      "step": 6300
+    },
+    {
+      "epoch": 1.06,
+      "eval_loss": 1.0492850542068481,
+      "eval_runtime": 14.8837,
+      "eval_samples_per_second": 624.843,
+      "eval_steps_per_second": 2.486,
+      "step": 6300
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.3429385156642655e-05,
+      "loss": 1.8044,
+      "step": 6350
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.3219969844195007e-05,
+      "loss": 1.8236,
+      "step": 6400
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 1.0615003108978271,
+      "eval_runtime": 14.7795,
+      "eval_samples_per_second": 629.251,
+      "eval_steps_per_second": 2.503,
+      "step": 6400
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.3010554531747362e-05,
+      "loss": 1.817,
+      "step": 6450
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.2801139219299718e-05,
+      "loss": 1.8547,
+      "step": 6500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 1.070224404335022,
+      "eval_runtime": 15.1165,
+      "eval_samples_per_second": 615.223,
+      "eval_steps_per_second": 2.448,
+      "step": 6500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.259172390685207e-05,
+      "loss": 1.817,
+      "step": 6550
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.2382308594404425e-05,
+      "loss": 1.8073,
+      "step": 6600
+    },
+    {
+      "epoch": 1.11,
+      "eval_loss": 1.0603699684143066,
+      "eval_runtime": 15.0786,
+      "eval_samples_per_second": 616.768,
+      "eval_steps_per_second": 2.454,
+      "step": 6600
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.2172893281956777e-05,
+      "loss": 1.8214,
+      "step": 6650
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.1963477969509132e-05,
+      "loss": 1.8323,
+      "step": 6700
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 1.0744497776031494,
+      "eval_runtime": 15.0113,
+      "eval_samples_per_second": 619.535,
+      "eval_steps_per_second": 2.465,
+      "step": 6700
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.1754062657061487e-05,
+      "loss": 1.8072,
+      "step": 6750
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.154464734461384e-05,
+      "loss": 1.8291,
+      "step": 6800
+    },
+    {
+      "epoch": 1.14,
+      "eval_loss": 1.0766249895095825,
+      "eval_runtime": 15.0159,
+      "eval_samples_per_second": 619.343,
+      "eval_steps_per_second": 2.464,
+      "step": 6800
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 2.1335232032166194e-05,
+      "loss": 1.856,
+      "step": 6850
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.1125816719718546e-05,
+      "loss": 1.8066,
+      "step": 6900
+    },
+    {
+      "epoch": 1.16,
+      "eval_loss": 1.0853835344314575,
+      "eval_runtime": 14.9684,
+      "eval_samples_per_second": 621.309,
+      "eval_steps_per_second": 2.472,
+      "step": 6900
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.09164014072709e-05,
+      "loss": 1.8015,
+      "step": 6950
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 2.0706986094823257e-05,
+      "loss": 1.8383,
+      "step": 7000
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 1.0606310367584229,
+      "eval_runtime": 14.9212,
+      "eval_samples_per_second": 623.274,
+      "eval_steps_per_second": 2.48,
+      "step": 7000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 2.049757078237561e-05,
+      "loss": 1.8252,
+      "step": 7050
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 2.028815546992796e-05,
+      "loss": 1.8075,
+      "step": 7100
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 1.0541033744812012,
+      "eval_runtime": 15.0551,
+      "eval_samples_per_second": 617.733,
+      "eval_steps_per_second": 2.458,
+      "step": 7100
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.0078740157480316e-05,
+      "loss": 1.8103,
+      "step": 7150
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.986932484503267e-05,
+      "loss": 1.8075,
+      "step": 7200
+    },
+    {
+      "epoch": 1.21,
+      "eval_loss": 1.0540446043014526,
+      "eval_runtime": 14.9234,
+      "eval_samples_per_second": 623.184,
+      "eval_steps_per_second": 2.479,
+      "step": 7200
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.9659909532585026e-05,
+      "loss": 1.8457,
+      "step": 7250
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.9450494220137378e-05,
+      "loss": 1.8445,
+      "step": 7300
+    },
+    {
+      "epoch": 1.22,
+      "eval_loss": 1.0582592487335205,
+      "eval_runtime": 15.172,
+      "eval_samples_per_second": 612.97,
+      "eval_steps_per_second": 2.439,
+      "step": 7300
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.924107890768973e-05,
+      "loss": 1.831,
+      "step": 7350
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.9031663595242085e-05,
+      "loss": 1.8413,
+      "step": 7400
+    },
+    {
+      "epoch": 1.24,
+      "eval_loss": 1.0817487239837646,
+      "eval_runtime": 14.9359,
+      "eval_samples_per_second": 622.66,
+      "eval_steps_per_second": 2.477,
+      "step": 7400
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.8822248282794437e-05,
+      "loss": 1.8035,
+      "step": 7450
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.8612832970346792e-05,
+      "loss": 1.8143,
+      "step": 7500
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 1.0620262622833252,
+      "eval_runtime": 14.9509,
+      "eval_samples_per_second": 622.036,
+      "eval_steps_per_second": 2.475,
+      "step": 7500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.8403417657899147e-05,
+      "loss": 1.8111,
+      "step": 7550
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.81940023454515e-05,
+      "loss": 1.8291,
+      "step": 7600
+    },
+    {
+      "epoch": 1.27,
+      "eval_loss": 1.0485789775848389,
+      "eval_runtime": 15.2218,
+      "eval_samples_per_second": 610.966,
+      "eval_steps_per_second": 2.431,
+      "step": 7600
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.7984587033003854e-05,
+      "loss": 1.8267,
+      "step": 7650
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.7775171720556206e-05,
+      "loss": 1.8234,
+      "step": 7700
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 1.0669416189193726,
+      "eval_runtime": 14.7589,
+      "eval_samples_per_second": 630.128,
+      "eval_steps_per_second": 2.507,
+      "step": 7700
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.756575640810856e-05,
+      "loss": 1.8435,
+      "step": 7750
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.7356341095660917e-05,
+      "loss": 1.7901,
+      "step": 7800
+    },
+    {
+      "epoch": 1.31,
+      "eval_loss": 1.0574383735656738,
+      "eval_runtime": 15.1846,
+      "eval_samples_per_second": 612.462,
+      "eval_steps_per_second": 2.437,
+      "step": 7800
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.714692578321327e-05,
+      "loss": 1.8135,
+      "step": 7850
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.693751047076562e-05,
+      "loss": 1.8241,
+      "step": 7900
+    },
+    {
+      "epoch": 1.32,
+      "eval_loss": 1.0570663213729858,
+      "eval_runtime": 14.8346,
+      "eval_samples_per_second": 626.913,
+      "eval_steps_per_second": 2.494,
+      "step": 7900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.6728095158317976e-05,
+      "loss": 1.8,
+      "step": 7950
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.651867984587033e-05,
+      "loss": 1.8202,
+      "step": 8000
+    },
+    {
+      "epoch": 1.34,
+      "eval_loss": 1.052140235900879,
+      "eval_runtime": 15.1776,
+      "eval_samples_per_second": 612.744,
+      "eval_steps_per_second": 2.438,
+      "step": 8000
+    }
+  ],
+  "max_steps": 11938,
+  "num_train_epochs": 2,
+  "total_flos": 1.4030127364571136e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d6a9068328893ac795bd5007ade8cb3bdfdf14743bd5c5f907f34834d995b1
+size 2991